Artificial intelligence and machine learning in design of mechanical materials

Designing intelligent bioorthogonal nanozymes: Recent advances of stimuli-responsive catalytic systems for biomedical applications

Bioorthogonal nanozymes have emerged as a potent tool in biomedicine due to their unique ability to perform enzymatic reactions that do not interfere with native biochemical processes. The integration of stimuli-responsive mechanisms into these nanozymes has further expanded their potential, allowing for controlled activation and targeted delivery. As such, intelligent bioorthogonal nanozymes have received more and more attention in developing therapeutic approaches. This review provides a comprehensive overview of the recent advances in the development and application of stimuli-responsive bioorthogonal nanozymes. By summarizing the design outlines for anchoring bioorthogonal nanozymes with stimuli-responsive capability, this review seeks to offer valuable insights and guidance for the rational design of these remarkable materials. This review highlights the significant progress made in this exciting field with different types of stimuli and the various applications. Additionally, it also examines the current challenges and limitations in the design, synthesis, and application of these systems, and proposes potential solutions and research directions. This review aims to stimulate further research toward the development of more efficient and versatile stimuli-responsive bioorthogonal nanozymes for biomedical applications.

A Multiscale Modeling and Experimental Study on the Tensile Strength of Plain-Woven Composites with Hybrid Bonded-Bolted Joints

CFRP hybrid bonded-bolted (HBB) joints combine the advantages of traditional joining methods, namely adhesive bonding, and bolting, to achieve optimal connection performance, making them the most favored connection method. The structural parameters of CFRP HBB joints, including overlap length, bolt-hole spacing, and fit clearance relationships, have a complex impact on connection performance. To enhance the connectivity performance of joint structures, this paper develops a multiscale finite element analysis model to investigate the impact of structural parameters on the strength of CFRP HBB joint structures. Coupled with experimental validation, the study reveals how changes in structural parameters affect the unidirectional tensile failure force of the joints. Building on this, an analytical approach and inverse design methodology for the mechanical properties of CFRP HBB joints based on deep supervised learning algorithms are developed. Neural networks accurately and efficiently predict the performance of joints with unprecedented combinations of parameters, thus expediting the inverse design process. This research combines experimentation and multiscale finite element analysis to explore the unknown relationships between the mechanical properties of CFRP HBB joints and their structural parameters. Furthermore, leveraging DNN neural networks, a rapid calculation method for the mechanical properties of hybrid joints is proposed. The findings lay the groundwork for the broader application and more intricate design of composite materials and their connection structures.

ProtAgents: protein discovery via large language model multi-agent collaborations combining physics and machine learning

Designing de novo proteins beyond those found in nature holds significant promise for advancements in both scientific and engineering applications. Current methodologies for protein design often rely on AI-based models, such as surrogate models that address end-to-end problems by linking protein structure to material properties or vice versa. However, these models frequently focus on specific material objectives or structural properties, limiting their flexibility when incorporating out-of-domain knowledge into the design process or comprehensive data analysis is required. In this study, we introduce ProtAgents, a platform for de novo protein design based on Large Language Models (LLMs), where multiple AI agents with distinct capabilities collaboratively address complex tasks within a dynamic environment. The versatility in agent development allows for expertise in diverse domains, including knowledge retrieval, protein structure analysis, physics-based simulations, and results analysis. The dynamic collaboration between agents, empowered by LLMs, provides a versatile approach to tackling protein design and analysis problems, as demonstrated through diverse examples in this study. The problems of interest encompass designing new proteins, analyzing protein structures and obtaining new first-principles data - natural vibrational frequencies - via physics simulations. The concerted effort of the system allows for powerful automated and synergistic design of de novo proteins with targeted mechanical properties. The flexibility in designing the agents, on one hand, and their capacity in autonomous collaboration through the dynamic LLM-based multi-agent environment on the other hand, unleashes great potentials of LLMs in addressing multi-objective materials problems and opens up new avenues for autonomous materials discovery and design.

Identifying constitutive parameters for complex hyperelastic materials using physics-informed neural networks

Identifying constitutive parameters in engineering and biological materials, particularly those with intricate geometries and mechanical behaviors, remains a longstanding challenge. The recent advent of physics-informed neural networks (PINNs) offers promising solutions, but current frameworks are often limited to basic constitutive laws and encounter practical constraints when combined with experimental data. In this paper, we introduce a robust PINN-based framework designed to identify material parameters for soft materials, specifically those exhibiting complex constitutive behaviors, under large deformation in plane stress conditions. Distinctively, our model emphasizes training PINNs with multi-modal synthetic experimental datasets consisting of full-field deformation and loading history, ensuring algorithm robustness even with noisy data. Our results reveal that the PINNs framework can accurately identify constitutive parameters of the incompressible Arruda-Boyce model for samples with intricate geometries, maintaining an error below 5%, even with an experimental noise level of 5%. We believe our framework provides a robust modulus identification approach for complex solids, especially for those with geometrical and constitutive complexity.

AI in analytical chemistry: Advancements, challenges, and future directions

This article explores the influence and applications of Artificial Intelligence (AI) in analytical chemistry, highlighting its potential to revolutionize the analysis of complex data sets and the development of innovative analytical methods. Additionally, it discusses the role of AI in interpreting large-scale data and optimizing experimental processes. AI has been fundamental in managing heterogeneous data and in advanced analysis of complex spectra in areas such as spectroscopy and chromatography. The article also examines the historical development of AI in chemistry, its current challenges, including the interpretation of AI models and the integration of large volumes of data. Finally, it forecasts future trends and the potential impact of AI on analytical chemistry, emphasizing the need for ethical and secure approaches in the use of AI.

Virtual node graph neural network for full phonon prediction

Understanding the structure-property relationship is crucial for designing materials with desired properties. The past few years have witnessed remarkable progress in machine-learning methods for this connection. However, substantial challenges remain, including the generalizability of models and prediction of properties with materials-dependent output dimensions. Here we present the virtual node graph neural network to address the challenges. By developing three virtual node approaches, we achieve Γ-phonon spectra and full phonon dispersion prediction from atomic coordinates. We show that, compared with the machine-learning interatomic potentials, our approach achieves orders-of-magnitude-higher efficiency with comparable to better accuracy. This allows us to generate databases for Γ-phonon containing over 146,000 materials and phonon band structures of zeolites. Our work provides an avenue for rapid and high-quality prediction of phonon band structures enabling materials design with desired phonon properties. The virtual node method also provides a generic method for machine-learning design with a high level of flexibility.

Physics-informed neural network for acoustic resonance analysis in a one-dimensional acoustic tube

This study devised a physics-informed neural network (PINN) framework to solve the wave equation for acoustic resonance analysis. The proposed analytical model, ResoNet, minimizes the loss function for periodic solutions and conventional PINN loss functions, thereby effectively using the function approximation capability of neural networks while performing resonance analysis. Additionally, it can be easily applied to inverse problems. The resonance in a one-dimensional acoustic tube, and the effectiveness of the proposed method was validated through the forward and inverse analyses of the wave equation with energy-loss terms. In the forward analysis, the applicability of PINN to the resonance problem was evaluated via comparison with the finite-difference method. The inverse analysis, which included identifying the energy loss term in the wave equation and design optimization of the acoustic tube, was performed with good accuracy.

Machine learning-enabled forward prediction and inverse design of 4D-printed active plates

Shape transformations of active composites (ACs) depend on the spatial distribution of constituent materials. Voxel-level complex material distributions can be encoded by 3D printing, offering enormous freedom for possible shape-change 4D-printed ACs. However, efficiently designing the material distribution to achieve desired 3D shape changes is significantly challenging yet greatly needed. Here, we present an approach that combines machine learning (ML) with both gradient-descent (GD) and evolutionary algorithm (EA) to design AC plates with 3D shape changes. A residual network ML model is developed for the forward shape prediction. A global-subdomain design strategy with ML-GD and ML-EA is then used for the inverse material-distribution design. For a variety of numerically generated target shapes, both ML-GD and ML-EA demonstrate high efficiency. By further combining ML-EA with a normal distance-based loss function, optimized designs are achieved for multiple irregular target shapes. Our approach thus provides a highly efficient tool for the design of 4D-printed active composites.

AI-Based Metamaterial Design

The use of metamaterials in various devices has revolutionized applications in optics, healthcare, acoustics, and power systems. Advancements in these fields demand novel or superior metamaterials that can demonstrate targeted control of electromagnetic, mechanical, and thermal properties of matter. Traditional design systems and methods often require manual manipulations which is time-consuming and resource intensive. The integration of artificial intelligence (AI) in optimizing metamaterial design can be employed to explore variant disciplines and address bottlenecks in design. AI-based metamaterial design can also enable the development of novel metamaterials by optimizing design parameters that cannot be achieved using traditional methods. The application of AI can be leveraged to accelerate the analysis of vast data sets as well as to better utilize limited data sets via generative models. This review covers the transformative impact of AI and AI-based metamaterial design for optics, acoustics, healthcare, and power systems. The current challenges, emerging fields, future directions, and bottlenecks within each domain are discussed.

Mechanical Field Guiding Structure Design Strategy for Meta-Fiber Reinforced Hydrogel Composites by Deep Learning

Fiber-reinforced hydrogel composites are widely employed in many engineering applications, such as drug release, and flexible electronics, with more flexible mechanical properties than pure hydrogel materials. Comparing to the hydrogel strengthened by continuous fiber, the meta-fiber reinforced hydrogel provides stronger individualized design ability of deformation patterns and tunable stiffness, especially for the elaborate applications in joint, cartilage, and organ. In this paper, a novel structure design strategy based on deep learning algorithm is proposed for hydrogel reinforced by meta-fiber to achieve targeted mechanical properties, such as stress and displacement fields. A solid mechanic model for meta-fiber reinforced hydrogel is first developed to construct the dataset of fiber distribution and the corresponding mechanical properties of the composite. Generative adversarial network (GAN) is then trained to characterize the relationship between stress or displacement field, and meta-fiber distribution. The well-trained GAN is implemented to design meta-fiber reinforced hydrogel composite structure under specific operation conditions. The results show that the deep learning method may efficiently predict the structure of the hydrogel composite with satisfied confidence, and has great potential for applications in drug delivery and flexible electronics.

An updated review of functional ingredients of Manuka honey and their value-added innovations

Manuka honey (MH) is a highly prized natural product from the nectar of Leptospermum scoparium flowers. Increased competition on the global market drives MH product innovations. This review updates comparative and non-comparative studies to highlight nutritional, therapeutic, bioengineering, and cosmetic values of MH. MH is a good source of phenolics and unique chemical compounds, such as methylglyoxal, dihydroxyacetone, leptosperin glyoxal, methylsyringate and leptosin. Based on the evidence from in vitro, in vivo and clinical studies, multifunctional bioactive compounds of MH have exhibited anti-oxidative, anti-inflammatory, immunomodulatory, anti-microbial, and anti-cancer activities. There are controversial topics related to MH, such as MH grading, safety/efficacy, implied benefits, and maximum levels of contaminants concerned. Artificial intelligence can optimize MH studies related to chemical analysis, toxicity prediction, multi-functional mechanism exploration and product innovation.

Predicting rare earth elements concentration in coal ashes with multi-task neural networks

The increasing demand for rare earth elements (REEs) makes them a scarce strategic resource for technical developments. In that regard, harvesting REEs from coal ashes-a waste byproduct from coal power plants-offers an alternative solution to conventional ore-based extraction. However, this approach is bottlenecked by our ability to screen coal ashes bearing large concentrations of REEs from feedstocks-since measuring the REE content in ashes is a time-consuming and costly task requiring advanced analytical tools. Here, we propose a machine learning approach to predict the REE contents based on the bulk composition of coal ashes, easily measurable under the routine testing protocol. We introduce a multi-task neural network that simultaneously predicts the contents of different REEs. Compared to the single-task model, this model exhibits notably improved accuracy and reduced sensitivity to noise. Further model analyses reveal key data patterns for screening coal ashes with high REE concentrations. Additionally, we showcase the utilization of transfer learning to improve the adaptability of our model to coal ashes from a distinct source.

Disentangling the Effects of Laser and Electron Irradiation on AgX (X = Cl, Br, and I): Insights from Quantum Chemical Calculations

The effects on the lattice structure and electronic properties of different polymorphs of silver halide, AgX (X = Cl, Br, and I), induced by laser irradiation (LI) and electron irradiation (EI) are investigated using a first-principles approach, based on the electronic temperature (Te) within a two-temperature model (TTM) and by increasing the total number of electrons (Ne), respectively. Ab initio molecular dynamics (AIMD) simulations provide a clear visualization of how Te and Ne induce a structural and electronic transformation process during LI/EI. Our results reveal the diffusion processes of Ag and X ions, the amorphization of the AgX lattices, and a straightforward interpretation of the time evolution for the formation of Ag and X nanoclusters under high values of Te and Ne. Overall, the present work provides fine details of the underlying mechanism of LI/EI and promises to be a powerful toolbox for further cross-scale modeling of other semiconductors.

Bottom-Up Film-to-Bulk Assembly Toward Bioinspired Bulk Structural Nanocomposites

Biological materials, although composed of meager minerals and biopolymers, often exhibit amazing mechanical properties far beyond their components due to hierarchically ordered structures. Understanding their structure-properties relationships and replicating them into artificial materials would boost the development of bulk structural nanocomposites. Layered microstructure widely exists in biological materials, serving as the fundamental structure in nanosheet-based nacres and nanofiber-based Bouligand tissues, and implying superior mechanical properties. High-efficient and scalable fabrication of bioinspired bulk structural nanocomposites with precise layered microstructure is therefore important yet remains difficult. Here, one straightforward bottom-up film-to-bulk assembly strategy is focused for fabricating bioinspired layered bulk structural nanocomposites. The bottom-up assembly strategy inherently offers a methodology for precise construction of bioinspired layered microstructure in bulk form, availability for fabrication of bioinspired bulk structural nanocomposites with large sizes and complex shapes, possibility for design of multiscale interfaces, feasibility for manipulation of diverse heterogeneities. Not limited to discussing what has been achieved by using the current bottom-up film-to-bulk assembly strategy, it is also envisioned how to promote such an assembly strategy to better benefit the development of bioinspired bulk structural nanocomposites. Compared to other assembly strategies, the highlighted strategy provides great opportunities for creating bioinspired bulk structural nanocomposites on demand.

Tough Hydrogels with Different Toughening Mechanisms and Applications

Load-bearing biological tissues, such as cartilage and muscles, exhibit several crucial properties, including high elasticity, strength, and recoverability. These characteristics enable these tissues to endure significant mechanical stresses and swiftly recover after deformation, contributing to their exceptional durability and functionality. In contrast, while hydrogels are highly biocompatible and hold promise as synthetic biomaterials, their inherent network structure often limits their ability to simultaneously possess a diverse range of superior mechanical properties. As a result, the applications of hydrogels are significantly constrained. This article delves into the design mechanisms and mechanical properties of various tough hydrogels and investigates their applications in tissue engineering, flexible electronics, and other fields. The objective is to provide insights into the fabrication and application of hydrogels with combined high strength, stretchability, toughness, and fast recovery as well as their future development directions and challenges.

Maximizing Triboelectric Nanogenerators by Physics-Informed AI Inverse Design

Triboelectric nanogenerators offer an environmentally friendly approach to harvesting energy from mechanical excitations. This capability has made them widely sought-after as an efficient, renewable, and sustainable energy source, with the potential to decrease reliance on traditional fossil fuels. However, developing triboelectric nanogenerators with specific output remains a challenge mainly due to the uncertainties associated with their complex designs for real-life applications. Artificial intelligence-enabled inverse design is a powerful tool to realize performance-oriented triboelectric nanogenerators. This is an emerging scientific direction that can address the concerns about the design and optimization of triboelectric nanogenerators leading to a next generation nanogenerator systems. This perspective paper aims at reviewing the principal analysis of triboelectricity, summarizing the current challenges of designing and optimizing triboelectric nanogenerators, and highlighting the physics-informed inverse design strategies to develop triboelectric nanogenerators. Strategic inverse design is particularly discussed in the contexts of expanding the four-mode analytical models by physics-informed artificial intelligence, discovering new conductive and dielectric materials, and optimizing contact interfaces. Various potential development levels of artificial intelligence-enhanced triboelectric nanogenerators are delineated. Finally, the potential of physics-informed artificial intelligence inverse design to propel triboelectric nanogenerators from prototypes to multifunctional intelligent systems for real-life applications is discussed.

Machine learning assisted biosensing technology: An emerging powerful tool for improving the intelligence of food safety detection

Recently, the application of biosensors in food safety assessment has gained considerable research attention. Nevertheless, the evaluation of biosensors' sensitivity, accuracy, and efficiency is still ongoing. The advent of machine learning has enhanced the application of biosensors in food security assessment, yielding improved results. Machine learning has been preliminarily applied in combination with different biosensors in food safety assessment, with positive results. This review offers a comprehensive summary of the diverse machine learning methods employed in biosensors for food safety. Initially, the primary machine learning methods were outlined, and the integrated application of biosensors and machine learning in food safety was thoroughly examined. Lastly, the challenges and limitations of machine learning and biosensors in the realm of food safety were underscored, and potential solutions were explored. The review's findings demonstrated that algorithms grounded in machine learning can aid in the early detection of food safety issues. Furthermore, preliminary research suggests that biosensors could be optimized through machine learning for real-time, multifaceted analyses of food safety variables and their interactions. The potential of machine learning and biosensors in real-time monitoring of food quality has been discussed.

Unlocking the Potential of the ANN Optimization in Sweet Potato Varieties Drying Processes

This study explores the unexploited potential of Artificial Neural Network (ANN) optimization techniques in enhancing different drying methods and their influence on the characteristics of various sweet potato varieties. Focusing on the intricate interplay between drying methods and the unique characteristics of white, pink, orange, and purple sweet potatoes, the presented experimental study indicates the impact of ANN-driven optimization on food-related characteristics such as color, phenols content, biological activities (antioxidant, antimicrobial, anti-hyperglycemic, and anti-inflammatory), chemical, and mineral contents. The results unveil significant variations in drying method efficacy across different sweet potato types, underscoring the need for tailored optimization strategies. Specifically, purple sweet potatoes emerge as robust carriers of phenolic compounds, showcasing superior antioxidant activities. Furthermore, this study reveals the optimized parameters of dried sweet potato, such as total phenols content of 1677.76 mg/100 g and anti-inflammatory activity of 8.93%, anti-hyperglycemic activity of 24.42%. The upgraded antioxidant capability is presented through DPPH●, ABTS●+, RP, and SoA assays with values of 1500.56, 10,083.37, 3130.81, and 22,753.97 μg TE/100 g, respectively. Additionally, the moisture content in the lyophilized sample reached a minimum of 2.97%, holding favorable chemical and mineral contents. The utilization of ANN optimization proves instrumental in interpreting complex interactions and unlocking efficiencies in sweet potato drying processes, thereby contributing valuable insights to food science and technology.

Evolution of dislocation substructures in metals via high-strain-rate nanoindentation

Deformation at high strain rates often results in high stresses on many engineering materials, potentially leading to catastrophic failure without proper design. High-strain-rate mechanical testing is thus needed to improve the design of future structural materials for a wide range of applications. Although several high-strain-rate mechanical testing techniques have been developed to provide a fundamental understanding of material responses and microstructural evolution under high-strain-rate deformation conditions, these tests are often very time consuming and costly. In this work, we utilize a high-strain-rate nanoindentation testing technique and system in combination with transmission electron microscopy to reveal the deformation mechanisms and dislocation substructures that evolve in pure metals from low (10-2 s-1) to very high indentation strain rates (104 s-1), using face-centered cubic aluminum and body-centered cubic molybdenum as model materials. The results help to establish the conditions under which micro- and macro-scale tests can be compared with validity and also provide a promising pathway that could lead to accelerated high-strain-rate testing at substantially reduced costs.

Machine learning-based inverse design methods considering data characteristics and design space size in materials design and manufacturing: a review

In the last few decades, the influence of machine learning has permeated many areas of science and technology, including the field of materials science. This toolkit of data driven methods accelerated the discovery and production of new materials by accurately predicting the complicated physical processes and mechanisms that are not fully described by existing materials theories. However, the availability of a growing number of increasingly complex machine learning models confronts us with the question of "which machine learning algorithm to employ". In this review, we provide a comprehensive review of common machine learning algorithms used for materials design, as well as a guideline for selecting the most appropriate model considering the nature of the design problem. To this end, we classify the material design problems into four categories of: (i) the training data set being sufficiently large to capture the trend of design space (interpolation problem), (ii) a vast design space that cannot be explored thoroughly with the initial training data set alone (extrapolation problem), (iii) multi-fidelity datasets (small accurate dataset and large approximate dataset), and (iv) only a small dataset available. The most successful machine learning-based surrogate models and design approaches will be discussed for each case along with pertinent literature. This review focuses mostly on the use of ML algorithms for the inverse design of complicated composite structures, a topic that has received a lot of attention recently with the rise of additive manufacturing.

Algorithmic encoding of adaptive responses in temperature-sensing multimaterial architectures

We envision programmable matters that can alter their physical properties in desirable manners based on user input or autonomous sensing. This vision motivates the pursuit of mechanical metamaterials that interact with the environment in a programmable fashion. However, this has not been systematically achieved for soft metamaterials because of the highly nonlinear deformation and underdevelopment of rational design strategies. Here, we use computational morphogenesis and multimaterial polymer 3D printing to systematically create soft metamaterials with arbitrarily programmable temperature-switchable nonlinear mechanical responses under large deformations. This is made possible by harnessing the distinct glass transition temperatures of different polymers, which, when optimally synthesized, produce local and giant stiffness changes in a controllable manner. Featuring complex geometries, the generated structures and metamaterials exhibit fundamentally different yet programmable nonlinear force-displacement relations and deformation patterns as temperature varies. The rational design and fabrication establish an objective-oriented synthesis of metamaterials with freely tunable thermally adaptive behaviors. This imbues structures and materials with environment-aware intelligence.

Deep Learning in Mechanical Metamaterials: From Prediction and Generation to Inverse Design

Mechanical metamaterials are meticulously designed structures with exceptional mechanical properties determined by their microstructures and constituent materials. Tailoring their material and geometric distribution unlocks the potential to achieve unprecedented bulk properties and functions. However, current mechanical metamaterial design considerably relies on experienced designers' inspiration through trial and error, while investigating their mechanical properties and responses entails time-consuming mechanical testing or computationally expensive simulations. Nevertheless, recent advancements in deep learning have revolutionized the design process of mechanical metamaterials, enabling property prediction and geometry generation without prior knowledge. Furthermore, deep generative models can transform conventional forward design into inverse design. Many recent studies on the implementation of deep learning in mechanical metamaterials are highly specialized, and their pros and cons may not be immediately evident. This critical review provides a comprehensive overview of the capabilities of deep learning in property prediction, geometry generation, and inverse design of mechanical metamaterials. Additionally, this review highlights the potential of leveraging deep learning to create universally applicable datasets, intelligently designed metamaterials, and material intelligence. This article is expected to be valuable not only to researchers working on mechanical metamaterials but also those in the field of materials informatics.

Untapped Potential of Deep Eutectic Solvents for the Synthesis of Bioinspired Inorganic-Organic Materials

Since the discovery of deep eutectic solvents (DESs) in 2003, significant progress has been made in the field, specifically advancing aspects of their preparation and physicochemical characterization. Their low-cost and unique tailored properties are reasons for their growing importance as a sustainable medium for the resource-efficient processing and synthesis of advanced materials. In this paper, the significance of these designer solvents and their beneficial features, in particular with respect to biomimetic materials chemistry, is discussed. Finally, this article explores the unrealized potential and advantageous aspects of DESs, focusing on the development of biomineralization-inspired hybrid materials. It is anticipated that this article can stimulate new concepts and advances providing a reference for breaking down the multidisciplinary borders in the field of bioinspired materials chemistry, especially at the nexus of computation and experiment, and to develop a rigorous materials-by-design paradigm.

Contemporary Role and Applications of Artificial Intelligence in Dentistry

Artificial Intelligence (AI) technologies play a significant role and significantly impact various sectors, including healthcare, engineering, sciences, and smart cities. AI has the potential to improve the quality of patient care and treatment outcomes while minimizing the risk of human error. Artificial Intelligence (AI) is transforming the dental industry, just like it is revolutionizing other sectors. It is used in dentistry to diagnose dental diseases and provide treatment recommendations. Dental professionals are increasingly relying on AI technology to assist in diagnosis, clinical decision-making, treatment planning, and prognosis prediction across ten dental specialties. One of the most significant advantages of AI in dentistry is its ability to analyze vast amounts of data quickly and accurately, providing dental professionals with valuable insights to enhance their decision-making processes. The purpose of this paper is to identify the advancement of artificial intelligence algorithms that have been frequently used in dentistry and assess how well they perform in terms of diagnosis, clinical decision-making, treatment, and prognosis prediction in ten dental specialties; dental public health, endodontics, oral and maxillofacial surgery, oral medicine and pathology, oral & maxillofacial radiology, orthodontics and dentofacial orthopedics, pediatric dentistry, periodontics, prosthodontics, and digital dentistry in general. We will also show the pros and cons of using AI in all dental specialties in different ways. Finally, we will present the limitations of using AI in dentistry, which made it incapable of replacing dental personnel, and dentists, who should consider AI a complimentary benefit and not a threat.

IRMSwin-T: A lightweight shifted windows transformer based on inverted residual structure and residual multi-layer perceptron for rolling bearing fault diagnosis

The data-driven fault diagnosis method has achieved many good results. However, classical convolutional and recurrent neural networks have problems with large parameters and poor anti-noise performance. To solve these problems, we propose a lightweight shifted windows transformer based on inverted residual structure and residual multi-layer perceptron (IRMSwin-T) for fault diagnosis of rolling bearings. First, the original data are expanded by using overlapping sampling technology. Then, the collected one-dimensional vibration signals are vector serialized by using the patch embedding strategy. Finally, the IRMSwin-T network is developed to extract features of vector sequences and classify faults. The experimental results showed that compared with mainstream lightweight models, the IRMSwin-T model in this paper has fewer parameters and higher diagnostic accuracy.

Application of Machine Learning in Material Synthesis and Property Prediction

Material innovation plays a very important role in technological progress and industrial development. Traditional experimental exploration and numerical simulation often require considerable time and resources. A new approach is urgently needed to accelerate the discovery and exploration of new materials. Machine learning can greatly reduce computational costs, shorten the development cycle, and improve computational accuracy. It has become one of the most promising research approaches in the process of novel material screening and material property prediction. In recent years, machine learning has been widely used in many fields of research, such as superconductivity, thermoelectrics, photovoltaics, catalysis, and high-entropy alloys. In this review, the basic principles of machine learning are briefly outlined. Several commonly used algorithms in machine learning models and their primary applications are then introduced. The research progress of machine learning in predicting material properties and guiding material synthesis is discussed. Finally, a future outlook on machine learning in the materials science field is presented.

Unleashing the Power of Artificial Intelligence in Materials Design

The integration of artificial intelligence (AI) algorithms in materials design is revolutionizing the field of materials engineering thanks to their power to predict material properties, design de novo materials with enhanced features, and discover new mechanisms beyond intuition. In addition, they can be used to infer complex design principles and identify high-quality candidates more rapidly than trial-and-error experimentation. From this perspective, herein we describe how these tools can enable the acceleration and enrichment of each stage of the discovery cycle of novel materials with optimized properties. We begin by outlining the state-of-the-art AI models in materials design, including machine learning (ML), deep learning, and materials informatics tools. These methodologies enable the extraction of meaningful information from vast amounts of data, enabling researchers to uncover complex correlations and patterns within material properties, structures, and compositions. Next, a comprehensive overview of AI-driven materials design is provided and its potential future prospects are highlighted. By leveraging such AI algorithms, researchers can efficiently search and analyze databases containing a wide range of material properties, enabling the identification of promising candidates for specific applications. This capability has profound implications across various industries, from drug development to energy storage, where materials performance is crucial. Ultimately, AI-based approaches are poised to revolutionize our understanding and design of materials, ushering in a new era of accelerated innovation and advancement.

Artificial intelligence enhanced sensors - enabling technologies to next-generation healthcare and biomedical platform

The fourth industrial revolution has led to the development and application of health monitoring sensors that are characterized by digitalization and intelligence. These sensors have extensive applications in medical care, personal health management, elderly care, sports, and other fields, providing people with more convenient and real-time health services. However, these sensors face limitations such as noise and drift, difficulty in extracting useful information from large amounts of data, and lack of feedback or control signals. The development of artificial intelligence has provided powerful tools and algorithms for data processing and analysis, enabling intelligent health monitoring, and achieving high-precision predictions and decisions. By integrating the Internet of Things, artificial intelligence, and health monitoring sensors, it becomes possible to realize a closed-loop system with the functions of real-time monitoring, data collection, online analysis, diagnosis, and treatment recommendations. This review focuses on the development of healthcare artificial sensors enhanced by intelligent technologies from the aspects of materials, device structure, system integration, and application scenarios. Specifically, this review first introduces the great advances in wearable sensors for monitoring respiration rate, heart rate, pulse, sweat, and tears; implantable sensors for cardiovascular care, nerve signal acquisition, and neurotransmitter monitoring; soft wearable electronics for precise therapy. Then, the recent advances in volatile organic compound detection are highlighted. Next, the current developments of human-machine interfaces, AI-enhanced multimode sensors, and AI-enhanced self-sustainable systems are reviewed. Last, a perspective on future directions for further research development is also provided. In summary, the fusion of artificial intelligence and artificial sensors will provide more intelligent, convenient, and secure services for next-generation healthcare and biomedical applications.

Machine learning dislocation density correlations and solute effects in Mg-based alloys

Magnesium alloys, among the lightest structural materials, represent excellent candidates for lightweight applications. However, industrial applications remain limited due to relatively low strength and ductility. Solid solution alloying has been shown to enhance Mg ductility and formability at relatively low concentrations. Zn solutes are significantly cost effective and common. However, the intrinsic mechanisms by which the addition of solutes leads to ductility improvement remain controversial. Here, by using a high throughput analysis of intragranular characteristics through data science approaches, we study the evolution of dislocation density in polycrystalline Mg and also, Mg-Zn alloys. We apply machine learning techniques in comparing electron back-scatter diffraction (EBSD) images of the samples before/after alloying and before/after deformation to extract the strain history of individual grains, and to predict the dislocation density level after alloying and after deformation. Our results are promising given that moderate predictions (coefficient of determination [Formula: see text] ranging from 0.25 to 0.32) are achieved already with a relatively small dataset ([Formula: see text] 5000 sub-millimeter grains).

Effective data sampling strategies and boundary condition constraints of physics-informed neural networks for identifying material properties in solid mechanics

Material identification is critical for understanding the relationship between mechanical properties and the associated mechanical functions. However, material identification is a challenging task, especially when the characteristic of the material is highly nonlinear in nature, as is common in biological tissue. In this work, we identify unknown material properties in continuum solid mechanics via physics-informed neural networks (PINNs). To improve the accuracy and efficiency of PINNs, we develop efficient strategies to nonuniformly sample observational data. We also investigate different approaches to enforce Dirichlet-type boundary conditions (BCs) as soft or hard constraints. Finally, we apply the proposed methods to a diverse set of time-dependent and time-independent solid mechanic examples that span linear elastic and hyperelastic material space. The estimated material parameters achieve relative errors of less than 1%. As such, this work is relevant to diverse applications, including optimizing structural integrity and developing novel materials.

Fill in the Blank: Transferrable Deep Learning Approaches to Recover Missing Physical Field Information

Solving materials engineering tasks is often hindered by limited information, such as in inverse problems with only boundary data information or design tasks with a simple objective but a vast search space. To address these challenges, multiple deep learning (DL) architectures are leveraged to predict missing mechanical information given limited known data in part of the domain, and further characterize the composite geometries from the recovered mechanical fields for 2D and 3D complex microstructures. In 2D, a conditional generative adversarial network (GAN) is utilized to complete partially masked field maps and predict the composite geometry with convolutional models with great accuracy and generality by making precise predictions on field data with mixed stress/strain components, hierarchical geometries, distinct materials properties and various types of microstructures including ill-posed inverse problems. In 3D, a Transformer-based architecture is implemented to predict complete 3D mechanical fields from input field snapshots. The model manifests excellent performance regardless of microstructural complexity and recovers the entire bulk field even from a single surface field image, allowing internal structural characterization from only boundary measurements. The whole frameworks provide efficient ways for analysis and design with incomplete information and allow the direct inverse translation from properties back to materials structures.

CyRSoXS: a GPU-accelerated virtual instrument for polarized resonant soft X-ray scattering

Polarized resonant soft X-ray scattering (P-RSoXS) has emerged as a powerful synchrotron-based tool that combines the principles of X-ray scattering and X-ray spectroscopy. P-RSoXS provides unique sensitivity to molecular orientation and chemical heterogeneity in soft materials such as polymers and biomaterials. Quantitative extraction of orientation information from P-RSoXS pattern data is challenging, however, because the scattering processes originate from sample properties that must be represented as energy-dependent three-dimensional tensors with heterogeneities at nanometre to sub-nanometre length scales. This challenge is overcome here by developing an open-source virtual instrument that uses graphical processing units (GPUs) to simulate P-RSoXS patterns from real-space material representations with nanoscale resolution. This computational framework - called CyRSoXS (https://github.com/usnistgov/cyrsoxs) - is designed to maximize GPU performance, including algorithms that minimize both communication and memory footprints. The accuracy and robustness of the approach are demonstrated by validating against an extensive set of test cases, which include both analytical solutions and numerical comparisons, demonstrating an acceleration of over three orders of magnitude relative to the current state-of-the-art P-RSoXS simulation software. Such fast simulations open up a variety of applications that were previously computationally unfeasible, including pattern fitting, co-simulation with the physical instrument for operando analytics, data exploration and decision support, data creation and integration into machine learning workflows, and utilization in multi-modal data assimilation approaches. Finally, the complexity of the computational framework is abstracted away from the end user by exposing CyRSoXS to Python using Pybind. This eliminates input/output requirements for large-scale parameter exploration and inverse design, and democratizes usage by enabling seamless integration with a Python ecosystem (https://github.com/usnistgov/nrss) that can include parametric morphology generation, simulation result reduction, comparison with experiment and data fitting approaches.

Utilizing ANN for Predicting the Cauchy Stress and Lateral Stretch of Random Elastomeric Foams under Uniaxial Loading

As a result of their cell structures, elastomeric foams exhibit high compressibility and are frequently used as buffer cushions in energy absorption. Foam pads between two surfaces typically withstand uniaxial loads. In this paper, we considered the effects of porosity and cell size on the mechanical behavior of random elastomeric foams, and proposed a constitutive model based on an artificial neural network (ANN). Uniform cell size distribution was used to represent monodisperse foam. The constitutive relationship between Cauchy stress and the four input variables of axial stretch λ_U, lateral stretch λ_L, porosity φ, and cell size θ was given by con-ANN. The mechanical responses of 500 different foam structures (20% < φ < 60%, 0.1 mm < θ < 0.5 mm) under compression and tension loads (0.4 < λ_U < 3) were simulated, and a dataset containing 100,000 samples was constructed. We also introduced a pre-ANN to predict lateral stretch to address the issue of missing lateral strain data in practical applications. By combining physical experience, we chose appropriate input forms and activation functions to improve ANN's extrapolation capability. The results showed that pre-ANN and con-ANN could provide reasonable predictions for λ_U outside the dataset. We can obtain accurate lateral stretch and axial stress predictions from two ANNs. The porosity affects the stress and λ_L, while the cell size only affects the stress during foam compression.

Artificial Intelligence in Physical Sciences: Symbolic Regression Trends and Perspectives

Symbolic regression (SR) is a machine learning-based regression method based on genetic programming principles that integrates techniques and processes from heterogeneous scientific fields and is capable of providing analytical equations purely from data. This remarkable characteristic diminishes the need to incorporate prior knowledge about the investigated system. SR can spot profound and elucidate ambiguous relations that can be generalizable, applicable, explainable and span over most scientific, technological, economical, and social principles. In this review, current state of the art is documented, technical and physical characteristics of SR are presented, the available programming techniques are investigated, fields of application are explored, and future perspectives are discussed.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11831-023-09922-z.

3D Printability of Silk/Hydroxyapatite Composites for Microprosthetic Applications

Micro-prosthetics requires the fabrication of mechanically robust and personalized components with sub-millimetric feature accuracy. Three-dimensional (3D) printing technologies have had a major impact on manufacturing such miniaturized devices for biomedical applications; however, biocompatibility requirements greatly constrain the choice of usable materials. Hydroxyapatite (HA) and its composites have been widely employed to fabricate bone-like structures, especially at the macroscale. In this work, we investigate the rheology, printability, and prosthetic mechanical properties of HA and HA-silk protein composites, focusing on the roles of composition and water content. We correlate key linear and nonlinear shear rheological parameters to geometric outcomes of printing and explain how silk compensates for the inherent brittleness of printed HA components. By increasing ink ductility, the inclusion of silk improves the quality of printed items through two mechanisms: (1) reducing underextrusion by lowering the required elastic modulus and, (2) reducing slumping by increasing the ink yield stress proportional to the modulus. We demonstrate that the elastic modulus and compressive strength of parts fabricated from silk-HA inks are higher than those for rheologically comparable pure-HA inks. We construct a printing map to guide the manufacturing of HA-based inks with excellent final properties, especially for use in biomedical applications for which sub-millimetric features are required.

Computational Design and Manufacturing of Sustainable Materials through First-Principles and Materiomics

Engineered materials are ubiquitous throughout society and are critical to the development of modern technology, yet many current material systems are inexorably tied to widespread deterioration of ecological processes. Next-generation material systems can address goals of environmental sustainability by providing alternatives to fossil fuel-based materials and by reducing destructive extraction processes, energy costs, and accumulation of solid waste. However, development of sustainable materials faces several key challenges including investigation, processing, and architecting of new feedstocks that are often relatively mechanically weak, complex, and difficult to characterize or standardize. In this review paper, we outline a framework for examining sustainability in material systems and discuss how recent developments in modeling, machine learning, and other computational tools can aid the discovery of novel sustainable materials. We consider these through the lens of materiomics, an approach that considers material systems holistically by incorporating perspectives of all relevant scales, beginning with first-principles approaches and extending through the macroscale to consider sustainable material design from the bottom-up. We follow with an examination of how computational methods are currently applied to select examples of sustainable material development, with particular emphasis on bioinspired and biobased materials, and conclude with perspectives on opportunities and open challenges.

Accelerating the design of compositionally complex materials via physics-informed artificial intelligence

The chemical space for designing materials is practically infinite. This makes disruptive progress by traditional physics-based modeling alone challenging. Yet, training data for identifying composition-structure-property relations by artificial intelligence are sparse. We discuss opportunities to discover new chemically complex materials by hybrid methods where physics laws are combined with artificial intelligence.

Perspectives on development of biomedical polymer materials in artificial intelligence age

Polymer materials are widely used in biomedicine, chemistry and material science, whose traditional preparations are mainly based on experience, intuition and conceptual insight, having been applied to the development of many new materials, but facing great challenges due to the vast design space for biomedical polymers. So far, the best way to solve these problems is to accelerate material design through artificial intelligence, especially machine learning. Herein, this paper will introduce several successful cases, and analyze the latest progress of machine learning in the field of biomedical polymers, then discuss the opportunities of this novel method. In particular, this paper summarizes the material database, open-source determination tools, molecular generation methods and machine learning models that have been used for biopolymer synthesis and property prediction. Overall, machine learning could be more effectively deployed on the material design of biomedical polymers, and it is expected to become an extensive driving force to meet the huge demand for customized designs.

Multimodal Deep-Learning Framework for Accurate Prediction of Wettability Evolution of Laser-Textured Surfaces

The lengthy process through which laser-textured surfaces transform from hydrophilic to hydrophobic severely restricts their practical applications. Accurately predicting the wettability evolution curve is crucial; however, developing a reliable prediction model remains challenging. Herein, a data-driven multimodal deep-learning framework was developed, in which multimodal data of micro/nanostructure morphology images, composition distribution images, and time information are effectively coupled and fed into a convolutional neural network (CNN). Rich data input and in-depth data mining make the framework more robust, achieving accurate prediction of the wettability evolution curves of various typical micro/nanostructures. Additionally, accurate prediction of input images with varying magnifications and untrained laser-textured surfaces demonstrates the generalizability of the multimodal CNN framework. The visualization results of the convolution layer confirmed the rationality of the information learned by the model. Additionally, the proposed multimodal CNN framework was successfully utilized to investigate the optimization process. Further, a laser-textured surface with a shorter evolution period and a larger final contact angle was realized. The proposed multimodal CNN framework offers an efficient and cost-effective method for predicting the wettability evolution curves and exploring the optimization processes, enhancing the application potential of laser micro/nanofabrication of superhydrophobic surfaces.

Hybrid Data-Driven Deep Learning Framework for Material Mechanical Properties Prediction with the Focus on Dual-Phase Steel Microstructures

A comprehensive approach to understand the mechanical behavior of materials involves costly and time-consuming experiments. Recent advances in machine learning and in the field of computational material science could significantly reduce the need for experiments by enabling the prediction of a material's mechanical behavior. In this paper, a reliable data pipeline consisting of experimentally validated phase field simulations and finite element analysis was created to generate a dataset of dual-phase steel microstructures and mechanical behaviors under different heat treatment conditions. Afterwards, a deep learning-based method was presented, which was the hybridization of two well-known transfer-learning approaches, ResNet50 and VGG16. Hyper parameter optimization (HPO) and fine-tuning were also implemented to train and boost both methods for the hybrid network. By fusing the hybrid model and the feature extractor, the dual-phase steels' yield stress, ultimate stress, and fracture strain under new treatment conditions were predicted with an error of less than 1%.

End-to-End Protein Normal Mode Frequency Predictions Using Language and Graph Models and Application to Sonification

The prediction of mechanical and dynamical properties of proteins is an important frontier, especially given the greater availability of proteins structures. Here we report a series of models that provide end-to-end predictions of nanodynamical properties of proteins, focused on high-throughput normal mode predictions directly from the amino acid sequence. Using neural network models within the family of Natural Language Processing and graph-based methods, we offer atomistically based mechanistic predictions of key protein mechanical features. The models include an end-to-end long short-term memory (LSTM) model, an end-to-end transformer model, a graph-based transformer model, and an equivariant graph neural network. All four models show exceptional performance, with the graph-based transformer architecture offering the best results but at the cost of requiring a graph structure as input. Conversely, the LSTM and transformer models offer end-to-end sequence-to-property prediction capabilities, providing efficient avenues for protein engineering, analysis, and design. We compare our results against published data based on a Principal Neighborhood Aggregation graph neural network, revealing that the transformer model offers better performance while also being able to predict a large set of the first 64 normal mode frequencies, simultaneously. The use of the end-to-end transformer model may facilitate other downstream applications through the use of transfer learning, and it offers a comprehensive prediction of dynamical properties without any structural knowledge, directly from the amino acid sequence. We demonstrate a potential application in scientific sonification, where the normal mode frequencies are transposed to generate audible signals for a detailed analysis of subtle changes of protein sequences.

Predicting stress, strain and deformation fields in materials and structures with graph neural networks

Developing accurate yet fast computational tools to simulate complex physical phenomena is a long-standing problem. Recent advances in machine learning have revolutionized the way simulations are approached, shifting from a purely physics- to AI-based paradigm. Although impressive achievements have been reached, efficiently predicting complex physical phenomena in materials and structures remains a challenge. Here, we present an AI-based general framework, implemented through graph neural networks, able to learn complex mechanical behavior of materials from a few hundreds data. Harnessing the natural mesh-to-graph mapping, our deep learning model predicts deformation, stress, and strain fields in various material systems, like fiber and stratified composites, and lattice metamaterials. The model can capture complex nonlinear phenomena, from plasticity to buckling instability, seemingly learning physical relationships between the predicted physical fields. Owing to its flexibility, this graph-based framework aims at connecting materials' microstructure, base materials' properties, and boundary conditions to a physical response, opening new avenues towards graph-AI-based surrogate modeling.

Multiscale Modeling at the Interface of Molecular Mechanics and Natural Language through Attention Neural Networks

Humans are continually bombarded with massive amounts of data. To deal with this influx of information, we use the concept of attention in order to perceive the most relevant input from vision, hearing, touch, and others. Thereby, the complex ensemble of signals is used to generate output by querying the processed data in appropriate ways. Attention is also the hallmark of the development of scientific theories, where we elucidate which parts of a problem are critical, often expressed through differential equations. In this Account we review the emergence of attention-based neural networks as a class of approaches that offer many opportunities to describe materials across scales and modalities, including how universal building blocks interact to yield a set of material properties. In fact, the self-assembly of hierarchical, structurally complex, and multifunctional biomaterials remains a grand challenge in modeling, theory, and experiment. Expanding from the process by which material building blocks physically interact to form a type of material, in this Account we view self-assembly as both the functional emergence of properties from interacting building blocks as well as the physical process by which elementary building blocks interact and yield structure and, thereby, functions. This perspective, integrated through the theory of materiomics, allows us to solve multiscale problems with a first-principles-based computational approach based on attention-based neural networks that transform information to feature to property while providing a flexible modeling approach that can integrate theory, simulation, and experiment. Since these models are based on a natural language framework, they offer various benefits including incorporation of general domain knowledge via general-purpose pretraining, which can be accomplished without labeled data or large amounts of lower-quality data. Pretrained models then offer a general-purpose platform that can be fine-tuned to adapt these models to make specific predictions, often with relatively little labeled data. The transferrable power of the language-based modeling approach realizes a neural olog description, where mathematical categorization is learned by multiheaded attention, without domain knowledge in its formulation. It can hence be applied to a range of complex modeling tasks─such as physical field predictions, molecular properties, or structure predictions, all using an identical formulation. This offers a complementary modeling approach that is already finding numerous applications, with great potential to solve complex assembly problems, enabling us to learn, build, and utilize functional categorization of how building blocks yield a range of material functions. In this Account, we demonstrate the approach in various application areas, including protein secondary structure prediction and prediction of normal-mode frequencies as well as predicting mechanical fields near cracks. Unifying these diverse problem areas is the building block approach, where the models are based on a universally applicable platform that offers benefits ranging from transferability, interpretability, and cross-domain pollination of knowledge as exemplified through a transformer model applied to predict how musical compositions infer de novo protein structures. We discuss future potentialities of this approach for a variety of material phenomena across scales, including the use in multiparadigm modeling schemes.

Predictive Modeling of Soft Stretchable Nanocomposites Using Recurrent Neural Networks

Human skin is characterized by rough, elastic, and uneven features that are difficult to recreate using conventional manufacturing technologies and rigid materials. The use of soft materials is a promising alternative to produce devices that mimic the tactile capabilities of biological tissues. Although previous studies have revealed the potential of fillers to modify the properties of composite materials, there is still a gap in modeling the conductivity and mechanical properties of these types of materials. While traditional Finite Element approximations can be used, these methodologies tend to be highly demanding of time and processing power. Instead of this approach, a data-driven learning-based approximation strategy can be used to generate prediction models via neural networks. This paper explores the fabrication of flexible nanocomposites using polydimethylsiloxane (PDMS) with different single-walled carbon nanotubes (SWCNTs) loadings (0.5, 1, and 1.5 wt.%). Simple Recurrent Neural Networks (SRNN), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRU) models were formulated, trained, and tested to obtain the predictive sequence data of out-of-plane quasistatic mechanical tests. Finally, the model learned is applied to a dynamic system using the Kelvin-Voight model and the phenomenon known as the bouncing ball. The best predictive results were achieved using a nonlinear activation function in the SRNN model implementing two units and 4000 epochs. These results suggest the feasibility of a hybrid approach of analogy-based learning and data-driven learning for the design and computational analysis of soft and stretchable nanocomposite materials.

An automated biomateriomics platform for sustainable programmable materials discovery

Recently, the potential to create functional materials from various forms of organic matter has received increased interest due to its potential to address environmental concerns. However, the process of creating novel materials from biomass requires extensive experimentation. A promising means of predicting the properties of such materials would be the use of machine-learning models trained on or integrated into self-learned experimental data and methods. We outline an automated system for the discovery and characterization of novel, sustainable, and functional materials from input biomass. Artificial intelligence provides the capacity to examine experimental data, draw connections between composite composition and behavior, and design future experiments to expand the system's understanding of the studied materials. Extensions to the system are described that could further accelerate the discovery of sustainable composites, including the use of interpretable machine-learning methods to expand the insights gleaned from to human-readable materiomic insights about material process-structure-functional relationships.

Al-Sn-Al Bonding Strength Investigation Based on Deep Learning Model

Al-Sn-Al wafer bonding is a new semiconductor manufacturing technology that plays an important role in device manufacturing. Optimization of the bonding process and testing of the bonding strength remain key issues. However, using only physical experiments to study the above problems presents difficulties such as repeating many experiments, high costs, and low efficiency. Deep learning algorithms can quickly simulate complex physical correlations by training large amounts of data, which is a good solution to the difficulties in studying wafer bonding. Therefore, this paper proposes the use of deep learning models (2-layer CNN and 50-layer ResNet) to achieve autonomous recognition of bonding strengths corresponding to different bonding conditions, and the results from a comparative test set show that the ResNet model has an accuracy of 99.17%, outperforming the CNN model with an accuracy of 91.67%. Then, the identified images are analyzed using the Canny edge detector, which showed that the fracture surface morphology of the wafer is a hole-shaped structure, with the smaller the area of hole movement on the wafer surface, the higher the bonding strength. In addition, the effects of bonding time and bonding temperature on bonding strength are verified, showing that relatively short bonding times and relatively low bonding temperatures resulted in better wafer bonding strength. This research demonstrates the potential of using deep learning to accelerate wafer bonding strength identification and process condition optimization.

Physics-informed neural networks based on adaptive weighted loss functions for Hamilton-Jacobi equations

Physics-informed neural networks (PINN) have lately become a research hotspot in the interdisciplinary field of machine learning and computational mathematics thanks to the flexibility in tackling forward and inverse problems. In this work, we explore the generality of the PINN training algorithm for solving Hamilton-Jacobi equations, and propose physics-informed neural networks based on adaptive weighted loss functions (AW-PINN) that is trained to solve unsupervised learning tasks with fewer training data while physical information constraints are imposed during the training process. To balance the contributions from different constrains automatically, the AW-PINN training algorithm adaptively update the weight coefficients of different loss terms by using the logarithmic mean to avoid additional hyperparameter. Moreover, the proposed AW-PINN algorithm imposes the periodicity requirement on the boundary condition and its gradient. The fully connected feedforward neural networks are considered and the optimizing procedure is taken as the Adam optimizer for some steps followed by the L-BFGS-B optimizer. The series of numerical experiments illustrate that the proposed algorithm effectively achieves noticeable improvements in predictive accuracy and the convergence rate of the total training error, and can approximate the solution even when the Hamiltonian is nonconvex. A comparison between the proposed algorithm and the original PINN algorithm for Hamilton-Jacobi equations indicates that the proposed AW-PINN algorithm can train the solutions more accurately with fewer iterations.

High-Throughput Generation of 3D Graphene Metamaterials and Property Quantification Using Machine Learning

3D graphene assemblies are proposed as solutions to meet the goal toward efficient utilization of 2D graphene sheets, showing excellent performances in applications such as mechanical support, energy storage, and electrochemical catalysis. However, given the diversity and complexity of possible graphene 3D structures, there does not yet exist a systematic approach that can generate target 3D shapes and also, evaluate their performance. Here high-throughput data generation is combined with artificial intelligence approaches to realize rapid structure formation and property quantification of 3D graphene foams with mathematically controlled topologies, driven by molecular dynamics simulations. More than 4000 different foam structures are created, which feature diverse topologies that contain potential pathways for small molecules and auxetic structures with negative Poisson's ratio. Empowered by machine learning (ML) algorithms including graph neural networks, not only global properties such as elastic moduli, but also local behaviors such as atomic stress can be predicted and optimized based on their atomic structure, bypassing expensive atomistic simulations. The key findings of the research reported in this paper include a high-throughput virtual framework of generating diverse 3D graphene assemblies with mechanical performances quantification, and highly efficient methods of evaluating physical properties based on ML.