Machine learning and reasoning for predictive maintenance in Industry 4.0: Current status and challenges

Holistic exploration of reading comprehension skills, technology and socioeconomic factors in Spanish teenagers

The intricate relationship between teenagers' literacy and technology underscores the need for a comprehensive understanding, particularly in the Spanish context. This study employs explainable artificial intelligence (AI) to delve into this complex interplay, focusing on the pivotal role of reading comprehension skills in the personal and career development of Spanish teenagers. With a sample of 22,400 15-year-olds from the PISA dataset, we investigate the impact of socioeconomic factors, technology habits, parental education, residential location, and school type on reading comprehension skills. Utilizing machine learning techniques, our analysis reveals a nuanced connection between autonomy, technological proficiency, and academic performance. Notably, family oversight of technology use emerges as a crucial factor in managing the impact of digital technology and the Internet on reading comprehension skills. The study emphasizes the necessity for a balanced and supervised introduction to technology from an early age. Contrary to current trends, our findings indicate that online gaming may not contribute positively to reading comprehension skills, while moderate daily Internet use (1-4 h) proves beneficial. Furthermore, the study underscores the ongoing nature of acquiring reading comprehension and technological skills, emphasizing the need for continuous attention and guidance from childhood. Parental education levels are identified as partial predictors of children's performance, emphasizing the importance of a holistic educational approach that considers autonomy and technological literacy. This study advocates for addressing socio-economic and gender inequalities in education and highlights the crucial role of cooperation between schools and families, particularly those with lower educational levels.

Digital Twin Meets Knowledge Graph for Intelligent Manufacturing Processes

In the highly competitive field of material manufacturing, stakeholders strive for the increased quality of the end products, reduced cost of operation, and the timely completion of their business processes. Digital twin (DT) technologies are considered major enablers that can be deployed to assist the development and effective provision of manufacturing processes. Additionally, knowledge graphs (KG) have emerged as efficient tools in the industrial domain and are able to efficiently represent data from various disciplines in a structured manner while also supporting advanced analytics. This paper proposes a solution that integrates a KG and DTs. Through this synergy, we aimed to develop highly autonomous and flexible DTs that utilize the semantic knowledge stored in the KG to better support advanced functionalities. The developed KG stores information about materials and their properties and details about the processes in which they are involved, following a flexible schema that is not domain specific. The DT comprises smaller Virtual Objects (VOs), each one acting as an abstraction of a single step of the Industrial Business Process (IBP), providing the necessary functionalities that simulate the corresponding real-world process. By executing appropriate queries to the KG, the DT can orchestrate the operation of the VOs and their physical counterparts and configure their parameters accordingly, in this way increasing its self-awareness. In this article, the architecture of such a solution is presented and its application in a real laser glass bending process is showcased.

Prediction of attention deficit hyperactivity disorder based on explainable artificial intelligence

Accurate assessment of Attention Deficit Hyperactivity Disorder (ADHD) is crucial for the effective treatment of affected individuals. Traditionally, psychometric tests such as the WISC-IV have been utilized to gather evidence and identify patterns or factors contributing to ADHD diagnosis. However, in recent years, the use of machine learning (ML) models in conjunction with post-hoc eXplainable Artificial Intelligence (XAI) techniques has improved our ability to make precise predictions and provide transparent explanations. The objective of this study is twofold: firstly, to predict the likelihood of an individual receiving an ADHD diagnosis using ML algorithms, and secondly, to offer interpretable insights into the decision-making process of the ML model. The dataset under scrutiny comprises 694 cases collected over the past decade in Spain, including information on age, gender, and WISC-IV test scores. The outcome variable is the professional diagnosis. Diverse ML algorithms representing various learning styles were rigorously evaluated through a stratified 10-fold cross-validation, with performance assessed using key metrics, including accuracy, area under the receiver operating characteristic curve, sensitivity, and specificity. Models were compared using both the full set of initial features and a well-suited wrapper-type feature selection algorithm (Boruta). Following the identification of the most suitable model, Shapley additive values were computed to assign weights to each predictor based on their additive contribution to the outcome and to elucidate the predictions. Strikingly, a reduced set of 8 out of the initial 20 variables produced results comparable to using the full feature set. Among the ML models tested, the Random Forest algorithm outperformed others on most metrics (ACC = 0.90, AUC = 0.94, Sensitivity = 0.91, Specificity = 0.92). Notably, the principal predictors, ranked by importance, included GAI - CPI, WMI, CPI, PSI, VCI, WMI - PSI, PRI, and LN. Individual case examples exhibit variations in predictions depending on unique characteristics, including instances of false positives and negatives. Our ML model adeptly predicted ADHD diagnoses in 90% of cases, with potential for further enhancement by expanding our database. Furthermore, the use of XAI techniques enables the elucidation of salient factors in individual cases, thereby aiding inexperienced professionals in the diagnostic process and facilitating comparison with expert assessments. It is important to note that this tool is designed to support the ADHD diagnostic process, where the medical professional always has the final say in decision-making.

Coaxial Flexible Fiber-Shaped Triboelectric Nanogenerator Assisted by Deep Learning for Self-Powered Vibration Monitoring

Self-powered vibration sensor is highly desired for distributed and continuous monitoring requirements of Industry 4.0. Herein, a flexible fiber-shaped triboelectric nanogenerator (F-TENG) with a coaxial core-shell structure is proposed for the vibration monitoring. The F-TENG exhibits higher adaptability to the complex surfaces, which has an outstanding application prospect due to vital compensation for the existing rigid sensors. Initially, the contact characteristics between the dielectric layers, that related to the perceiving performance of the TENG, are theoretically analyzed. Such a TENG with 1D structure endows high sensitivity, allowing for accurately responding to a wide range of vibration frequencies (0.1 to 100 Hz). Even applying to the real diesel engine, the error in detecting the vibration frequencies is only 0.32% compared with the commercial vibration sensor, highlighting its potential in practical application. Further, assisted by deep learning, the recognition accuracy in monitoring nine operating conditions of the system achieves 97.87%. Overall, the newly designed F-TENG with the merits of high-adaptability, cost-efficiency, and self-powered, has offered a promising solution to fulfill an extensive range of vibration sensing applications in the future.

Green loops and clean skies: Optimizing municipal solid waste management using data science for a circular economy

The interplay between Municipal Solid Waste (MSW) Management and data science unveils a panorama of opportunities and challenges, set against the backdrop of rising global waste and evolving technological landscapes. This article threads through the multifaceted aspects of incorporating data science into MSW management, unearthing key findings, novel knowledge, and instigating a call to action for stakeholders (e.g. policymakers, local authorities, waste management professionals, technology developers, and the general public) across the spectrum. Predominant challenges like the enigmatic nature of "black-box" models and tangible knowledge gaps in the sector are scrutinized, ushering in a narrative that emphasizes transparent, stakeholder-inclusive, and policy-adaptive approaches. Notably, a conscious shift towards "white-box" and "grey-box" data science models has been spotlighted as a pivotal response to transparency issues. Furthermore, the discourse highlights the necessity of crafting data science solutions that are specifically moulded to the nuanced challenges of MSW management, and it underscores the importance of recalibrating existing policies to be reflexive to technological advancements. A resolute call echoes for stakeholders to not just adapt but immerse themselves in a continuous learning trajectory, championing transparency, and fostering collaborations that hinge on innovative, data-driven methodologies. Thus, as the realms of data science and MSW management entwine, the article sheds light on the potential transformation awaiting waste management paradigms, contingent on the nurtured amalgamation of technological advances, policy alignment, and collaborative synergy.

A Method for Predicting Production Costs Based on Data Fusion from Multiple Sources for Industry 4.0: Trends and Applications of Machine Learning Methods

There is a growing need for manufacturing processes that improve product quality and production rates while reducing costs. With the advent of multisensory information fusion technology, individuals can acquire a broader range of information. Several data fusion and machine learning methods have been discussed in this article within the context of the Industry 4.0 paradigm. Depending on its purpose, a prognostic method can be categorized as descriptive, predictive, or prescriptive. ANN and CNN models are applied to predicting production costs using neural networks based on multisource information fusion, and multisource information fusion theory is examined and applied to ANNs and CNNs. In this study, ANN and CNN predictions have been compared. CNN has demonstrated more remarkable skill in predicting the six cost categories than ANN. When predicting the true value of each cost category, CNN is superior to ANN. As a result, CNN's forecast error for the current month's total income is 0.0234. Because of its improved prediction accuracy and more straightforward training technique, CNN is better suited to incorporating information from several sources. Furthermore, both neural networks overestimate indirect costs, including direct material costs and item consumption prices.

Machine learning for fault analysis in rotating machinery: A comprehensive review

As the concept of Industry 4.0 is introduced, artificial intelligence-based fault analysis is attracted the corresponding community to develop effective intelligent fault diagnosis and prognosis (IFDP) models for rotating machinery. Hence, various challenges arise regarding model assessment, suitability for real-world applications, fault-specific model development, compound fault existence, domain adaptability, data source, data acquisition, data fusion, algorithm selection, and optimization. It is essential to resolve those challenges for each component of the rotating machinery since each issue of each part has a unique impact on the vital indicators of a machine. Based on these major obstacles, this study proposes a comprehensive review regarding IFDP procedures of rotating machinery by minding all the challenges given above for the first time. In this study, the developed IFDP approaches are reviewed regarding the pursued fault analysis strategies, considered data sources, data types, data fusion techniques, machine learning techniques within the frame of the fault type, and compound faults that occurred in components such as bearings, gear, rotor, stator, shaft, and other parts. The challenges and future directions are presented from the perspective of recent literature and the necessities concerning the IFDP of rotating machinery.

A Taxonomy and Archetypes of Business Analytics in Smart Manufacturing

Fueled by increasing data availability and the rise of technological advances for data processing and communication, business analytics is a key driver for smart manufacturing. However, due to the multitude of different local advances as well as its multidisciplinary complexity, both researchers and practitioners struggle to keep track of the progress and acquire new knowledge within the field, as there is a lack of a holistic conceptualization. To address this issue, we performed an extensive structured literature review, yielding 904 relevant hits, to develop a quadripartite taxonomy as well as to derive archetypes of business analytics in smart manufacturing. The taxonomy comprises the following meta-characteristics: application domain, orientation as the objective of the analysis, data origins, and analysis techniques. Collectively, they comprise eight dimensions with a total of 52 distinct characteristics. Using a cluster analysis, we found six archetypes that represent a synthesis of existing knowledge on planning, maintenance (reactive, offline, and online predictive), monitoring, and quality management. A temporal analysis highlights the push beyond predictive approaches and confirms that deep learning already dominates novel applications. Our results constitute an entry point to the field but can also serve as a reference work and a guide with which to assess the adequacy of one's own instruments.

Maintenance Performance in the Age of Industry 4.0: A Bibliometric Performance Analysis and a Systematic Literature Review

Recently, there has been a growing interest in issues related to maintenance performance management, which is confirmed by a significant number of publications and reports devoted to these problems. However, theoretical and application studies indicate a lack of research on the systematic literature reviews and surveys of studies that would focus on the evolution of Industry 4.0 technologies used in the maintenance area in a cross-sectional manner. Therefore, the paper reviews the existing literature to present an up-to-date and content-relevant analysis in this field. The proposed methodology includes bibliometric performance analysis and a review of the systematic literature. First, the general bibliometric analysis was conducted based on the literature in Scopus and Web of Science databases. Later, the systematic search was performed using the Primo multi-search tool following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The main inclusion criteria included the publication dates (studies published from 2012-2022), studies published in English, and studies found in the selected databases. In addition, the authors focused on research work within the scope of the Maintenance 4.0 study. Therefore, papers within the following research fields were selected: (a) augmented reality, (b) virtual reality, (c) system architecture, (d) data-driven decision, (e) Operator 4.0, and (f) cybersecurity. This resulted in the selection of the 214 most relevant papers in the investigated area. Finally, the selected articles in this review were categorized into five groups: (1) Data-driven decision-making in Maintenance 4.0, (2) Operator 4.0, (3) Virtual and Augmented reality in maintenance, (4) Maintenance system architecture, and (5) Cybersecurity in maintenance. The obtained results have led the authors to specify the main research problems and trends related to the analyzed area and to identify the main research gaps for future investigation from academic and engineering perspectives.

Machine Learning for Industry 4.0: A Systematic Review Using Deep Learning-Based Topic Modelling

Machine learning (ML) has a well-established reputation for successfully enabling automation through its scalable predictive power. Industry 4.0 encapsulates a new stage of industrial processes and value chains driven by smart connection and automation. Large-scale problems within these industrial settings are a prime example of an environment that can benefit from ML. However, a clear view of how ML currently intersects with industry 4.0 is difficult to grasp without reading an infeasible number of papers. This systematic review strives to provide such a view by gathering a collection of 45,783 relevant papers from Scopus and Web of Science and analysing it with BERTopic. We analyse the key topics to understand what industry applications receive the most attention and which ML methods are used the most. Moreover, we manually reviewed 17 white papers of consulting firms to compare the academic landscape to an industry perspective. We found that security and predictive maintenance were the most common topics, CNNs were the most used ML method and industry companies, at the moment, generally focus more on enabling successful adoption rather than building better ML models. The academic topics are meaningful and relevant but technology focused on making ML adoption easier deserves more attention.

Integrating Industry 4.0 and Total Productive Maintenance for global sustainability

Purpose

The integration of Total Productive Maintenance (TPM) and Industry 4.0 (I4.0) is an emerging model, and the global pressure of various stakeholders raises scepticism of any emerging model towards providing sustainability. Therefore, this research aims to identify and rank the potential significant drivers of an integrated model of I4.0 and TPM to guide manufacturing enterprises towards sustainability.

Design/methodology/approach

This research follows a four-phase methodology including literature review and expert opinion to select the sustainability indicators and I4.0-integrated TPM key drivers, followed by employing the analytic hierarchy process approach for weight determination of sustainability indicators. The research then deploys the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) to prioritise the I4.0-integrated TPM key drivers based on their effect on various sustainability indicators. Finally, a sensitivity analysis is conducted to check the robustness of the TOPSIS.

Findings

The findings establish the top five most influential key drivers of an I4.0-integrated TPM system, which include top management support, formal I4.0 adoption program, mid-management involvement and support, solid TPM baseline knowledge and high engagement of the production team. These top drives can lead manufacturing firms towards sustainability.

Research limitations/implications

The digitalisation of shop floor practices, such as TPM, could be adapted by shop floor managers and policymakers of manufacturing companies to deliver sustainability-oriented outcomes. In addition, this research may aid decision-makers in the manufacturing sector in identifying the most important drivers of I4.0 and TPM, which will assist them in more effectively implementing an integrated system of I4.0 and TPM to practice sustainability. The scope of TPM applicability is wide, and the current research is limited to manufacturing companies. Therefore, there is a huge scope for developing and testing the integrated system of I4.0 and TPM in other industrial settings, such as the textile, food and aerospace industries.

Originality/value

This research makes a first-of-its-kind effort to examine how an I4.0-integrated TPM model affects manufacturing companies' sustainability and how such effects might be maximised.

Machine learning approach for predicting production delays: a quarry company case study

Predictive maintenance employing machine learning techniques and big data analytics is a benefit to the industrial business in the Industry 4.0 era. Companies, on the other hand, have difficulties as they move from reactive to predictive manufacturing processes. The purpose of this paper is to demonstrate how data analytics and machine learning approaches may be utilized to predict production delays in a quarry firm as a case study. The dataset contains production records for six months, with a total of 20 columns for each production record for two machines. Cross Industry Standard Process for Data Mining approach is followed to build the machine learning models. Five predictive models were created using machine learning algorithms such as Decision Tree, Neural Network, Random Forest, Nave Bayes and Logistic Regression. The results show that Multilayer Perceptron Neural Network and Logistic Regression outperform other techniques and accurately predicts production delays with a F-measure score of 0.973. The quarry company's improved decision-making reducing potential production line delays demonstrates the value of this study.

Development of a Framework to Aid the Transition from Reactive to Proactive Maintenance Approaches to Enable Energy Reduction

The disparity between public datasets and real industrial datasets is limiting the practical application of advanced data analysis. Therefore, industry is stuck in a reactive mode regarding their maintenance strategy and cannot transition to cost-effective and energy-efficient proactive maintenance approaches. In this paper, an integration-type adaptation of the CRISP-DM data mining process model is proposed to combine domain expertise with data science techniques to address the pervasive data issues in industrial datasets. The development of the Industrial Data Analysis Improvement Cycle (IDAIC) framework led to the novel repurposing of knowledge-based fault detection and diagnosis (FDD) techniques for data quality assessment. Through interdisciplinary collaboration, the proposed framework facilitates a transition from reactive to proactive problem solving by firstly resolving known faults and data issues using domain expertise, and secondly exploring unknown or novel faults using data analysis.

Prognostic modeling of predictive maintenance with survival analysis for mobile work equipment

In recent years there is a data surge of industrial and business data. This posses opportunities and challenges at the same time because the wealth of information is usually buried in complex and frequently disconnected data sets. Predictive maintenance utilizes such data for developing prognostic and diagnostic models that allow the optimization of the life cycle of machine components. In this paper, we address the modeling of the prognostics of machine components from mobile work equipment. Specifically, we are estimating survival curves and hazard rates using parametric and non-parametric models to characterize time dependent failure probabilities of machine components. As a result, we find the presence of different types of censoring masking the presence of different populations that can cause severe problems for statistical estimators and the interpretations of results. Furthermore, we show that the obtained hazard functions for different machine components are complex and versatile and are best modeled via non-parametric estimators. However, notable exceptions for individual machine components can be found amenable for a Generalized-gamma and Weibull model.

A Machine Learning Modeling Framework for Predictive Maintenance Based on Equipment Load Cycle: An Application in a Real World Case

From a practical point of view, a turbine load cycle (TLC) is defined as the time a turbine in a power plant remains in operation. TLC is used by many electric power plants as a stop indicator for turbine maintenance. In traditional operations, a maximum time for the operation of a turbine is usually estimated and, based on the TLC, the remaining operating time until the equipment is subjected to new maintenance is determined. Today, however, a better process is possible, as there are many turbines with sensors that carry out the telemetry of the operation, and machine learning (ML) models can use this data to support decision making, predicting the optimal time for equipment to stop, from the actual need for maintenance. This is predictive maintenance, and it is widely used in Industry 4.0 contexts. However, knowing which data must be collected by the sensors (the variables), and their impact on the training of an ML algorithm, is a challenge to be explored on a case-by-case basis. In this work, we propose a framework for mapping sensors related to a turbine in a hydroelectric power plant and the selection of variables involved in the load cycle to: (i) investigate whether the data allow identification of the future moment of maintenance, which is done by exploring and comparing four ML algorithms; (ii) discover which are the most important variables (MIV) for each algorithm in predicting the need for maintenance in a given time horizon; (iii) combine the MIV of each algorithm through weighting criteria, identifying the most relevant variables of the studied data set; (iv) develop a methodology to label the data in such a way that the problem of forecasting a future need for maintenance becomes a problem of binary classification (need for maintenance: yes or no) in a time horizon. The resulting framework was applied to a real problem, and the results obtained pointed to rates of maintenance identification with very high accuracies, in the order of 98%.

Novelty Detection with Autoencoders for System Health Monitoring in Industrial Environments

Predictive Maintenance (PdM) is the newest strategy for maintenance management in industrial contexts. It aims to predict the occurrence of a failure to minimize unexpected downtimes and maximize the useful life of components. In data-driven approaches, PdM makes use of Machine Learning (ML) algorithms to extract relevant features from signals, identify and classify possible faults (diagnostics), and predict the components’ remaining useful life (prognostics). The major challenge lies in the high complexity of industrial plants, where both operational conditions change over time and a large number of unknown modes occur. A solution to this problem is offered by novelty detection, where a representation of the machinery normal operating state is learned and compared with online measurements to identify new operating conditions. In this paper, a systematic study of autoencoder-based methods for novelty detection is conducted. We introduce an architecture template, which includes a classification layer to detect and separate the operative conditions, and a localizer for identifying the most influencing signals. Four implementations, with different deep learning models, are described and used to evaluate the approach on data collected from a test rig. The evaluation shows the effectiveness of the architecture and that the autoencoders outperform the current baselines.

Machine remaining life prediction based on multi-layer self-attention and temporal convolution network

Convolution neural network (CNN) has been widely used in the field of remaining useful life (RUL) prediction. However, the CNN-based RUL prediction methods have some limitations. The receptive field of CNN is limited and easy to happen gradient vanishing problem when the network is too deep. The contribution differences of different channels and different time steps to RUL prediction are not considered, and only use deep learning features or handcrafted statistical features for prediction. These limitations can lead to inaccurate prediction results. To solve these problems, this paper proposes an RUL prediction method based on multi-layer self-attention (MLSA) and temporal convolution network (TCN). The TCN is used to extract deep learning features. Dilated convolution and residual connection are adopted in TCN structure. Dilated convolution is an efficient way to widen receptive field, and the residual structure can avoid the gradient vanishing problem. Besides, we propose a feature fusion method to fuse deep learning features and statistical features. And the MLSA is designed to adaptively assign feature weights. Finally, the turbofan engine dataset is used to verify the proposed method. Experimental results indicate the effectiveness of the proposed method.

Keeping the organization in the loop: a socio-technical extension of human-centered artificial intelligence

The human-centered AI approach posits a future in which the work done by humans and machines will become ever more interactive and integrated. This article takes human-centered AI one step further. It argues that the integration of human and machine intelligence is achievable only if human organizations—not just individual human workers—are kept “in the loop.” We support this argument with evidence of two case studies in the area of predictive maintenance, by which we show how organizational practices are needed and shape the use of AI/ML. Specifically, organizational processes and outputs such as decision-making workflows, etc. directly influence how AI/ML affects the workplace, and they are crucial for answering our first and second research questions, which address the pre-conditions for keeping humans in the loop and for supporting continuous and reliable functioning of AI-based socio-technical processes. From the empirical cases, we extrapolate a concept of “keeping the organization in the loop” that integrates four different kinds of loops: AI use, AI customization, AI-supported original tasks, and taking contextual changes into account. The analysis culminates in a systematic framework of keeping the organization in the loop look based on interacting organizational practices.

The fourth industrial revolution in the food industry-Part I: Industry 4.0 technologies

Climate change, the growth in world population, high levels of food waste and food loss, and the risk of new disease or pandemic outbreaks are examples of the many challenges that threaten future food sustainability and the security of the planet and urgently need to be addressed. The fourth industrial revolution, or Industry 4.0, has been gaining momentum since 2015, being a significant driver for sustainable development and a successful catalyst to tackle critical global challenges. This review paper summarizes the most relevant food Industry 4.0 technologies including, among others, digital technologies (e.g., artificial intelligence, big data analytics, Internet of Things, and blockchain) and other technological advances (e.g., smart sensors, robotics, digital twins, and cyber-physical systems). Moreover, insights into the new food trends (such as 3D printed foods) that have emerged as a result of the Industry 4.0 technological revolution will also be discussed in Part II of this work. The Industry 4.0 technologies have significantly modified the food industry and led to substantial consequences for the environment, economics, and human health. Despite the importance of each of the technologies mentioned above, ground-breaking sustainable solutions could only emerge by combining many technologies simultaneously. The Food Industry 4.0 era has been characterized by new challenges, opportunities, and trends that have reshaped current strategies and prospects for food production and consumption patterns, paving the way for the move toward Industry 5.0.

Knowledge Graph Based Hard Drive Failure Prediction

The hard drive is one of the important components of a computing system, and its failure can lead to both system failure and data loss. Therefore, the reliability of a hard drive is very important. Realising this importance, a number of studies have been conducted and many are still ongoing to improve hard drive failure prediction. Most of those studies rely solely on machine learning, and a few others on semantic technology. The studies based on machine learning, despite promising results, lack context-awareness such as how failures are related or what other factors, such as humidity, influence the failure of hard drives. Semantic technology, on the other hand, by means of ontologies and knowledge graphs (KGs), is able to provide the context-awareness that machine learning-based studies lack. However, the studies based on semantic technology lack the advantages of machine learning, such as the ability to learn a pattern and make predictions based on learned patterns. Therefore, in this paper, leveraging the benefits of both machine learning (ML) and semantic technology, we present our study, knowledge graph-based hard drive failure prediction. The experimental results demonstrate that our proposed method achieves higher accuracy in comparison to the current state of the art.

Providing Fault Detection from Sensor Data in Complex Machines That Build the Smart City

Household appliances, climate control machines, vehicles, elevators, cash counting machines, etc., are complex machines with key contributions to the smart city. Those devices have limited memory and processing power, but they are not just actuators; they embed tens of sensors and actuators managed by several microcontrollers and microprocessors communicated by control buses. On the other hand, predictive maintenance and the capability of identifying failures to avoid greater damage of machines is becoming a topic of great relevance in Industry 4.0, and the large amount of data to be processed is a concern. This article proposes a layered methodology to enable complex machines with automatic fault detection or predictive maintenance. It presents a layered structure to perform the collection, filtering and extraction of indicators, along with their processing. The aim is to reduce the amount of data to work with, and to optimize them by generating indicators that concentrate the information provided by data. To test its applicability, a prototype of a cash counting machine has been used. With this prototype, different failure cases have been simulated by introducing defective elements. After the extraction of the indicators, using the Kullback–Liebler divergence, it has been possible to visualize the differences between the data associated with normal and failure operation. Subsequently, using a neural network, good results have been obtained, being able to correctly classify the failure in 90% of the cases. The result of this application demonstrates the proper functioning of the proposed approach in complex machines.

Deep Auto-Encoder and Deep Forest-Assisted Failure Prognosis for Dynamic Predictive Maintenance Scheduling

Prognostics and health management (PHM) with failure prognosis and maintenance decision-making as the core is an advanced technology to improve the safety, reliability, and operational economy of engineering systems. However, studies of failure prognosis and maintenance decision-making have been conducted separately over the past years. Key challenges remain open when the joint problem is considered. The aim of this paper is to develop an integrated strategy for dynamic predictive maintenance scheduling (DPMS) based on a deep auto-encoder and deep forest-assisted failure prognosis method. The proposed DPMS method involves a complete process from performing failure prognosis to making maintenance decisions. The first step is to extract representative features reflecting system degradation from raw sensor data by using a deep auto-encoder. Then, the features are fed into the deep forest to compute the failure probabilities in moving time horizons. Finally, an optimal maintenance-related decision is made through quickly evaluating the costs of different decisions with the failure probabilities. Verification was accomplished using NASA's open datasets of aircraft engines, and the experimental results show that the proposed DPMS method outperforms several state-of-the-art methods, which can benefit precise maintenance decisions and reduce maintenance costs.

A Workflow for Synthetic Data Generation and Predictive Maintenance for Vibration Data

Digital twins, virtual representations of real-life physical objects or processes, are becoming widely used in many different industrial sectors. One of the main uses of digital twins is predictive maintenance, and these technologies are being adapted to various new applications and datatypes in many industrial processes. The aim of this study was to propose a methodology to generate synthetic vibration data using a digital twin model and a predictive maintenance workflow, consisting of preprocessing, feature engineering, and classification model training, to classify faulty and healthy vibration data for state estimation. To assess the success of the proposed workflow, the mentioned steps were applied to a publicly available vibration dataset and the synthetic data from the digital twin, using five different state-of-the-art classification algorithms. For several of the classification algorithms, the accuracy result for the classification of healthy and faulty data achieved on the public dataset reached approximately 86%, and on the synthetic data, approximately 98%. These results showed the great potential for the proposed methodology, and future work in the area.

Machine Learning for Smart Environments in B5G Networks: Connectivity and QoS

The number of Internet of Things (IoT) devices to be connected via the Internet is overgrowing. The heterogeneity and complexity of the IoT in terms of dynamism and uncertainty complicate this landscape dramatically and introduce vulnerabilities. Intelligent management of IoT is required to maintain connectivity, improve Quality of Service (QoS), and reduce energy consumption in real time within dynamic environments. Machine Learning (ML) plays a pivotal role in QoS enhancement, connectivity, and provisioning of smart applications. Therefore, this survey focuses on the use of ML for enhancing IoT applications. We also provide an in-depth overview of the variety of IoT applications that can be enhanced using ML, such as smart cities, smart homes, and smart healthcare. For each application, we introduce the advantages of using ML. Finally, we shed light on ML challenges for future IoT research, and we review the current literature based on existing works.

A Versatile Punch Stroke Correction Model for Trial V-Bending of Sheet Metals Based on Data-Driven Method

During air bending of sheet metals, the correction of punch stroke for springback control is always implemented through repeated trial bending until achieving the forming accuracy of bending parts. In this study, a modelling method for correction of punch stroke is presented for guiding trial bending based on a data-driven technique. Firstly, the big data for the model are mainly generated from a large number of finite element simulations, considering many variables, e.g., material parameters, dimensions of V-dies and blanks, and processing parameters. Based on the big data, two punch stroke correction models are developed via neural network and dimensional analysis, respectively. The analytic comparison shows that the neural network model is more suitable for guiding trial bending of sheet metals than the dimensional analysis model, which has mechanical significance. The actual trial bending tests prove that the neural-network-based punch stroke correction model presents great versatility and accuracy in the guidance of trial bending, leading to a reduction in the number of trial bends and an improvement in the production efficiency of air bending.

Smart Anomaly Detection and Prediction for Assembly Process Maintenance in Compliance with Industry 4.0

One of the big problems of today's manufacturing companies is the risks of the assembly line unexpected cessation. Although planned and well-performed maintenance will significantly reduce many of these risks, there are still anomalies that cannot be resolved within standard maintenance approaches. In our paper, we aim to solve the problem of accidental carrier bearings damage on an assembly conveyor. Sometimes the bearing of one of the carrier wheels is seized, causing the conveyor, and of course the whole assembly process, to halt. Applying standard approaches in this case does not bring any visible improvement. Therefore, it is necessary to propose and implement a unique approach that incorporates Industrial Internet of Things (IIoT) devices, neural networks, and sound analysis, for the purpose of predicting anomalies. This proposal uses the mentioned approaches in such a way that the gradual integration eliminates the disadvantages of individual approaches while highlighting and preserving the benefits of our solution. As a result, we have created and deployed a smart system that is able to detect and predict arising anomalies and achieve significant reduction in unexpected production cessation.

Symbiotic Relationship Between Machine Learning and Industry 4.0: A Review

Industry 4.0 though launched less than a decade ago, has revolutionized the way technologies are being used. It has found its application in almost every field of manufacturing, cybersecurity, health, banking, and other services. Industry 4.0 is heavily dependent on interconnectivity and data. Machine learning (ML) acts as a foundation for building industry 4.0 applications. In this paper, we have provided a broad view of how ML is necessary to accomplish the benefits of industry 4.0. The paper includes ML usage in companies and the limitations of ML, which need to be mitigated. There are also some instances of the failure of ML algorithms and their repercussions. Though industry 4.0 requires a lot more inputs and capital than normal processes, the long-run benefits outweigh the initial costs. ML is gaining popularity, and extensive research is happening to exploit its potential and develop full smart applications.