Comprehensive evaluation of a data driven control strategy: Experimental application to a pharmaceutical crystallization process

Data-Knowledge-Driven Modeling and Operational Adjustment for the Pharmaceutical Tablet Manufacturing Process via Wet Granulation

In the context of Pharma 4.0, pharmaceutical quality control (PQC) is beset by issues such as uncertainties from ever-changing critical material attributes and strong coupling between variables in the multi-unit pharmaceutical tablet manufacturing process (PTMP), and how to timely adjust the operational variables to deal with such challenges has become a key problem in PQC. In this study, we propose a novel data-knowledge-driven modeling and operational adjustment framework for PTMP by integrating Bayesian network (BN) and case-based reasoning (CBR). At the modeling level, first, a distributed concept is introduced, i.e., the BN model for each subunit of PTMP is established in accordance with the operation process sequence, and the transition variables are given by the BN model established first and retrieved as the new query for the next unit. Once the BN models of all subunits are built, they are integrated into a global BN model. At the operational adjustment level, by taking the expected critical quality attributes (CQAs) and related prior information as evidence, the operational adjustment is achieved through global BN reasoning. Finally, the case study in a sprayed fluidized-bed granulation-based PTMP demonstrates the feasibility and effectiveness in improving the terminal CQAs of the proposed method, which is also compared with other methods to showcase its efficacy and merits.

A spatio-temporal data decoupling convolution network model for specific surface area prediction in cement grind process

The specific surface area is one of the important indicators for measuring the quality of cement products. Realizing accurate prediction for specific surface area is very important for the production scheduling of the cement industry, energy conservation and consumption reduction and improvement of cement performance. However, due to the non-linearity, uncertainty, multiple interference, dynamic time-varying delay and multi scales in cement grinding process, it is difficult to establish an accurate soft-sensing model for cement quality prediction. Aiming at the above problems, we proposed a spatio-temporal decoupling convolution neural network model (STG-DCNN) to predict specific surface area by extracting and fusing data features in temporal and spatial dimension. To complete the prediction of specific surface area, we established the temporal series map and spatial series map by the production variables data according to the mechanism of cement grinding process. Then, sliding window technique was utilized to match the time scale in temporal series map and construct variable coupling relationship in spatial series map. The prediction accuracy, robustness and superiority of the proposed method were demonstrated by experiments results implemented on the actual cement grinding quality management database in a cement production enterprise.

Active control of equilibrium, near-equilibrium, and far-from-equilibrium colloidal systems

The development of top-down active control over bottom-up colloidal assembly processes has the potential to produce materials, surfaces, and objects with applications in a wide range of fields spanning from computing to materials science to biomedical engineering. In this review, we summarize recent progress in the field using a taxonomy based on how active control is used to guide assembly. We find there are three distinct scenarios: (1) navigating kinetic pathways to reach a desirable equilibrium state, (2) the creation of a desirable metastable, kinetically trapped, or kinetically arrested state, and (3) the creation of a desirable far-from-equilibrium state through continuous energy input. We review seminal works within this framework, provide a summary of important application areas, and present a brief introduction to the fundamental concepts of control theory that are necessary for the soft materials community to understand this literature. In addition, we outline current and potential future applications of actively-controlled colloidal systems, and we highlight important open questions and future directions.

Applications of Artificial Intelligence and Machine Learning Algorithms to Crystallization

Artificial intelligence and specifically machine learning applications are nowadays used in a variety of scientific applications and cutting-edge technologies, where they have a transformative impact. Such an assembly of statistical and linear algebra methods making use of large data sets is becoming more and more integrated into chemistry and crystallization research workflows. This review aims to present, for the first time, a holistic overview of machine learning and cheminformatics applications as a novel, powerful means to accelerate the discovery of new crystal structures, predict key properties of organic crystalline materials, simulate, understand, and control the dynamics of complex crystallization process systems, as well as contribute to high throughput automation of chemical process development involving crystalline materials. We critically review the advances in these new, rapidly emerging research areas, raising awareness in issues such as the bridging of machine learning models with first-principles mechanistic models, data set size, structure, and quality, as well as the selection of appropriate descriptors. At the same time, we propose future research at the interface of applied mathematics, chemistry, and crystallography. Overall, this review aims to increase the adoption of such methods and tools by chemists and scientists across industry and academia.

Implementation of Dynamic and Static Moisture Control in Fluidized Bed Granulation

The application of process analysis and control is essential to enhance process understanding and ensure output material quality. The present study focuses on the stability of the feedback control system for a fluidized bed granulation process. Two strategies of dynamic moisture control (DMC) and static moisture control (SMC) were established based on the in-line moisture value obtained from the near-infrared sensor and control algorithm. The performance of these strategies on quality consistency control was examined using process moisture similarity analysis and principal component analysis. The stable moisture control performance and low batch-to-batch variability indicated that the DMC method was significantly better than other granulation methods. In addition, the investigation of robustness further showed that the implemented DMC method was able to produce predetermined target moisture values by varying process parameters. This study provides an advanced and simple control method for fluidized bed granulation quality assurance.

Application of Artificial Neural Networks in the Process Analytical Technology of Pharmaceutical Manufacturing-a Review

Industry 4.0 has started to transform the manufacturing industries by embracing digitalization, automation, and big data, aiming for interconnected systems, autonomous decisions, and smart factories. Machine learning techniques, such as artificial neural networks (ANN), have emerged as potent tools to address the related computational tasks. These advancements have also reached the pharmaceutical industry, where the Process Analytical Technology (PAT) initiative has already paved the way for the real-time analysis of the processes and the science- and risk-based flexible production. This paper aims to assess the potential of ANNs within the PAT concept to aid the modernization of pharmaceutical manufacturing. The current state of ANNs is systematically reviewed for the most common manufacturing steps of solid pharmaceutical products, and possible research gaps and future directions are identified. In this way, this review could aid the further development of machine learning techniques for pharmaceutical production and eventually contribute to the implementation of intelligent manufacturing lines with automated quality assurance.

An Ultrasound Tomography Method for Monitoring CO2 Capture Process Involving Stirring and CaCO3 Precipitation

In this work, an ultrasound computed tomography (USCT) system was employed to investigate the fast-kinetic reactive crystallization process of calcium carbonate. USCT measurements and reconstruction provided key insights into the bulk particle distribution inside the stirred tank reactor and could be used to estimate the settling rate and settling time of the particles. To establish the utility of the USCT system for dynamical crystallization processes, first, the experimental imaging tasks were carried out with the stirred solid beads, as well as the feeding and stirring of the CaCO₃ crystals. The feeding region, the mixing process, and the particles settling time could be detected from USCT data. Reactive crystallization experiments for CO₂ capture were then conducted. Moreover, there was further potential for quantitative characterization of the suspension density in this process. USCT-based reconstructions were investigated for several experimental scenarios and operating conditions. This study demonstrates a real-time monitoring and fault detection application of USCT for reactive crystallization processes. As a robust noninvasive and nonintrusive tool, real-time signal analysis and reconstruction can be beneficial in the development of monitoring and control systems with real-world applications for crystallization processes. A diverse range of experimental studies shown here demonstrate the versatility of the USCT system in process application, hoping to unlock the commercial and industrial utility of the USCT devices.

Model-Based Evaluation of a Data-Driven Control Strategy: Application to Ibuprofen Crystallization

This work presents a methodology that relies on the application of the radial basis functions network (RBF)-based feedback control algorithms to a pharmaceutical crystallization process. Within the scope of the model-based evaluation of the proposed strategy, firstly strategies for the data treatment, data structure and the training methods reflecting the possible scenarios in the industry (Moving Window, Growing Window and Golden Batch strategies) were introduced. This was followed by the incorporation of such RBF strategies within a soft sensor application and a nonlinear predictive data-driven control application. The performance of the RBF control strategies was tested for the undisturbed cases as well as in the presence of disturbances in the process. The promising results from both RBF soft sensor control and the RBF predictive control demonstrated great potential of these techniques for the control of the crystallization process. In particular, both Moving Window and Golden Batch strategies performed the best results for an RBF soft sensor, and the Growing Window outperformed the remaining methodologies for predictive control.

Application of PAT-Based Feedback Control Approaches in Pharmaceutical Crystallization

Crystallization is one of the important unit operations for the separation and purification of solid products in the chemical, pharmaceutical, and pesticide industries, especially for realizing high-end, high-value solid products. The precise control of the solution crystallization process determines the polymorph, crystal shape, size, and size distribution of the crystal product, which is of great significance to improve product quality and production efficiency. In order to develop the crystallization process in a scientific method that is based on process parameters and data, process analysis technology (PAT) has become an important enabling platform. In this paper, we review the development of PAT in the field of crystallization in recent years. Based on the current research status of drug crystallization process control, the monitoring methods and control strategies of feedback control in the crystallization process were systematically summarized. The focus is on the application of model-free feedback control strategies based on the solution and solid information collected by various online monitoring equipment in product engineering, including improving particle size distribution, achieving polymorphic control, and improving purity. In this paper, the challenges of feedback control strategy in the crystallization process are also discussed, and the development trend of the feedback control strategy has been prospected.

Integrated Model for Understanding N2O Emissions from Wastewater Treatment Plants: A Deep Learning Approach

This study aims to demonstrate the application of deep learning to quantitatively describe long-term full-scale data observed from wastewater treatment plants (WWTPs) from the perspectives of process modeling, process analysis, and forecasting modeling. Approximately, 750,000 measurements including the influent flow rate, air flow rate, temperature, ammonium, nitrate, dissolved oxygen, and nitrous oxide (N₂O) collected for more than a year from the Avedøre WWTP located in Denmark are utilized to develop a deep neural network (DNN) through supervised learning for process modeling, and the optimal DNN (R² > 0.90) is selected for further evaluation. For process analysis, global sensitivity analysis based on variance decomposition is considered to identify the key parameters contributing to high N₂O emission characteristics. For N₂O forecasting, the proposed DNN-based model is compared with long short-term memory (LSTM), showing that the LSTM-based forecasting model performs significantly better than the DNN-based model (R² > 0.94 and the root-mean-squared error is reduced by 64%). The results account for the feasibility of data-driven methods based on deep learning for quantitatively describing and understanding the rather complex N₂O dynamics in WWTPs. Research into hybrid modeling concepts integrating mechanistic models of WWTPs (e.g., ASMs) with deep learning would be suggested as a future direction for monitoring N₂O emissions from WWTPs.