Recent advances in continuous nanomanufacturing: focus on machine learning-driven process control

The process industry (PI) plays a vital role in the global economy and faces mounting pressure to enhance sustainability, operational agility, and resource efficiency amid tightening regulatory and market demands. Although artificial intelligence (AI) has been explored in this domain for decades, its adoption in industrial practice remains limited. Recently, machine learning (ML) has gained momentum, particularly when integrated with core PI systems such as process control, instrumentation, quality management, and enterprise platforms. Among ML techniques, reinforcement learning (RL) has emerged as a promising approach to tackle complex operational challenges. In contrast to conventional data-driven methods that focus on prediction or classification, RL directly addresses sequential decision making under uncertainty, a defining characteristic of dynamic process operations. Given RL’s growing relevance, this study conducts a systematic literature review to evaluate its current applications in the PI, assess methodological developments, and identify barriers to broader industrial adoption. The review follows the PRISMA methodology, a structured framework for identifying, screening, and selecting relevant publications. This approach ensures alignment with a clearly defined research question and minimizes bias, focusing on studies that demonstrate meaningful industrial applications of RL. The findings reveal that RL is transitioning from a theoretical construct to a practical tool, particularly in the chemical sector and for tasks such as process control and scheduling. Methodological maturity is improving, with algorithm selection increasingly tailored to problem-specific requirements and a trend toward hybrid models that integrate RL with established control strategies. However, most implementations remain confined to simulated environments, underscoring the need for real-world deployment, safety assurances, and improved interpretability. Overall, RL exhibits the potential to serve as a foundational component of next-generation smart manufacturing systems.

Compact and efficient continuous mixing processes for production of food and pharmaceutical powders

Process control and optimization have been widely used to solve decision-making problems in chemical engineering applications. However, identifying and tuning the best solution algorithm is challenging and time-consuming. Machine learning tools can be used to automate these steps by learning the behavior of a numerical solver from data. In this paper, we discuss recent advances in (i) the representation of decision-making problems for machine learning tasks, (ii) algorithm selection, and (iii) algorithm configuration for monolithic and decomposition-based algorithms. Finally, we discuss open problems related to the application of machine learning for accelerating process optimization and control.

— The objective of this paper is to investigate the Model Predictive Control (MPC) strategy, analyze and compare the control effects with Proportional-Integral-Derivative (PID) control strategy in maintaining a level of spherical tank system using VFD. An advanced control method, MPC has been widely used and well received in a wide variety of applications in process control, it utilizes an explicit process model to predict the future response of a process and solve an optimal control problem with a finite horizon at each sampling instant. In this paper, an algorithm is developed for controlling the speed of the pump using VFD to maintain the level of the spherical tank system. Next, the system is modeled and linearized for analysis and design. Model is implemented in a simulation environment based on LabVIEW. Both MPC and PID control methods are tried to design the controller for the water level system in a spherical tank and compared the results in terms of peak time, settling time, overshoot, and steady-state error under various operational conditions including time delays. The results showed the advantage of MPC for dealing with the system dynamic over PID and could be designed for more complex and fast system dynamics even in presence of constraints and Reduction of power consumption by the pump due to usage of VFD for controlling level by varying the speed of the pump based on the level of the tank. Keywords: Non Linear - Spherical Tank System – Level Control – Variable Frequency Drive – PID Controller – MPC Controller – Modeling - LabVIEW. Cite this Article R. Dhanasekar, S. Vijayachitra, M. Pravin Savaridass. Controlling of Level Process in Nonlinear System Using Variable Frequency Drive. Current Trends in Information Technology. 2019; 9(1): 24–33p.

Machine learning real-time control of continuous granulation process.

Injection molding is one of the major processes applied for production of thermoplastic products. Thermoplastic materials are used in manufacturing of dozens of products seen in everyday life, such as: car bumpers, children toys, bodies of electronic devices, etc. At the same time, plastic pollution is a well-known problem. One of the sources of this pollution is plastic scrap, which might appear because of using faulty process parameters during production process. To decrease amount of scrap, injection molding needs to include better process and quality control routines. Quality of a product can be defined in different ways and product dimensions can be one of criteria for accepting or declining a product. The following paper applies machine learning (ML) methods to predict width and thickness of the injection molded HDPE dogbone specimens with 4 mm thickness based on process parameter values used to produce the parts. Data used for creation of regression models with help of ML methods was acquired during an experiment, which included 160 machine runs during which 47 machine and process parameters were logged. Application of ML methods for training of product dimensions prediction models will increase overall intelligence level of injection molding machines and their compliance with Industry 4.0 standards. Beforehand prediction of product’s dimensions will allow to decrease amount of scrap and energy consumption. This will contribute to more environmentally conscious use of thermoplastic materials and more sustainable design of manufacturing systems.

The increased interest in artificial intelligence in manufacturing has driven the adoption of machine learning to optimize processes and improve efficiency. A key challenge in injection molding is the variability of recycled materials, which affects part quality and processing stability. This study presents a novel closed-loop process control approach for injection molding, leveraging machine learning to adaptively predict processing inputs and quality outcomes. The methodology was tested on five blends of recycled polypropylene (rPP), using artificial neural networks (ANNs), linear regression, and polynomial regression to model the relationships between material properties and process parameters. The dataset was split 80/20 into training and testing sets. The ANN model was implemented using TensorFlow and Keras, with six hidden layers of 32 neurons per layer, ReLU activation, and an Adam optimizer. Empirical tuning and early stopping were used to optimize performance and prevent overfitting. Predictions were evaluated based on mean absolute error (MAE), mean squared error (MSE), and percentage error. The results showed that yield stress, ultimate elongation, and part weight were accurately predicted within a 5% error for linear and polynomial regression models and within a 10% error for the ANN. However, modulus predictions were less reliable, with errors of ~11% for ANN and linear regression and ~40% for polynomial regression, reflecting the inherent variability of this property in rPP blends. Predictions of processing inputs had errors ranging from 3% to 25%, depending on the model and response variable. No single modeling approach was consistently superior across all responses, highlighting the complexity of the relationship between material properties, process parameters, and quality metrics. Overall, the work demonstrates that closed-loop process control, powered by machine learning, can effectively predict key quality parameters in injection molding of recycled materials. The proposed approach can improve process stability and material utilization, facilitating increased adoption of sustainable materials.

Escherichia coli still serves as a beloved workhorse for the production of many biopharmaceuticals as it fulfills essential criteria, such as having fast doubling times, exhibiting a low risk of contamination, and being easy to upscale. Most industrial processes in E. coli are carried out in fed-batch mode. However, recent trends show that the biotech industry is moving toward time-independent processing, trying to improve the space–time yield, and especially targeting constant quality attributes. In the 1950s, the term “chemostat” was introduced for the first time by Novick and Szilard, who followed up on the previous work performed by Monod. Chemostat processing resulted in a major hype 10 years after its official introduction. However, enthusiasm decreased as experiments suffered from genetic instabilities and physiology issues. Major improvements in strain engineering and the usage of tunable promotor systems facilitated chemostat processes. In addition, critical process parameters have been identified, and the effects they have on diverse quality attributes are understood in much more depth, thereby easing process control. By pooling the knowledge gained throughout the recent years, new applications, such as parallelization, cascade processing, and population controls, are applied nowadays. However, to control the highly heterogeneous cultivation broth to achieve stable productivity throughout long-term cultivations is still tricky. Within this review, we discuss the current state of E. coli fed-batch process understanding and its tech transfer potential within continuous processing. Furthermore, the achievements in the continuous upstream applications of E. coli and the continuous downstream processing of intracellular proteins will be discussed.

Due to diversity and many possibilities for data collection in semiconductor manufacturing, various complex machine learning approaches exist for different process steps. However, a systematic overview of these approaches is missing. This study, therefore, systematically reviews machine learning applications for process monitoring and control in semiconductor manufacturing based on peer-reviewed literature. To structure the review, we use the wafer fabrication plant-wide framework for process monitoring and control and the framework of continuous process improvement based on machine learning technique. We identify respective application areas and future research needs of machine learning for process monitoring and control in semiconductor manufactnring.

Integrate circuit (IC) technology is going through multiple changes in terms of patterning techniques (multiple patterning, EUV and DSA), device architectures (FinFET, nanowire, graphene) and patterning scale (few nanometers). These changes require tight controls on processes and measurements to achieve the required device performance, and challenge the metrology and process control in terms of capability and quality. Multivariate data with complex nonlinear trends and correlations generally cannot be described well by mathematical or parametric models but can be relatively easily learned by computing machines and used to predict or extrapolate. This paper introduces the predictive metrology approach which has been applied to three different applications. Machine learning and predictive analytics have been leveraged to accurately predict dimensions of EUV resist patterns down to 18 nm half pitch leveraging resist shrinkage patterns. These patterns could not be directly and accurately measured due to metrology tool limitations. Machine learning has also been applied to predict the electrical performance early in the process pipeline for deep trench capacitance and metal line resistance. As the wafer goes through various processes its associated cost multiplies. It may take days to weeks to get the electrical performance readout. Predicting the electrical performance early on can be very valuable in enabling timely actionable decision such as rework, scrap, feedforward, feedback predicted information or information derived from prediction to improve or monitor processes. This paper provides a general overview of machine learning and advanced analytics application in the advanced semiconductor development and manufacturing.

Recent advancements in biologics production using CHO cells have been partly driven by improved understanding of how variations in the cell culture environment influence cellular metabolism, productivity, and the attributes of the final product. In-silico models serve a valuable role in mapping the effects of various process parameters and media changes on cellular response. Advances in technologies such as data-driven analysis, self-learning systems, and digital twins are reinforcing progress toward smart manufacturing, enabling the real-time control of production processes. Furthermore, kinetic, and constraint-based mechanistic modeling, combined with omics approaches, are becoming increasingly incorporated into the bioprocess development and manufacturing innovation ecosystem. In this review, we cover CHO central metabolism as a foundation for mechanistic modeling and extend the discussion to include various mechanistic modeling approaches, highlighting the incorporation of glycosylation and secretory pathways. Multi-omics approaches provide a deeper understanding of intracellular processes and the dynamic interactions between product quality and pathways. In parallel, to achieve the Industry 4.0 vision of digitalization and machine learning techniques are finding wider adoption in biopharmaceutical development. We discuss the potential applications of these techniques for predictions, inference, optimization, and control. The role of big data analytics and artificial intelligence methods in reinforcing progress towards smart manufacturing and enabling real-time control of production processes is discussed. Finally, we summarize the application of machine learning and hybrid models to CHO bioprocesses, aiming to develop and manufacture drugs more efficiently and at a lower cost for patients.

Process control is vital for the safe and efficient operation of any processing facility. It may be necessary to control the height of liquid within a column, the pressure within a vessel, or the temperature within a reactor. If a process parameter such as temperature, pressure, flow rate or level is to be controlled then it must be possible to reliably measure that parameter. This chapter begins by looking at the various sensors available to measure temperature, pressure, flow rate and level. The reader is then introduced to how this information may be used to manipulate a process parameter to achieve control using proportional-integral-derivative control systems. Concepts such as feedforward and feedback control will also be studied. The role of alarms, safety trips and interlocks in providing safe control of a facility will be examined before considering how all these aspects may be combined to provide control of real process units.

5 - Process control in the manufacturing of synthetic textile fibres

The calibration of large-diameter flow meters is performed in the calibration station where real flow passes through. The typical calibration process is manipulated by human operators, which is time-consuming and easily affected. Since most of the process parameters are detectable, the smart calibration system was aided by the on-line modeling process and consisted of three parts: the digital twin model, the process controller, and the human-machine interface (HMI). The digital twin model was based on the basic partial differential equations of the gas flow in pipelines and was meant for the flow behavior prediction over short periods and provided decision-making assistance for human operators. The verification of the digital model was based on both the historical process data and the real-time process data. The process controller represented the manipulator meant to replace the human operator. The function of the controller included process control and calibration flow point adjustment. The HMI was designed based on the industrial supervisory control and data acquisition (SCADA) system. Since the process control was essential, the scheduling scheme and command sequence feedback to the SCADA system was rechecked by human operators via the HMI. The result of the active control was displayed in the HMI based on the digital twin model. Since smart control was the tendency in the piping system, the automated process verification and control formed the basis of the smart system. By entering the size and range of the flow meters into the HMI, the entire industrial system inside the calibration station was executed automatically.

Buildings are subject to faults in their heating, ventilation and air-conditioning (HVAC) systems that can lead to excessive energy wastage, poor indoor climate, equipment failures and high maintenance costs. Field studies have shown that employing fault detection, diagnosis and prognosis (FDDP) tools followed up with equipment services and corrections can help achieve up to 40% of energy savings within the HVAC system and improve indoor climate, increase equipment lifecycle and reduce maintenance costs. The increasing adoption of building automation systems (BAS), Internet of Things (IoT) and other smart technologies in recent years have allowed large amounts of data to be continuously collected from building systems. This data-rich environment, along with the surge in data analytics and machine learning tools, has made cost-effective data-driven FDDP strategies possible. Compared to purely physics-based methods, data-driven methods require less explicit knowledge of the underlying physical system, thus are often easier to develop, and can learn certain intricate relationships that exist among data. Within the reported data-driven FDDP methods, there exists a few research gaps: 1) data imputation methods that leverage mutual information from correlated measurements to defy poor data quality from BAS have not been utilized efficiently; 2) there lacks a systematic and scalable fault diagnosis framework that incorporates probabilistic temporal relationships to track fault evolution; 3) existing fault diagnosis strategies typically focus on traditional rule-based control strategies and their scalability for advanced control strategies such as Guideline 36 have not been explored yet; 4) active threats information such as cyber-attacks, are typically not incorporated in an FDDP framework; 5) fault prognosis strategies to preemptively identify gradual faults for predictive maintenance have rarely been studied. This research attempts to address the above-mentioned research gaps through the following: Data Imputation: reported data imputation methods that are suitable for handling and repairing multi-source BAS data are evaluated. Data collected from a medium-sized, mixed-use institution building situated in Stockholm, Sweden and a small commercial building simulated in a laboratory setup is used to evaluate five different data imputation methods. Results demonstrate that incorporating time-lagged cross-correlations within the k-Nearest Neighbor (kNN) method helps to significantly improve the imputation accuracy and minimize the impact of repaired data on data-driven algorithms. Dynamic Bayesian Network (DBN)-based Framework for Cyber-Physical Fault Diagnosis: a DBN framework with discretized conditional probabilities parameters to represent the temporal relationships among building measurements is developed. Both domain knowledge and machine learning methods are used to develop the DBN structure and parameter model. The developed framework is evaluated for both traditional rule-based and Guideline 36 controls using datasets from a real building, a laboratory building, and a virtual testbed. Results show that the developed DBN framework is effective in diagnosing and isolating faults in systems even with different control strategies. The framework also successfully distinguishes whether system abnormalities originate from cyber-attacks or naturally occurring physical faults. Potential future direction to improve fault isolation using modified DBN topological structure is also reported in this study. DBN-based Framework for Fault Prognosis: an extension of the DBN framework in conjunction with Robust Multivariate Temporal (RMT) variate selection is proposed for fault prognosis. The RMT variate selection is used to extract localized temporal features from high dimensional datasets to determine the best inputs for training forecasting models. The expected fault-free behavior of multiple target variates, selected using domain knowledge, is forecasted using incoming data. The prediction errors generated from the forecasting phase are used as evidences in the DBN inference to estimate future fault probabilities. Gradual faults simulated in the virtual testbed are used to evaluate the prognosis framework. Results show that the developed framework is effective in prognosing gradual faults by leveraging the trending growth on the prediction errors. The research presented in this thesis contributes to the overall objective of developing a robust and cost-effective DBN-based framework for fault diagnosis and prognosis of building HVAC systems. Potential solutions to other existing challenges of implementing data-driven FDDP strategies, such as obtaining high-quality datasets, handling and repairing missing data, establishing a baseline model for detecting abnormalities despite other disturbances such as weather and internal conditions changes, and extracting temporal features from timeseries data are also examined.