Search

Ohmic heating is a highly efficient method for rapid fluid heating, with applications in fields such as food processing, pharmaceuticals, and chemical engineering. Prior to its industrial application, thorough analysis and modeling are crucial to ensure safe and efficient operations. Therefore, this research focuses on the development and validation of a transfer function-based model for a continuous flow ohmic heater (CFOH). Validation metrics include root mean square error (RMSE) and mean absolute percentage error (MAPE). The developed model achieves an RMSE of ±1.48 and a MAPE of ±2.58% compared to experimental results, demonstrating its accuracy. Furthermore, the research presents the implementation of robust real-time applications of advanced process controllers, including PID, MPC, and AMPC. These controllers were first simulated using the developed model and subsequently deployed in the pilot plant ohmic heater system to achieve precise temperature control and optimised input voltage. The reliability of this procedure was affirmed through a comparison between simulated results and empirical data obtained from the CFOH pilot plant. The study concludes by suggesting potential applications in fault diagnosis, educational training, system identification, and controller design. [ABSTRACT FROM AUTHOR]

Municipal solid waste incineration (MSWI) is essential for tackling urban environmental challenges and facilitating renewable energy recycling. The MSWI process has characteristics of multiple variables, strong coupling, and complex nonlinearity, requiring advanced process control (APC) technology. Although there have been several reviews on the modeling and control of the MSWI process, there is a lack of focus on model predictive control (MPC), a widely used APC technology. This article aims to comprehensively review MPC strategies in the MSWI process. First, it describes MSWI process technology in detail, examining control issues and objectives to highlight the complexity and challenges in controller design while providing an overview of MPC methods and their benefits. Second, it reviews incinerator modeling for control, including traditional modeling techniques and machine learning technologies such as fuzzy neural networks. Third, it reviews the controllers used for MSWI process, emphasizing the advantages of MPC over existing control methods. Fourth, it discusses the current status of MPC design and online updates, covering the need for an accurate dynamic predictive model and objective function and the online updates components such as predictive modeling, rolling optimization, and feedback correction. Finally, the study concludes with a summary of the findings. [ABSTRACT FROM AUTHOR]

Semiconductor manufacturing processing can be jeopardized due to process fluctuations, and the degradation of equipment parts can significantly influence process variation. Timely diagnosing equipment faults causing process variations is desired in current high-end product manufacturing. This paper proposes a diagnostic method for the SiH4 gas flow rate drift using N2 vibrational transition in oxide deposition. In this research, optical emission spectroscopy (OES) and quadrupole mass spectrometer (QMS) are employed as condition monitoring sensors serving as a reference model to compare the diagnostic performance for gas flow rate drift. The study observes that the OES model exhibits much higher performance for minor diagnoses of less than 5% drift. The diagnostic model performance can be enhanced by incorporating plasma condition and gas indicators compared to when these indicators are used individually. This suggests that when conducting diagnostics for equipment and processes, it is crucial to consider indirect indicators like plasma indicators along with direct indicators such as gas radical density. The comprehensive use of both types of indicators enhances the diagnostic performance, providing a more accurate assessment of the conditions and potential problem in semiconductor manufacturing. [ABSTRACT FROM AUTHOR]

Ohmic heating is a highly efficient method for rapid fluid heating, with applications in fields such as food processing, pharmaceuticals, and chemical engineering. Prior to its industrial application, thorough analysis and modeling are crucial to ensure safe and efficient operations. Therefore, this research focuses on the development and validation of a transfer function-based model for a continuous flow ohmic heater (CFOH). Validation metrics include root mean square error (RMSE) and mean absolute percentage error (MAPE). The developed model achieves an RMSE of ±1.48 and a MAPE of ±2.58% compared to experimental results, demonstrating its accuracy. Furthermore, the research presents the implementation of robust real-time applications of advanced process controllers, including PID, MPC, and AMPC. These controllers were first simulated using the developed model and subsequently deployed in the pilot plant ohmic heater system to achieve precise temperature control and optimised input voltage. The reliability of this procedure was affirmed through a comparison between simulated results and empirical data obtained from the CFOH pilot plant. The study concludes by suggesting potential applications in fault diagnosis, educational training, system identification, and controller design.

Artificial intelligence (AI) and its data-driven counterpart, machine learning (ML), are rapidly evolving disciplines with increasing applications in modeling, simulation, control, and optimization within the drying industry. This paper presents a comprehensive overview of progress made in ML from shallow to deep learning and its implications for food drying. Theoretical foundations, advantages, and limitations of various ML approaches employed in this domain are explored. Additionally, advancements in ML models, particularly those enhanced by optimization algorithms, are reviewed. The review underscores the role of intelligent configuration of ML models, which affects their accuracy and ability to solve problems of high energy consumption, nutrient degradation, and uneven drying. Drawing upon research achievements, integrating of AI models with real-time measuring methods is discussed, enabling dynamic determination of optimal drying conditions and parameter adjustments. This integration facilitates automated decision-making, reducing human errors and enhancing operational efficiency in food drying. Moreover, AI models demonstrate proficiency in predicting drying times and analyzing energy usage patterns, thereby enabling optimization to minimize resource consumption while preserving product quality. Finally, this paper identifies current obstacles in technology development and proposes novel research avenues for sustainable drying technologies. The strengths and weaknesses of various AI methodologies are examined Artificial neural networks are extensively used for modeling drying phenomena Machine learning models can simulate complex processes of food drying Deep learning has significant potential for real-time monitoring of drying Intelligent control systems can optimize food drying [ABSTRACT FROM AUTHOR]

This paper addresses the quality control of the photolithography process in the semiconductor industry. Overlay errors in the process seriously affect the wafer yield, and cause the wafer to be forced to rework and affect the production efficiency of the equipment. We examine the current state of its process control, develop a novel overlay predict model, and verify the prediction results. This study proposes a Global Attention Generative Adversarial Networks (GAGAN) model to precisely predict the overlay error for the feed-forward data of the front layer, which is used as the important information and process parameters for the advanced process control of the current layer. Experiment results on a semiconductor shop-floor confirms that our proposed method achieves high predictive performance while maintaining extensibility and visual quality. [ABSTRACT FROM AUTHOR]

Accurate trajectory tracking is a paramount objective when a mobile robot must perform complicated tasks. In high-speed movements, hardware-induced delays may produce overshoots and even instability when controlling the system. In this case, Smith predictor controllers can be used because they are well suited for delayed processes. This paper addresses the accurate positioning of a mobile robot on a terrain of an unknown slope. This slope produces disturbance torques of unknown amplitudes in the robot actuators that yield a steady-state error in the positioning. Because our actuators are integrating plus time delay plants, the standard Smith predictor cannot remove these disturbances. This paper proposes a modification of this control scheme in order to remove these disturbances yielding a zero steady-state error in the actuators. Our new scheme is compared with other modified S P s existing in the literature by means of simulations. These simulations show the superior performance of our scheme in the sense of removing the steady-state error more efficiently (i.e., faster) than other schemes. Finally, the performance of our control scheme is tested experimentally in a low-cost mobile robot. [ABSTRACT FROM AUTHOR]

Digital twins have emerged as a powerful concept for real-time monitoring and analysis, facilitating Quality by Design integration into biopharmaceutical manufacturing. Traditionally, lyophilization processes are developed through trial-and-error, incorporating high security margins and inflexible process set points. Digital twins enable the integration of adaptable operating conditions and implementation of automation through Advanced Process Control (APC) with Process Analytical Technology (PAT) and validated physicochemical models that rely on heat and mass transfer principles, allowing us to overcome the challenges imposed by the lyophilization process. In this study, a digital twin for freeze-drying processes is developed and experimentally validated. Using the digital twin, primary drying conditions were optimized for controlled nucleation and annealing methods by carrying out a few laboratory tests beforehand. By incorporating PAT and modeling, the digital twin accurately predicts the product's temperature and drying endpoint, showing smaller errors than the experiments. The digital twin significantly increases productivity by up to 300% while reducing the costs by 74% and the Global Warming Potential by 64%. [ABSTRACT FROM AUTHOR]

Abstract The accurate dynamic model of the chemical process is an important condition for the successful implementation of advanced control in the plant. In this paper, an efficient second order algorithm for long short-term memory (LSTM) network training is proposed for chemical process intelligent identification. A novel Hessian inverse recursion method is adopted to achieve fast convergence and avoid the high-cost operation of the classic second order optimization method. Besides, more information is back propagated since the proposed method retains the real curvature information of the neural network. Considering the large amount of chemical process data, a sub-sampled recursive second order-stochastic gradient descent (SRSO-SGD) algorithm which uses sub-sampling method and hybrid strategy is proposed. The identification experiment on a delayed coker fractionator shows that the proposed sub-sampled neural network second order training algorithm has better performance than other learning algorithms in terms of model identification accuracy and convergence speed. By adopting a hybrid strategy that performing Hessian inverse estimation every 3 training epochs, the expensive Hessian inverse calculation cost in the identification process is further reduced while low training and testing errors are maintained.

Several papers have proven that advanced process controller (APC) systems can save more energy in the process than proportional-integral-differential (PID) controller systems. Therefore, implementing an APC system is ultimately beneficial for saving energy in the plant. In a typical APC system deployment, the APC model parameters are calculated from dynamic data intervals obtained through the plant test. However, depending on the proficiency of the APC engineer, the results of the plant test and the APC model parameters are implemented differently. To minimize the influence of the APC engineer and calculate universal APC model parameters, a technique is needed to obtain dynamic data without a plant test. In this study, we utilize time-series data from a real petrochemical plant to determine dynamic intervals and estimate APC model parameters, which have not been investigated in previous studies. This involves extracting the data of the dynamic intervals with the smallest mean absolute error (MAE) by utilizing statistical techniques such as pruned exact linear time, linear kernel, and radial basis function kernel of change-point detection (CPD). After that, we fix the hyper parameters at the minimum MAE value and estimate the APC model parameters by training with the data from the dynamic intervals. The estimated APC model parameters are applied to the APC program to compare the APC model fitting rate and verify the accuracy of the APC model parameters in the dynamic intervals obtained through CPD. The final validation of the model fitting rates demonstrates that the identification of the dynamic intervals and the estimation of the APC model parameters through CPD show high accuracy. We show that it is possible to estimate APC model parameters from dynamic intervals determined by CPD without a plant test. [ABSTRACT FROM AUTHOR]

Coal gasification is a crucial unit of coal chemical production process. Coal and oxygen are used as the main reaction raw materials in the coal gasification process and the crude syngas is generated by chemical reaction under high temperature and high pressure. Compared with the petrochemical industry, it is more difficult to implement advanced process control (APC) in the coal gasification industrial process because of the time varying disturbance of coal quality. The time varying disturbance may lead to the mismatch of the APC model that could cause some large fluctuations of key process indices (oxygen coal ratio and gasifier temperature). In view of above problems, based on the actual production of coal-water slurry gasifier, a dynamic matrix control method based on multiple models switching is proposed in this paper. The off-line process data under different coal quality conditions are used to construct a multiple working model set for on-line dynamic matrix controller. The intergral squared error-total squared variation (ISE-TSV) is used as the controller performance index to monitor the controller performance and model mismatch and the multiple model prediction value is used as the model switching criterion. The advanced control of the coal gasification unit is realized through the multiple models switching dynamic matrix control. According to the proposed method, a multiple model switching control software Wisdom-Controller has been developed. The Wisdom-Controller has been tested on the UniSim simulation platform and applied to the real industrial gasifier. The simulation and industrial application results have verified that the proposed method can accurately control the change of oxygen-coal ratio and gasifier temperature under the condition of fluctuating coal quality conditions. Compared with the traditional manual operation, the mean square control deviation of oxygen-coal ratio and the gasifier temperature have been reduced obviously with the proposed advanced process control method based on multiple models switching. Also, the specific coal consumption has been reduced, the synthetic gas output has been increased and the economic benefit of the unit has been significantly improved. The industrial application results have verified that the proposed method provides a new and effective way to realize the advanced process control of coal gasification industrial process.

The present paper proposes a steel industry case study focused on a reheating furnace and a rolling mill. Hardware and software innovations were successfully combined in order to obtain process control and energy efficiency improvement. The reheating furnace at study is pusher type and processes billets. The hardware innovation is related to the installation of an insulated tunnel at the end of the reheating furnace, in order to guarantee a higher heat retention of the billets before their path along the rolling mill stands. The software innovation refers to the design and the installation of an Advanced Process Control system which manipulates the gas flow rate and the stoichiometric ratio of the furnace zones in order to satisfy the control specifications on billets and furnace variables. The control system is based on Model Predictive Control strategy and on a virtual sensor which tracks and estimates the billet features inside/outside the furnace. The designed controller was commissioned on the real plant, providing significant performances in terms of service factor, process control, and energy efficiency. [ABSTRACT FROM AUTHOR]

The cement industry includes energy-intensive processes, e.g., clinker rotary kilns and clinker grate coolers. Clinker is obtained through chemical and physical reactions in a rotary kiln from raw meal; these reactions also involve combustion processes. The grate cooler is located downstream of the clinker rotary kiln with the purpose of suitably cooling the clinker. The clinker is cooled through the action of multiple cold air fan units as it is transported within the grate cooler. The present work describes a project where Advanced Process Control techniques are applied to a clinker rotary kiln and a clinker grate cooler. Model Predictive Control was selected as the main control strategy. Linear models with delays are obtained through ad hoc plant experiments and suitably included in the controllers' formulation. A cooperation and coordination policy is introduced between the kiln and the cooler controllers. The main objectives of the controllers are to control the rotary kiln and grate cooler critical process variables while minimizing the fuel/coal specific consumption of the kiln and the electric energy consumption of the cold air fan units within the cooler. The overall control system was installed on the real plant, obtaining significant results in terms of service factor and control and energy-saving performances. [ABSTRACT FROM AUTHOR]

The present work is in the framework of water resource control and optimization. Specifically, an advanced process control system was designed and implemented in a hydroelectric power plant for water management. Two reservoirs (connected through a regulation gate) and a set of turbines for energy production constitute the main elements of the process. In-depth data analysis was carried out to determine the control variables and the major issues related to the previous conduction of the plant. A tailored modelization process was conducted, and satisfactory fitting performances were obtained with linear models. In particular, first-principles equations were combined with data-based techniques. The achievement of a reliable model of the plant and the availability of reliable forecasts of the measured disturbance variables—e.g., the hydroelectric power production plan—motivated the choice of a control approach based on model predictive control techniques. A tailored methodology was proposed to account for model uncertainties, and an ad hoc model mismatch compensation strategy was designed. Virtual environment simulations based on meaningful scenarios confirmed the validity of the proposed approach for reducing water waste while meeting the water demand for electric energy production. The control system was commissioned for the real plant, obtaining significant performance and a remarkable service factor. [ABSTRACT FROM AUTHOR]

Accurate trajectory tracking is a paramount objective when a mobile robot must perform complicated tasks. In high-speed movements, hardware-induced delays may produce overshoots and even instability when controlling the system. In this case, Smith predictor controllers can be used because they are well suited for delayed processes. This paper addresses the accurate positioning of a mobile robot on a terrain of an unknown slope. This slope produces disturbance torques of unknown amplitudes in the robot actuators that yield a steady-state error in the positioning. Because our actuators are integrating plus time delay plants, the standard Smith predictor cannot remove these disturbances. This paper proposes a modification of this control scheme in order to remove these disturbances yielding a zero steady-state error in the actuators. Our new scheme is compared with other modified SPs existing in the literature by means of simulations. These simulations show the superior performance of our scheme in the sense of removing the steady-state error more efficiently (i.e., faster) than other schemes. Finally, the performance of our control scheme is tested experimentally in a low-cost mobile robot.

This paper presents an analysis of the energy consumption of a continuous flow ohmic heater (CFOH) with advanced process controls for heating operations in the food and drinks industry. The study was carried out by using operational data collected from a CFOH pilot plant that was designed and constructed at the National Centre of Excellence for Food Engineering (NCEFE), Sheffield Hallam University. The CFOH is controlled by a PC and includes an onboard Programmable Logic Controller (PLC) and a Human Machine Interface (HMI) so that it can be operated as a stand-alone unit with basic on/off and power setting control but without any advanced control features. The technical solution presented in this paper for heating foods demonstrates significant energy saving compared with conventional heating methods. Using the CFOH, the electric current generated in the food products by the Joule effect produces a rapid temperature increase with very high energy efficiency. This technique eliminates the low efficiency of heat transfer from the surface of vessels typically used to heat and cook food products. The analysis presented in this paper describes the energy consumption of the CFOH and compares the efficiency of the CFOH when different advanced process control techniques are used. Experimental results and analysis have shown that the CFOH can achieve an energy efficiency conversion of at least 87.9%. It has also shown that the energy conversion percentage can be increased by applying advanced controllers such as model predictive control (MPC) or adaptive model predictive control (AMPC). [ABSTRACT FROM AUTHOR]

Accurate trajectory tracking is a paramount objective when a mobile robot must perform complicated tasks. In high-speed movements, time delays appear when reaching the desired position and orientation, as well as overshoots in the changes of orientation, which prevent the execution of some tasks. One of the aspects that most influences the tracking performance is the control system of the actuators of the robot wheels. It usually implements PID controllers that, in the case of low-cost robots, do not yield a good tracking performance owing to friction nonlinearity, hardware time delay and saturation. We propose to overcome these problems by designing an advanced process control system composed of a PID controller plus a prefilter combined with a Smith predictor, an anti-windup scheme and a Coulomb friction compensator. The contribution of this article is the motor control scheme and the method to tune the parameters of the controllers. It has been implemented in a well-known low-cost small mobile robot and experiments have been carried out that demonstrate the improvement achieved in the performance by using this control system. [ABSTRACT FROM AUTHOR]

• Efficient active process control of a pharmaceutical purification step. • Universally applicable development procedure for process models. • Process modeling approach capable for early development stages. • Evaluation of control concepts with different real-time measurements. • Process route selection based on simulation studies. Many continuously operated pharmaceutical process routes have been presented recently. Most of these cover the synthesis of the active pharmaceutical ingredient (API) or solid dosage processing. However, the API purification is also gaining attraction. One widespread and waste-intensive unit operation for purification is the liquid–liquid-extraction (LLE). In continuous manufacturing active process control is required, especially for fast processes. Control concepts must be able to react on product quality deviations caused by disturbances or inadequate process settings in real-time. In this study different control concepts for LLE were developed for an extraction column and a multistage extraction. A universally applicable process model was derived and parametrized. The impact of several control concepts including different real-time measurements was evaluated in simulation for both LLE process routes. The results show that simulation tools based on proper process models can support the selection of the most efficient process route and of suitable control concepts. [ABSTRACT FROM AUTHOR]

Advanced Process Control (APC) has become an increasingly pressing issue for the semiconductor industry, particularly in the new era of sub-5 nm process technology. To minimize human input in analyzing equipment state and output quality, Virtual Metrology (VM), one such incredibly reliable and resource-saving APC tool built on artificial intelligence and machine learning techniques, was introduced as an aide to real metrology and is aimed at predicting semiconductor product quality based on equipment status/process variables and sampled actual metrology. In this paper, VM efforts for semiconductor manufacturing applications are, for the first time, systematically reviewed. Based on comprehensive mining of literature, a generic architecture for semiconductor VM is presented, and the general requirements are discussed. Moreover, the state-of-the-art VM works for prominent processes involved in semiconductor manufacturing are surveyed, and the unique contributions of those VM predictive works are summarized and compared. Nevertheless, VM is still in its infancy stage, and there are significant hurdles that prevent wider VM implementation and acceptance in semiconductor industry. In this end, a critical analysis is provided to reveal the research gaps and discuss the challenges, such that further research can be simulated in the future. It is hoped that this work could illuminate researchers to understand the needs and future directions towards developing VM technology for semiconductor processes. [ABSTRACT FROM AUTHOR]

mRNA-based therapeutics are predicted to have a bright future. Recently, a B2C study was published highlighting the critical bottlenecks of mRNA manufacturing. The study focused on supply bottlenecks of various chemicals as well as shortages of skilled personnel. The assessment of existing messenger ribonucleic acid (mRNA) vaccine processing shows the need for continuous manufacturing processes that are capable of about 80% chemical reduction and more than 70% personnel at factor five more efficient equipment utilization. The key technology to solve these problems is both a higher degree of automation and the maximization of process throughput. In this paper, the application of a quality-by-design process development approach is demonstrated, using process models as digital twins. Their systematic application leads to both robust optimized process parameters, with an increase in productivity of up to 108%, and sophisticated control concepts, preventing batch failures and minimizing the operating workload in terms of personnel and chemicals' consumption. The approach thereby provides a data-driven decision basis for the industrialization of such processes, which fulfills the regulatory requirements of the approval authorities and paves the way for PAT integration. In the process investigated, it was shown that conventional PID-based controls can regulate fluctuations in the input streams sufficiently well. Model-based control based on digital twins may have potential above all in a further increase in productivity, but is not mandatory to implement for the industrialization of continuous mRNA manufacturing. [ABSTRACT FROM AUTHOR]

The present paper proposes a steel industry case study focused on a reheating furnace and a rolling mill. Hardware and software innovations were successfully combined in order to obtain process control and energy efficiency improvement. The reheating furnace at study is pusher type and processes billets. The hardware innovation is related to the installation of an insulated tunnel at the end of the reheating furnace, in order to guarantee a higher heat retention of the billets before their path along the rolling mill stands. The software innovation refers to the design and the installation of an Advanced Process Control system which manipulates the gas flow rate and the stoichiometric ratio of the furnace zones in order to satisfy the control specifications on billets and furnace variables. The control system is based on Model Predictive Control strategy and on a virtual sensor which tracks and estimates the billet features inside/outside the furnace. The designed controller was commissioned on the real plant, providing significant performances in terms of service factor, process control, and energy efficiency.

The cement industry includes energy-intensive processes, e.g., clinker rotary kilns and clinker grate coolers. Clinker is obtained through chemical and physical reactions in a rotary kiln from raw meal; these reactions also involve combustion processes. The grate cooler is located downstream of the clinker rotary kiln with the purpose of suitably cooling the clinker. The clinker is cooled through the action of multiple cold air fan units as it is transported within the grate cooler. The present work describes a project where Advanced Process Control techniques are applied to a clinker rotary kiln and a clinker grate cooler. Model Predictive Control was selected as the main control strategy. Linear models with delays are obtained through ad hoc plant experiments and suitably included in the controllers’ formulation. A cooperation and coordination policy is introduced between the kiln and the cooler controllers. The main objectives of the controllers are to control the rotary kiln and grate cooler critical process variables while minimizing the fuel/coal specific consumption of the kiln and the electric energy consumption of the cold air fan units within the cooler. The overall control system was installed on the real plant, obtaining significant results in terms of service factor and control and energy-saving performances.

[Display omitted] • Synthesis of mesalazine in continuous flow. • Implementation of a concept for real-time data acquisition. • Development of a model-based control concept for the complete synthesis line. • Implementation of PAT and control strategy in an automation platform. A continuous synthesis line was developed integrating different common reaction steps namely nitration, substitution and hydrogenation. Mesalazine as model drug substance was produced from 2-chlorobenzoic acid in continuous flow mode. A multi-instrument PAT strategy was implemented to equip the full line with in-line monitoring capability for critical quality attributes (CQAs) at several points. While most applications of PAT in research and manufacturing of the drug substance are limited to in-process control of quality, in this study real-time process information was generated to support automated process control actions. Process models were developed for all steps of the synthesis route either mechanistic based on reaction kinetics, data driven based on process data or depicting the residence time distribution (RTD). These models facilitated the development and implementation of an automation concept. Feedback loops were established using model predictive controllers for each unit operation, with the objective to maximize yield and minimize side products. The results indicate the high potential of an advanced control concept based on process models and real-time process data. [ABSTRACT FROM AUTHOR]

The heating furnace of residue hydrogenation unit has the problems, such as high excess oxygen content, large fluctuation of oxygen content in radiation chamber, high concentration of NO% in exhaust gas, high exhaust gas temperature and low thermal efficiency. To solve the above problems, a comprehensive transformation of the hating furnace system is carried out. Adding an advanced process controller, the fluctuation of negative pressure and oxygen content of the heating furnace are significantly reduced, making the operation of the heating furnace more stable. Replacing the low nitrogen burner, the mass concentration of NOx in the discharged flue gas is reduced from 80.43 mg/m³ to 24.66 mg/m³, which is far lower than the national emission standard (100 mg/m³). Upgrading the heat pipe air preheater to a steel pate and cast iron plate combined air preheater, the flue gas temperature in summer is reduced from more than 130 °C to about 115 °C, and the thermal efficiency of the heating furnace increases significantly. After a series of transformation, the operation indexes of the heating furnace of the residue hydrogenation unit have been greatly improved, and the transformation purpose of energy conservation and environmental protection has been achieved. [ABSTRACT FROM AUTHOR]

The need for load flexibility and increased efficiency of energy‐intensive processes has become more and more important in recent years. Control of the process variables plays a decisive role in maximizing the efficiency of a plant. The widely used control models of linear model predictive controllers (LMPC) are only partly suitable for nonlinear processes. One possibility for improvement is machine learning. In this work, one approach for a purely data‐driven controller based on reinforcement learning is explored at an air separation plant (ASU) in productive use. The approach combines the model predictive controller with a data‐generated nonlinear control model. The resulting controller and its control performance are examined in more detail on an ASU in real operation and compared with the previous LMPC solution. During the tests, stable behavior of the new control concept could be observed for several weeks in productive operation. [ABSTRACT FROM AUTHOR]

In early 2018, the Boliden Garpenberg operation implemented an optimized control strategy as an addition to the existing ventilation on demand system. The purpose of the strategy is to further minimize energy use for main and booster fans, whilst also fulfilling airflow setpoints without violating constraints such as min/max differential pressure over fans and interaction of air between areas in mines. Using air flow measurements and a dynamical model of the ventilation system, a mine-wide coordination control of fans can be carried out. The numerical model is data driven and derived from historical operational data or step changes experiments. This makes both initial deployment and lifetime model maintenance, as the mine evolves, a comparably easy operation. The control has been proven to operate in a stable manner over long periods without having to re-calibrate the model. Results prove a 40% decrease in energy use for the fans involved and a greater controllability of air flow. Moreover, a 15% decrease of the total air flow into the mine will give additional proportional heating savings during winter periods. All in all, the multivariable controller shows a correlation between production in the mine and the ventilation system performance superior to all of its predecessors.

This paper presents an analysis of the energy consumption of a continuous flow ohmic heater (CFOH) with advanced process controls for heating operations in the food and drinks industry. The study was carried out by using operational data collected from a CFOH pilot plant that was designed and constructed at the National Centre of Excellence for Food Engineering (NCEFE), Sheffield Hallam University. The CFOH is controlled by a PC and includes an onboard Programmable Logic Controller (PLC) and a Human Machine Interface (HMI) so that it can be operated as a stand-alone unit with basic on/off and power setting control but without any advanced control features. The technical solution presented in this paper for heating foods demonstrates significant energy saving compared with conventional heating methods. Using the CFOH, the electric current generated in the food products by the Joule effect produces a rapid temperature increase with very high energy efficiency. This technique eliminates the low efficiency of heat transfer from the surface of vessels typically used to heat and cook food products. The analysis presented in this paper describes the energy consumption of the CFOH and compares the efficiency of the CFOH when different advanced process control techniques are used. Experimental results and analysis have shown that the CFOH can achieve an energy efficiency conversion of at least 87.9%. It has also shown that the energy conversion percentage can be increased by applying advanced controllers such as model predictive control (MPC) or adaptive model predictive control (AMPC).

Accurate trajectory tracking is a paramount objective when a mobile robot must perform complicated tasks. In high-speed movements, time delays appear when reaching the desired position and orientation, as well as overshoots in the changes of orientation, which prevent the execution of some tasks. One of the aspects that most influences the tracking performance is the control system of the actuators of the robot wheels. It usually implements PID controllers that, in the case of low-cost robots, do not yield a good tracking performance owing to friction nonlinearity, hardware time delay and saturation. We propose to overcome these problems by designing an advanced process control system composed of a PID controller plus a prefilter combined with a Smith predictor, an anti-windup scheme and a Coulomb friction compensator. The contribution of this article is the motor control scheme and the method to tune the parameters of the controllers. It has been implemented in a well-known low-cost small mobile robot and experiments have been carried out that demonstrate the improvement achieved in the performance by using this control system.

Reducing variations of fabrication processes is a primary focus for improvement in etching process. One powerful tool employed towards this goal is Advanced Process Control (APC). APC adjusts recipes to compensate for measured variations. Systemic variations that were acceptable previously can become problematic as node sizes get smaller and structures become more complex. Dry etch can be a major source of variations and will be the focus of this research. Different APC methods have been developed to adjust recipes. However it is challenging to determine an optimal recipe to achieve multiple critical dimensions. In this article, an optimization method is proposed to generate optimal recipes for multiple input and multiple output (MIMO) systems. Models are constructed by applying Gaussian Process Regression and the optimal recipe is predicted using the proposed optimization method. Experimental data in dry etch process were collected and processed for model construction and recipe prediction. The results demonstrate the effectiveness of the proposed method in exploring optimal recipes for MIMO systems. [ABSTRACT FROM AUTHOR]

This whitepaper summarizes the outcome of the first Advanced Process Control (APC) workshop in the pharmaceutical industry, presented by AIChE PD2M, and held in Washington DC, Sep 30 to Oct 01, 2019. Approximately 50 attendees from regulatory agencies, industry and academia had an opportunity to share perspectives and best practices on the business, technical and regulatory aspects of APC for both small and large molecule drug manufacturing. The event consisted of keynote talks, case studies and panel discussions, filled with lively interactions that focused on: (a) Business drivers for APC in pharma; (b) Alignment on the definitions of key terminology; (c) Clarification of roles and relationships of APC with regards to popular initiatives such as Quality by Design (QbD), Process Analytical Technology (PAT), Real Time Release testing (RTRt), Continued Process Verification (CPV), continuous manufacturing and digital manufacturing; (d) APC manufacturing implementation considerations; (e) Quality system and regulatory considerations for APC implementation; (f) APC opportunities in modular manufacturing, process intensification, integrated continuous manufacturing. (g) standards, training, and collaboration. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI), which is characterized by ability to learn and adapt continuously, can enhance the fault tolerance and robustness in process control. Application of high-efficiency physical fields such as microwave, radio frequency, infrared radiation and ultrasonic fields can result in efficient production of dried fruit and vegetable products with high quality. Whether the combination of AI technology and efficient physical field can obtain better dried products of fruits and vegetables, and how AI can be applied in the drying process of fruit and vegetable, has attracted extensive attention. The application of artificial intelligence technology to assist the efficient physical field in the drying of fruits and vegetables is the development trend of fruit and vegetable drying industry in the future. This paper aims to provide a concise overview of recent research in the rapidly emerging area of AI-assisted drying of fruits and vegetables using physical fields to provide energy for drying process. A selection of AI technologies is introduced such as sensor technology, computer vision systems as well as a few relevant AI technologies used in the drying process of fruits or vegetables. Afterwards, it summarizes the application of artificial intelligence in the physical drying of fruits and vegetables, and how to improve the shortcomings of highly efficient physical field drying of fruits and vegetables with AI. The application of high efficiency physical field in the drying process of fruits and vegetables can solve the problems of large energy consumption, uneven drying, poor sensory evaluation, and large nutrient loss. The drying process and the corresponding drying model of fruits and vegetables can be detected and controlled online, and the optimum drying scheme can be determined using artificial intelligence technology. The most important thing is to make up for the shortcomings of highly efficient physical field drying of fruits and vegetables. The artificial intelligence technology has a promising application prospect to assist the efficient physical field drying of fruits and vegetables. • Introduce artificial intelligence technologies, including sensor technology, computer vision system and other technologies. • The application of artificial intelligence (sensor, computer vision, ANN, GA) in fruit and vegetable drying was reviewed. • The application of artificial intelligence technology combined in fruit and vegetable drying using efficient physical field. • The development suggestion of artificial intelligence drying technology based on efficient physical field was provided. [ABSTRACT FROM AUTHOR]

• Several controller strategies for a feeding-blending unit are designed and applied in a simulation and on a real plant. • Standard controller concepts are compared to a model predictive controller. • Brief feeder fluctuations are successfully attenuated by adjusting the blender speed. • Application of a model predictive controller shows advantageous behaviour compared to the other controller strategies. This paper outlines several control strategies for a feeding blending unit in a continuous pharmaceutical manufacturing setup, with the goal of damping feeder fluctuations by adjusting the blender speed. An advanced model predictive control concept and two standard concepts, PI- and model-based feed-forward control, are described and compared with respect to their performance in the simulation. The concepts which showed satisfactory behaviour in the simulation are further tested on the real system. The paper also provides a detailed explanation of each implementation step in a real system, i.e., measurement device setup, signal processing, parameter identification and controller design. The properties of control concepts are compared and analysed, particularly in view of further work on the complete direct compaction line. [ABSTRACT FROM AUTHOR]

In this paper, the problem of optimal system identification in nonlinear model predictive control (NMPC) for highly nonlinear dynamic processes is presented. Due to the short term changes in the operating point, the process may escape from its frequent operating points (FOP) to some infrequent operating points (IOP) for a short period. On the other hand, because the nonlinear model is identified using the operating data, it is mainly accurate for the FOP. Therefore, the NMPC causes tracking error or even instability in the IOP. To handle this problem, in this paper, we present a novel optimal identification algorithm, which is highly depended on the nonlinearity of the understudy plant, to train the nonlinear model of the NMPC. The nonlinear model is selected as a multi-layer perceptron neural network (MLP) which is trained to describe the nonlinear behaviour of the nonlinear dynamic system accurately in the FOP and while it has acceptable performance in the IOP. To validate the proposed algorithm, the well-known nonlinear dynamic pH neutralization process is chosen in both simulation and implementation parts. Finally, the simulation and implementation results prove the effectiveness of the proposed algorithm. • Identification data ratio in frequent and infrequent operating points are studied. • Volterra series is used to generate a model bank with different nonlinearity. • It is shown that data distribution is related to the nonlinearity measure. • The identified model is used as predictor in the nonlinear model predictive control. • The proposed method is experimentally evaluated on a pH neutralization process. [ABSTRACT FROM AUTHOR]

In semiconductor manufacturing, the chemical mechanical planarization (CMP) process produces higher thickness variability in the edge area of the wafer than that in the center area due to the characteristics of the polishing operation. To address this problem, advanced CMP equipment includes a function that controls the removal rate of each area. However, to take full advantage of this capability, effective advanced process control systems must be implemented with a virtual metrology (VM) model. However, the prediction performance of the VM model often deteriorates due to process drift. Here, we present a deep learning-based VM model that demonstrates high performance in the presence of nonlinear process drift. The proposed model combines a recurrent neural network and a convolutional neural network to extract time-dependent and time-independent features. A two-stage model training method is proposed that alternately updates the weights of each network to improve prediction performance. In the experiments using on-site CMP process data, the performance of the deep learning models exceeded that of standard machine learning models. The proposed model showed an 8.48% decrease in process variability relative to the best-performing machine learning model, which was elastic nets. [ABSTRACT FROM AUTHOR]

• A Deep Learning approach for feature extraction in industrial big data is proposed. • DeepVM is completely plug-n-play and naturally deals with 2d data. • An extensive comparison of different autoencoders and regression methods is provided. • DeepVM efficacy is tested on a real Semiconductor Manufacturing dataset. • DeepVM outperforms classical feature extraction procedures in the Virtual Metrology task. Industry 4.0 encapsulates methods, technologies, and procedures that transform data into informed decisions and added value in an industrial context. In this regard, technologies such as Virtual Metrology or Soft Sensing have gained much interest in the last two decades due to their ability to provide valuable knowledge for production purposes at limited added expense. However, these technologies have struggled to achieve wide-scale industrial adoption, largely due to the challenges associated with handling complex data structures and the feature extraction phase of model building. This phase is generally hand-engineered and based on specific domain knowledge, making it time consuming, difficult to automate, and prone to loss of information, thus ultimately limiting portability. Moreover, in the presence of complex data structures, such as 2-dimensional input data, there are no established procedures for feature extraction. In this paper, we present a Deep Learning approach for Virtual Metrology, called DeepVM, that exploits semi-supervised feature extraction based on Convolutional Autoencoders. The proposed approach is demonstrated using a real world Semiconductor Manufacturing dataset where the Virtual Metrology input data is 2-dimensional Optical Emission Spectrometry data. The feature extraction method is tested with different types of state-of-the-art autoencoder. [ABSTRACT FROM AUTHOR]

Virtual metrology (VM) predicts the actual measurement for ongoing semiconductor process. Optical emission spectroscopy (OES) data is often used to build up VM models, since it has a lot of information on process quality. However, it also includes significant redundant information, so it is important how to select only meaningful features. Deep learning (DL) techniques have been very successful in analyzing image data and it is tempting to apply those techniques to the OES data. In this paper, we propose DL configurations specific to OES data that outperform those used for image analysis. Specifically, our proposed method accounts for variable size data, chamber to chamber differences, condition drift due to accumulation, observation data drift due to an accumulation of deposition on a window, and the effects of maintenance. We evaluated our method on a real, mass-production dataset and compared our results with those obtained by using state-of-the-art image analysis DL techniques in the famous contest, ImageNet large-scale visual recognition challenge (ILSVRC). [ABSTRACT FROM AUTHOR]