Pub Date : 2025-10-28DOI: 10.1016/j.jprocont.2025.103577
Jiamin Xu , Nazli Demirer , Vy Pho , Kaixiao Tian , He Zhang , Ketan Bhaidasna , Robert Darbe , Dongmei Chen
This paper presents a multi-input, multi-output (MIMO) economic model predictive control (MPC) approach for directional drilling using an efficient model with state and parameter estimation using sensor fusion. The MPC framework coordinates weight-on-bit (WOB) and pad force to ensure the bit follows the planned well trajectory while maintaining high WOB, implying a high rate of penetration (ROP). The simulation studies, conducted under scenarios with initial bit positions both ahead of and behind the well plan, demonstrate the robustness and effectiveness of the proposed MPC strategy. The results show that the controller can maintain the bit on the well plan despite various disturbances and noise, indicating its potential for practical application in the field.
{"title":"Real time multi-inputs multi-outputs economic model predictive control for directional drilling based on fast modeling and sensor fusion","authors":"Jiamin Xu , Nazli Demirer , Vy Pho , Kaixiao Tian , He Zhang , Ketan Bhaidasna , Robert Darbe , Dongmei Chen","doi":"10.1016/j.jprocont.2025.103577","DOIUrl":"10.1016/j.jprocont.2025.103577","url":null,"abstract":"<div><div>This paper presents a multi-input, multi-output (MIMO) economic model predictive control (MPC) approach for directional drilling using an efficient model with state and parameter estimation using sensor fusion. The MPC framework coordinates weight-on-bit (WOB) and pad force to ensure the bit follows the planned well trajectory while maintaining high WOB, implying a high rate of penetration (ROP). The simulation studies, conducted under scenarios with initial bit positions both ahead of and behind the well plan, demonstrate the robustness and effectiveness of the proposed MPC strategy. The results show that the controller can maintain the bit on the well plan despite various disturbances and noise, indicating its potential for practical application in the field.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"156 ","pages":"Article 103577"},"PeriodicalIF":3.9,"publicationDate":"2025-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145371409","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-25DOI: 10.1016/j.jprocont.2025.103573
Chuan Wang , Haojie Liao , Kui Xie , Chao Yu
This study proposes a robust control framework that integrates sliding mode control (SMC) with a novel hybrid observer (UKF-LSTM in series) to stabilize separator level and pressure. The stability of the control system is ensured by the Lyapunov method. A significant innovation is a hybrid observer that combines an Unscented Kalman Filter (UKF) and a Long Short-Term Memory (LSTM) network in series to accurately estimate the unmeasurable multiphase inflow. In OLGA plug flow simulations, the framework reduced flow estimation Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) by 73.9 % and 64.7 % over the baseline. The Control tests showed Integral of Squared Error (ISE), Integral of Absolute Error (IAE), and Integral of Time-weighted Absolute Error (ITAE) were 49.8 %, 24.8 %, and 18.0 %, with convergence accelerated by at least 250 s. Results demonstrate that the method achieves a practical balance between accuracy, robustness, and computational efficiency, making it suitable for real-time industrial separator control under variable conditions.
{"title":"Research on control methods for gas-liquid separators based on UKF-LSTM hybrid observation and sliding mode control","authors":"Chuan Wang , Haojie Liao , Kui Xie , Chao Yu","doi":"10.1016/j.jprocont.2025.103573","DOIUrl":"10.1016/j.jprocont.2025.103573","url":null,"abstract":"<div><div>This study proposes a robust control framework that integrates sliding mode control (SMC) with a novel hybrid observer (UKF-LSTM in series) to stabilize separator level and pressure. The stability of the control system is ensured by the Lyapunov method. A significant innovation is a hybrid observer that combines an Unscented Kalman Filter (UKF) and a Long Short-Term Memory (LSTM) network in series to accurately estimate the unmeasurable multiphase inflow. In OLGA plug flow simulations, the framework reduced flow estimation Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) by 73.9 % and 64.7 % over the baseline. The Control tests showed Integral of Squared Error (ISE), Integral of Absolute Error (IAE), and Integral of Time-weighted Absolute Error (ITAE) were 49.8 %, 24.8 %, and 18.0 %, with convergence accelerated by at least 250 s. Results demonstrate that the method achieves a practical balance between accuracy, robustness, and computational efficiency, making it suitable for real-time industrial separator control under variable conditions.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"155 ","pages":"Article 103573"},"PeriodicalIF":3.9,"publicationDate":"2025-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145362338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-21DOI: 10.1016/j.jprocont.2025.103533
Zhengang Zhong, Ehecatl Antonio del Rio-Chanona, Panagiotis Petsagkourakis
This paper presents a novel data-driven stochastic MPC design for discrete-time nonlinear systems with additive disturbances by leveraging the Koopman operator and a distributionally robust optimization (DRO) framework. By lifting the dynamical system into a linear space, we achieve a finite-dimensional approximation of the Koopman operator. We explicitly account for the modeling approximation and additive disturbance error by a mixed stochastic–deterministic tube for the lifted linear model. This ensures the regulation of the original nonlinear system while complying with the prespecified constraints. Stochastic and deterministic tubes are constructed using a DRO and a hyper-cube hull, respectively. We provide finite sample error bounds for both types of tubes. The effectiveness of the proposed approach is demonstrated through numerical simulations.
{"title":"Data-driven Koopman MPC using mixed stochastic–deterministic tubes","authors":"Zhengang Zhong, Ehecatl Antonio del Rio-Chanona, Panagiotis Petsagkourakis","doi":"10.1016/j.jprocont.2025.103533","DOIUrl":"10.1016/j.jprocont.2025.103533","url":null,"abstract":"<div><div>This paper presents a novel data-driven stochastic MPC design for discrete-time nonlinear systems with additive disturbances by leveraging the Koopman operator and a distributionally robust optimization (DRO) framework. By lifting the dynamical system into a linear space, we achieve a finite-dimensional approximation of the Koopman operator. We explicitly account for the modeling approximation and additive disturbance error by a mixed stochastic–deterministic tube for the lifted linear model. This ensures the regulation of the original nonlinear system while complying with the prespecified constraints. Stochastic and deterministic tubes are constructed using a DRO and a hyper-cube hull, respectively. We provide finite sample error bounds for both types of tubes. The effectiveness of the proposed approach is demonstrated through numerical simulations.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"155 ","pages":"Article 103533"},"PeriodicalIF":3.9,"publicationDate":"2025-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145362337","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-21DOI: 10.1016/j.jprocont.2025.103572
Chongyang Liu , Jinxu Cui , Jianzhi Wu , Zhaohua Gong
Optimal control of biochemical processes remains an open research and industrial challenge due to intrinsic system nonlinearity, unsteady dynamics and stringent operation constraints. Although reinforcement learning has recently gained attention, its direct application in biochemical process control has been hindered by the presence of multiple conflicting control objectives. To address this, we formulate a multi-objective optimal control problem in biochemical processes with both control inputs and terminal time as decision variables and subject to path and terminal inequality constraints. For this problem, a time-scaling transformation and an exact penalty method are exploited to convert it into the one with fixed terminal time and simple box constraints. Furthermore, the problem is transformed to a set of single-objective problems by using the scalarization techniques of weighted sum and normalized norm constraint. Then, based on an improved proximal policy optimization algorithm with dynamic clipping threshold, we develop a reinforcement learning algorithm to solve the resulting problems. Finally, two case studies on glucose batch fermentation and lysine fed-batch fermentation show that the proposed reinforcement algorithm can achieve more uniform distribution of optimal solution sets and faster convergence.
{"title":"Multi-objective optimal control of biochemical processes based on reinforcement learning","authors":"Chongyang Liu , Jinxu Cui , Jianzhi Wu , Zhaohua Gong","doi":"10.1016/j.jprocont.2025.103572","DOIUrl":"10.1016/j.jprocont.2025.103572","url":null,"abstract":"<div><div>Optimal control of biochemical processes remains an open research and industrial challenge due to intrinsic system nonlinearity, unsteady dynamics and stringent operation constraints. Although reinforcement learning has recently gained attention, its direct application in biochemical process control has been hindered by the presence of multiple conflicting control objectives. To address this, we formulate a multi-objective optimal control problem in biochemical processes with both control inputs and terminal time as decision variables and subject to path and terminal inequality constraints. For this problem, a time-scaling transformation and an exact penalty method are exploited to convert it into the one with fixed terminal time and simple box constraints. Furthermore, the problem is transformed to a set of single-objective problems by using the scalarization techniques of weighted sum and normalized norm constraint. Then, based on an improved proximal policy optimization algorithm with dynamic clipping threshold, we develop a reinforcement learning algorithm to solve the resulting problems. Finally, two case studies on glucose batch fermentation and lysine fed-batch fermentation show that the proposed reinforcement algorithm can achieve more uniform distribution of optimal solution sets and faster convergence.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"155 ","pages":"Article 103572"},"PeriodicalIF":3.9,"publicationDate":"2025-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145362339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-18DOI: 10.1016/j.jprocont.2025.103567
Mingyu Liang, Yi Zheng, Shaoyuan Li
This paper addresses the hybrid modeling challenges arising from incomplete mechanistic models and operational data noise interference in process industries, proposing a two-layer joint iterative optimization framework for updating parameters of hybrid models integrating mechanistic and data-driven models. The framework achieves real-time anomaly elimination through an outlier screening algorithm, while employing a bidirectional feedback algorithm to enable continuous collaboration and mutual constraints between mechanistic and data-driven models during parameter identification and iterative updates, ensuring robust hybrid model predictions. The proposed method resolves hybrid modeling and updating under conditions of mechanistic model information deficiency. Additionally, by incorporating model uncertainty and prior knowledge, it accomplishes a knowledge-incorporated hybrid modeling process, demonstrating significant practical value. Unlike conventional hybrid modeling approaches where mechanistic knowledge merely guides the modeling process, our method achieves dynamic co-evolution between mechanistic and data-driven models. This paper elaborates on three key aspects: (1) using mechanistic models to screen anomalous data; (2) incorporating mechanistic parameter uncertainty and prior knowledge through Bayesian methods to design knowledge-guided parameter updating method; (3) implementation details of the two-layer joint iterative optimization algorithm. Comparative experiments validate the method’s superior performance under multiple operating conditions and anomalies, demonstrating its scientific validity and practical value in dynamic optimization processes.
{"title":"Towards hybrid modeling with mechanistic and real-time data embed iterative co-optimization for industrial processes","authors":"Mingyu Liang, Yi Zheng, Shaoyuan Li","doi":"10.1016/j.jprocont.2025.103567","DOIUrl":"10.1016/j.jprocont.2025.103567","url":null,"abstract":"<div><div>This paper addresses the hybrid modeling challenges arising from incomplete mechanistic models and operational data noise interference in process industries, proposing a two-layer joint iterative optimization framework for updating parameters of hybrid models integrating mechanistic and data-driven models. The framework achieves real-time anomaly elimination through an outlier screening algorithm, while employing a bidirectional feedback algorithm to enable continuous collaboration and mutual constraints between mechanistic and data-driven models during parameter identification and iterative updates, ensuring robust hybrid model predictions. The proposed method resolves hybrid modeling and updating under conditions of mechanistic model information deficiency. Additionally, by incorporating model uncertainty and prior knowledge, it accomplishes a knowledge-incorporated hybrid modeling process, demonstrating significant practical value. Unlike conventional hybrid modeling approaches where mechanistic knowledge merely guides the modeling process, our method achieves dynamic co-evolution between mechanistic and data-driven models. This paper elaborates on three key aspects: (1) using mechanistic models to screen anomalous data; (2) incorporating mechanistic parameter uncertainty and prior knowledge through Bayesian methods to design knowledge-guided parameter updating method; (3) implementation details of the two-layer joint iterative optimization algorithm. Comparative experiments validate the method’s superior performance under multiple operating conditions and anomalies, demonstrating its scientific validity and practical value in dynamic optimization processes.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"155 ","pages":"Article 103567"},"PeriodicalIF":3.9,"publicationDate":"2025-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145324807","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-17DOI: 10.1016/j.jprocont.2025.103568
C. Bisset , R. Coetzer , PVZ. Venter
Optimising boiler operations is challenging due to fluctuating conditions in complex thermo-fluid systems. This study introduces a novel approach to improve efficiency in coal-fired boilers by developing and validating an artificial neural network (ANN) model that provides both statistically accurate and scientifically feasible predictions. Three multi-layer perceptron (MLP) feedforward ANN models were developed, with variable selection supported by principal component analysis (PCA) and hyperparameter optimisation performed using Latin hypercube sampling (LHS). The best ANN achieved test root mean square errors (RMSEs) of 2.11 t/h for steam flow, 2.11 t/h for blowdown, 4.98 °C for superheated steam temperature, 0.69 bar for steam pressure, and 0.86 % for efficiency. The mean absolute percentage error (MAPE) for efficiency remained below 1.25 %, with deviations constrained within ±4.25 %. Statistical and thermodynamic validations were applied, including bootstrap aggregation of prediction variance and mass and energy balance checks. Results showed that 96.76 % of samples achieved water mass balance deviations of less than 0.01 %. Furthermore, 100 % of predictions for efficiency and energy output fell within a 5 % absolute error range. The novelty of this work lies in integrating ANN predictions with thermo-fluid validation. Theoretically, it advances current literature by bridging the gap between statistical accuracy and physical feasibility. Practically, it provides a reliable framework for evaluating efficiency in operational settings and lays the foundation for a machine learning (ML)–aided decision-support framework (DSF) for energy efficiency optimisation in coal-fired boilers.
{"title":"Boiler operation predictions by integrating thermo-fluid principles within an artificial neural network framework","authors":"C. Bisset , R. Coetzer , PVZ. Venter","doi":"10.1016/j.jprocont.2025.103568","DOIUrl":"10.1016/j.jprocont.2025.103568","url":null,"abstract":"<div><div>Optimising boiler operations is challenging due to fluctuating conditions in complex thermo-fluid systems. This study introduces a novel approach to improve efficiency in coal-fired boilers by developing and validating an artificial neural network (ANN) model that provides both statistically accurate and scientifically feasible predictions. Three multi-layer perceptron (MLP) feedforward ANN models were developed, with variable selection supported by principal component analysis (PCA) and hyperparameter optimisation performed using Latin hypercube sampling (LHS). The best ANN achieved test root mean square errors (RMSEs) of 2.11 t/h for steam flow, 2.11 t/h for blowdown, 4.98 °C for superheated steam temperature, 0.69 bar for steam pressure, and 0.86 % for efficiency. The mean absolute percentage error (MAPE) for efficiency remained below 1.25 %, with deviations constrained within ±4.25 %. Statistical and thermodynamic validations were applied, including bootstrap aggregation of prediction variance and mass and energy balance checks. Results showed that 96.76 % of samples achieved water mass balance deviations of less than 0.01 %. Furthermore, 100 % of predictions for efficiency and energy output fell within a 5 % absolute error range. The novelty of this work lies in integrating ANN predictions with thermo-fluid validation. Theoretically, it advances current literature by bridging the gap between statistical accuracy and physical feasibility. Practically, it provides a reliable framework for evaluating efficiency in operational settings and lays the foundation for a machine learning (ML)–aided decision-support framework (DSF) for energy efficiency optimisation in coal-fired boilers.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"155 ","pages":"Article 103568"},"PeriodicalIF":3.9,"publicationDate":"2025-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145324809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-14DOI: 10.1016/j.jprocont.2025.103569
Long Gao , Donghua Zhou , Steven X. Ding
Kalman filters are widely applied for residual generation thanks to the property that the generated residual is white and of minimum covariance. This enables an optimal monitoring. However, the explicit mathematical model is difficult to achieve in a real industrial automation system, and the effect of the feedback has not been explicitly considered in the existing data-driven design method, which degrades the monitoring performance of a Kalman filter-based monitoring system. To deal with such an issue, this paper proposes a purely data-driven realization of the Kalman filter-based residual generator for process monitoring of industrial control systems with a closed-loop configuration. Firstly, a least-mean-square interpretation of canonical correlation analysis (CCA) is introduced, which is helpful to explore the relationships between inputs and outputs of industrial control systems. Then, a CCA-aided Kalman filter-based residual generator is constructed, which is realized by identifying the Kalman gain matrix and the data-driven stable kernel representation. Different from the existing method, the proposed one achieves superior monitoring performance by considering closed-loop dynamics and the correlation between inputs and noises, which is caused by the feedback control structure of systems. The effectiveness of the proposed method is demonstrated and compared through an experimental three-tank system.
{"title":"Canonical correlation analysis-aided design of Kalman filter-based residual generator for monitoring of industrial control systems","authors":"Long Gao , Donghua Zhou , Steven X. Ding","doi":"10.1016/j.jprocont.2025.103569","DOIUrl":"10.1016/j.jprocont.2025.103569","url":null,"abstract":"<div><div>Kalman filters are widely applied for residual generation thanks to the property that the generated residual is white and of minimum covariance. This enables an optimal monitoring. However, the explicit mathematical model is difficult to achieve in a real industrial automation system, and the effect of the feedback has not been explicitly considered in the existing data-driven design method, which degrades the monitoring performance of a Kalman filter-based monitoring system. To deal with such an issue, this paper proposes a purely data-driven realization of the Kalman filter-based residual generator for process monitoring of industrial control systems with a closed-loop configuration. Firstly, a least-mean-square interpretation of canonical correlation analysis (CCA) is introduced, which is helpful to explore the relationships between inputs and outputs of industrial control systems. Then, a CCA-aided Kalman filter-based residual generator is constructed, which is realized by identifying the Kalman gain matrix and the data-driven stable kernel representation. Different from the existing method, the proposed one achieves superior monitoring performance by considering closed-loop dynamics and the correlation between inputs and noises, which is caused by the feedback control structure of systems. The effectiveness of the proposed method is demonstrated and compared through an experimental three-tank system.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"155 ","pages":"Article 103569"},"PeriodicalIF":3.9,"publicationDate":"2025-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145324810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-13DOI: 10.1016/j.jprocont.2025.103565
San Dinh, Yao Tong, Zhenyu Wei, Owen Gerdes, L.T. Biegler
Current nonlinear model predictive control (NMPC) strategies are formulated as finite predictive horizon nonlinear programs (NLPs), which maintain NMPC stability and recursive feasibility through the construction of terminal cost functions and/or terminal constraints. However, computing these terminal properties may pose formidable challenges with a fixed horizon, particularly in the context of nonlinear dynamic processes. Motivated by these issues, we introduce an alternate moving horizon approach where the final element in the horizon is constructed from an infinite-horizon time transformation. The key feature of this approach lies in solving the proposed NMPC formulation as an extended boundary value problem, using orthogonal collocation on finite elements. Numerical stability is ensured through a dichotomy property for an infinite horizon optimal control problem, which pins down the unstable modes, extending beyond open-loop stable dynamic systems, and leads to both asymptotic and robust stability guarantees. The efficacy of the proposed NMPC formulation is demonstrated on three case studies, which validate the practical application and robustness of the developed approach on real-world problems.
{"title":"Nonlinear model predictive control with an infinite horizon approximation","authors":"San Dinh, Yao Tong, Zhenyu Wei, Owen Gerdes, L.T. Biegler","doi":"10.1016/j.jprocont.2025.103565","DOIUrl":"10.1016/j.jprocont.2025.103565","url":null,"abstract":"<div><div>Current nonlinear model predictive control (NMPC) strategies are formulated as finite predictive horizon nonlinear programs (NLPs), which maintain NMPC stability and recursive feasibility through the construction of terminal cost functions and/or terminal constraints. However, computing these terminal properties may pose formidable challenges with a fixed horizon, particularly in the context of nonlinear dynamic processes. Motivated by these issues, we introduce an alternate moving horizon approach where the final element in the horizon is constructed from an infinite-horizon time transformation. The key feature of this approach lies in solving the proposed NMPC formulation as an extended boundary value problem, using orthogonal collocation on finite elements. Numerical stability is ensured through a dichotomy property for an infinite horizon optimal control problem, which pins down the unstable modes, extending beyond open-loop stable dynamic systems, and leads to both asymptotic and robust stability guarantees. The efficacy of the proposed NMPC formulation is demonstrated on three case studies, which validate the practical application and robustness of the developed approach on real-world problems.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"155 ","pages":"Article 103565"},"PeriodicalIF":3.9,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145324811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-13DOI: 10.1016/j.jprocont.2025.103564
Guoqing Zhang , Yang Xu , Jiqiang Li , Zehua Jia , Weidong Zhang
In this article, a spatiotemporal integrated control scheme for ballast water heat treatment is proposed that utilizes an improved nonlinear predictive control algorithm relying on a kernel-learning-based model to lower the concentration of microorganisms by manipulating the temperature of heated water indirectly. Firstly, multiple heat exchangers treating process is simplified into a plug flow reactor model with the properties of distributed parameter systems (DPSs). Based on the simplified model, the kernel-learning-based model is derived by using kernel principal component analysis (KPCA) and kernel extreme learning machine (KELM) for modeling the spatiotemporal temperature data. Further, the hyperparameters of the KELM involved therein are determined by a numerical optimization approach. The superiority of this design is to accurately explore the nonlinear dynamics and uncertainties of the actual system. Associated with the modeling method, the nonlinear predictive control strategy is designed to control and maintain the heating temperature. The remarkable trait is that a model predictive path integral (MPPI) is introduced to avoid the problem of “sinking into the local optimal solution”, which often emerges searching for the optimal control sequence. Finally, the stability analysis and numerical experiments support the effectiveness of the proposed scheme.
{"title":"Spatiotemporal integrated control for ballast water heat treatment via the kernel learning and model predictive path integral","authors":"Guoqing Zhang , Yang Xu , Jiqiang Li , Zehua Jia , Weidong Zhang","doi":"10.1016/j.jprocont.2025.103564","DOIUrl":"10.1016/j.jprocont.2025.103564","url":null,"abstract":"<div><div>In this article, a spatiotemporal integrated control scheme for ballast water heat treatment is proposed that utilizes an improved nonlinear predictive control algorithm relying on a kernel-learning-based model to lower the concentration of microorganisms by manipulating the temperature of heated water indirectly. Firstly, multiple heat exchangers treating process is simplified into a plug flow reactor model with the properties of distributed parameter systems (DPSs). Based on the simplified model, the kernel-learning-based model is derived by using kernel principal component analysis (KPCA) and kernel extreme learning machine (KELM) for modeling the spatiotemporal temperature data. Further, the hyperparameters of the KELM involved therein are determined by a numerical optimization approach. The superiority of this design is to accurately explore the nonlinear dynamics and uncertainties of the actual system. Associated with the modeling method, the nonlinear predictive control strategy is designed to control and maintain the heating temperature. The remarkable trait is that a model predictive path integral (MPPI) is introduced to avoid the problem of “sinking into the local optimal solution”, which often emerges searching for the optimal control sequence. Finally, the stability analysis and numerical experiments support the effectiveness of the proposed scheme.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"155 ","pages":"Article 103564"},"PeriodicalIF":3.9,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145324808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-11DOI: 10.1016/j.jprocont.2025.103566
Xue Xu , Chaomin Luo , Yuanjian Fu
Interactions across process variables are complicated in large-scale industrial processes characterized with multiple operating units, posing significant challenges for fault detection and root cause analysis. In this work, a distributed modeling approach termed causal-geometry joint dictionary embedding learning (CGDE) is proposed to monitor large-scale industrial processes and identify the root cause. An information decomposition based block division algorithm is proposed to divide the entire process into blocks that account for unique, redundant, and synergistic information among variables. Meanwhile, a geometry similarity matrix derived by the minimum spanning tree is constructed to exploit the underlying structure of data. Furthermore, a causal consistency matrix is developed to characterize the causality among variables such that the intrinsic and stable information of industrial processes can be effectively captured. The CGDE approach provides an in-depth and faithful process analysis with consideration of causalities and geometry similarity of data, enhancing the distributed monitoring and root cause analysis performance. The effectiveness of CGDE is illustrated through a simulated platform and a real fluid catalytic cracking application.
{"title":"Causal-geometry joint dictionary embedding learning for distributed monitoring and root cause analysis","authors":"Xue Xu , Chaomin Luo , Yuanjian Fu","doi":"10.1016/j.jprocont.2025.103566","DOIUrl":"10.1016/j.jprocont.2025.103566","url":null,"abstract":"<div><div>Interactions across process variables are complicated in large-scale industrial processes characterized with multiple operating units, posing significant challenges for fault detection and root cause analysis. In this work, a distributed modeling approach termed causal-geometry joint dictionary embedding learning (CGDE) is proposed to monitor large-scale industrial processes and identify the root cause. An information decomposition based block division algorithm is proposed to divide the entire process into blocks that account for unique, redundant, and synergistic information among variables. Meanwhile, a geometry similarity matrix derived by the minimum spanning tree is constructed to exploit the underlying structure of data. Furthermore, a causal consistency matrix is developed to characterize the causality among variables such that the intrinsic and stable information of industrial processes can be effectively captured. The CGDE approach provides an in-depth and faithful process analysis with consideration of causalities and geometry similarity of data, enhancing the distributed monitoring and root cause analysis performance. The effectiveness of CGDE is illustrated through a simulated platform and a real fluid catalytic cracking application.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"155 ","pages":"Article 103566"},"PeriodicalIF":3.9,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145268431","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号