{"title":"Proper orthogonal decomposition based simultaneous approach for solving PDE-constrained optimal control problems","authors":"Jie Zhu, Weifeng Chen","doi":"10.1016/j.jprocont.2025.103392","DOIUrl":"10.1016/j.jprocont.2025.103392","url":null,"abstract":"<div><div>Optimal control problems constrained by partial differential equations (PDEs) are widely encountered in engineering and scientific research and remain a challenging topic. Traditional methods for solving such problems typically discretize the temporal and spatial domains, often resulting in large-scale nonlinear programming problems that are computationally intensive to solve. This paper proposes a simultaneous approach based on proper orthogonal decomposition (POD). The method adopts a rolling strategy for simulating the PDEs and develops a reduced-order model using POD. To minimize the discrepancy between the reduced-order model and the full-order model, a heuristic strategy utilizing posterior error estimation is designed to enhance the model's accuracy. Numerical results indicate that the POD-based simultaneous approach not only substantially reduces the computational burden but also yields accurate solutions for PDE-constrained optimal control problems.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"148 ","pages":"Article 103392"},"PeriodicalIF":3.3,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143510748","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}
{"title":"Adaptive fixed-time terminal sliding mode control of a Peltier cell fused with a fuzzy fixed-time perturbation estimator","authors":"Sadra Rafatnia","doi":"10.1016/j.jprocont.2025.103391","DOIUrl":"10.1016/j.jprocont.2025.103391","url":null,"abstract":"<div><div>This study focuses on constructing an enhanced dynamic model for the Peltier cell to develop a model-based temperature controller. To simplify the control system design, a reduced-order model of the system is developed. Perturbations in the reduced-order model with nominal parameters are compensated using a novel fixed-time observer, aligning it with the actual system. The proposed scheme utilizes measurements from thermometers on both the cold and hot sides of the cell to estimate the system states and perturbations. The parameters of the proposed observer are tuned automatically using a fuzzy inference system to provide an accurate state estimation and attenuate the effects of noise in measurements. Mathematical analyses demonstrate the fixed-time convergence of the estimation method. Accordingly, a novel adaptive fixed-time terminal sliding mode controller is designed based on the enhanced model to maintain the desired temperature on the cold side. The proposed controller adapts to the actual system and is reliable and cost-effective due to the use of the reduced-order model. Additionally, mathematical analyses show the fixed-time convergence of the tracking error to the sliding surface and guarantee convergence to the origin within a fixed time. Experimental tests conducted on a constructed Peltier platform demonstrate the improved efficiency of the proposed control method. Comparative results with prevalent controllers highlight the superior accuracy of the suggested controller in tracking the desired temperature despite the presence of perturbations.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"148 ","pages":"Article 103391"},"PeriodicalIF":3.3,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143510108","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}
{"title":"Concentrate grade prediction of industrial zinc flotation process based on Cross-Temporal Feature Fusion Transformer","authors":"Yunrui Xie, Jie Wang, Lin Xiao","doi":"10.1016/j.jprocont.2025.103390","DOIUrl":"10.1016/j.jprocont.2025.103390","url":null,"abstract":"<div><div>Flotation industrial process data usually have temporal characteristics and feature nonlinearities. Aiming at the problem that the existing Transformer-based prediction model only considers the temporal information of time series data and ignores the importance of different feature variables, a Cross-Temporal Feature Fusion Transformer (CTFF-Transformer) is proposed for the prediction of concentrate grade of industrial zinc flotation process. The feature multivariate correlation and temporal dependence of the industrial data are captured by the feature attention module and the temporal attention module, respectively, and post-fusion is performed to enhance the model prediction performance. Due to the unsynchronized sampling time of froth video data and concentrate grade data in the flotation process, a fusion feature vector extraction strategy based on the froth video temporal segmentation is proposed, which improves the characterization ability of the data by constructing multi-segment froth video feature vectors and fusing the related grades. The proposed method is validated by using zinc rougher flotation froth video data, and comparative experiments show the merits in predicting the concentrate grade.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"148 ","pages":"Article 103390"},"PeriodicalIF":3.3,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438140","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}
{"title":"Two-stage stacked autoencoder monitoring model based on deep slow feature representation for dynamic processes","authors":"Qing Li, Jiaqi Wan, Xu Yang, Jian Huang, Jiarui Cui, Qun Yan","doi":"10.1016/j.jprocont.2025.103389","DOIUrl":"10.1016/j.jprocont.2025.103389","url":null,"abstract":"<div><div>The slow feature analysis (SFA) method constitutes a robust technique for dynamic process monitoring, capable of extracting slow-varying features to reveal process dynamics. A significant challenge in SFA-based monitoring involves nonlinear relationships within process data. Therefore, this paper introduces a slow feature constraint two-stage stacked autoencoder algorithm for dynamic process analysis. In the first stage, AE units aim to produce decorrelated and normalized signals through nonlinear expansion, with loss term focusing on the related properties. In the second stage, AE units serve to explore deep slow feature representations under constraints on variations of features. By fusing principles of SFA with the representational depth of SAE, the algorithm not only captures nonlinear relationships but also preserves crucial temporal dependencies within data, thereby providing more accurate insights for process monitoring. The proposed algorithm is validated in the vinyl acetate monomer process.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"147 ","pages":"Article 103389"},"PeriodicalIF":3.3,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143403693","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}
Albertus V. Richter , Johan D. le Roux , Ian K. Craig
{"title":"Bayesian optimization for automatic tuning of a MIMO controller of a flotation bank","authors":"Albertus V. Richter , Johan D. le Roux , Ian K. Craig","doi":"10.1016/j.jprocont.2025.103388","DOIUrl":"10.1016/j.jprocont.2025.103388","url":null,"abstract":"<div><div>A flotation bank consisting of 6 cells in series where each level is controlled by a Proportional–Integral (PI) controller is tuned using Bayesian Optimization (BO) in simulation. A Multi-Input–Multi-Output (MIMO) inventory controller is tuned to optimize the level response of the entire bank. The objective function defining optimality is a trade-off between disturbance rejection and reference tracking in the form of a weighted average of the integral squared error and the integral time absolute error of the level reference tracking error for each cell. The MIMO inventory controller used is a lower diagonal matrix where each element has a PI controller structure. The controller settings selected by the BO are constrained, assuming that the plant is linear, such that only controllers which produce stable closed-loop responses will result. Structured singular value analysis is performed, before tuning, to confirm that this is the case. The BO automated tuner is able to tune multiple PI elements to provide an overall improvement of the flotation bank level control. The method is applied successfully with and without measurement noise on a simulated plant. For use in industry, since the process is simple to model, the controller can be tuned off-line in simulation. To compensate for model-plant mismatch, once the controller is implemented the BO automatic tuner can be allowed a limited number of steps to obtain the optimal controller parameters. This provides a valuable time-saving tool for a process control engineer to tune an industrial plant quickly and efficiently.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"147 ","pages":"Article 103388"},"PeriodicalIF":3.3,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143388269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shuyao Tan , Alain Rapaport , Peter A. Vanrolleghem , Denis Dochain , Elodie Passeport , Joshua A. Taylor
{"title":"Predictive control of flow rates and concentrations in sewage transport and treatment systems","authors":"Shuyao Tan , Alain Rapaport , Peter A. Vanrolleghem , Denis Dochain , Elodie Passeport , Joshua A. Taylor","doi":"10.1016/j.jprocont.2025.103386","DOIUrl":"10.1016/j.jprocont.2025.103386","url":null,"abstract":"<div><div>We design a predictive flow rate and concentration controller for wastewater transport and treatment networks. It manages flow rates to avoid overflows during times of high flow, and maximizes treatment efficiency when the system is within capacity limits. The underlying optimization is nonlinear due to the microbial growth kinetics and bilinear mass flows. Using a second-order cone relaxation of the microbial growth constraints and the alternating direction method of multipliers, we break down the problem into second-order cone and quadratic programs. This allows us to solve the problem at large scales in real-time. In a case study based on the wastewater transport and treatment system in the City of Paris, our controller outperforms the conventional flowrate-based controller by removing 13.7% more pollutant mass while treating the same amount of wastewater.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"147 ","pages":"Article 103386"},"PeriodicalIF":3.3,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143372288","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}
Qingyuan Liu , Tao Liu , Dexian Huang , Chao Shang
{"title":"Subspace identification of dynamic processes with consideration of time delays: A Bayesian optimization scheme","authors":"Qingyuan Liu , Tao Liu , Dexian Huang , Chao Shang","doi":"10.1016/j.jprocont.2025.103387","DOIUrl":"10.1016/j.jprocont.2025.103387","url":null,"abstract":"<div><div>For decades, subspace identification method (SIM) has been widely adopted for modeling multiple-input multiple-output processes. However, conventional SIMs yield unsatisfactory performance in modeling processes with evident dead time characteristics. To tackle this challenge, we develop in this work an efficient SIM scheme with consideration of time delays along with a tailored Bayesian optimization (BO) solution algorithm, aiming at simultaneously identifying the state-space matrices, time delays and model order of a time-delayed state-space model from input–output data. The identification problem is formulated as a black-box optimization problem over time delays and model order. In the proposed tailored BO algorithm, a decomposition strategy is developed to address the existence of multiple identical solutions. Besides, a prior-weighted acquisition function is proposed to improve the algorithm efficiency. Numerical examples and an experiment on industrial dataset showcase that the proposed method achieves significant improvement in identification accuracy over conventional SIMs owing to the explicit consideration of time delays. In addition, the proposed BO algorithm outperforms the naive random search and the naive BO algorithm in terms of computational efficiency.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"147 ","pages":"Article 103387"},"PeriodicalIF":3.3,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143349123","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}
Zhenhua Yu , Guan Wang , Xuefeng Yan , Qingchao Jiang , Zhixing Cao
{"title":"Mutual information and attention-based variable selection for soft sensing of industrial processes","authors":"Zhenhua Yu , Guan Wang , Xuefeng Yan , Qingchao Jiang , Zhixing Cao","doi":"10.1016/j.jprocont.2025.103373","DOIUrl":"10.1016/j.jprocont.2025.103373","url":null,"abstract":"<div><div>This study introduces a novel method called mutual information (MI) and attention-based variable selection (MAVS) to address the challenges of irrelevant and redundant variables in industrial process soft sensing while providing interpretability in variable contribution analysis. First, irrelevant variables are eliminated based on low MI values with the quality variable. Second, attention scores are used to remove redundant variables, and the false discovery rate is used to determine the number of beneficial variables. Finally, this work provides an interpretable and accurate contribution of the selected variables by using kernelSHAP, a kernel-based Shapley analysis. Unlike traditional approaches, MAVS integrates MI with attention mechanisms to optimize variable selection dynamically and adaptively. MAVS obtains stronger robustness and higher accuracy than the existing state-of-the-art models through optimal variable selection. The former also obtains better superior generalization than the latter through adaptive adjustment of attention weights. The superiority of MAVS is demonstrated using two real-world datasets and one simulated dataset.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"146 ","pages":"Article 103373"},"PeriodicalIF":3.3,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174882","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}
Xinghan Du , Qi Liu , Wu Cai , Na Geng , Qibing Jin
{"title":"An ETF-based disturbance observer-based control for multivariable processes with time delays","authors":"Xinghan Du , Qi Liu , Wu Cai , Na Geng , Qibing Jin","doi":"10.1016/j.jprocont.2024.103368","DOIUrl":"10.1016/j.jprocont.2024.103368","url":null,"abstract":"<div><div>As an effective technique for rejecting unmeasurable disturbances, the disturbance observer-based (DOB) control has two key issues to be addressed when applied to multivariable processes with time delays, i.e., the design of the nominal inverse model and the analytical synthesis of the <em>Q</em>(<em>s</em>) filter. Focusing on the above issues, this paper presents a novel equivalent transfer function-based (ETF-based) DOB control for multivariable processes with time delays. First, considering the potential relation between the ETF matrix and the inverse model, the design of the inverse model can be simplified by calculating the ETF matrix. The method for determining the parameters of the ETF matrix is modified to improve the rationality of the inverse model. Then, a realizable inverse model is achieved by compensating the modified ETF matrix. Unlike the multivariable DOB (MDOB) control using simple diagonal inverse models, the proposed strategy presents a full-element inverse model with full consideration of the process model information. Since the calculation of the modified ETF matrix only involves several simple matrix operations, the design of the inverse model is streamlined. Based on the modified inverse model, the <em>Q</em>(<em>s</em>) filter is synthesized analytically by minimizing the performance index, i.e., the 2-norm of disturbance responses. The adjustable parameters of the <em>Q</em>(<em>s</em>) filter are determined with due consideration of control performance and robustness. Simulation results demonstrate that compared to other MDOB control strategies, the proposed strategy provides the best results in terms of the integral absolute error (IAE) values of the disturbance responses, the total variations (TV) of the inputs, and the robustness indices.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"146 ","pages":"Article 103368"},"PeriodicalIF":3.3,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174878","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}
{"title":"Kernel entropy quality correlation analysis for nonlinear industrial process fault detection","authors":"Hao Ma , Yan Wang , Xiang Liu , Jie Yuan","doi":"10.1016/j.jprocont.2024.103369","DOIUrl":"10.1016/j.jprocont.2024.103369","url":null,"abstract":"<div><div>Quality-oriented fault detection plays a critical role in industrial processes, significantly boosting modern industrial efficiency since its inception. While kernel canonical correlation analysis is commonly used for nonlinear quality-oriented fault detection, it has certain limitations. To address these issues, this paper proposes a kernel entropy quality correlation analysis. The proposed approach initiates with nonlinear mapping to project the process variable space into a higher-dimensional space, effectively capturing nonlinear features within the data. By extracting the primary features contributing to the Renyi entropy of the dataset, a kernel entropy latent variable space is constructed, facilitating both nonlinear mapping and dimensionality reduction. Subsequently, canonical correlation analysis is employed to elucidate the relationship between the kernel entropy latent variable and the quality indicators. To rationally decompose the kernel entropy latent variable space according to the quality indicators, two decomposition strategies are proposed: the singular value decomposition-based method and the generalized singular value decomposition-based method. Moreover, this paper provides a theoretical justification for the validity of these two decomposition strategies. Finally, the effectiveness of the proposed method is validated through two numerical examples and two industrial case studies.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"146 ","pages":"Article 103369"},"PeriodicalIF":3.3,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174881","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}