Journal of Process Control最新文献_第2页

Enabling robust mixed-integer nonlinear model predictive control via self-supervised learning and combinatorial integral approximation 利用自监督学习和组合积分逼近实现鲁棒混合整数非线性模型预测控制

IF 3.9 2区计算机科学 Q2 AUTOMATION & CONTROL SYSTEMS

Journal of Process Control

Pub Date : 2026-03-01 Epub Date: 2026-01-27 DOI: 10.1016/j.jprocont.2026.103636

Joshua Adamek, Lukas Lüken, Sergio Lucia

We present a novel approach that enables the solution of nonlinear model predictive control with integer decisions in real time even when when the model is subject to many uncertainties. Our approach tightly integrates three different ideas.

First, we use combinatorial integral approximation as a powerful heuristic to approximate the mixed-integer nonlinear problems with two nonlinear problems. Next, we formulate a scenario tree formulation to deal with uncertain parameters. To tackle the large number of uncertainties, we propose a scenario decomposition method to solve each scenario problem in parallel. We integrate the combinatorial approximation within this scenario decomposition method to provide a method for uncertain parameters within mixed-integer model predictive control. This method leads to many smaller optimization problems that can be solved in parallel. As the third idea, we propose the use of learned iterative solvers, as opposed to traditional numerical solvers, to solve each subproblem. This methodology can be massively parallelized by evaluating neural networks on powerful GPUs. As a result, the proposed approach leads to an order of magnitude faster solutions when compared to a solution of the entire robust problem with a traditional numerical solver, as well as to improved accuracy in comparison to a supervised learning approach. This is illustrated in the simulation example of an uncertain nonlinear reactor with mixed-integer decisions.

本文提出了一种新颖的方法，使具有整数决策的非线性模型预测控制即使在模型具有许多不确定性的情况下也能实时求解。我们的方法紧密结合了三种不同的想法。首先，我们将组合积分近似作为一种强大的启发式方法，用两个非线性问题近似混合整数非线性问题。接下来，我们制定了一个场景树公式来处理不确定参数。为了解决大量的不确定性，我们提出了一种场景分解方法来并行解决每个场景问题。在此场景分解方法中引入组合逼近，为混合整数模型预测控制中的不确定参数提供了一种方法。这种方法导致许多较小的优化问题可以并行解决。作为第三个想法，我们建议使用学习迭代求解器来解决每个子问题，而不是传统的数值求解器。这种方法可以通过在强大的gpu上评估神经网络来大规模并行化。因此，与传统的数值求解器解决整个鲁棒问题相比，该方法的求解速度要快一个数量级，而且与监督学习方法相比，该方法的精度也有所提高。通过一个不确定非线性混合整数决策电抗器的仿真实例说明了这一点。

{"title":"Enabling robust mixed-integer nonlinear model predictive control via self-supervised learning and combinatorial integral approximation","authors":"Joshua Adamek, Lukas Lüken, Sergio Lucia","doi":"10.1016/j.jprocont.2026.103636","DOIUrl":"10.1016/j.jprocont.2026.103636","url":null,"abstract":"<div><div>We present a novel approach that enables the solution of nonlinear model predictive control with integer decisions in real time even when when the model is subject to many uncertainties. Our approach tightly integrates three different ideas.</div><div>First, we use combinatorial integral approximation as a powerful heuristic to approximate the mixed-integer nonlinear problems with two nonlinear problems. Next, we formulate a scenario tree formulation to deal with uncertain parameters. To tackle the large number of uncertainties, we propose a scenario decomposition method to solve each scenario problem in parallel. We integrate the combinatorial approximation within this scenario decomposition method to provide a method for uncertain parameters within mixed-integer model predictive control. This method leads to many smaller optimization problems that can be solved in parallel. As the third idea, we propose the use of learned iterative solvers, as opposed to traditional numerical solvers, to solve each subproblem. This methodology can be massively parallelized by evaluating neural networks on powerful GPUs. As a result, the proposed approach leads to an order of magnitude faster solutions when compared to a solution of the entire robust problem with a traditional numerical solver, as well as to improved accuracy in comparison to a supervised learning approach. This is illustrated in the simulation example of an uncertain nonlinear reactor with mixed-integer decisions.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"159 ","pages":"Article 103636"},"PeriodicalIF":3.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146045295","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}

引用次数: 0

A deep KM-GRU learning approach to time series prediction for non-linear dynamic industry process with outlier and time delay 具有离群值和时滞的非线性动态工业过程时间序列预测的深度KM-GRU学习方法

IF 3.9 2区计算机科学 Q2 AUTOMATION & CONTROL SYSTEMS

Journal of Process Control

Pub Date : 2026-03-01 Epub Date: 2026-02-07 DOI: 10.1016/j.jprocont.2026.103653

Kaixun He , Xiaolong Chen , Hongyu Guo , Maiying Zhong , Han Jiang , Xin Peng

In non-linear dynamic industrial processes, time delay often lead to numerous misalignment time labels and outliers in the raw data, thereby considerably compromising the accuracy and robustness of time series prediction models. To deal with these issues, a novel framework based on deep learning is proposed, which adopts gated recurrent unit (GRU) to construct a long-term time-series prediction model. In addition, kernel density estimation (KDE) and the maximum information coefficient (MIC) are employed for outlier detection and time delay calibration, respectively. Then, an improved variable selection mechanism is designed to identify important features. Furthermore, a differential evolution (DE) based algorithm is designed to obtain the optimal parameters of GRU model. Finally, to show the effectiveness of the proposed approach, two real-world industrial dataset exhibiting pronounced temporal nonlinear dynamics and a simulation dataset are considered. It is shown from the experimental results that the proposed approach can achieve accurate prediction performance.

在非线性动态工业过程中，时间延迟通常会导致原始数据中出现大量的时间标签和异常值，从而大大影响时间序列预测模型的准确性和鲁棒性。为了解决这些问题，提出了一种新的基于深度学习的框架，该框架采用门控循环单元（GRU）构建长期时间序列预测模型。此外，采用核密度估计（KDE）和最大信息系数（MIC）分别进行离群点检测和时延校正。然后，设计了一种改进的变量选择机制来识别重要特征。在此基础上，设计了一种基于差分进化（DE）的GRU模型最优参数求解算法。最后，为了证明所提出方法的有效性，我们考虑了两个具有明显时间非线性动态的真实工业数据集和一个模拟数据集。实验结果表明，该方法能够达到准确的预测效果。

{"title":"A deep KM-GRU learning approach to time series prediction for non-linear dynamic industry process with outlier and time delay","authors":"Kaixun He , Xiaolong Chen , Hongyu Guo , Maiying Zhong , Han Jiang , Xin Peng","doi":"10.1016/j.jprocont.2026.103653","DOIUrl":"10.1016/j.jprocont.2026.103653","url":null,"abstract":"<div><div>In non-linear dynamic industrial processes, time delay often lead to numerous misalignment time labels and outliers in the raw data, thereby considerably compromising the accuracy and robustness of time series prediction models. To deal with these issues, a novel framework based on deep learning is proposed, which adopts gated recurrent unit (GRU) to construct a long-term time-series prediction model. In addition, kernel density estimation (KDE) and the maximum information coefficient (MIC) are employed for outlier detection and time delay calibration, respectively. Then, an improved variable selection mechanism is designed to identify important features. Furthermore, a differential evolution (DE) based algorithm is designed to obtain the optimal parameters of GRU model. Finally, to show the effectiveness of the proposed approach, two real-world industrial dataset exhibiting pronounced temporal nonlinear dynamics and a simulation dataset are considered. It is shown from the experimental results that the proposed approach can achieve accurate prediction performance.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"159 ","pages":"Article 103653"},"PeriodicalIF":3.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146190701","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}

引用次数: 0

Sparse optimization assisted adaptive and smart hybrid data-driven modeling for process systems 稀疏优化辅助过程系统的自适应和智能混合数据驱动建模

IF 3.9 2区计算机科学 Q2 AUTOMATION & CONTROL SYSTEMS

Journal of Process Control

Pub Date : 2026-03-01 Epub Date: 2026-01-30 DOI: 10.1016/j.jprocont.2026.103642

Shubhasmita Behera, Santhosh Kumar Varanasi

Integration of data-driven and physics-based modeling approaches has become essential for achieving intelligent monitoring and control in modern process industries. This paper presents an adaptive hybrid data-driven identification framework for process systems that operate under varying conditions. The proposed method uses B-spline representations along with model-based regularization to ensure consistency. A sparsity constraint on model parameters improves interpretability and simplicity. To handle process variations, we developed an error-triggered adaptive mechanism that automatically updates the model structure and parameters when significant deviations occur. The resulting framework effectively captures dynamic behavior across multiple operating regimes. Validation on a quadruple-tank system and a non-isothermal continuous stirred-tank reactor shows improved prediction accuracy and greater robustness compared to standard methods. These results highlight the potential of the proposed framework as a tool for adaptive process modeling and predictive control in the context of Industry 4.0.

在现代过程工业中，数据驱动和基于物理的建模方法的集成对于实现智能监测和控制至关重要。本文提出了一种自适应混合数据驱动的识别框架，用于在不同条件下运行的过程系统。该方法使用b样条表示和基于模型的正则化来确保一致性。模型参数的稀疏性约束提高了可解释性和简单性。为了处理过程变化，我们开发了一种错误触发的自适应机制，它在发生重大偏差时自动更新模型结构和参数。生成的框架有效地捕获跨多个操作机制的动态行为。在四槽系统和非等温连续搅拌槽反应器上的验证表明，与标准方法相比，预测精度更高，鲁棒性更强。这些结果突出了所提出的框架作为工业4.0背景下自适应过程建模和预测控制工具的潜力。

{"title":"Sparse optimization assisted adaptive and smart hybrid data-driven modeling for process systems","authors":"Shubhasmita Behera, Santhosh Kumar Varanasi","doi":"10.1016/j.jprocont.2026.103642","DOIUrl":"10.1016/j.jprocont.2026.103642","url":null,"abstract":"<div><div>Integration of data-driven and physics-based modeling approaches has become essential for achieving intelligent monitoring and control in modern process industries. This paper presents an adaptive hybrid data-driven identification framework for process systems that operate under varying conditions. The proposed method uses B-spline representations along with model-based regularization to ensure consistency. A sparsity constraint on model parameters improves interpretability and simplicity. To handle process variations, we developed an error-triggered adaptive mechanism that automatically updates the model structure and parameters when significant deviations occur. The resulting framework effectively captures dynamic behavior across multiple operating regimes. Validation on a quadruple-tank system and a non-isothermal continuous stirred-tank reactor shows improved prediction accuracy and greater robustness compared to standard methods. These results highlight the potential of the proposed framework as a tool for adaptive process modeling and predictive control in the context of Industry 4.0.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"159 ","pages":"Article 103642"},"PeriodicalIF":3.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146090448","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}

引用次数: 0

A predictive modular approach to constraint satisfaction under uncertainty — with application to glycosylation in continuous monoclonal antibody biosimilar production 不确定条件下约束满足的预测模块化方法-应用于连续单克隆抗体生物仿制药生产中的糖基化

IF 3.9 2区计算机科学 Q2 AUTOMATION & CONTROL SYSTEMS

Journal of Process Control

Pub Date : 2026-02-01 Epub Date: 2026-01-18 DOI: 10.1016/j.jprocont.2026.103632

Yu Wang , Xiao Chen , Hubert Schwarz , Véronique Chotteau , Elling W. Jacobsen

The paper proposes a modular-based approach to constraint handling in process optimization and control. This is partly motivated by the recent interest in learning-based methods, e.g., within bioproduction, for which constraint handling under uncertainty is a challenge. The proposed constraint handler, called predictive filter, is combined with an adaptive constraint margin and a constraint violation cost monitor to minimize the cost of violating soft constraints due to model uncertainty and disturbances. The module can be combined with any controller and is based on minimally modifying the controller output, in a least squares sense, such that constraints are satisfied within the considered horizon. The proposed method is computationally efficient and suitable for real-time applications. The effectiveness of the method is illustrated through a realistic case study of glycosylation constraint satisfaction in continuous monoclonal antibody biosimilar production using Chinese hamster ovary cells, employing a metabolic network model consisting of 23 extracellular metabolites and 126 reactions. In the case study, the average constraint-violation cost is reduced by more than 60% compared to the case without the proposed constraint-handling method.

提出了一种基于模块化的过程优化控制约束处理方法。这部分是由于最近对基于学习的方法的兴趣，例如，在生物生产中，在不确定性下的约束处理是一个挑战。所提出的约束处理程序称为预测滤波器，它与自适应约束裕度和约束违反代价监视器相结合，以最小化由于模型不确定性和干扰而违反软约束的代价。该模块可以与任何控制器组合，并且基于最小二乘意义上的最小修改控制器输出，从而在考虑的范围内满足约束。该方法计算效率高，适合实时应用。采用23种细胞外代谢物和126种反应组成的代谢网络模型，通过对中国仓鼠卵巢细胞连续生产单克隆抗体生物仿制药中糖基化约束满足的实际案例研究，证明了该方法的有效性。在案例研究中，与没有提出约束处理方法的情况相比，平均违反约束成本降低了60%以上。

{"title":"A predictive modular approach to constraint satisfaction under uncertainty — with application to glycosylation in continuous monoclonal antibody biosimilar production","authors":"Yu Wang , Xiao Chen , Hubert Schwarz , Véronique Chotteau , Elling W. Jacobsen","doi":"10.1016/j.jprocont.2026.103632","DOIUrl":"10.1016/j.jprocont.2026.103632","url":null,"abstract":"<div><div>The paper proposes a modular-based approach to constraint handling in process optimization and control. This is partly motivated by the recent interest in learning-based methods, e.g., within bioproduction, for which constraint handling under uncertainty is a challenge. The proposed constraint handler, called predictive filter, is combined with an adaptive constraint margin and a constraint violation cost monitor to minimize the cost of violating soft constraints due to model uncertainty and disturbances. The module can be combined with any controller and is based on minimally modifying the controller output, in a least squares sense, such that constraints are satisfied within the considered horizon. The proposed method is computationally efficient and suitable for real-time applications. The effectiveness of the method is illustrated through a realistic case study of glycosylation constraint satisfaction in continuous monoclonal antibody biosimilar production using Chinese hamster ovary cells, employing a metabolic network model consisting of 23 extracellular metabolites and 126 reactions. In the case study, the average constraint-violation cost is reduced by more than 60% compared to the case without the proposed constraint-handling method.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"158 ","pages":"Article 103632"},"PeriodicalIF":3.9,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146038430","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}

引用次数: 0

A microbial fuel cell with an optimal controller based on improved reptile search algorithm 一种基于改进爬行动物搜索算法的最优控制器微生物燃料电池

IF 3.9 2区计算机科学 Q2 AUTOMATION & CONTROL SYSTEMS

Journal of Process Control

Pub Date : 2026-02-01 Epub Date: 2026-01-14 DOI: 10.1016/j.jprocont.2026.103629

Chenlong Wang, Fengying Ma

Microbial fuel cells (MFCs) are novel energy technologies that convert the chemical energy of organic matter in wastewater into electrical energy. However, MFC systems generally require external control to achieve stable voltage output. In this paper, an optimal controller for MFC systems is designed. By adopting the

θ

–

D

technique, the intractable Hamilton–Jacobi–Bellman (HJB) equation is transformed into a set of algebraic equations, which enables the solution of the optimal control problem with large initial states. To address parameter uncertainty in the optimal controller, an optimization algorithm is employed to tune its parameters. Furthermore, to overcome the limitations of existing optimization algorithms, including slow convergence speed, low solution accuracy, and premature convergence, an improved reptile search algorithm is proposed by integrating chaotic mechanisms, an elite-guided differential perturbation strategy, and an adaptive crossover probability control mechanism. Simulation results demonstrate that the improved algorithm achieves faster convergence and higher accuracy. Moreover, the designed optimal controller exhibits smaller overshoot and steady-state error in the MFC.

微生物燃料电池（mfc）是一种将废水中有机物的化学能转化为电能的新型能源技术。然而，MFC系统通常需要外部控制来实现稳定的电压输出。本文设计了MFC系统的最优控制器。采用θ-D技术，将棘手的Hamilton-Jacobi-Bellman （HJB）方程转化为一组代数方程，使具有大初始状态的最优控制问题得以求解。为了解决最优控制器中参数的不确定性，采用了一种优化算法对其参数进行整定。此外，针对现有优化算法收敛速度慢、求解精度低、过早收敛等局限性，提出了一种综合混沌机制、精英引导微分摄动策略和自适应交叉概率控制机制的改进爬行动物搜索算法。仿真结果表明，改进后的算法具有更快的收敛速度和更高的精度。此外，所设计的最优控制器在MFC中具有较小的超调量和稳态误差。

{"title":"A microbial fuel cell with an optimal controller based on improved reptile search algorithm","authors":"Chenlong Wang, Fengying Ma","doi":"10.1016/j.jprocont.2026.103629","DOIUrl":"10.1016/j.jprocont.2026.103629","url":null,"abstract":"<div><div>Microbial fuel cells (MFCs) are novel energy technologies that convert the chemical energy of organic matter in wastewater into electrical energy. However, MFC systems generally require external control to achieve stable voltage output. In this paper, an optimal controller for MFC systems is designed. By adopting the <span><math><mi>θ</mi></math></span>–<span><math><mi>D</mi></math></span> technique, the intractable Hamilton–Jacobi–Bellman (HJB) equation is transformed into a set of algebraic equations, which enables the solution of the optimal control problem with large initial states. To address parameter uncertainty in the optimal controller, an optimization algorithm is employed to tune its parameters. Furthermore, to overcome the limitations of existing optimization algorithms, including slow convergence speed, low solution accuracy, and premature convergence, an improved reptile search algorithm is proposed by integrating chaotic mechanisms, an elite-guided differential perturbation strategy, and an adaptive crossover probability control mechanism. Simulation results demonstrate that the improved algorithm achieves faster convergence and higher accuracy. Moreover, the designed optimal controller exhibits smaller overshoot and steady-state error in the MFC.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"158 ","pages":"Article 103629"},"PeriodicalIF":3.9,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145979671","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}

引用次数: 0

Fuzzy advanced control: Boosting efficiency and economic benefits in offshore gas compression systems 模糊先进控制：提高海上天然气压缩系统的效率和经济效益

IF 3.9 2区计算机科学 Q2 AUTOMATION & CONTROL SYSTEMS

Journal of Process Control

Pub Date : 2026-02-01 Epub Date: 2026-01-19 DOI: 10.1016/j.jprocont.2026.103635

Thamires A.L. Guedes , Sergio A.C. Giraldo , Marcelo L. de Lima , Mario C.M.M. Campos , Daniel M. Lima , Leonardo D. Ribeiro , Argimiro R. Secchi

In this work, an advanced control system based on fuzzy logic is analyzed and implemented for a gas compression system on an offshore platform. This solution was applied after identifying an operational problem causing substantial economic losses due to unscheduled stops from high-temperature events at the compressor discharge. A detailed analysis of process variables that could be employed within the controller to mitigate this phenomenon was conducted, identifying compressor discharge temperatures as controlled variables and the machine’s discharge pressure setpoint as the primary manipulated variable. Through dynamic simulations and using a digital twin, it was possible to validate the behavior and effect of the variables, along with implementing the control system. Operational tests on the platform were conducted to verify the proposal and confirm the simulation results. The open-loop implementation of the control algorithm, i.e. the computed control action was not sent to the process, allowed the tracking and observation of the control system’s reaction to critical incidents, which validated its expected behavior. The activation of the closed-loop control successfully prevented machine stops, avoiding economic losses in production. This preventive approach avoided operational stops and highlighted the potential of advanced control systems to significantly improve safety, efficiency, and reliability in complex industrial environments.

本文分析并实现了一种基于模糊逻辑的海洋平台气体压缩系统的先进控制系统。该解决方案是在确定了一个运行问题后应用的，该问题由于压缩机排气高温事件导致的计划外停机而造成了巨大的经济损失。为了缓解这一现象，研究人员对控制器中的过程变量进行了详细分析，将压缩机排放温度确定为受控变量，将机器的排放压力设定点确定为主要操纵变量。通过动态模拟和使用数字孪生，可以验证变量的行为和效果，以及实现控制系统。在平台上进行了运行测试，验证了该方案并验证了仿真结果。控制算法的开环实现，即计算控制动作不发送到过程中，允许跟踪和观察控制系统对关键事件的反应，从而验证其预期行为。闭环控制的启动成功地防止了机器停机，避免了生产中的经济损失。这种预防性方法避免了作业停止，并突出了先进控制系统在复杂工业环境中显著提高安全性、效率和可靠性的潜力。

{"title":"Fuzzy advanced control: Boosting efficiency and economic benefits in offshore gas compression systems","authors":"Thamires A.L. Guedes , Sergio A.C. Giraldo , Marcelo L. de Lima , Mario C.M.M. Campos , Daniel M. Lima , Leonardo D. Ribeiro , Argimiro R. Secchi","doi":"10.1016/j.jprocont.2026.103635","DOIUrl":"10.1016/j.jprocont.2026.103635","url":null,"abstract":"<div><div>In this work, an advanced control system based on fuzzy logic is analyzed and implemented for a gas compression system on an offshore platform. This solution was applied after identifying an operational problem causing substantial economic losses due to unscheduled stops from high-temperature events at the compressor discharge. A detailed analysis of process variables that could be employed within the controller to mitigate this phenomenon was conducted, identifying compressor discharge temperatures as controlled variables and the machine’s discharge pressure setpoint as the primary manipulated variable. Through dynamic simulations and using a digital twin, it was possible to validate the behavior and effect of the variables, along with implementing the control system. Operational tests on the platform were conducted to verify the proposal and confirm the simulation results. The open-loop implementation of the control algorithm, i.e. the computed control action was not sent to the process, allowed the tracking and observation of the control system’s reaction to critical incidents, which validated its expected behavior. The activation of the closed-loop control successfully prevented machine stops, avoiding economic losses in production. This preventive approach avoided operational stops and highlighted the potential of advanced control systems to significantly improve safety, efficiency, and reliability in complex industrial environments.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"158 ","pages":"Article 103635"},"PeriodicalIF":3.9,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146038431","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}

引用次数: 0

A tutorial overview of model predictive control for continuous crystallization: Current possibilities and future perspectives 连续结晶模型预测控制的教程概述：当前的可能性和未来的观点

IF 3.9 2区计算机科学 Q2 AUTOMATION & CONTROL SYSTEMS

Journal of Process Control

Pub Date : 2026-02-01 Epub Date: 2026-01-15 DOI: 10.1016/j.jprocont.2026.103630

Collin R. Johnson , Kerstin Wohlgemuth , Sergio Lucia

Continuous crystallization processes require advanced control strategies to ensure consistent product quality, yet deploying optimization-based controllers such as model predictive control remains challenging. Combining spatially distributed crystallizer models with detailed particle size distributions leads to computationally demanding problems that are difficult to solve in real-time. This tutorial provides a comprehensive overview of how to address this challenge. Topics include numerical methods for solving population balance equations, modeling of crystallizers, and data-driven surrogate modeling. We show how these elements combine within a model predictive control framework to enable real-time control of particle size distributions. Two case studies illustrate the complete workflow: a well-mixed crystallizer that allows comparison with established methods, and a spatially distributed plug-flow crystallizer that demonstrates application to more complex systems. Readers gain a practical roadmap for implementing model predictive control in continuous crystallization, supported by open-source code and interactive examples. The tutorial concludes by outlining open challenges and emerging opportunities in the field.

连续结晶过程需要先进的控制策略来确保一致的产品质量，但部署基于优化的控制器（如模型预测控制）仍然具有挑战性。将空间分布结晶器模型与详细的粒度分布相结合，导致难以实时解决的计算要求很高的问题。本教程提供了如何应对这一挑战的全面概述。主题包括解决人口平衡方程的数值方法，结晶器的建模和数据驱动的代理建模。我们展示了这些元素如何在模型预测控制框架内组合，以实现粒度分布的实时控制。两个案例研究说明了完整的工作流程：一个充分混合的结晶器，允许与已建立的方法进行比较，以及一个空间分布的塞流结晶器，演示了在更复杂系统中的应用。读者获得了在连续结晶中实现模型预测控制的实用路线图，由开源代码和交互式示例支持。本教程最后概述了该领域的公开挑战和新出现的机会。

{"title":"A tutorial overview of model predictive control for continuous crystallization: Current possibilities and future perspectives","authors":"Collin R. Johnson , Kerstin Wohlgemuth , Sergio Lucia","doi":"10.1016/j.jprocont.2026.103630","DOIUrl":"10.1016/j.jprocont.2026.103630","url":null,"abstract":"<div><div>Continuous crystallization processes require advanced control strategies to ensure consistent product quality, yet deploying optimization-based controllers such as model predictive control remains challenging. Combining spatially distributed crystallizer models with detailed particle size distributions leads to computationally demanding problems that are difficult to solve in real-time. This tutorial provides a comprehensive overview of how to address this challenge. Topics include numerical methods for solving population balance equations, modeling of crystallizers, and data-driven surrogate modeling. We show how these elements combine within a model predictive control framework to enable real-time control of particle size distributions. Two case studies illustrate the complete workflow: a well-mixed crystallizer that allows comparison with established methods, and a spatially distributed plug-flow crystallizer that demonstrates application to more complex systems. Readers gain a practical roadmap for implementing model predictive control in continuous crystallization, supported by open-source code and interactive examples. The tutorial concludes by outlining open challenges and emerging opportunities in the field.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"158 ","pages":"Article 103630"},"PeriodicalIF":3.9,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145979670","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}

引用次数: 0

A physics-guided hybrid model for calendering width prediction in rubber tire manufacturing 橡胶轮胎压延宽度预测的物理导向混合模型

IF 3.9 2区计算机科学 Q2 AUTOMATION & CONTROL SYSTEMS

Journal of Process Control

Pub Date : 2026-02-01 Epub Date: 2026-01-04 DOI: 10.1016/j.jprocont.2025.103612

Shaoyuan Li, Haolei Yin, Xiaohong Yin, Wenjian Cai

The width in rubber extrusion-calendering is a crucial process parameter in the rubber production workflow, as it directly influences both the quality and performance of rubber products, as well as overall production efficiency. However, the rubber extrusion-calendering process involves strong coupling among multiple parameters, with operating condition variations and significant external disturbances, leading to complex dynamic characteristics such as nonlinearity and time delays, which severely impact the accuracy of width prediction. To address these challenges, a hybrid modeling approach that integrates physical mechanisms with data-driven methods has been proposed within the framework of Physics-Informed Neural Networks (PINN). Firstly, a data-driven prediction model for calendering width was developed using a combination of a Temporal Convolutional Network and a Bidirectional Long Short-Term Memory network (TCN-BiLSTM). Secondly, an analysis of the physical mechanism underlying the extrusion-calendering process was conducted based on the power-law constitutive relationship to provide essential physical constraints for the prediction model. Furthermore, a dynamically adaptive weighting strategy was proposed to effectively reconcile conflicts between physical constraints and data fitting in the PINN model. Validation experiments demonstrate that this hybrid modeling approach can sustain high prediction accuracy even when faced with limited training data, noise interference, and varying operating conditions.

橡胶挤出压延宽度是橡胶生产流程中一个至关重要的工艺参数，它直接影响到橡胶制品的质量、性能和整体生产效率。然而，橡胶挤出-压延过程是一个多参数强耦合的过程，操作条件变化大，外部干扰大，导致非线性和时滞等复杂动态特性，严重影响宽度预测的准确性。为了应对这些挑战，在物理信息神经网络（PINN）框架内提出了一种将物理机制与数据驱动方法相结合的混合建模方法。首先，将时序卷积网络与双向长短期记忆网络（TCN-BiLSTM）相结合，建立了一种数据驱动的压延宽度预测模型；其次，基于幂律本构关系分析了挤压压延过程的物理机制，为预测模型提供了必要的物理约束条件。在此基础上，提出了一种动态自适应加权策略，有效地解决了PINN模型中物理约束与数据拟合之间的冲突。验证实验表明，即使面对有限的训练数据、噪声干扰和变化的操作条件，这种混合建模方法也能保持较高的预测精度。

{"title":"A physics-guided hybrid model for calendering width prediction in rubber tire manufacturing","authors":"Shaoyuan Li, Haolei Yin, Xiaohong Yin, Wenjian Cai","doi":"10.1016/j.jprocont.2025.103612","DOIUrl":"10.1016/j.jprocont.2025.103612","url":null,"abstract":"<div><div>The width in rubber extrusion-calendering is a crucial process parameter in the rubber production workflow, as it directly influences both the quality and performance of rubber products, as well as overall production efficiency. However, the rubber extrusion-calendering process involves strong coupling among multiple parameters, with operating condition variations and significant external disturbances, leading to complex dynamic characteristics such as nonlinearity and time delays, which severely impact the accuracy of width prediction. To address these challenges, a hybrid modeling approach that integrates physical mechanisms with data-driven methods has been proposed within the framework of Physics-Informed Neural Networks (PINN). Firstly, a data-driven prediction model for calendering width was developed using a combination of a Temporal Convolutional Network and a Bidirectional Long Short-Term Memory network (TCN-BiLSTM). Secondly, an analysis of the physical mechanism underlying the extrusion-calendering process was conducted based on the power-law constitutive relationship to provide essential physical constraints for the prediction model. Furthermore, a dynamically adaptive weighting strategy was proposed to effectively reconcile conflicts between physical constraints and data fitting in the PINN model. Validation experiments demonstrate that this hybrid modeling approach can sustain high prediction accuracy even when faced with limited training data, noise interference, and varying operating conditions.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"158 ","pages":"Article 103612"},"PeriodicalIF":3.9,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928436","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}

引用次数: 0

Gain-scheduled tube-based MPC for quasi-LPV systems using vertex models 使用顶点模型的准lpv系统的增益调度管MPC

IF 3.9 2区计算机科学 Q2 AUTOMATION & CONTROL SYSTEMS

Journal of Process Control

Pub Date : 2026-02-01 Epub Date: 2026-01-05 DOI: 10.1016/j.jprocont.2025.103617

Rangoli Singh , Sandip Ghosh , Devender Singh , Pawel Dworak

This work develops a tube-based model predictive control (MPC) scheme for quasi–linear parameter-varying (quasi-LPV) systems affected by bounded disturbances and time-varying but measurable scheduling parameters. The controller uses a polytopic model together with a gain-scheduled feedback law to maintain robustness against parameter variations and external disturbances. To describe the terminal region more flexibly, a parameter-dependent terminal cost is introduced. In addition, an auxiliary cost function, evaluated only at the vertices of the polytope, removes the need to update parameters at every prediction step. Although the proposed formulation increases the computational load slightly, it provides stronger disturbance rejection and improved constraint handling. Experiments on a coupled-tank setup demonstrate that the method is both effective and practical for real-time implementation.

针对受有界扰动和时变但可测量的调度参数影响的准线性变参系统，提出了一种基于管的模型预测控制（MPC）方案。控制器采用多面体模型和增益调度反馈律来保持对参数变化和外部干扰的鲁棒性。为了更灵活地描述终端区域，引入了与参数相关的终端成本。此外，一个辅助的代价函数，只在多面体的顶点处计算，消除了在每个预测步骤更新参数的需要。虽然提出的公式稍微增加了计算量，但它提供了更强的抗干扰性和改进的约束处理。在一个耦合槽装置上的实验证明了该方法的有效性和实时性。

引用次数: 0

On data-driven robust optimization with multiple uncertainty subsets: Unified uncertainty set representation and mitigating conservatism 多不确定性子集数据驱动鲁棒优化：统一不确定性集表示和缓和保守性

IF 3.9 2区计算机科学 Q2 AUTOMATION & CONTROL SYSTEMS

Journal of Process Control

Pub Date : 2026-02-01 Epub Date: 2026-01-06 DOI: 10.1016/j.jprocont.2025.103611

Yun Li , Neil Yorke-Smith , Tamas Keviczky

Constructing uncertainty sets as unions of multiple subsets has emerged as an effective approach for creating compact and flexible uncertainty representations in data-driven robust optimization (RO). This paper focuses on two separate research questions. The first concerns the computational challenge in applying these uncertainty sets in RO-based predictive control. To address this, a monolithic mixed-integer representation of the uncertainty set is proposed to uniformly describe the union of multiple subsets, enabling the computation of the worst-case uncertainty scenario across all subsets within a single mixed-integer linear programming (MILP) problem. The second research question focuses on mitigating the conservatism of conventional RO formulations by leveraging the structure of the uncertainty set. To achieve this, a novel objective function is proposed to exploit the uncertainty set structure and integrate the existing RO and distributionally robust optimization (DRO) formulations, yielding less conservative solutions than conventional RO formulations, while avoiding the high-dimensional continuous uncertainty distributions and the high computational burden typically associated with existing DRO formulations. Given the proposed formulations, numerically efficient computation methods based on column-and-constraint generation (CCG) are also developed. Extensive simulations across three case studies are performed to demonstrate the effectiveness of the proposed schemes.

在数据驱动鲁棒优化（RO）中，将不确定性集构造为多个子集的并集已成为创建紧凑和灵活的不确定性表示的有效方法。本文主要关注两个独立的研究问题。第一个问题是在基于ro的预测控制中应用这些不确定性集的计算挑战。为了解决这个问题，提出了不确定性集的整体混合整数表示，以统一描述多个子集的并集，从而能够在单个混合整数线性规划（MILP）问题中计算所有子集的最坏情况不确定性情景。第二个研究问题侧重于利用不确定性集的结构来减轻传统RO公式的保守性。为了实现这一目标，提出了一种新的目标函数，利用不确定性集结构，将现有的RO和分布鲁棒优化（DRO）公式集成在一起，产生比传统RO公式更少的保守解，同时避免了高维连续不确定性分布和现有DRO公式通常相关的高计算负担。在此基础上，提出了基于列约束生成（CCG）的高效数值计算方法。在三个案例研究中进行了广泛的模拟，以证明所提出方案的有效性。

{"title":"On data-driven robust optimization with multiple uncertainty subsets: Unified uncertainty set representation and mitigating conservatism","authors":"Yun Li , Neil Yorke-Smith , Tamas Keviczky","doi":"10.1016/j.jprocont.2025.103611","DOIUrl":"10.1016/j.jprocont.2025.103611","url":null,"abstract":"<div><div>Constructing uncertainty sets as unions of multiple subsets has emerged as an effective approach for creating compact and flexible uncertainty representations in data-driven robust optimization (RO). This paper focuses on two separate research questions. The first concerns the computational challenge in applying these uncertainty sets in RO-based predictive control. To address this, a monolithic mixed-integer representation of the uncertainty set is proposed to uniformly describe the union of multiple subsets, enabling the computation of the worst-case uncertainty scenario across all subsets within a single mixed-integer linear programming (MILP) problem. The second research question focuses on mitigating the conservatism of conventional RO formulations by leveraging the structure of the uncertainty set. To achieve this, a novel objective function is proposed to exploit the uncertainty set structure and integrate the existing RO and distributionally robust optimization (DRO) formulations, yielding less conservative solutions than conventional RO formulations, while avoiding the high-dimensional continuous uncertainty distributions and the high computational burden typically associated with existing DRO formulations. Given the proposed formulations, numerically efficient computation methods based on <em>column-and-constraint generation</em> (CCG) are also developed. Extensive simulations across three case studies are performed to demonstrate the effectiveness of the proposed schemes.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"158 ","pages":"Article 103611"},"PeriodicalIF":3.9,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928383","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}

引用次数: 0