Journal of Process Control最新文献_第7页

Multivariable soft sensor with a predictor of mutually dependent errors applied to an industrial fractionator 具有相互依赖误差预测器的多变量软传感器应用于工业分馏器

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

Journal of Process Control

Pub Date : 2025-11-01 Epub Date: 2025-09-22 DOI: 10.1016/j.jprocont.2025.103555

Oleg Snegirev , Vladimir Klimchenko , Denis Shtakin , Andrei Torgashov , Fan Yang

This paper addresses the development of a multivariable soft sensor (SS) with a predictor designed to handle mutual dependencies within multivariate error series. Typically, the mutual influence in vector time series is characterized using cross-correlation. The proposed multivariable cross-correlated error predictor (MCCEP) framework effectively manages such dependencies and is compatible with any data-driven SS model. Forecasted error values are fed back into the SS output as corrections, refining the final predictions of quality indicators. The MCCEP model is constructed through statistical analysis to minimize the generalized variance – defined as the determinant of the covariance matrix – of multivariate forecast errors. Unlike conventional approaches such as bias update techniques, the MCCEP model is chosen from a broad class of predictors for multivariate linear processes, explicitly considering the dynamic relationships among the univariate components of the SS error process. For the n-dimensional case, it is analytically demonstrated that MCCEP minimizes the generalized variance of multivariate errors by leveraging the cross-correlation functions among the univariate components of the time series, thereby enhancing SS accuracy. Analytical methods for constructing MCCEP using the autocovariance generating function and the squared SS error coherence spectrum are developed. The framework’s superiority is highlighted through a case study involving an industrial fractionator, where the SS with MCCEP outperforms conventional SSs employing dynamic partial least squares and bias updates or developed sequentially without considering interdependencies among univariate components of multi-output model errors.

本文讨论了一种多变量软传感器（SS）的发展，其预测器旨在处理多变量误差序列中的相互依赖性。通常，矢量时间序列中的相互影响是用相互关系来表征的。提出的多变量交叉相关误差预测器（MCCEP）框架有效地管理了这些依赖关系，并与任何数据驱动的SS模型兼容。预测的误差值作为修正反馈到SS输出，完善质量指标的最终预测。MCCEP模型是通过统计分析来最小化多元预测误差的广义方差（定义为协方差矩阵的行列式）。与偏差更新技术等传统方法不同，MCCEP模型是从多元线性过程的广泛预测因子中选择的，明确考虑了SS误差过程的单变量成分之间的动态关系。对于n维情况，分析表明MCCEP通过利用时间序列单变量分量之间的相互关联函数最小化多变量误差的广义方差，从而提高SS精度。提出了利用自协方差产生函数和SS误差相干谱的平方构造MCCEP的分析方法。通过涉及工业分分器的案例研究，突出了该框架的优势，其中具有MCCEP的SS优于采用动态偏最小二乘法和偏差更新的传统SS，或者在不考虑多输出模型误差的单变量组件之间的相互依赖性的情况下顺序开发。

{"title":"Multivariable soft sensor with a predictor of mutually dependent errors applied to an industrial fractionator","authors":"Oleg Snegirev , Vladimir Klimchenko , Denis Shtakin , Andrei Torgashov , Fan Yang","doi":"10.1016/j.jprocont.2025.103555","DOIUrl":"10.1016/j.jprocont.2025.103555","url":null,"abstract":"<div><div>This paper addresses the development of a multivariable soft sensor (SS) with a predictor designed to handle mutual dependencies within multivariate error series. Typically, the mutual influence in vector time series is characterized using cross-correlation. The proposed multivariable cross-correlated error predictor (MCCEP) framework effectively manages such dependencies and is compatible with any data-driven SS model. Forecasted error values are fed back into the SS output as corrections, refining the final predictions of quality indicators. The MCCEP model is constructed through statistical analysis to minimize the generalized variance – defined as the determinant of the covariance matrix – of multivariate forecast errors. Unlike conventional approaches such as bias update techniques, the MCCEP model is chosen from a broad class of predictors for multivariate linear processes, explicitly considering the dynamic relationships among the univariate components of the SS error process. For the <em>n</em>-dimensional case, it is analytically demonstrated that MCCEP minimizes the generalized variance of multivariate errors by leveraging the cross-correlation functions among the univariate components of the time series, thereby enhancing SS accuracy. Analytical methods for constructing MCCEP using the autocovariance generating function and the squared SS error coherence spectrum are developed. The framework’s superiority is highlighted through a case study involving an industrial fractionator, where the SS with MCCEP outperforms conventional SSs employing dynamic partial least squares and bias updates or developed sequentially without considering interdependencies among univariate components of multi-output model errors.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"155 ","pages":"Article 103555"},"PeriodicalIF":3.9,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145106723","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

Towards hybrid modeling with mechanistic and real-time data embed iterative co-optimization for industrial processes 面向工业过程机械与实时数据融合的混合建模与迭代协同优化

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

Journal of Process Control

Pub Date : 2025-11-01 Epub Date: 2025-10-18 DOI: 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.

针对过程工业中机械模型不完整和运行数据噪声干扰等问题带来的混合建模挑战，提出了一种结合机械模型和数据驱动模型的两层联合迭代优化框架，用于混合模型参数更新。该框架通过异常点筛选算法实现实时异常消除，同时采用双向反馈算法，在参数识别和迭代更新过程中实现机制模型和数据驱动模型之间的持续协作和相互约束，确保混合模型预测的鲁棒性。该方法解决了机械模型信息缺乏情况下的混合建模和更新问题。此外，通过将模型不确定性和先验知识相结合，实现了知识融合的混合建模过程，具有重要的实用价值。不同于传统的混合建模方法，机械知识仅仅指导建模过程，我们的方法实现了机械模型和数据驱动模型的动态协同进化。本文重点阐述了三个方面：(1)利用机制模型筛选异常数据；(2)通过贝叶斯方法结合机械参数不确定性和先验知识，设计知识引导的参数更新方法；(3)两层联合迭代优化算法的实现细节。对比实验验证了该方法在多种工况和异常情况下的优越性能，证明了该方法在动态优化过程中的科学有效性和实用价值。

{"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":"2025-11-01","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}

引用次数: 0

Output consensus for interconnected systems via the internal model principle and a model predictive control based strategy 基于内模原理和模型预测控制策略的互联系统输出一致性

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

Journal of Process Control

Pub Date : 2025-11-01 Epub Date: 2025-09-18 DOI: 10.1016/j.jprocont.2025.103551

Ye Zhang , Fei Li , Dongya Zhao , Xing-Gang Yan , Sarah K. Spurgeon

Interconnected systems are commonly found in process networks. In this paper, an output consensus framework is proposed for a class of continuous interconnected linear heterogeneous systems subject to constraints. A distributed output consensus control strategy is developed by combining the internal model principle (IMP) with model predictive control (MPC). A distributed iterative algorithm is designed to solve the IMP conditions for interconnected systems. The IMP based control plays two main roles: On the one hand, it helps to deal with the interconnection effects existing between the subsystems; on the other hand, it drives the subsystems to track the reference dynamics in order to achieve output consensus. The MPC determines an optimized control gain while being able to handle constraints. Simulation examples and experimental trials are presented to validate the effectiveness and superiority of the proposed method.

相互连接的系统通常出现在过程网络中。本文提出了一类具有约束的连续互联线性异构系统的输出一致性框架。将内模原理（IMP）与模型预测控制（MPC）相结合，提出了一种分布式输出一致性控制策略。设计了一种分布式迭代算法来求解互联系统的IMP条件。基于IMP的控制主要有两个作用：一方面，它有助于处理子系统之间存在的互连效应；另一方面，它驱动子系统跟踪参考动态，以达到输出一致性。MPC在能够处理约束条件的同时确定了优化的控制增益。通过仿真算例和实验验证了该方法的有效性和优越性。

引用次数: 0

A cross-layer cooperative optimization framework for optimal scheduling of multi-grade PET fiber production 多级聚酯纤维生产优化调度的跨层协同优化框架

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

Journal of Process Control

Pub Date : 2025-11-01 Epub Date: 2025-09-11 DOI: 10.1016/j.jprocont.2025.103540

Jiale Zhang, Wenli Du, Xin Dai

The fluctuations in the supply chain market of polyethylene terephthalate (PET) fibers have been intensifying in recent years. Existing research on the production scheduling of PET plants is usually based on the assumption of a stationary supply chain market. However, these works ignore supply chain fluctuations and market competition, and the schedule obtained may become sub-optimal or infeasible in the real market. This paper considers using the game to represent the competition and cooperation relationships in the market among enterprises with limited supply capacity to obtain equilibrium supplies. Meanwhile, changes in the market prices will cause changes in the equilibrium supplies of the game. In addition, price prediction and supply decisions support the production schedule to achieve high economic efficiency. Therefore, we propose a cross-layer cooperative optimization framework between the supply chain layer and production chain layer for production scheduling optimization. In the supply chain layer, price trends are predicted by synchronous spatio-temporal relationship network, and equilibrium supplies are obtained through a multi-firm multi-product game. In the production chain layer, a production scheduling optimization model that integrates predicted prices and equilibrium supplies from the supply chain layer is established. The effectiveness of the proposed method is verified on a real-world PET plant.

近年来，聚对苯二甲酸乙二醇酯（PET）纤维供应链市场的波动不断加剧。现有的PET工厂生产调度研究通常是基于固定供应链市场的假设。然而，这些工作忽略了供应链的波动和市场竞争，得到的计划在实际市场中可能是次优的或不可行的。本文考虑用博弈来表示供应能力有限的企业之间为获得均衡供给的竞争与合作关系。同时，市场价格的变化会引起博弈均衡供给的变化。此外，价格预测和供应决策支持生产计划，以实现较高的经济效益。为此，我们提出了供应链层与生产链层之间的跨层协同优化框架，用于生产调度优化。在供应链层，通过同步时空关系网络预测价格趋势，并通过多企业多产品博弈获得均衡供给。在生产链层，建立了整合供应链层预测价格和均衡供给的生产调度优化模型。在实际的PET装置上验证了该方法的有效性。

{"title":"A cross-layer cooperative optimization framework for optimal scheduling of multi-grade PET fiber production","authors":"Jiale Zhang, Wenli Du, Xin Dai","doi":"10.1016/j.jprocont.2025.103540","DOIUrl":"10.1016/j.jprocont.2025.103540","url":null,"abstract":"<div><div>The fluctuations in the supply chain market of polyethylene terephthalate (PET) fibers have been intensifying in recent years. Existing research on the production scheduling of PET plants is usually based on the assumption of a stationary supply chain market. However, these works ignore supply chain fluctuations and market competition, and the schedule obtained may become sub-optimal or infeasible in the real market. This paper considers using the game to represent the competition and cooperation relationships in the market among enterprises with limited supply capacity to obtain equilibrium supplies. Meanwhile, changes in the market prices will cause changes in the equilibrium supplies of the game. In addition, price prediction and supply decisions support the production schedule to achieve high economic efficiency. Therefore, we propose a cross-layer cooperative optimization framework between the supply chain layer and production chain layer for production scheduling optimization. In the supply chain layer, price trends are predicted by synchronous spatio-temporal relationship network, and equilibrium supplies are obtained through a multi-firm multi-product game. In the production chain layer, a production scheduling optimization model that integrates predicted prices and equilibrium supplies from the supply chain layer is established. The effectiveness of the proposed method is verified on a real-world PET plant.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"155 ","pages":"Article 103540"},"PeriodicalIF":3.9,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145050180","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

Excitation-free closed-loop identification based on adaptive hysteresis loop width adjustment strategy 基于自适应磁滞环宽度调整策略的无激励闭环辨识

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

Journal of Process Control

Pub Date : 2025-11-01 Epub Date: 2025-09-13 DOI: 10.1016/j.jprocont.2025.103552

Chonggao Hu , Ridong Zhang , Furong Gao

Aiming at the problem that the traditional system identification methods are not adaptive enough when the system model parameters change significantly, this paper proposes an excitation-free closed-loop identification method based on an adaptive hysteresis loop width adjustment (AHLWA) strategy. Firstly, the AHLWA strategy is proposed according to the direction of change of the mean value of the power spectrum (MVPS) of the input signal, which can respond to the trend of the system's dynamic characteristics and dynamically adjust the hysteresis loop width parameters in real time. Secondly, an excitation-free closed-loop identification method based on the AHLWA strategy was developed by integrating the AHLWA strategy with the prediction error method. In addition, to accurately quantify the model error and detect model parameter variations, an improved model error detection method is proposed to quantify the model error by using the unexcited closed-loop identification technique. The numerical example simulation results indicate that the MVPS of the proposed identification method increases from 0.01 to 0.25 compared to the relay feedback identification method, which ensures the continuous excitation of the input signals and significantly improves the identification accuracy when the system model parameters change significantly. Meanwhile, the proposed identification method is further validated by applying it to the temperature control system of industrial coking furnaces. In addition, the proposed identification method can update the benchmark model on time, which makes the system model error significantly lower than 30%, providing an effective solution for model error detection in industrial closed-loop systems.

针对传统系统辨识方法在系统模型参数发生显著变化时适应性不足的问题，提出了一种基于自适应滞回环宽度调整（AHLWA）策略的无激励闭环辨识方法。首先，根据输入信号功率谱均值（MVPS）的变化方向，提出了AHLWA策略，该策略能够实时响应系统动态特性的变化趋势，动态调整滞回环宽度参数；其次，将AHLWA策略与预测误差法相结合，提出了一种基于AHLWA策略的无激励闭环辨识方法；此外，为了准确量化模型误差和检测模型参数变化，提出了一种改进的模型误差检测方法，利用非激励闭环辨识技术对模型误差进行量化。数值算例仿真结果表明，与继电器反馈辨识方法相比，所提辨识方法的MVPS从0.01提高到0.25，保证了输入信号的持续激励，在系统模型参数发生显著变化时显著提高了辨识精度。同时，将该辨识方法应用于工业焦化炉温度控制系统，进一步验证了辨识方法的有效性。此外，所提出的识别方法能够及时更新基准模型，使系统模型误差显著低于30%，为工业闭环系统的模型误差检测提供了有效的解决方案。

{"title":"Excitation-free closed-loop identification based on adaptive hysteresis loop width adjustment strategy","authors":"Chonggao Hu , Ridong Zhang , Furong Gao","doi":"10.1016/j.jprocont.2025.103552","DOIUrl":"10.1016/j.jprocont.2025.103552","url":null,"abstract":"<div><div>Aiming at the problem that the traditional system identification methods are not adaptive enough when the system model parameters change significantly, this paper proposes an excitation-free closed-loop identification method based on an adaptive hysteresis loop width adjustment (AHLWA) strategy. Firstly, the AHLWA strategy is proposed according to the direction of change of the mean value of the power spectrum (MVPS) of the input signal, which can respond to the trend of the system's dynamic characteristics and dynamically adjust the hysteresis loop width parameters in real time. Secondly, an excitation-free closed-loop identification method based on the AHLWA strategy was developed by integrating the AHLWA strategy with the prediction error method. In addition, to accurately quantify the model error and detect model parameter variations, an improved model error detection method is proposed to quantify the model error by using the unexcited closed-loop identification technique. The numerical example simulation results indicate that the MVPS of the proposed identification method increases from 0.01 to 0.25 compared to the relay feedback identification method, which ensures the continuous excitation of the input signals and significantly improves the identification accuracy when the system model parameters change significantly. Meanwhile, the proposed identification method is further validated by applying it to the temperature control system of industrial coking furnaces. In addition, the proposed identification method can update the benchmark model on time, which makes the system model error significantly lower than 30%, providing an effective solution for model error detection in industrial closed-loop systems.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"155 ","pages":"Article 103552"},"PeriodicalIF":3.9,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145050181","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

Melt viscosity control in polymer extrusion using nonlinear model predictive control with neural state space modelling and soft sensor feedback 基于神经状态空间建模和软传感器反馈的非线性模型预测控制在聚合物挤出过程中的熔体粘度控制

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

Journal of Process Control

Pub Date : 2025-11-01 Epub Date: 2025-09-29 DOI: 10.1016/j.jprocont.2025.103556

Yasith S. Perera , Jie Li , Chamil Abeykoon

Melt viscosity is a key quality indicator in polymer extrusion processes, as it directly influences the mechanical properties, dimensional stability, and surface finish of the final product. However, real-time melt viscosity monitoring and control remain a major challenge in industrial polymer extrusion, due to the limitations of physical viscosity monitoring techniques, such as disturbances to the melt flow, reduced throughputs, and measurement delays. To address this issue, this study proposes a nonlinear model predictive control framework that enables direct, real-time control of melt viscosity using non-invasive feedback from a deep neural network-based soft sensor. A neural state-space model is trained on real experimental data to learn the underlying process dynamics and serves as the internal model of the controller. The soft sensor provides melt viscosity estimates based on readily available process variables (i.e., screw speed and barrel temperatures). These estimates are used by an extended Kalman filter with state augmentation to correct the internal state predictions. The proposed control system was rigorously evaluated via simulation across a variety of setpoint changes and disturbance scenarios. Results show that the controller maintains the melt viscosity within

\pm

2 % of the setpoint, irrespective of the initial conditions used, with settling times below 20 s. Under step and ramp disturbances applied to the output variable, screw speed, and barrel temperatures, the controller exhibited strong disturbance rejection capabilities. Notably, under step disturbances of

\pm

100 Pa⋅s acting on the melt viscosity output, the controller quickly restored the viscosity to the setpoint with settling times under 18 s. The real-time closed-loop melt viscosity control framework proposed in this study should be invaluable for advancing process monitoring and control of polymer extrusion processes.

熔体粘度是聚合物挤出过程中一个关键的质量指标，因为它直接影响到最终产品的机械性能、尺寸稳定性和表面光洁度。然而，由于物理粘度监测技术的局限性，如熔体流动的干扰、吞吐量的降低和测量延迟，熔体粘度的实时监测和控制仍然是工业聚合物挤出的主要挑战。为了解决这个问题，本研究提出了一种非线性模型预测控制框架，该框架可以使用基于深度神经网络的软传感器的非侵入性反馈直接实时控制熔体粘度。在实际实验数据上训练神经状态空间模型来学习潜在的过程动力学，并作为控制器的内部模型。软传感器根据现成的工艺变量（即螺杆速度和料筒温度）提供熔体粘度估计。这些估计被一个带状态增强的扩展卡尔曼滤波器用来修正内部状态预测。所提出的控制系统通过各种设定值变化和干扰情景的仿真进行了严格的评估。结果表明，无论使用何种初始条件，该控制器都能将熔体粘度保持在设定值的±2%以内，沉降时间低于20 s。在施加于输出变量、螺杆转速和筒体温度的阶跃和斜坡扰动下，控制器表现出较强的抗干扰能力。值得注意的是，在对熔体粘度输出施加±100 Pa·s阶跃扰动的情况下，控制器可以快速将粘度恢复到设定值，沉降时间小于18 s。本研究提出的熔体粘度实时闭环控制框架对于推进聚合物挤出过程的过程监测和控制具有重要意义。

{"title":"Melt viscosity control in polymer extrusion using nonlinear model predictive control with neural state space modelling and soft sensor feedback","authors":"Yasith S. Perera , Jie Li , Chamil Abeykoon","doi":"10.1016/j.jprocont.2025.103556","DOIUrl":"10.1016/j.jprocont.2025.103556","url":null,"abstract":"<div><div>Melt viscosity is a key quality indicator in polymer extrusion processes, as it directly influences the mechanical properties, dimensional stability, and surface finish of the final product. However, real-time melt viscosity monitoring and control remain a major challenge in industrial polymer extrusion, due to the limitations of physical viscosity monitoring techniques, such as disturbances to the melt flow, reduced throughputs, and measurement delays. To address this issue, this study proposes a nonlinear model predictive control framework that enables direct, real-time control of melt viscosity using non-invasive feedback from a deep neural network-based soft sensor. A neural state-space model is trained on real experimental data to learn the underlying process dynamics and serves as the internal model of the controller. The soft sensor provides melt viscosity estimates based on readily available process variables (i.e., screw speed and barrel temperatures). These estimates are used by an extended Kalman filter with state augmentation to correct the internal state predictions. The proposed control system was rigorously evaluated via simulation across a variety of setpoint changes and disturbance scenarios. Results show that the controller maintains the melt viscosity within <span><math><mo>±</mo></math></span>2 % of the setpoint, irrespective of the initial conditions used, with settling times below 20 s. Under step and ramp disturbances applied to the output variable, screw speed, and barrel temperatures, the controller exhibited strong disturbance rejection capabilities. Notably, under step disturbances of <span><math><mo>±</mo></math></span> 100 Pa⋅s acting on the melt viscosity output, the controller quickly restored the viscosity to the setpoint with settling times under 18 s. The real-time closed-loop melt viscosity control framework proposed in this study should be invaluable for advancing process monitoring and control of polymer extrusion processes.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"155 ","pages":"Article 103556"},"PeriodicalIF":3.9,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145221456","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

Nonlinear model predictive control with an infinite horizon approximation 具有无限水平逼近的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 : 2025-11-01 Epub Date: 2025-10-13 DOI: 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.

当前的非线性模型预测控制（NMPC）策略是通过构建终端成本函数和/或终端约束来维持NMPC的稳定性和递归可行性的有限预测水平非线性规划（nlp）。然而，在固定视界下计算这些终端属性可能会带来巨大的挑战，特别是在非线性动态过程的背景下。基于这些问题，我们引入了一种交替移动视界方法，其中视界中的最终元素由无限视界时间变换构造。该方法的关键特点在于将提出的NMPC公式作为扩展边值问题求解，在有限元上使用正交配置。通过对无限视界最优控制问题的二分性，确定了不稳定模式，扩展到开环稳定动态系统之外，从而保证了系统的渐近稳定性和鲁棒稳定性。提出的NMPC公式的有效性通过三个案例研究进行了验证，验证了该方法在现实问题上的实际应用和鲁棒性。

{"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":"2025-11-01","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}

引用次数: 0

Optimal inventory control for bottleneck isolation in general processes 一般工艺中瓶颈隔离的最优库存控制

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

Journal of Process Control

Pub Date : 2025-11-01 Epub Date: 2025-10-07 DOI: 10.1016/j.jprocont.2025.103557

Archana Kumaraswamy, Evren Mert Turan, Johannes Jäschke

Optimal inventory control seeks to isolate the economic effect of bottlenecks and maximise the throughput of processes. This is challenging in complex topologies with disturbances causing shifting bottlenecks. Decentralised and model predictive control schemes have been proposed for bottleneck isolation of sequential processes. Although decentralised control schemes work well for sequential processes, they are difficult to apply to more complex topologies such as parallel arrangement of units, flow splits, mergers, and recycles that are common in the industry. In contrast, such multi-input multi-output systems can be naturally handled with model predictive control schemes. This work extends a preliminary model predictive control scheme in the literature to achieve bottleneck isolation in general process topologies. In particular, a seriatim amongst inventories and system outflows is created using weights in the objective function. Our approach is simple to implement and is shown to optimally isolate bottlenecks on a wide range of case studies and topologies.

最佳库存控制旨在隔离瓶颈的经济影响，并最大限度地提高流程的吞吐量。这在复杂的拓扑结构中是具有挑战性的，因为干扰会导致移动瓶颈。针对顺序过程的瓶颈隔离问题，提出了分散和模型预测控制方案。尽管分散控制方案对顺序过程很有效，但它们很难应用于更复杂的拓扑结构，如并行安排单元、流分裂、合并和工业中常见的循环。相比之下，这种多输入多输出系统可以用模型预测控制方案自然地处理。这项工作扩展了文献中的初步模型预测控制方案，以实现一般过程拓扑中的瓶颈隔离。特别是，库存和系统流出之间的序列是使用目标函数中的权重创建的。我们的方法易于实现，并被证明可以在广泛的案例研究和拓扑中以最佳方式隔离瓶颈。

引用次数: 0

Fault detection and isolation for a class of nonlinear systems based on a bundle of observers and zonotope analysis 一类基于观测器束和共格分析的非线性系统故障检测与隔离

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

Journal of Process Control

Pub Date : 2025-11-01 Epub Date: 2025-10-09 DOI: 10.1016/j.jprocont.2025.103561

Chi Xu , Zhenhua Wang , Nacim Meslem , Tarek Raïssi , Yi Shen

This paper introduces a novel fault detection and isolation (FDI) approach for nonlinear systems subject to unknown but bounded disturbances. The proposed approach combines a bundle of fault detection observers (FDOs), tuned by a peak-to-peak performance technique, with an offline reachability method to generate reliable actuator fault detection and isolation thresholds. Moreover, a sliding-window algorithm, based on zonotopic computation, is designed to be able to provide dynamical fault detection thresholds. This allows one to reduce the conservatism and, by the way, enhance the efficiency of the proposed approach. A quadruple-tank system is considered as a case study, where the theoretical findings of this work are supported by simulation results. In addition, on this example, the performance of the proposed method is compared to that of another method selected from the literature.

本文介绍了一种针对未知有界扰动的非线性系统的故障检测与隔离方法。该方法将一组故障检测观测器（fdo）与离线可达性方法相结合，通过峰对峰性能技术进行调优，生成可靠的执行器故障检测和隔离阈值。此外，设计了一种基于分区计算的滑动窗口算法，以提供动态故障检测阈值。这允许人们减少保守性，顺便提一下，提高所提出方法的效率。一个四缸系统被认为是一个案例研究，其中这项工作的理论发现得到了模拟结果的支持。此外，在此示例中，将所提出方法的性能与文献中选择的另一种方法的性能进行了比较。

引用次数: 0

Canonical correlation analysis-aided design of Kalman filter-based residual generator for monitoring of industrial control systems 典型相关分析辅助设计基于卡尔曼滤波的工业控制系统监测残差发生器

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

Journal of Process Control

Pub Date : 2025-11-01 Epub Date: 2025-10-14 DOI: 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.

卡尔曼滤波由于产生的残差是白色的，协方差最小，被广泛应用于残差生成。这样可以实现最佳监控。然而，在实际的工业自动化系统中难以实现显式的数学模型，并且现有的数据驱动设计方法没有明确考虑反馈的影响，从而降低了基于卡尔曼滤波的监控系统的监控性能。为了解决这一问题，本文提出了一种纯数据驱动的基于卡尔曼滤波的残差发生器，用于闭环结构的工业控制系统过程监测。首先，介绍了典型相关分析（CCA）的最小均方解释，这有助于探索工业控制系统输入和输出之间的关系。然后，通过辨识卡尔曼增益矩阵和数据驱动的稳定核表示，构造了基于cca辅助卡尔曼滤波的残差发生器。与现有方法不同的是，该方法考虑了系统反馈控制结构引起的闭环动力学和输入与噪声之间的相关性，实现了较好的监测性能。通过一个三槽系统的实验验证和比较了该方法的有效性。

{"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":"2025-11-01","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}

引用次数: 0