Journal of Process Control最新文献_第7页

A multi-model fault-tolerant control method for concurrent faults in wastewater treatment processes based on semi-supervised learning and physical constraints 基于半监督学习和物理约束的污水处理过程并发故障多模型容错控制方法

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

Journal of Process Control

Pub Date : 2025-09-30 DOI: 10.1016/j.jprocont.2025.103560

Huan Luo, Ying Tian

Wastewater treatment processes (WWTP) is one of the most essential means to achieve water resource protection and sustainable utilization, with dissolved oxygen and nitrate serving as main factors limiting effluent quality through their direct involvement in carbon consumption, nitrification, and denitrification processes. Existing fault-tolerant control strategies primarily focus on single sensor anomalies, while practical operations frequently encounter concurrent faults across multiple measurement channels. Moreover, the scarcity of labeled operational data in industrial settings poses significant challenges for developing reliable fault-tolerant control systems. This paper presents a passive fault-tolerant control approach using an innovative semi-supervised deep learning framework to address simultaneous failures in critical dissolved oxygen and nitrate sensors. The proposed methodology features four key innovations: (1) A novel SAE-MNN architecture that integrates stacked autoencoders with multi-output neural networks for simultaneous multi-parameter prediction through hierarchical feature extraction. (2) A confidence-based pseudo-labeling semi-supervised co-training mechanism that effectively leverages limited labeled data and abundant unlabeled operational data under data scarcity conditions. (3) Physics-constrained learning that enforces biochemical principles and mass conservation laws to ensure physically plausible predictions. (4) A multi-sensor passive fault-tolerant control strategy that handles simultaneous failures across multiple critical measurement channels without hardware redundancy or controller reconfiguration. This integrated framework enables robust operation during concurrent sensor failures, where predicted values seamlessly replace multiple faulty sensor measurements while maintaining stable control performance. The effectiveness is validated using the Benchmark Simulation Model No. 1 (BSM1), demonstrating superior system performance during multi-sensor fault scenarios compared to conventional methods, thereby enhancing the reliability and resilience of wastewater treatment systems.

污水处理工艺是实现水资源保护和可持续利用的重要手段之一，溶解氧和硝酸盐直接参与碳消耗、硝化和反硝化过程，是限制出水水质的主要因素。现有的容错控制策略主要针对单个传感器异常，而实际操作中往往会遇到多个测量通道并发故障。此外，工业环境中标记操作数据的稀缺性为开发可靠的容错控制系统带来了重大挑战。本文提出了一种被动容错控制方法，使用创新的半监督深度学习框架来解决关键溶解氧和硝酸盐传感器的同时故障。提出的方法具有四个关键创新：(1)一种新颖的SAE-MNN架构，该架构将堆叠自编码器与多输出神经网络集成在一起，通过分层特征提取同时进行多参数预测。(2)基于置信度的伪标注半监督协同训练机制，在数据稀缺条件下有效利用有限的标注数据和丰富的未标注操作数据。(3)物理约束的学习，强制执行生化原理和质量守恒定律，以确保物理上合理的预测。(4)一种多传感器无源容错控制策略，可处理多个关键测量通道同时发生的故障，无需硬件冗余或控制器重构。这种集成框架可以在并发传感器故障期间实现稳健的操作，其中预测值可以无缝地替换多个故障传感器测量值，同时保持稳定的控制性能。通过基准仿真模型1 （BSM1）验证了该方法的有效性，与传统方法相比，该方法在多传感器故障场景下表现出优越的系统性能，从而提高了废水处理系统的可靠性和弹性。

{"title":"A multi-model fault-tolerant control method for concurrent faults in wastewater treatment processes based on semi-supervised learning and physical constraints","authors":"Huan Luo, Ying Tian","doi":"10.1016/j.jprocont.2025.103560","DOIUrl":"10.1016/j.jprocont.2025.103560","url":null,"abstract":"<div><div>Wastewater treatment processes (WWTP) is one of the most essential means to achieve water resource protection and sustainable utilization, with dissolved oxygen and nitrate serving as main factors limiting effluent quality through their direct involvement in carbon consumption, nitrification, and denitrification processes. Existing fault-tolerant control strategies primarily focus on single sensor anomalies, while practical operations frequently encounter concurrent faults across multiple measurement channels. Moreover, the scarcity of labeled operational data in industrial settings poses significant challenges for developing reliable fault-tolerant control systems. This paper presents a passive fault-tolerant control approach using an innovative semi-supervised deep learning framework to address simultaneous failures in critical dissolved oxygen and nitrate sensors. The proposed methodology features four key innovations: (1) A novel SAE-MNN architecture that integrates stacked autoencoders with multi-output neural networks for simultaneous multi-parameter prediction through hierarchical feature extraction. (2) A confidence-based pseudo-labeling semi-supervised co-training mechanism that effectively leverages limited labeled data and abundant unlabeled operational data under data scarcity conditions. (3) Physics-constrained learning that enforces biochemical principles and mass conservation laws to ensure physically plausible predictions. (4) A multi-sensor passive fault-tolerant control strategy that handles simultaneous failures across multiple critical measurement channels without hardware redundancy or controller reconfiguration. This integrated framework enables robust operation during concurrent sensor failures, where predicted values seamlessly replace multiple faulty sensor measurements while maintaining stable control performance. The effectiveness is validated using the Benchmark Simulation Model No. 1 (BSM1), demonstrating superior system performance during multi-sensor fault scenarios compared to conventional methods, thereby enhancing the reliability and resilience of wastewater treatment systems.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"155 ","pages":"Article 103560"},"PeriodicalIF":3.9,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145221455","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 : 2025-09-29 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":"2025-09-29","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

Real-time freeze point prediction using multirate measurements in the blending process 在混合过程中使用多速率测量的实时凝固点预测

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

Journal of Process Control

Pub Date : 2025-09-23 DOI: 10.1016/j.jprocont.2025.103550

Khizer Mohamed , Om Prakash , Junyao Xie , Yanjun Ma , Haitao Zhang , Biao Huang

In blending processes, real-time monitoring of product properties is crucial for maintaining quality and optimizing operational efficiency. However, properties such as the freeze point are typically measured using slow and expensive laboratory tests. To enable real-time monitoring, analyzers are developed based on these laboratory measurements. Additionally, there are certain compounds whose freeze point is less than

- 70^{\circ} C

, which are beyond the detection limits of conventional laboratory techniques. This paper introduces a framework that combines the expectation–maximization algorithm with particle-filtering to estimate the freeze point of a compound used in the fuel-blending process, where conventional laboratory methods struggle to provide measurements. The method integrates multirate data, by combining high-frequency sensor data with low-frequency laboratory measurements, to estimate the freeze point. The soft sensor parameters are then identified using the estimated freeze point and directly measured input features such as the true boiling point. The proposed model allows estimation of the freeze point, particularly for components whose properties are not readily measurable using standard laboratory techniques. The proposed approach is compared against two other approaches: (1) a estimation using only high-frequency sensor data and (2) a estimation using only slow laboratory measurements. The soft sensor developed using the proposed framework reduces dependence on offline testing, providing a cost-effective and operationally viable alternative, while validation with industrial data confirms its applicability and effectiveness in real time, achieving an

R^{2}

value of 0.4074 that demonstrates reasonable predictive performance under industrial conditions.

在混合过程中，产品性能的实时监控对于保持质量和优化操作效率至关重要。然而，诸如凝固点之类的特性通常是通过缓慢而昂贵的实验室测试来测量的。为了实现实时监控，根据这些实验室测量结果开发了分析仪。此外，还有某些凝固点小于- 70°C的化合物，超出了传统实验室技术的检测极限。本文介绍了一个将期望最大化算法与颗粒过滤相结合的框架，以估计燃料混合过程中使用的化合物的凝固点，而传统的实验室方法难以提供测量。该方法通过将高频传感器数据与低频实验室测量数据相结合，集成多速率数据来估计凝固点。然后使用估计的冰点和直接测量的输入特征（如真沸点）来识别软传感器参数。所提出的模型允许对凝固点进行估计，特别是对于那些不能用标准实验室技术轻易测量的成分。将所提出的方法与其他两种方法进行比较：(1)仅使用高频传感器数据的估计和(2)仅使用慢速实验室测量的估计。利用所提出的框架开发的软传感器减少了对离线测试的依赖，提供了一种具有成本效益和操作可行性的替代方案，而工业数据验证则证实了其实时适用性和有效性，R2值为0.4074，在工业条件下显示出合理的预测性能。

{"title":"Real-time freeze point prediction using multirate measurements in the blending process","authors":"Khizer Mohamed , Om Prakash , Junyao Xie , Yanjun Ma , Haitao Zhang , Biao Huang","doi":"10.1016/j.jprocont.2025.103550","DOIUrl":"10.1016/j.jprocont.2025.103550","url":null,"abstract":"<div><div>In blending processes, real-time monitoring of product properties is crucial for maintaining quality and optimizing operational efficiency. However, properties such as the freeze point are typically measured using slow and expensive laboratory tests. To enable real-time monitoring, analyzers are developed based on these laboratory measurements. Additionally, there are certain compounds whose freeze point is less than <span><math><mrow><mo>−</mo><mn>70</mn><msup><mrow><mspace></mspace></mrow><mrow><mo>∘</mo></mrow></msup><mtext>C</mtext></mrow></math></span>, which are beyond the detection limits of conventional laboratory techniques. This paper introduces a framework that combines the expectation–maximization algorithm with particle-filtering to estimate the freeze point of a compound used in the fuel-blending process, where conventional laboratory methods struggle to provide measurements. The method integrates multirate data, by combining high-frequency sensor data with low-frequency laboratory measurements, to estimate the freeze point. The soft sensor parameters are then identified using the estimated freeze point and directly measured input features such as the true boiling point. The proposed model allows estimation of the freeze point, particularly for components whose properties are not readily measurable using standard laboratory techniques. The proposed approach is compared against two other approaches: (1) a estimation using only high-frequency sensor data and (2) a estimation using only slow laboratory measurements. The soft sensor developed using the proposed framework reduces dependence on offline testing, providing a cost-effective and operationally viable alternative, while validation with industrial data confirms its applicability and effectiveness in real time, achieving an <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> value of 0.4074 that demonstrates reasonable predictive performance under industrial conditions.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"155 ","pages":"Article 103550"},"PeriodicalIF":3.9,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145119249","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

Prior model identification for stochastic optimal control of continuous aqueous two-phase flotation 连续水两相浮选随机最优控制的先验模型辨识

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

Journal of Process Control

Pub Date : 2025-09-23 DOI: 10.1016/j.jprocont.2025.103524

Katrin Baumgärtner , Kim Carina Lohfink , Hermann Nirschl , Moritz Diehl

In chemical process control, where an accurate model of the system dynamics is often not available, advanced control strategies such as stochastic optimal control promise superior control performance as opposed to nominal approaches neglecting the – often significant – uncertainty associated with the model predictions. A crucial prerequisite for stochastic optimal control is a suitable description of the uncertainty associated with the available model as well as a computational description of how this uncertainty evolves as more measurements become available. In this work, we exemplify how a stochastic model might be identified from experimental data and illustrate how non-stochastic models fail to describe the available data in the presence of high inter-experimental variation within the dataset. To this end, model identification from experimental data of the continuous aqueous two-phase flotation serves as a case study. In a second step, we showcase the performance of an optimization-based control strategy which is based on the identified stochastic model in closed-loop experiments.

在化学过程控制中，通常无法获得精确的系统动力学模型，与忽略与模型预测相关的（通常是显著的）不确定性的标称方法相反，诸如随机最优控制之类的高级控制策略保证了优越的控制性能。随机最优控制的一个关键先决条件是对与可用模型相关的不确定性的适当描述，以及随着更多测量变得可用，这种不确定性如何演变的计算描述。在这项工作中，我们举例说明了如何从实验数据中识别随机模型，并说明了在数据集中存在高实验间差异的情况下，非随机模型如何无法描述可用数据。为此，从连续两相水浮选实验数据中进行模型识别作为案例研究。在第二步中，我们展示了基于识别的随机模型的基于优化的控制策略在闭环实验中的性能。

{"title":"Prior model identification for stochastic optimal control of continuous aqueous two-phase flotation","authors":"Katrin Baumgärtner , Kim Carina Lohfink , Hermann Nirschl , Moritz Diehl","doi":"10.1016/j.jprocont.2025.103524","DOIUrl":"10.1016/j.jprocont.2025.103524","url":null,"abstract":"<div><div>In chemical process control, where an accurate model of the system dynamics is often not available, advanced control strategies such as stochastic optimal control promise superior control performance as opposed to nominal approaches neglecting the – often significant – uncertainty associated with the model predictions. A crucial prerequisite for stochastic optimal control is a suitable description of the uncertainty associated with the available model as well as a computational description of how this uncertainty evolves as more measurements become available. In this work, we exemplify how a stochastic model might be identified from experimental data and illustrate how non-stochastic models fail to describe the available data in the presence of high inter-experimental variation within the dataset. To this end, model identification from experimental data of the continuous aqueous two-phase flotation serves as a case study. In a second step, we showcase the performance of an optimization-based control strategy which is based on the identified stochastic model in closed-loop experiments.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"155 ","pages":"Article 103524"},"PeriodicalIF":3.9,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145119250","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

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 : 2025-09-22 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":"2025-09-22","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

Advances in modeling and control of nonlinear distributed parameter systems and their applications: A review 非线性分布参数系统的建模与控制及其应用研究进展

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

Journal of Process Control

Pub Date : 2025-09-20 DOI: 10.1016/j.jprocont.2025.103549

Bowen Xu , Weiqi Yang , Xinjiang Lu , Yunxu Bai , Yajun Wang

Numerous processes in various fields including engineering, physics, and chemistry, etc., belong to distributed parameter systems (DPSs). These systems are strongly spatiotemporal coupled, possessing complex time-varying dynamics and infinite-dimensional spatial distribution characteristics. Additionally, there are unknown initial/ boundary conditions and parameter variation during the interaction of information or energy exchange, especially in complex application scenarios (i.e., large operation range, large spatial region, etc.). These factors make the modeling, prediction and control of spatiotemporal dynamics extremely difficult and challenging. With the enrichment of computational resources and data-driven/ intelligent methods, many new frameworks and strategies are designed and applied for nonlinear DPSs, which promotes the research diversity and maturity of DPS theory. Meanwhile, the development also gives rise to new problems. From the perspective of review, this paper starts from the practical modeling and control problems in combination with several application cases of nonlinear DPSs, and summarizes the research and application progress, including traditional methods, data-driven methods, intelligent modeling methods etc., and looks forward to the future development trends, providing guidance for related research and practical problem-solving of nonlinear DPSs.

工程、物理、化学等领域的许多过程都属于分布式参数系统（dps）。这些系统具有强烈的时空耦合性，具有复杂的时变动力学和无限维空间分布特征。此外，在信息或能量交换的交互过程中，存在未知的初始/边界条件和参数变化，特别是在复杂的应用场景中（如大操作范围、大空间区域等）。这些因素使得时空动态的建模、预测和控制变得极其困难和具有挑战性。随着计算资源的丰富和数据驱动/智能方法的发展，许多新的DPS框架和策略被设计和应用，促进了DPS理论研究的多样性和成熟度。与此同时，发展也带来了新的问题。本文从综述的角度出发，结合非线性dps的几个应用案例，从实际建模和控制问题出发，总结了包括传统方法、数据驱动方法、智能建模方法等方面的研究和应用进展，并展望了未来的发展趋势，为非线性dps的相关研究和实际解决提供指导。

{"title":"Advances in modeling and control of nonlinear distributed parameter systems and their applications: A review","authors":"Bowen Xu , Weiqi Yang , Xinjiang Lu , Yunxu Bai , Yajun Wang","doi":"10.1016/j.jprocont.2025.103549","DOIUrl":"10.1016/j.jprocont.2025.103549","url":null,"abstract":"<div><div>Numerous processes in various fields including engineering, physics, and chemistry, etc., belong to distributed parameter systems (DPSs). These systems are strongly spatiotemporal coupled, possessing complex time-varying dynamics and infinite-dimensional spatial distribution characteristics. Additionally, there are unknown initial/ boundary conditions and parameter variation during the interaction of information or energy exchange, especially in complex application scenarios (i.e., large operation range, large spatial region, etc.). These factors make the modeling, prediction and control of spatiotemporal dynamics extremely difficult and challenging. With the enrichment of computational resources and data-driven/ intelligent methods, many new frameworks and strategies are designed and applied for nonlinear DPSs, which promotes the research diversity and maturity of DPS theory. Meanwhile, the development also gives rise to new problems. From the perspective of review, this paper starts from the practical modeling and control problems in combination with several application cases of nonlinear DPSs, and summarizes the research and application progress, including traditional methods, data-driven methods, intelligent modeling methods etc., and looks forward to the future development trends, providing guidance for related research and practical problem-solving of nonlinear DPSs.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"155 ","pages":"Article 103549"},"PeriodicalIF":3.9,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145097511","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

Maximum extrem biogas yield prediction based tracking control for two-stage anaerobic digestion using CKF robust observer feedback 基于CKF鲁棒观测器反馈的两级厌氧消化最大极值沼气产量预测跟踪控制

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

Journal of Process Control

Pub Date : 2025-09-19 DOI: 10.1016/j.jprocont.2025.103558

Hongxuan Li , Haoping Wang , Yang Tian , Nicolai Christov

Two-stage anaerobic digestion process, recognized as a promising microbiological technology, can effectively converts organic pollutants into renewable energy gases. However, practical implementation faces two fundamental challenges: the critical process states (for example, concentrations of anaerobic microorganisms) are not directly measurable through conventional sensors, and the gas production efficiency remains suboptimal under current operational paradigms. To address these challenges, this study proposed a robust observer-based biogas yield extremum prediction tracking controller (RO-EPTC). The proposed RO-EPTC controller integrates a cubature Kalman filter robust observer and an artificial neural network-based prediction tracking controller. The RO-EPTC enables dynamic extremum prediction of biogas yield while ensuring real-time convergence of actual gas production to the identified optimal trajectory. Additionally, the proposed scheme provides accurate estimation of unmeasurable system states. Finally, through simulation comparison experiments, the effects of proposed RO-EPTC method were verified.

两级厌氧消化技术可以有效地将有机污染物转化为可再生能源气体，是一种很有前途的微生物技术。然而，实际实施面临两个基本挑战：关键过程状态（例如，厌氧微生物的浓度）不能通过传统传感器直接测量，并且在当前的操作范式下，产气效率仍然不是最佳的。为了解决这些挑战，本研究提出了一种鲁棒的基于观测器的沼气产量极值预测跟踪控制器（RO-EPTC）。提出的RO-EPTC控制器集成了培养卡尔曼滤波鲁棒观测器和基于人工神经网络的预测跟踪控制器。RO-EPTC能够对生物气产量进行动态极值预测，同时确保将实际产气量实时收敛到确定的最佳轨迹。此外，该方案提供了对不可测系统状态的准确估计。最后，通过仿真对比实验，验证了所提RO-EPTC方法的效果。

{"title":"Maximum extrem biogas yield prediction based tracking control for two-stage anaerobic digestion using CKF robust observer feedback","authors":"Hongxuan Li , Haoping Wang , Yang Tian , Nicolai Christov","doi":"10.1016/j.jprocont.2025.103558","DOIUrl":"10.1016/j.jprocont.2025.103558","url":null,"abstract":"<div><div>Two-stage anaerobic digestion process, recognized as a promising microbiological technology, can effectively converts organic pollutants into renewable energy gases. However, practical implementation faces two fundamental challenges: the critical process states (for example, concentrations of anaerobic microorganisms) are not directly measurable through conventional sensors, and the gas production efficiency remains suboptimal under current operational paradigms. To address these challenges, this study proposed a robust observer-based biogas yield extremum prediction tracking controller (RO-EPTC). The proposed RO-EPTC controller integrates a cubature Kalman filter robust observer and an artificial neural network-based prediction tracking controller. The RO-EPTC enables dynamic extremum prediction of biogas yield while ensuring real-time convergence of actual gas production to the identified optimal trajectory. Additionally, the proposed scheme provides accurate estimation of unmeasurable system states. Finally, through simulation comparison experiments, the effects of proposed RO-EPTC method were verified.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"155 ","pages":"Article 103558"},"PeriodicalIF":3.9,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145097510","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 : 2025-09-18 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

Deep learning-based model predictive control with exponential weighting strategy and its application in energy management systems 基于深度学习的指数加权模型预测控制及其在能源管理系统中的应用

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

Journal of Process Control

Pub Date : 2025-09-17 DOI: 10.1016/j.jprocont.2025.103542

Dan Cui , Yanfang Mo , Xiaofeng Yuan , Lingjian Ye , Kai Wang , Feifan Shen , Yalin Wang , Chunhua Yang , Weihua Gui

Building energy management plays an important role in improving the overall system efficiency and reducing energy consumption. To achieve this goal, it is significant and challenging for the optimization of energy consumption and the utilization of renewable energy sources. This work presents a deep learning-based model predictive control with exponential weighting (DLEMPC) strategy to control and optimize Energy Management Systems (EMS). First, an exponential weighting technique with decreasing characteristic is introduced to the cost function over the timeslots in the receding horizon of the MPC to improve the control performance of the system, which aims to obtain the control actions by paying more importance on recent timeslots in the finite time-horizon. Second, a controller based on the deep belief network (DBN) model is proposed to reduce computational complexity of the rolling horizon optimization in practical applications. The deep learning controller is obtained by training it with a large number of input and output data pairs that are generated from a well-defined MPC designed with the new cost function. Finally, the DLEMPC strategy is used to control and optimize an EMS, connected to a grid, battery, HVAC, and solar panel. The results demonstrate that DLEMPC strategy can significantly improve the energy efficiency of buildings and reduce energy consumption compared to the traditional MPC formula.

建筑能源管理对提高系统整体效率、降低能耗具有重要作用。实现这一目标，对能源消耗的优化和可再生能源的利用具有重要的意义和挑战性。本文提出了一种基于深度学习的指数加权模型预测控制（DLEMPC）策略来控制和优化能源管理系统。首先，为了提高系统的控制性能，在MPC的后退水平时隙的代价函数中引入了具有递减特征的指数加权技术，其目的是在有限的时间范围内更重视最近时隙的控制动作。其次，提出了一种基于深度信念网络（DBN）模型的控制器，以降低实际应用中滚动地平线优化的计算复杂度。深度学习控制器是通过训练大量的输入输出数据对得到的，这些数据对是由一个定义良好的MPC生成的，该MPC设计了新的成本函数。最后，将该策略用于控制和优化与电网、电池、暖通空调和太阳能电池板相连的EMS。结果表明，与传统的MPC公式相比，DLEMPC策略可以显著提高建筑的能源效率，降低能耗。

{"title":"Deep learning-based model predictive control with exponential weighting strategy and its application in energy management systems","authors":"Dan Cui , Yanfang Mo , Xiaofeng Yuan , Lingjian Ye , Kai Wang , Feifan Shen , Yalin Wang , Chunhua Yang , Weihua Gui","doi":"10.1016/j.jprocont.2025.103542","DOIUrl":"10.1016/j.jprocont.2025.103542","url":null,"abstract":"<div><div>Building energy management plays an important role in improving the overall system efficiency and reducing energy consumption. To achieve this goal, it is significant and challenging for the optimization of energy consumption and the utilization of renewable energy sources. This work presents a deep learning-based model predictive control with exponential weighting (DLEMPC) strategy to control and optimize Energy Management Systems (EMS). First, an exponential weighting technique with decreasing characteristic is introduced to the cost function over the timeslots in the receding horizon of the MPC to improve the control performance of the system, which aims to obtain the control actions by paying more importance on recent timeslots in the finite time-horizon. Second, a controller based on the deep belief network (DBN) model is proposed to reduce computational complexity of the rolling horizon optimization in practical applications. The deep learning controller is obtained by training it with a large number of input and output data pairs that are generated from a well-defined MPC designed with the new cost function. Finally, the DLEMPC strategy is used to control and optimize an EMS, connected to a grid, battery, HVAC, and solar panel. The results demonstrate that DLEMPC strategy can significantly improve the energy efficiency of buildings and reduce energy consumption compared to the traditional MPC formula.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"155 ","pages":"Article 103542"},"PeriodicalIF":3.9,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145097508","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 : 2025-09-13 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":"2025-09-13","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