Journal of Process Control最新文献_第4页

Prescribed performance based direct data-driven model predictive control for continuous stirred tank reactor 基于预定性能的连续搅拌槽式反应器直接数据驱动模型预测控制

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

Journal of Process Control

Pub Date : 2026-01-01 Epub Date: 2025-12-19 DOI: 10.1016/j.jprocont.2025.103609

Chengyu Zhou , Li Jia , Jianfang Li

Continuous stirred tank reactor (CSTR) is the most important and widely used reaction equipment in the process industry. The use of an indirect data-driven model predictive control (MPC) plays an important role in controlling the key variable in the CSTR system. However, because of the complex nonlinear dynamics in the reaction process, the existing indirect data-driven MPC strategies are always unable to avoid the problem of unmodeled dynamics, resulting in the inability to ensure the control performance of the system. To this end, this paper designs a new direct data-driven model predictive control (DDMPC) method for the CSTR system under the prescribed performance control (PPC) framework. Using dynamic linearization technology, a converted-output-based equivalent data-driven prediction model in the input–output sense to the original CSTR system is first established to deal with the unknown system dynamics under performance constraints. Then, a prescribed performance function and the converted-output-based data-driven prediction model are directly incorporated into the criterion function to derive the constraint MPC control scheme, which achieves the prescribed performance requirements of the system. Furthermore, the stability of the tracking error and the bounded-input-bounded-output (BIBO) are rigorously proved based on the contractive mapping principle. As a result, the resulting DDMPC control scheme only requires the input and output data of the controlled CSTR system without any explicit model information. In the end, the effectiveness and superiority of the developed control method are demonstrated by a nonlinear CSTR system.

连续搅拌槽式反应器（CSTR）是过程工业中最重要、应用最广泛的反应设备。间接数据驱动模型预测控制（MPC）在CSTR系统的关键变量控制中起着重要的作用。然而，由于反应过程中存在复杂的非线性动力学，现有的间接数据驱动MPC策略总是无法避免未建模的动力学问题，导致无法保证系统的控制性能。为此，本文设计了一种在规定性能控制（PPC）框架下的CSTR系统直接数据驱动模型预测控制（DDMPC）方法。利用动态线性化技术，首先建立了基于转换输出的原CSTR系统输入输出意义上的等效数据驱动预测模型，以处理性能约束下未知的系统动态。然后，将规定的性能函数和基于转换输出的数据驱动预测模型直接纳入准则函数，推导出约束MPC控制方案，使系统达到规定的性能要求。此外，基于压缩映射原理，严格证明了跟踪误差和有界输入-有界输出（BIBO）的稳定性。因此，得到的DDMPC控制方案只需要被控CSTR系统的输入和输出数据，不需要任何显式的模型信息。最后，通过一个非线性CSTR系统验证了所提控制方法的有效性和优越性。

{"title":"Prescribed performance based direct data-driven model predictive control for continuous stirred tank reactor","authors":"Chengyu Zhou , Li Jia , Jianfang Li","doi":"10.1016/j.jprocont.2025.103609","DOIUrl":"10.1016/j.jprocont.2025.103609","url":null,"abstract":"<div><div>Continuous stirred tank reactor (CSTR) is the most important and widely used reaction equipment in the process industry. The use of an indirect data-driven model predictive control (MPC) plays an important role in controlling the key variable in the CSTR system. However, because of the complex nonlinear dynamics in the reaction process, the existing indirect data-driven MPC strategies are always unable to avoid the problem of unmodeled dynamics, resulting in the inability to ensure the control performance of the system. To this end, this paper designs a new direct data-driven model predictive control (DDMPC) method for the CSTR system under the prescribed performance control (PPC) framework. Using dynamic linearization technology, a converted-output-based equivalent data-driven prediction model in the input–output sense to the original CSTR system is first established to deal with the unknown system dynamics under performance constraints. Then, a prescribed performance function and the converted-output-based data-driven prediction model are directly incorporated into the criterion function to derive the constraint MPC control scheme, which achieves the prescribed performance requirements of the system. Furthermore, the stability of the tracking error and the bounded-input-bounded-output (BIBO) are rigorously proved based on the contractive mapping principle. As a result, the resulting DDMPC control scheme only requires the input and output data of the controlled CSTR system without any explicit model information. In the end, the effectiveness and superiority of the developed control method are demonstrated by a nonlinear CSTR system.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"157 ","pages":"Article 103609"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145797809","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

Dry biomass estimation in production of insects larvae using Interconnected Generalized Super-Twisting Observer 利用互联广义超扭观测器估算昆虫幼虫生产中的干生物量

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

Journal of Process Control

Pub Date : 2026-01-01 Epub Date: 2025-12-31 DOI: 10.1016/j.jprocont.2025.103615

Rania Tafat , Jaime A. Moreno , Stefan Streif

Alternative protein sources are becoming essential for achieving a sustainable food system. The Black Soldier Fly larvae (BSFL), a protein-rich insect capable of feeding on a wide range of organic materials, shows immense potential for use in bio-conversion. It is already being used in poultry and fish aquaculture and is currently under evaluation for human consumption. Consequently, the farming of this insect is of great interest, and advanced control methods could significantly optimize the process and improve resource efficiency. One of the main challenges in applying these advanced techniques is the lack of information about certain critical system states, particularly the estimation of dry biomass weight. Measuring the dry biomass weight of the larvae is a destructive process that can only be performed at the beginning and end of the cycle. This low sampling frequency is insufficient for the application of advanced control strategies. Thus, a non-invasive estimation method is required. This work addresses the observer design problem for estimating the dry biomass weight of BSFL. The objective is to obtain an online estimation of this weight before the larvae reach maturity. To achieve this, a reduced version of the existing BSFL full-fledged model is proposed, based on specific assumptions. A subsystem is extracted from this BSFL reduced model, for which, a necessary and sufficient condition is provided for its global strong observability. Moreover, an interconnection of Generalized Super-Twisting Observers is designed, and a comparison is made between this method and the high-gain observer.

替代蛋白质来源对于实现可持续粮食系统至关重要。黑兵蝇幼虫（BSFL）是一种富含蛋白质的昆虫，能够以多种有机材料为食，在生物转化方面显示出巨大的潜力。它已用于家禽和鱼类水产养殖，目前正在评估是否供人食用。因此，这种昆虫的养殖具有重要意义，先进的控制方法可以显着优化过程并提高资源效率。应用这些先进技术的主要挑战之一是缺乏关于某些关键系统状态的信息，特别是对干生物量重量的估计。测量幼虫的干生物量重量是一个破坏性的过程，只能在周期的开始和结束时进行。这种低采样频率不足以应用先进的控制策略。因此，需要一种非侵入性的估计方法。这项工作解决了估计BSFL干生物量重量的观察者设计问题。目的是在幼虫成熟之前获得该重量的在线估计。为了实现这一目标，基于特定的假设，提出了现有BSFL全功能模型的简化版本。从该BSFL简化模型中提取了一个子系统，并给出了其全局强可观测性的充分必要条件。设计了一种广义超扭观测器的互连方法，并与高增益观测器进行了比较。

{"title":"Dry biomass estimation in production of insects larvae using Interconnected Generalized Super-Twisting Observer","authors":"Rania Tafat , Jaime A. Moreno , Stefan Streif","doi":"10.1016/j.jprocont.2025.103615","DOIUrl":"10.1016/j.jprocont.2025.103615","url":null,"abstract":"<div><div>Alternative protein sources are becoming essential for achieving a sustainable food system. The Black Soldier Fly larvae (BSFL), a protein-rich insect capable of feeding on a wide range of organic materials, shows immense potential for use in bio-conversion. It is already being used in poultry and fish aquaculture and is currently under evaluation for human consumption. Consequently, the farming of this insect is of great interest, and advanced control methods could significantly optimize the process and improve resource efficiency. One of the main challenges in applying these advanced techniques is the lack of information about certain critical system states, particularly the estimation of dry biomass weight. Measuring the dry biomass weight of the larvae is a destructive process that can only be performed at the beginning and end of the cycle. This low sampling frequency is insufficient for the application of advanced control strategies. Thus, a non-invasive estimation method is required. This work addresses the observer design problem for estimating the dry biomass weight of BSFL. The objective is to obtain an online estimation of this weight before the larvae reach maturity. To achieve this, a reduced version of the existing BSFL full-fledged model is proposed, based on specific assumptions. A subsystem is extracted from this BSFL reduced model, for which, a necessary and sufficient condition is provided for its global strong observability. Moreover, an interconnection of Generalized Super-Twisting Observers is designed, and a comparison is made between this method and the high-gain observer.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"157 ","pages":"Article 103615"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145884228","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 physical activity detection module during sensor augmented insulin pump therapy 传感器增强胰岛素泵治疗过程中的实时身体活动检测模块

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

Journal of Process Control

Pub Date : 2026-01-01 Epub Date: 2025-12-29 DOI: 10.1016/j.jprocont.2025.103608

Eleonora Manzoni , Emilia Fushimi , Eleonora M. Aiello , Zoey Li , Robin Gal , Corby K. Martin , Susana R. Patton , Simone Del Favero , Francis J. Doyle III

Individuals living with type 1 diabetes (T1D) face important challenges when engaging in physical activity (PA), as it necessitates careful management of blood glucose levels often through insulin adjustments and carbohydrate intake. Integrating PA detection into sensor augmented insulin pumps (SAP) is a promising strategy to enhance glycemic control by suggesting basal insulin reduction or carbohydrate ingestion in the critical 24 h after the PA detection.

We have developed a real-time, model-based module for PA detection based solely on measured glucose levels, insulin infusion rates, and carbohydrate intake. The approach is based on the monitoring of the magnitude as well as various statistical properties of the prediction residuals, i.e., the discrepancies between actual sensor-measured glucose levels and model-predicted levels.

We tested our algorithm on the Type 1 Diabetes and Exercise Initiative (T1DEXI) dataset, which includes structured sessions of aerobic, resistance, and interval exercises. In a dataset containing all three activity types, the detection approach based on the median of the prediction residuals successfully detected an average of 59% of PA instances, while keeping the false alarms to 3.5 per considered timeframe, when considering models tailored to each participant. When using a population model identified on in-silico data from the UVa/Padova T1D simulator, the approach successfully detected 62% of PAs, while keeping the false alarms to 3.6 per considered timeframe.

These encouraging findings open the possibility of integrating PA detection into SAP systems without the need for additional physiological signals, thus enabling improved glucose management.

1型糖尿病（T1D）患者在进行体育活动（PA）时面临着重要的挑战，因为它需要经常通过胰岛素调节和碳水化合物摄入来仔细管理血糖水平。将PA检测整合到传感器增强胰岛素泵（SAP）中是一种很有前景的策略，通过提示在PA检测后关键的24小时内基础胰岛素减少或碳水化合物摄入来加强血糖控制。我们开发了一个实时的、基于模型的模块，用于仅根据测量的葡萄糖水平、胰岛素输注率和碳水化合物摄入量检测PA。该方法基于对预测残差的大小和各种统计特性的监测，即传感器实际测量的葡萄糖水平与模型预测的水平之间的差异。我们在1型糖尿病和运动倡议（T1DEXI）数据集上测试了我们的算法，该数据集包括有氧、阻力和间歇运动的结构化会话。在包含所有三种活动类型的数据集中，基于预测残差中位数的检测方法成功地检测了平均59%的PA实例，同时在考虑为每个参与者定制的模型时，将每个考虑的时间框架的假警报保持在3.5。当使用来自UVa/Padova T1D模拟器的计算机数据识别的种群模型时，该方法成功检测到62%的pa，同时将每个考虑的时间范围内的假警报保持在3.6。这些令人鼓舞的发现开启了将PA检测整合到SAP系统的可能性，而不需要额外的生理信号，从而改善葡萄糖管理。

{"title":"Real-time physical activity detection module during sensor augmented insulin pump therapy","authors":"Eleonora Manzoni , Emilia Fushimi , Eleonora M. Aiello , Zoey Li , Robin Gal , Corby K. Martin , Susana R. Patton , Simone Del Favero , Francis J. Doyle III","doi":"10.1016/j.jprocont.2025.103608","DOIUrl":"10.1016/j.jprocont.2025.103608","url":null,"abstract":"<div><div>Individuals living with type 1 diabetes (T1D) face important challenges when engaging in physical activity (PA), as it necessitates careful management of blood glucose levels often through insulin adjustments and carbohydrate intake. Integrating PA detection into sensor augmented insulin pumps (SAP) is a promising strategy to enhance glycemic control by suggesting basal insulin reduction or carbohydrate ingestion in the critical 24 h after the PA detection.</div><div>We have developed a real-time, model-based module for PA detection based solely on measured glucose levels, insulin infusion rates, and carbohydrate intake. The approach is based on the monitoring of the magnitude as well as various statistical properties of the prediction residuals, i.e., the discrepancies between actual sensor-measured glucose levels and model-predicted levels.</div><div>We tested our algorithm on the Type 1 Diabetes and Exercise Initiative (T1DEXI) dataset, which includes structured sessions of aerobic, resistance, and interval exercises. In a dataset containing all three activity types, the detection approach based on the median of the prediction residuals successfully detected an average of 59% of PA instances, while keeping the false alarms to 3.5 per considered timeframe, when considering models tailored to each participant. When using a population model identified on in-silico data from the UVa/Padova T1D simulator, the approach successfully detected 62% of PAs, while keeping the false alarms to 3.6 per considered timeframe.</div><div>These encouraging findings open the possibility of integrating PA detection into SAP systems without the need for additional physiological signals, thus enabling improved glucose management.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"157 ","pages":"Article 103608"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145884230","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

Robust soft sensing with causal and injectivity-preserving Graph Neural Network 基于因果保注入图神经网络的鲁棒软检测

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

Journal of Process Control

Pub Date : 2026-01-01 Epub Date: 2025-12-27 DOI: 10.1016/j.jprocont.2025.103614

Warren Acheampong , Om Prakash , Biao Huang

Graph Neural Networks (GNNs) excel in soft sensing by effectively modeling complex interdependencies among process variables. This study presents a graph-based framework for improved process quality prediction in nonlinear, dynamic industrial systems. We address two key challenges in chemical process soft sensing: (i) unknown graphs where the structure is not available a priori, and (ii) injectivity issues from scalar features. To resolve non-injective aggregation, where distinct neighborhoods become indistinguishable, we expand the input domain to preserve structural uniqueness in both undirected and directed graphs. We also propose a method for learning directed graphs using Sparse Debiased Dynamic Mode Decomposition, which captures temporal dynamics and produces sparse, interpretable, and noise-resilient representations. An end-to-end framework jointly learns the graph structure and GNN parameters, allowing the graph to adapt during training based on the prediction task. The proposed methods are validated through simulations under varying noise levels and a benchmark case study involving a Sulfur Recovery Unit, demonstrating strong robustness and predictive performance.

图神经网络（gnn）通过有效地模拟过程变量之间复杂的相互依赖关系，在软测量方面表现出色。本研究提出了一个基于图的框架，用于改进非线性动态工业系统的过程质量预测。我们解决了化学过程软测量中的两个关键挑战：(i)结构不可先验的未知图，以及（ii）标量特征的注入性问题。为了解决非内射聚集问题，我们扩展了输入域以保持无向图和有向图的结构唯一性。我们还提出了一种使用稀疏去偏动态模式分解学习有向图的方法，该方法捕获时间动态并产生稀疏、可解释和抗噪声的表示。端到端框架共同学习图结构和GNN参数，允许图在训练过程中根据预测任务进行适应。通过不同噪声水平下的模拟和涉及硫回收装置的基准案例研究，验证了所提出的方法的鲁棒性和预测性能。

{"title":"Robust soft sensing with causal and injectivity-preserving Graph Neural Network","authors":"Warren Acheampong , Om Prakash , Biao Huang","doi":"10.1016/j.jprocont.2025.103614","DOIUrl":"10.1016/j.jprocont.2025.103614","url":null,"abstract":"<div><div>Graph Neural Networks (GNNs) excel in soft sensing by effectively modeling complex interdependencies among process variables. This study presents a graph-based framework for improved process quality prediction in nonlinear, dynamic industrial systems. We address two key challenges in chemical process soft sensing: (i) unknown graphs where the structure is not available <em>a priori</em>, and (ii) injectivity issues from scalar features. To resolve non-injective aggregation, where distinct neighborhoods become indistinguishable, we expand the input domain to preserve structural uniqueness in both undirected and directed graphs. We also propose a method for learning directed graphs using Sparse Debiased Dynamic Mode Decomposition, which captures temporal dynamics and produces sparse, interpretable, and noise-resilient representations. An end-to-end framework jointly learns the graph structure and GNN parameters, allowing the graph to adapt during training based on the prediction task. The proposed methods are validated through simulations under varying noise levels and a benchmark case study involving a Sulfur Recovery Unit, demonstrating strong robustness and predictive performance.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"157 ","pages":"Article 103614"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145840842","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

Least squares and marginal log-likelihood model predictive control using normalizing flows 使用归一化流的最小二乘和边际对数似然模型预测控制

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

Journal of Process Control

Pub Date : 2025-12-01 Epub Date: 2025-11-21 DOI: 10.1016/j.jprocont.2025.103593

Eike Cramer

Real-world (bio)chemical processes often exhibit stochastic dynamics with non-trivial correlations and state-dependent fluctuations. Model predictive control (MPC) often must consider these fluctuations to achieve reliable performance. However, most process models simply add stationary noise terms to a deterministic prediction. This work proposes using conditional normalizing flows as discrete-time models to learn stochastic dynamics. Normalizing flows learn the probability density function (PDF) of the states explicitly, given prior states and control inputs. In addition to standard least squares (LSQ) objectives, this work derives a marginal log-likelihood (MLL) objective based on the explicit PDF and Markov chain simulations. In a reactor study, the normalizing flow MPC setpoint errors in open and closed-loop cases are competitive with a full model-based stochastic MPC. Furthermore, the chance constraints lead to fewer constraint violations than the benchmark controller. The MLL objective yields slightly more stable optimization results than the LSQ, particularly for small scenario sets.

现实世界（生物）化学过程通常表现出具有非平凡相关性和状态依赖波动的随机动力学。模型预测控制（MPC）通常必须考虑这些波动才能获得可靠的性能。然而，大多数过程模型只是将平稳噪声项添加到确定性预测中。这项工作提出使用条件归一化流作为离散时间模型来学习随机动力学。在给定先验状态和控制输入的情况下，规范化流明确地学习状态的概率密度函数（PDF）。除了标准最小二乘（LSQ）目标之外，本工作还基于显式PDF和马尔可夫链模拟导出了边际对数似然（MLL）目标。在反应器研究中，开环和闭环情况下的归一化流MPC设定值误差与基于全模型的随机MPC具有竞争性。此外，机会约束比基准控制器导致更少的约束违规。MLL目标比LSQ产生更稳定的优化结果，特别是对于小场景集。

引用次数: 0

Bioprocess model-predictive control with physics-informed neural networks: Driving microbiome evolution toward high polyhydroxyalkanoates production capacity 生物过程模型预测控制与物理信息神经网络：推动微生物群向高聚羟基烷酸酯生产能力的进化

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

Journal of Process Control

Pub Date : 2025-12-01 Epub Date: 2025-11-21 DOI: 10.1016/j.jprocont.2025.103594

Marta Catalão , José Pinto , Cristiana A.V. Torres , Filomena Freitas , Maria A.M. Reis , Rafael S. Costa , Rui Oliveira

Many previous studies have investigated the economic production of polyhydroxyalkanoates (PHA) by natural microbiomes. A key underlying strategy is the feast and famine (F/F) feeding regimen for bacteria selection. For this purpose, a sequencing batch reactor (SBR) is commonly operated in a sequence of F/F cycles until an evolved microbiome is attained with high PHA storage capacity. The effectiveness of this process is critically dependent on control parameters such as the hydraulic retention time (HRT), organic loading rate (OLR) and carbon-to-nitrogen ratio (C/N) applied at each cycle. This study evaluates for the first time a physics-informed neural network (PINN) for model predictive control (MPC) of microbiome evolution in a SBR. A PINN model was trained on historical data collected in a SBR operated over 93 days and 31 cycles. Carbon (acetate), Nitrogen (ammonium), Volatile Suspended Solids (VSS) and intracellular PHA concentration data were used to train and validate the PINN. Subsequently, a second SBR experiment was conducted under automatic control of the PINN over a period of 36 days and 12 cycles. A transfer learning method was implemented leverage on in-process data to minimize process-model mismatch. The results showed a systematic cycle-to-cycle prediction error decrease. The intracellular PHA concentration systematic increased from 0.51 % (w/w) to 16.5 % (w/w) at the 12th cycle (32-fold increase). The final evolved microbiome, collected at the 12th cycle, was inoculated in a production reactor yielding a final intracellular PHA content of 52.86 % (w/w) and volumetric concentration of 8.93 g PHA/L. Overall, the PINN-MPC method has shown high potential to efficiently explore the reactor design space and to implement in autonomy efficient strategies for natural microbiome evolution.

许多先前的研究已经研究了天然微生物群对聚羟基烷酸酯（PHA）的经济生产。一个关键的潜在策略是细菌选择的盛宴和饥荒（F/F）喂养方案。为此目的，测序间歇式反应器（SBR）通常以F/F循环的顺序运行，直到进化的微生物组达到具有高PHA存储能力。该工艺的有效性主要取决于控制参数，如水力停留时间（HRT）、有机载荷率（OLR）和碳氮比（C/N）。本研究首次评估了用于SBR微生物组进化模型预测控制（MPC）的物理信息神经网络（PINN）。根据SBR运行93天31个周期收集的历史数据，对PINN模型进行了训练。碳（乙酸）、氮（铵）、挥发性悬浮物（VSS）和细胞内PHA浓度数据用于训练和验证PINN。随后，在PINN自动控制下进行第二次SBR实验，为期36天，12个周期。利用进程内数据实现迁移学习方法，最大限度地减少过程模型不匹配。结果表明，系统的周期间预测误差减小。第12个循环时，细胞内PHA浓度从0.51 % （w/w）增加到16.5 % (w/w)，增加了32倍。在第12个循环中收集最终进化的微生物组，在生产反应器中接种，最终细胞内PHA含量为52.86 % (w/w)，体积浓度为8.93 g PHA/L。总体而言，PINN-MPC方法在有效探索反应器设计空间和实现自然微生物群进化的自主高效策略方面显示出很高的潜力。

{"title":"Bioprocess model-predictive control with physics-informed neural networks: Driving microbiome evolution toward high polyhydroxyalkanoates production capacity","authors":"Marta Catalão , José Pinto , Cristiana A.V. Torres , Filomena Freitas , Maria A.M. Reis , Rafael S. Costa , Rui Oliveira","doi":"10.1016/j.jprocont.2025.103594","DOIUrl":"10.1016/j.jprocont.2025.103594","url":null,"abstract":"<div><div>Many previous studies have investigated the economic production of polyhydroxyalkanoates (PHA) by natural microbiomes. A key underlying strategy is the feast and famine (F/F) feeding regimen for bacteria selection. For this purpose, a sequencing batch reactor (SBR) is commonly operated in a sequence of F/F cycles until an evolved microbiome is attained with high PHA storage capacity. The effectiveness of this process is critically dependent on control parameters such as the hydraulic retention time (HRT), organic loading rate (OLR) and carbon-to-nitrogen ratio (C/N) applied at each cycle. This study evaluates for the first time a physics-informed neural network (PINN) for model predictive control (MPC) of microbiome evolution in a SBR. A PINN model was trained on historical data collected in a SBR operated over 93 days and 31 cycles. Carbon (acetate), Nitrogen (ammonium), Volatile Suspended Solids (VSS) and intracellular PHA concentration data were used to train and validate the PINN. Subsequently, a second SBR experiment was conducted under automatic control of the PINN over a period of 36 days and 12 cycles. A transfer learning method was implemented leverage on in-process data to minimize process-model mismatch. The results showed a systematic cycle-to-cycle prediction error decrease. The intracellular PHA concentration systematic increased from 0.51 % (w/w) to 16.5 % (w/w) at the 12th cycle (32-fold increase). The final evolved microbiome, collected at the 12th cycle, was inoculated in a production reactor yielding a final intracellular PHA content of 52.86 % (w/w) and volumetric concentration of 8.93 g PHA/L. Overall, the PINN-MPC method has shown high potential to efficiently explore the reactor design space and to implement in autonomy efficient strategies for natural microbiome evolution.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"156 ","pages":"Article 103594"},"PeriodicalIF":3.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145571421","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

Dynamic compensation of the threading speed drop in rolling processes: Bayesian optimization of the roughing and finishing mill 轧制过程中螺纹速度下降的动态补偿：粗精轧机的贝叶斯优化

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

Journal of Process Control

Pub Date : 2025-12-01 Epub Date: 2025-10-31 DOI: 10.1016/j.jprocont.2025.103579

Johannes Reinhard , Klaus Löhe , Sebastian Kallabis , Knut Graichen

This paper introduces an advanced approach for dynamic speed drop compensation during threading in rolling processes. The approach combines a data-driven machine learning procedure with a recently presented flatness-based feedforward control to robustly compensate for the speed drop. The feedforward control design accelerates both the rolls and the drivetrain, ensuring that the acceleration torque matches the rolling torque during threading, while maintaining the roll at the desired target speed. Ideally, this prevents the speed drop and enhances the quality and stability of the rolling process. The dynamic speed drop compensation approach is extended in this paper to optimize all stands of a rolling mill, finishing mill as well as roughing mill. To achieve this, the flatness-based feedforward trajectories are adapted to account for uncertainties in the threading event. Moreover, a cost function dependent on optimization parameters is established to optimize the dynamic speed drop compensation. This optimization is carried out using Bayesian Optimization with a Gaussian Process as surrogate model. Both the feedforward control and the Bayesian Optimization run in real-time on an industrial Programmable Logic Controller (PLC). Extensive experimental validation on a hot strip finishing mill, including both the roughing and finishing mill, demonstrates the superior performance of this approach across various key performance indicators in comparison to standard compensation methods.

介绍了一种轧钢螺纹加工过程中动态降速补偿的先进方法。该方法将数据驱动的机器学习过程与最近提出的基于平面度的前馈控制相结合，以鲁棒地补偿速度下降。前馈控制设计使滚道和传动系统同时加速，确保加速扭矩与滚道扭矩匹配，同时使滚道保持在预期的目标速度。理想情况下，这可以防止速度下降，提高轧制过程的质量和稳定性。本文将动态降速补偿方法推广到轧机、精轧机和粗轧机的全机架优化中。为了实现这一点，基于平面度的前馈轨迹适应于考虑线程事件中的不确定性。建立了依赖于优化参数的代价函数，对动态降速补偿进行了优化。该优化是用高斯过程作为代理模型的贝叶斯优化来实现的。前馈控制和贝叶斯优化都在工业可编程控制器（PLC）上实时运行。在热轧带钢精轧机（包括粗轧和精轧机）上进行的大量实验验证表明，与标准补偿方法相比，该方法在各种关键性能指标上具有优越的性能。

{"title":"Dynamic compensation of the threading speed drop in rolling processes: Bayesian optimization of the roughing and finishing mill","authors":"Johannes Reinhard , Klaus Löhe , Sebastian Kallabis , Knut Graichen","doi":"10.1016/j.jprocont.2025.103579","DOIUrl":"10.1016/j.jprocont.2025.103579","url":null,"abstract":"<div><div>This paper introduces an advanced approach for dynamic speed drop compensation during threading in rolling processes. The approach combines a data-driven machine learning procedure with a recently presented flatness-based feedforward control to robustly compensate for the speed drop. The feedforward control design accelerates both the rolls and the drivetrain, ensuring that the acceleration torque matches the rolling torque during threading, while maintaining the roll at the desired target speed. Ideally, this prevents the speed drop and enhances the quality and stability of the rolling process. The dynamic speed drop compensation approach is extended in this paper to optimize all stands of a rolling mill, finishing mill as well as roughing mill. To achieve this, the flatness-based feedforward trajectories are adapted to account for uncertainties in the threading event. Moreover, a cost function dependent on optimization parameters is established to optimize the dynamic speed drop compensation. This optimization is carried out using Bayesian Optimization with a Gaussian Process as surrogate model. Both the feedforward control and the Bayesian Optimization run in real-time on an industrial Programmable Logic Controller (PLC). Extensive experimental validation on a hot strip finishing mill, including both the roughing and finishing mill, demonstrates the superior performance of this approach across various key performance indicators in comparison to standard compensation methods.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"156 ","pages":"Article 103579"},"PeriodicalIF":3.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145420506","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

Model predictive control of pressure-swing distillation via closed-loop system identification 基于闭环系统辨识的变压蒸馏模型预测控制

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

Journal of Process Control

Pub Date : 2025-12-01 Epub Date: 2025-11-10 DOI: 10.1016/j.jprocont.2025.103589

Daye Yang , Jingcheng Wang , Naiyi Ban , Yanjiu Zhong , David Shan-Hill Wong , Abolhassan Razminia , Chengtian Cui

Pressure-swing distillation (PSD) is a proven technique for separating azeotropic mixtures by exploiting pressure-dependent shifts in azeotropic composition. Despite its efficacy, PSD systems present significant control challenges due to inherent nonlinearities, complex multivariable interactions, and internal recycle loops. This study proposes a model predictive control (MPC) framework for PSD systems, founded on closed-loop system identification. A comprehensive plantwide nonlinear dynamic model of a PSD process for separating a maximum-boiling azeotrope of acetone and chloroform is developed using Aspen Dynamics and interfaced with MATLAB/Simulink for controller design and testing. To address the limitations of open-loop excitation in systems with recycles, pseudo-random binary sequence (PRBS) signals are applied under closed-loop operation to sufficiently excite the process. Subsequently, linear state-space models are identified using the prediction error method. Based on these models, two MPC configurations are developed: temperature control (TC) and composition–temperature cascade control (CC–TC). Simulation results demonstrate that the proposed MPC strategies quantitatively outperform proportional–integral (PI) controllers. Specifically, under the TC strategy, the total integral of absolute error (IAE) values of

X_{D 1, A C E}

and

X_{D 2, C H L}

are reduced by approximately 10% and 3%, respectively; while under the CC–TC strategy, the reductions reach about 26% and 55%. Moreover, across four disturbance scenarios, the steady convergence times of both composition purities are shortened by more than 5 h compared with PI controllers. These results highlight the advantages of the proposed MPC strategies in disturbance rejection and transient product quality regulation. These findings underscore the effectiveness of closed-loop system identification as a basis for advanced control of PSD processes.

变压蒸馏（PSD）是一种成熟的分离共沸混合物的技术，它利用了共沸成分的压力相关变化。尽管PSD系统很有效，但由于其固有的非线性、复杂的多变量相互作用和内部循环循环，PSD系统在控制方面存在重大挑战。本文提出了一种基于闭环辨识的PSD系统模型预测控制框架。利用Aspen Dynamics软件建立了丙酮和氯仿最高沸点共沸物PSD分离过程的全厂非线性动力学模型，并结合MATLAB/Simulink进行了控制器设计和测试。为了解决循环系统开环激励的局限性，在闭环操作下应用伪随机二值序列（PRBS）信号来充分激励过程。然后，利用预测误差法对线性状态空间模型进行识别。基于这些模型，提出了两种MPC配置：温度控制（TC）和成分-温度级联控制（CC-TC）。仿真结果表明，所提出的MPC策略在数量上优于比例积分（PI）控制器。具体而言，在TC策略下，XD1、ACE和XD2的绝对误差（IAE）值的总积分，CHL分别降低了约10%和3%；而在CC-TC战略下，减排幅度分别达到26%和55%左右。此外，在四种干扰情况下，与PI控制器相比，两种组合纯度的稳定收敛时间缩短了5小时以上。这些结果突出了所提出的MPC策略在干扰抑制和瞬态产品质量调节方面的优势。这些发现强调了闭环系统识别作为PSD过程高级控制基础的有效性。

{"title":"Model predictive control of pressure-swing distillation via closed-loop system identification","authors":"Daye Yang , Jingcheng Wang , Naiyi Ban , Yanjiu Zhong , David Shan-Hill Wong , Abolhassan Razminia , Chengtian Cui","doi":"10.1016/j.jprocont.2025.103589","DOIUrl":"10.1016/j.jprocont.2025.103589","url":null,"abstract":"<div><div>Pressure-swing distillation (PSD) is a proven technique for separating azeotropic mixtures by exploiting pressure-dependent shifts in azeotropic composition. Despite its efficacy, PSD systems present significant control challenges due to inherent nonlinearities, complex multivariable interactions, and internal recycle loops. This study proposes a model predictive control (MPC) framework for PSD systems, founded on closed-loop system identification. A comprehensive plantwide nonlinear dynamic model of a PSD process for separating a maximum-boiling azeotrope of acetone and chloroform is developed using Aspen Dynamics and interfaced with MATLAB/Simulink for controller design and testing. To address the limitations of open-loop excitation in systems with recycles, pseudo-random binary sequence (PRBS) signals are applied under closed-loop operation to sufficiently excite the process. Subsequently, linear state-space models are identified using the prediction error method. Based on these models, two MPC configurations are developed: temperature control (TC) and composition–temperature cascade control (CC–TC). Simulation results demonstrate that the proposed MPC strategies quantitatively outperform proportional–integral (PI) controllers. Specifically, under the TC strategy, the total integral of absolute error (IAE) values of <span><math><msub><mrow><mi>X</mi></mrow><mrow><mi>D</mi><mn>1</mn><mo>,</mo><mi>A</mi><mi>C</mi><mi>E</mi></mrow></msub></math></span> and <span><math><msub><mrow><mi>X</mi></mrow><mrow><mi>D</mi><mn>2</mn><mo>,</mo><mi>C</mi><mi>H</mi><mi>L</mi></mrow></msub></math></span> are reduced by approximately 10% and 3%, respectively; while under the CC–TC strategy, the reductions reach about 26% and 55%. Moreover, across four disturbance scenarios, the steady convergence times of both composition purities are shortened by more than 5 h compared with PI controllers. These results highlight the advantages of the proposed MPC strategies in disturbance rejection and transient product quality regulation. These findings underscore the effectiveness of closed-loop system identification as a basis for advanced control of PSD processes.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"156 ","pages":"Article 103589"},"PeriodicalIF":3.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145520304","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

Adaptive ensemble reinforcement learning for industrial process control 工业过程控制中的自适应集成强化学习

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

Journal of Process Control

Pub Date : 2025-12-01 Epub Date: 2025-11-01 DOI: 10.1016/j.jprocont.2025.103575

Soroush Rastegarpour, Hamid Reza Feyzmahdavian, Alf J. Isaksson

Reinforcement learning (RL) has shown significant promise in optimizing control strategies for industrial processes. However, maintaining robustness and stability remains a critical challenge, especially in continuous-time systems affected by uncertainties and nonlinearities. This paper introduces an Adaptive Ensemble RL framework that improves control performance and robustness by dynamically integrating multiple process models. Instead of relying on a fixed model ensemble, we employ a deep neural network to predict optimal weighting factors for combining models based on input-state conditions during training. This adaptive strategy refines the representation of system dynamics, improving robustness against disturbances and model mismatches. We validate the proposed framework using a continuous stirred tank reactor (CSTR) benchmark, showing improved robustness, faster convergence, and reduced performance degradation under varying uncertainties compared to existing methods.

强化学习（RL）在优化工业过程控制策略方面显示出巨大的前景。然而，保持鲁棒性和稳定性仍然是一个关键的挑战，特别是在受不确定性和非线性影响的连续时间系统中。本文介绍了一种自适应集成RL框架，该框架通过动态集成多个过程模型来提高控制性能和鲁棒性。在训练过程中，我们使用深度神经网络来预测基于输入状态条件的组合模型的最优权重因子，而不是依赖于固定的模型集合。这种自适应策略改进了系统动力学的表示，提高了对干扰和模型不匹配的鲁棒性。我们使用连续搅拌槽反应器（CSTR）基准验证了所提出的框架，与现有方法相比，在不同的不确定性下，该框架具有更好的鲁棒性，更快的收敛速度和更少的性能退化。

引用次数: 0

Exponential admissibility and control for singular LPV-PDE systems with application to chemical tubular reactor 广义LPV-PDE系统的指数容许性与控制及其在化工管式反应器中的应用

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

Journal of Process Control

Pub Date : 2025-12-01 Epub Date: 2025-11-15 DOI: 10.1016/j.jprocont.2025.103590

Xiaona Song , Ao Shang , Shuai Song , Danjing Zheng , Choon Ki Ahn

In this work, the issue of exponential admissibility analysis and controller designs for the singular linear parameter-varying partial differential equation (LPV-PDE) system is investigated. First, the reaction process in the chemical tubular reactor is described by a singular LPV-PDE, and the definition for the singular LPV-PDE system to be exponentially admissible is established by the Galerkin method, energy estimates, etc. Second, the parameter-dependent fuzzy dynamic event-triggered mechanism is developed to alleviate communication pressure by reducing the amount of transmitted data. Furthermore, a sliding surface is constructed, then a suitable control law is designed to ensure the reachability of system states, and sufficient conditions for the singular LPV-PDE system to be exponentially admissible are given during the sliding phase. Finally, the effectiveness of the proposed method is verified through simulation studies.

本文研究奇异线性变参数偏微分方程（LPV-PDE）系统的指数容许性分析和控制器设计问题。首先，用奇异LPV-PDE来描述化学管式反应器中的反应过程，并通过伽辽金方法、能量估计等建立了奇异LPV-PDE系统指数可容许的定义。其次，提出了参数依赖模糊动态事件触发机制，通过减少传输数据量来缓解通信压力。在此基础上，构造了一个滑动曲面，设计了适当的控制律以保证系统状态的可达性，并给出了在滑动阶段奇异LPV-PDE系统指数可容许的充分条件。最后，通过仿真研究验证了所提方法的有效性。

引用次数: 0