Journal of Process Control最新文献

{"title":"Trustworthy data-driven model predictive control using a hybrid model with monitoring and adaptation of the domain of validity","authors":"Mohamed Elsheikh ,&nbsp;Yak Ortmanns ,&nbsp;Felix Hecht ,&nbsp;Volker Roßmann ,&nbsp;Stefan Krämer ,&nbsp;Sebastian Engell","doi":"10.1016/j.jprocont.2025.103496","DOIUrl":"10.1016/j.jprocont.2025.103496","url":null,"abstract":"<div><div>The quality of the plant model is a key factor for a successful implementation of model predictive control schemes. An inaccurate process model can result in unsatisfactory dynamics of the controlled system and may lead to violations of quality and safety constraints or even instability. Building reliable models that are based on physics and chemistry can be challenging in practice due to the difficulty of accurately modeling all aspects of the real system, and there will always be discrepancies between the model and the behavior of the real plant. Recently, there has been a renewed research trend to use or incorporate data-driven models that are obtained by machine learning algorithms into model predictive control (MPC). However, developing reliable standalone data-driven models needs large sets of training data that are obtained for sufficiently rich excitation of the system which are not often available in practice. A promising direction to overcome this issue is the use of hybrid process models which combine models based on first-principles and data-based elements. In this work, we present and evaluate a nonlinear model predictive control approach based on a hybrid model that is formed of a simplified first-principles model and a data-based model to capture the dynamics that are not adequately represented in the semi-rigorous model. In order to increase the reliability of the hybrid model, the domain of validity of the data-based model element is monitored and the contribution of the data-based model component is faded out when the plant is not operated in the region where sufficient data had been collected. Moreover it is proposed to adapt the domain of validity of the data-based component based on the measured data during operation. An extensive simulation study of an industrial control problem using a faithful simulation model is performed to investigate the potential of the approach for a typical complex application. The use of the hybrid model with and without adaptation of the domain of validity is compared to conventional nonlinear model predictive control using the simplified physics-based model, and a nonlinear model predictive controller based on a standalone data-driven model for different situations regarding the available data set for model training and the operating conditions of the plant.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"153 ","pages":"Article 103496"},"PeriodicalIF":3.3,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144679154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robust identification of linear parameter-varying dual-rate system with non-stationary heavy-tailed noise","authors":"Xiang Chen ,&nbsp;Ke Li ,&nbsp;Fei Liu","doi":"10.1016/j.jprocont.2025.103500","DOIUrl":"10.1016/j.jprocont.2025.103500","url":null,"abstract":"<div><div>This paper addresses the identification of linear parameter-varying (LPV) dual-rate systems with non-stationary heavy-tailed measurement noise using a variational Bayesian (VB) approach. It provides a comprehensive analysis of dual-rate sampling and noise distribution variations commonly found in system data. To model the outliers, the Student’s <em>t</em> distribution is employed, and a Bernoulli variable is introduced to construct a Gaussian-Student’s <em>t</em> mixture (GTM) distribution that accounts for non-stationary heavy-tailed noise. The GTM distribution is then transformed into a Gaussian hierarchical model to develop a probabilistic representation of the system. Given the unknown process outputs in the regression vector, this study employs a modified Kalman filter for estimation. Based on the obtained estimates and observed data, a prior distribution is defined to establish a Bayesian framework, allowing for iterative parameter estimation via the VB approach. Finally, the effectiveness of this algorithm is validated through a numerical example and a cascaded tank system.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"153 ","pages":"Article 103500"},"PeriodicalIF":3.3,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144672331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Causality-driven sequence-to-sequence gated recurrent unit for performance-indicator-related root cause diagnosis","authors":"Chengtian Wang,&nbsp;Hongbo Shi,&nbsp;Bing Song,&nbsp;Yang Tao,&nbsp;Kun Wang","doi":"10.1016/j.jprocont.2025.103428","DOIUrl":"10.1016/j.jprocont.2025.103428","url":null,"abstract":"<div><div>Process monitoring and root cause diagnosis (RCD) are significant for maintaining process safety and ensuring product quality in industrial processes. Existing RCD methods have achieved great success under linear and stationary assumptions, which limits their application in complex industrial processes. In addition, causality analysis of the performance indicator (PI) helps to precisely identify the path of propagation of faults and locate the root cause that leads to performance degradation. However, PI is not online measurable, which makes it difficult to achieve PI-related RCD in time. A novel causality-driven sequence-to-sequence gated recurrent unit (CSGRU) is proposed for PI-related RCD to address these issues. The proposed method is built under the distributed process monitoring framework based on a PI-related process decomposition strategy to first locate the faulty unit. CSGRU is integrated with the concept of Granger causality (GC) to learn nonlinear and dynamic causal dependencies. Sequence-to-sequence multi-task learning is introduced to avoid time-consuming pairwise causal analysis and improves the predictive accuracy even under strong sparsity constraints. The predictive contribution statistic is built to obtain the real-time faulty causal graph, which contains the causal impacts on PI without using online PI data. Finally, through a reverse causal inference from effect to cause, the fault propagation path is identified backward from PI, and the root cause is subsequently located, which leads to the degradation of PI. The effectiveness of the proposed method is validated on two benchmarks, the Tennessee Eastman process (TEP) and the vinyl acetate monomer (VAM) plant model, and a real industrial application on the three-phase flow facility (TPF).</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"153 ","pages":"Article 103428"},"PeriodicalIF":3.3,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144632254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Metropolis–Hastings-within-Gibbs approach for nonlinear state–space system estimation","authors":"Wenxin Sun ,&nbsp;Hongtian Chen ,&nbsp;Chao Shang ,&nbsp;Weili Xiong ,&nbsp;Biao Huang","doi":"10.1016/j.jprocont.2025.103490","DOIUrl":"10.1016/j.jprocont.2025.103490","url":null,"abstract":"<div><div>This paper presents a new Metropolis–Hastings-within-Gibbs (MH–Gibbs) sampling method for state-estimation and parameter-identification in nonlinear state–space systems. Compared to the conventional filtering and smoothing approaches, the proposed method offers substantial improvements in both time efficiency and memory usage, while maintaining effective estimation accuracy. Furthermore, owing to the high efficiency of the proposed state-estimation method, a new approach is proposed to approximate the gradient of the log-likelihood function with respect to the system-parameters, which facilitates parameter-identification. Case studies on three benchmark systems show that: (1) compared to the forward-filtering–backward-smoothing approach, the proposed state-estimation method achieves comparable accuracy with only one-tenth the computational time; and (2) the proposed parameter-identification method has reasonable accuracy.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"153 ","pages":"Article 103490"},"PeriodicalIF":3.3,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144632253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"On optimal control of hybrid dynamical systems using complementarity constraints","authors":"Saif R. Kazi ,&nbsp;Kexin Wang ,&nbsp;Lorenz Biegler","doi":"10.1016/j.jprocont.2025.103492","DOIUrl":"10.1016/j.jprocont.2025.103492","url":null,"abstract":"<div><div>Optimal control for switch-based dynamical systems is a challenging problem in the process control literature. In this study, we model these systems as hybrid dynamical systems with finite number of unknown switching points and reformulate them using non-smooth and non-convex complementarity constraints as a mathematical program with complementarity constraints (MPCC). We utilize a moving finite element based strategy to discretize the differential equation system to accurately locate the unknown switching points at the finite element boundary and achieve high-order accuracy at intermediate non-collocation points. We propose a globalization approach to solve the discretized MPCC problem using a mixed NLP/MILP-based strategy to converge to a non-spurious first-order optimal solution. The method is tested on three dynamic optimization examples, including a gas–liquid tank model and an optimal control problem with a sliding mode solution.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"153 ","pages":"Article 103492"},"PeriodicalIF":3.3,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144572506","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Capturing principal features in slow industrial processes for anomaly detection application","authors":"Kai Wang ,&nbsp;Xinlong Yuan ,&nbsp;Zihui Cao ,&nbsp;Gecheng Chen ,&nbsp;Xiaofeng Yuan ,&nbsp;Chunhua Yang ,&nbsp;Yalin Wang ,&nbsp;Le Zhou","doi":"10.1016/j.jprocont.2025.103487","DOIUrl":"10.1016/j.jprocont.2025.103487","url":null,"abstract":"<div><div>Dynamics is the fundamental characteristic of running industrial processes, and online industrial anomaly detection requires satisfactory real-time property and precision. Uncertain noise and outliers are also common in industrial data, sharply decreasing the performance of data models. Moreover, the embedded dimension has been a consensus for high-dimensional processes because several factors drive the plant. Based on these rationales, we propose a new dynamic anomaly detection strategy named robust principal slow feature analysis (RPSFA). This method could preserve the local geometric structure and is robust to outliers. Moreover, the proposed method effectively realizes information-noise separation to improve detection performance. Two pairs of detection statistics are constructed to concurrently monitor the process’s steady state deviation, dynamic characteristics change, noise anomaly, and the breakdown of variable correlations. A numerical case and a simulated industrial cascaded continuous stirred tank heater process are used to present the superiority of the proposed method.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"153 ","pages":"Article 103487"},"PeriodicalIF":3.3,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144571147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel few-shot fault diagnosis model for addressing nonstationarity in the ironmaking process","authors":"Xujie Zhang ,&nbsp;Chunjie Yang ,&nbsp;Ming Ge ,&nbsp;Siwei Lou ,&nbsp;Yuelin Yang ,&nbsp;Ping Wu","doi":"10.1016/j.jprocont.2025.103491","DOIUrl":"10.1016/j.jprocont.2025.103491","url":null,"abstract":"<div><div>The fourth industrial revolution is a green industrial revolution represented by artificial intelligence, clean energy, and other fields, which is both a challenge and an opportunity for the blast furnace ironmaking process (BFIP). Considering the dynamics, nonlinearity, nonstationarity, few shots, and many outliers in BFIP fault diagnosis, we proposed a novel method called Slow Feature Constrained-Least Squares Improved Generative Adversarial Network (SFC-LSIGAN). First, the sliding window is used to explore the process dynamics, while the deep learning model could better extract the deep nonlinearity between variables. Secondly, aiming at the properties of few shots and nonstationarity in BFIP, a new model was proposed based on the similar training process of Auxiliary Classifier GAN (ACGAN) and Deep Slow Feature Analysis (DSFA). Therefore, while completing the task of few-shot fault diagnosis, the proposed method further extracts the nonstationarity to improve the accuracy of the model. Furthermore, many outliers in the BFIP data are likely to have an impact on the quality of the generated samples. The least squares loss form function was introduced to enhance the quality of the generated samples and alleviate the mode collapse problem during the proposed model training process. Experiments on a real BFIP showed that, compared with the state-of-the-art methods, our SFC-LSIGAN method achieved superior performance in both data enhancement and fault diagnosis.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"152 ","pages":"Article 103491"},"PeriodicalIF":3.3,"publicationDate":"2025-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144557290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robust PINN modeling via sensitivity-based adaptive sampling: Integration of optimal sensor placement and structural uncertainty handling","authors":"Shuji Chang ,&nbsp;Piyush Agarwal ,&nbsp;Chris McCready ,&nbsp;Luis Ricardez-Sandoval ,&nbsp;Hector Budman","doi":"10.1016/j.jprocont.2025.103493","DOIUrl":"10.1016/j.jprocont.2025.103493","url":null,"abstract":"<div><div>Physics-informed neural networks (PINNs) have emerged as promising surrogate models for systems governed by partial differential equations (PDEs), yet their practical implementation faces challenges in training efficiency and robustness to uncertainties. This study refines and improves a recently proposed sensitivity-based adaptive sampling (SBS) methodology to address these challenges specifically for twice-differentiable PDE systems. We first conduct a systematic investigation of SBS hyper-parameters, including prediction horizon and adaptation rate, revealing their crucial role in training performance. To enhance PINN model robustness facing uncertainties, we propose two approaches: (1) incorporating sensor measurements at sensitivity-identified locations into the loss function, and (2) augmenting the PINN architecture with direct sensor data inputs. Results show that our proposed approaches achieve superior generalization capabilities and robustness. Furthermore, we demonstrate that the SBS methodology can serve for optimal sensor placement by identifying locations that maximize information gain for model training.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"152 ","pages":"Article 103493"},"PeriodicalIF":3.3,"publicationDate":"2025-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144557294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting transfer learning suitability in ANN-based control of FOPDT industrial processes","authors":"Pau Comas,&nbsp;Antoni Morell,&nbsp;Ramon Vilanova,&nbsp;Jose Lopez Vicario","doi":"10.1016/j.jprocont.2025.103476","DOIUrl":"10.1016/j.jprocont.2025.103476","url":null,"abstract":"<div><div>The application of Artificial Neural Networks (ANN) in industrial control has become a popular topic of research in recent years. The adoption of strategies showing satisfactory results in other domains, such as Transfer Learning, have been proposed to overcome scarce data limitations. However, there is a lack of studies specifically addressing the requirements of control environments, where applying unsuitable ANN-based controllers can have critical consequences. In this work, we conduct an analysis of Transfer Learning focusing on the control of First-Order plus Dead-Time (FOPDT) processes. In particular, we first provide an overview of state-of-the-art Transfer Suitability Metrics (TSM) along with an analysis of their applicability to control. To do that, we define two transference scenarios that can be found in practice. Based on the insights extracted from the analysis, we propose a novel learning-based metric aimed at estimating the transfer deterioration when applying a data-based controller to a target domain. This metric enables the quantification of transfer suitability, so that a low deterioration value indicates that training a new neural network specifically for this process would yield similar performance. The proposed metric shows a good performance, and a simplified version is also proposed to offer a balanced trade-off between complexity and predictive accuracy.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"152 ","pages":"Article 103476"},"PeriodicalIF":3.3,"publicationDate":"2025-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144557293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A semi-supervised temporal modeling strategy integrating VAE and Wasserstein GAN under sparse sampling constraints","authors":"Yujie Hu ,&nbsp;Changrui Xie ,&nbsp;Xi Chen","doi":"10.1016/j.jprocont.2025.103497","DOIUrl":"10.1016/j.jprocont.2025.103497","url":null,"abstract":"<div><div>Time series network models are widely applied in process industries for soft sensing, fault monitoring, and real-time optimization, serving as a powerful tool to enhance the safety and efficiency of industrial production. Typically, time series networks require labeled data for supervised learning. However, labeled data often exhibits sparse sampling characteristics in industrial settings, which limits the model's performance. To address this issue, a semi-supervised modeling strategy based on Variational Autoencoder (VAE) and Wasserstein Generative Adversarial Network (WGAN) is proposed in this paper. The strategy consists of three steps. First, for the labeled samples, process data and labeled data are used as input to train a supervised VAE model (SVAE). Upon completion of the training, the posterior distribution of the latent variable <em><strong>z</strong></em>_{<em><strong>S</strong></em>} is obtained. Second, in all samples, only process data is used to train an unsupervised VAE model (UVAE) to extract the latent variable <em><strong>z</strong></em>_{<em><strong>U</strong></em>}, and the WGAN discriminator is introduced to distinguish between \"fake data\" (<em><strong>z</strong></em>_{<em><strong>U</strong></em>}) and \"real data\" (<em><strong>z</strong></em>_{<em><strong>S</strong></em>}). Through adversarial learning between the UVAE and WGAN discriminator, the posterior distribution of <em><strong>z</strong></em>_{<em><strong>U</strong></em>} is forced to approximate <em><strong>z</strong></em>_{<em><strong>S</strong></em>}. Finally, the encoder of UVAE and the decoder of SVAE are combined to form a Semi-Supervised Variational Autoencoder model (SS-VAE), which extracts the latent variable <em><strong>z</strong></em>_{<em><strong>SS</strong></em>} and the reconstructed labeled data from the decoder as inputs for the time series network. Long Short-Term Memory (LSTM) and Temporal Convolutional Network (TCN) are selected as two basic time series models, and their performance, both with and without the proposed semi-supervised approach, is compared to assess the effectiveness and robustness of the strategy. The improvements observed in two industrial case studies validate the efficiency of the proposed approach.</div></div>","PeriodicalId":50079,"journal":{"name":"Journal of Process Control","volume":"152 ","pages":"Article 103497"},"PeriodicalIF":3.3,"publicationDate":"2025-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144563215","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}