Control Engineering Practice最新文献_第5页

Enhanced variational autoencoder with continual learning capability for multimode process monitoring

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2024-12-31 DOI: 10.1016/j.conengprac.2024.106219

Zhenhua Yu , Guan Wang , Qingchao Jiang , Xuefeng Yan , Zhixing Cao

{"title":"Enhanced variational autoencoder with continual learning capability for multimode process monitoring","authors":"Zhenhua Yu , Guan Wang , Qingchao Jiang , Xuefeng Yan , Zhixing Cao","doi":"10.1016/j.conengprac.2024.106219","DOIUrl":"10.1016/j.conengprac.2024.106219","url":null,"abstract":"<div><div>Existing mode segmentation methods in multimode process monitoring generally fail to simultaneously determine the number of modes and segmentation points. In addition, traditional monitoring methods typically suffer from “catastrophic forgetting”, resulting in poor monitoring performance. This paper proposes a novel mode segmentation method called latent variable mapping greedy Gaussian segmentation (LMGGS) and enhances the variational autoencoder (VAE) with continual learning (CL-VAE) capability to address the problem of catastrophic forgetting. First, the LMGGS is used for mode segmentation, which reformulates the mode segmentation problem as a covariance-regularized maximum likelihood estimation problem. Second, weights in VAE deemed unimportant were set to zero, and the remaining ones were updated by training the model with important samples in a direction orthogonal to the gradient space of the previous modes. Finally, statistics and thresholds based on the reconstruction error were established to determine the system states. The LMGGS can simultaneously determine the segmentation point and the number of modes, while the CL-VAE can effectively address catastrophic forgetting and reduce data storage requirements. The superiority of the proposed methods was validated through experiments on two simulated datasets and an actual penicillin fermentation dataset.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"156 ","pages":"Article 106219"},"PeriodicalIF":5.4,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143158493","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

Application of a predictive method to protect privacy of mobility data

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2024-12-28 DOI: 10.1016/j.conengprac.2024.106223

Emilio Molina , Mirko Fiacchini , Arthur Goarant , Rémy Raes , Sophie Cerf , Bogdan Robu

引用次数: 0

Real-time application of Koopman-based optimal control strategies for fuel cell stack thermal management

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2024-12-28 DOI: 10.1016/j.conengprac.2024.106225

Da Huo, Adwoa Adunyah, Carrie M. Hall

{"title":"Real-time application of Koopman-based optimal control strategies for fuel cell stack thermal management","authors":"Da Huo, Adwoa Adunyah, Carrie M. Hall","doi":"10.1016/j.conengprac.2024.106225","DOIUrl":"10.1016/j.conengprac.2024.106225","url":null,"abstract":"<div><div>In this study, a Koopman operator was applied in conjunction with linear optimal control algorithms, specially linear quadratic regulator (LQR), to enable real-time control of a 5 kW open cathode proton exchange membrane fuel cell (PEMFC) stack. A proportional–integral (PI) controller and two Koopman-based linear quadratic regulator (KLQR) controllers were developed. These controllers were designed to focus on minimizing in-stack temperature and temperature variations across the PEMFC stack, while also reducing auxiliary power consumption. To evaluate the real-time performance of these controllers, they were integrated with associated hardware using a National Instruments data acquisition system (DAQ) through LabVIEW. Various real-world scenario test conditions were conducted to assess the controllers’ performance and disturbance rejection, including evaluations based on the net power output of the PEMFC stack, as well as temperature and temperature variations in transient and steady states. Additionally, a comparative analysis of the controllers’ hardware-in-loop performance was conducted and compared to simulation results. The results demonstrate that the proposed Koopman-based LQR approach offers several advantages in thermal management and control of temperature variations across the PEMFC stack, leading to improved net power outputs.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"156 ","pages":"Article 106225"},"PeriodicalIF":5.4,"publicationDate":"2024-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143157090","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 adaptive shear thickening fluid variable admittance control in image-based visual servo feature space

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2024-12-27 DOI: 10.1016/j.conengprac.2024.106222

Wenru Lu, Lei Ma, Deqing Huang, Dongrui Wang, Jianfei Lin, Zeyu Deng

{"title":"Robust adaptive shear thickening fluid variable admittance control in image-based visual servo feature space","authors":"Wenru Lu, Lei Ma, Deqing Huang, Dongrui Wang, Jianfei Lin, Zeyu Deng","doi":"10.1016/j.conengprac.2024.106222","DOIUrl":"10.1016/j.conengprac.2024.106222","url":null,"abstract":"<div><div>To improve the compliance and robustness of robots during physical human–robot interaction (pHRI) and to enhance the success rate and stability of peg-in-hole experiments, a robust adaptive shear-thickening fluid (STF) variable admittance control in feature space is proposed in this article. Leveraging STF’s adaptability to contact forces and its energy dissipation properties during impacts, a robust adaptive virtual damping coefficient based on the maximum feature point of virtual velocity is designed. Additionally, an adaptive virtual stiffness coefficient that adjusts with contact force is developed to ensure rapid convergence of the manipulator when subjected to external impacts during servoing. The designed variable admittance controller ensures the manipulator’s compliance and robustness during pHRI. Furthermore, image-based visual servoing (IBVS) is coupled with admittance control in feature space to avoid the need for precise environmental modeling during tasks. Finally, the system’s stability is verified through the Lyapunov stability theorem. Experimental results demonstrate enhanced convergence and compliance during tasks, along with robustness and energy dissipation capabilities against external impacts.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"156 ","pages":"Article 106222"},"PeriodicalIF":5.4,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143158492","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

Data driven roll bending prediction via dynamic sliding window and basis function decomposition

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2024-12-24 DOI: 10.1016/j.conengprac.2024.106220

Peng Shi, Guoyan Huang, Yifang Huang, Hongdou He, Guyu Zhao

{"title":"Data driven roll bending prediction via dynamic sliding window and basis function decomposition","authors":"Peng Shi, Guoyan Huang, Yifang Huang, Hongdou He, Guyu Zhao","doi":"10.1016/j.conengprac.2024.106220","DOIUrl":"10.1016/j.conengprac.2024.106220","url":null,"abstract":"<div><div>Roll bending is suitable for the production of high-precision and complex curved products in the aerospace field. During the dynamic forming process of variable curvature profiles, the bending moment distribution on the profile exhibits complex spatio-temporal coupling effects, leading to difficulties in accurately predicting the final shape. This study proposes a data-driven method for variable curvature roll bending prediction. Firstly, by analyzing influencing factors in roll bending process, a representation method using dynamic sliding windows is proposed to achieve temporal decoupling. Subsequently, a target region representation method based on basis function decomposition is introduced to mitigate the impact of outliers. Next, a Multi-Frequency Recurrent Neural Network (MFRNN) is proposed to model the relationship between control sequences and the final formed shape, where the MFRNN module learns features of different control sequence scales, and the frequency attention module learns the correspondence between scales and basis functions. Finally, a series of experiments demonstrate that the proposed method can accurately model the control relationships of variable curvature roll bending process, thereby providing effective solutions for the precision forming field.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"156 ","pages":"Article 106220"},"PeriodicalIF":5.4,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143157053","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 fault-tolerant observer-based control for multi-input multi-output interconnected systems with bandwidth-limited communication

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2024-12-23 DOI: 10.1016/j.conengprac.2024.106217

Aref Ghoreishee , Masoud Soroush

{"title":"Adaptive fault-tolerant observer-based control for multi-input multi-output interconnected systems with bandwidth-limited communication","authors":"Aref Ghoreishee , Masoud Soroush","doi":"10.1016/j.conengprac.2024.106217","DOIUrl":"10.1016/j.conengprac.2024.106217","url":null,"abstract":"<div><div>The intensification of distributed manufacturing processes often increases the level of process interconnectivity, which subsequently leads to more intricate and complex process dynamics. Furthermore, wireless communication between processes and their controllers requires signal quantization. Motivated by these, this work presents an adaptive finite-time fault-tolerant observer-based quantized controller for a class of nonlinear state-delayed interconnected switched multi-input multi-output systems subject to arbitrary switching, quantized control and sensor signals, actuator and sensor faults, and nonlinear actuator behavior. The controller is tailored for interconnected distributed manufacturing processes with limited bandwidth communication channels for signal transmission. Sensor-fault-model parameters are estimated using a new adaptation law. Distributed observers are designed based on sensor-fault parameter estimates, the quantized faulty sensor data, and the quantized control signal. Nonlinear actuator behaviors including saturation, back-lash, and hysteresis are considered. The unknown nonlinear behavior of each subsystem is approximated using radial basis function neural networks. Using the Lyapunov-Razumikhin approach and an appropriate common Lyapunov function, the stability of the closed-loop system and the convergence of the tracking error to a desired neighborhood of the origin within a finite time are proved. The effectiveness of the proposed controller is validated through a simulation study conducted on a process system comprising integrated chemical reactors. The study highlights the controller’s ability to manage the interconnected dynamics of the system, ensuring stable and efficient operation under varying conditions.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"156 ","pages":"Article 106217"},"PeriodicalIF":5.4,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143158459","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An active tool holder and robust LPV control design for practical vibration suppression in internal turning

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2024-12-21 DOI: 10.1016/j.conengprac.2024.106215

Ziv Brand , Matthew O.T. Cole , Nikolay Razoronov

{"title":"An active tool holder and robust LPV control design for practical vibration suppression in internal turning","authors":"Ziv Brand , Matthew O.T. Cole , Nikolay Razoronov","doi":"10.1016/j.conengprac.2024.106215","DOIUrl":"10.1016/j.conengprac.2024.106215","url":null,"abstract":"<div><div>This study presents a new system and control design for an active tool holder that can effectively suppress vibration and chatter in internal turning. The controller accounts for the influence of tool deflection during a preceding cut affecting the dynamics of the current cut, a key source of instability in machining processes. To deal with variability in dynamic behavior due to changing of the tool mounting conditions and overhang length, a robust H-infinity controller is synthesized based on a linear-parameter-varying (LPV) description of the machining dynamics. The parametric dependence allows the robustness levels and modal properties of the control system to be easily tuned in a workshop setting to achieve the best possible vibration reduction performance. The controller design accounts for the time-delayed feedback from cutting forces, and also the need to avoid spillover instability of unmodeled high frequency modes. The method is applied using a tool holder that integrates piezoelectric bending actuators and strain sensors in such a way that the overall size and shape of the tool is unaltered, thereby providing the functionality and ease of operation necessary for widespread adoption in manufacturing industries. Experiments conducted on a lathe machine demonstrate that root-mean-square vibration levels can be reduced by over 95% (and peak-to-peak values reduced by approximately 90%) in unstable cutting regimes, allowing high material removal rates with good surface finish. For stable cutting, the system can also reduce vibration by 10% to 50%, depending on cutting conditions.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"156 ","pages":"Article 106215"},"PeriodicalIF":5.4,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143157111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Constrained LPV control for collision avoidance using mixed steering and differential braking

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2024-12-20 DOI: 10.1016/j.conengprac.2024.106214

Anh-Lam Do, François Fauvel

引用次数: 0

Hierarchical Deep Reinforcement Learning for cubesat guidance and control

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2024-12-19 DOI: 10.1016/j.conengprac.2024.106213

Abdulla Tammam, Nabil Aouf

引用次数: 0

Balancing production maximization and equipment degradation: Experimental application of a health-aware controller

IF 5.4 2区计算机科学

Control Engineering Practice Pub Date : 2024-12-18 DOI: 10.1016/j.conengprac.2024.106193

José Matias, Johannes Jäschke

{"title":"Balancing production maximization and equipment degradation: Experimental application of a health-aware controller","authors":"José Matias, Johannes Jäschke","doi":"10.1016/j.conengprac.2024.106193","DOIUrl":"10.1016/j.conengprac.2024.106193","url":null,"abstract":"<div><div>This study implements a Health-Aware Controller (HAC) in an experimental rig that emulates an oil well system. The operational goal for the system is to maximize production, while ensuring that the degradation in each of the wells is controlled, such that no critical equipment breakdown happens before a planned maintenance stop. Health-aware control systems combine production optimization techniques with equipment health monitoring and they were recently proposed to systematically address the intuitive trade-off between optimizing production and minimizing equipment degradation. As such the controller is intended to maximize the system’s economic performance, while proactively preventing unexpected breakdowns. However, so far the concepts for health-aware control have been tested only in simulations. The main contribution of this paper is to implement and test a Health-Aware Controller on a physical system in lab conditions. Our experimental results confirm the <em>in-silico</em> findings on health-aware control that show that it is able to realize a balance between decreasing the equipment degradation and maximizing the system production, and has the potential to improve the system performance considering both revenues and maintenance costs. We further discuss several implementation aspects and highlight some implementation challenges that can be faced by other practitioners.</div></div>","PeriodicalId":50615,"journal":{"name":"Control Engineering Practice","volume":"156 ","pages":"Article 106193"},"PeriodicalIF":5.4,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143157826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0