{"title":"A new optimal adaptive backstepping control approach for nonlinear systems under deception attacks via reinforcement learning","authors":"Wendi Chen , Qinglai Wei","doi":"10.1016/j.jai.2023.11.001","DOIUrl":"10.1016/j.jai.2023.11.001","url":null,"abstract":"<div><p>In this paper, a new optimal adaptive backstepping control approach for nonlinear systems under deception attacks via reinforcement learning is presented in this paper. The existence of nonlinear terms in the studied system makes it very difficult to design the optimal controller using traditional methods. To achieve optimal control, RL algorithm based on critic–actor architecture is considered for the nonlinear system. Due to the significant security risks of network transmission, the system is vulnerable to deception attacks, which can make all the system state unavailable. By using the attacked states to design coordinate transformation, the harm brought by unknown deception attacks has been overcome. The presented control strategy can ensure that all signals in the closed-loop system are semi-globally ultimately bounded. Finally, the simulation experiment is shown to prove the effectiveness of the strategy.</p></div>","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"3 1","pages":"Pages 34-39"},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2949855423000461/pdfft?md5=f1d39b9fda2a82a6aab8a2a790f387cb&pid=1-s2.0-S2949855423000461-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138626837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Stochastic sampled-data multi-objective control of active suspension systems for in-wheel motor driven electric vehicles","authors":"Iftikhar Ahmad, Xiaohua Ge, Qing-Long Han","doi":"10.1016/j.jai.2023.12.002","DOIUrl":"https://doi.org/10.1016/j.jai.2023.12.002","url":null,"abstract":"<div><p>This paper addresses the sampled-data multi-objective active suspension control problem for an in-wheel motor driven electric vehicle subject to stochastic sampling periods and asynchronous premise variables. The focus is placed on the scenario that the dynamical state of the half-vehicle active suspension system is transmitted over an in-vehicle controller area network that only permits the transmission of sampled data packets. For this purpose, a stochastic sampling mechanism is developed such that the sampling periods can randomly switch among different values with certain mathematical probabilities. Then, an asynchronous fuzzy sampled-data controller, featuring distinct premise variables from the active suspension system, is constructed to eliminate the stringent requirement that the sampled-data controller has to share the same grades of membership. Furthermore, novel criteria for both stability analysis and controller design are derived in order to guarantee that the resultant closed-loop active suspension system is stochastically stable with simultaneous <span><math><msub><mrow><mi>H</mi></mrow><mrow><mn>2</mn></mrow></msub></math></span> and <span><math><msub><mrow><mi>H</mi></mrow><mrow><mi>∞</mi></mrow></msub></math></span> performance requirements. Finally, the effectiveness of the proposed stochastic sampled-data multi-objective control method is verified via several numerical cases studies in both time domain and frequency domain under various road disturbance profiles.</p></div>","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"3 1","pages":"Pages 2-18"},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2949855423000588/pdfft?md5=ff0ade3f22bb12125122c96483204edf&pid=1-s2.0-S2949855423000588-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140160229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Practical prescribed-time fuzzy tracking control for uncertain nonlinear systems with time-varying actuators faults","authors":"Shuxing Xuan , Hongjing Liang , Tingwen Huang","doi":"10.1016/j.jai.2023.12.003","DOIUrl":"https://doi.org/10.1016/j.jai.2023.12.003","url":null,"abstract":"<div><p>The paper investigates the practical prescribed-time fuzzy tracking control problem for a category of nonlinear system subject to time-varying actuator faults. The presence of unknown nonlinear dynamics and actuator faults makes achieving tracking control within a prescribed-time challenging. To tackle this issue, we propose a novel practical prescribed-time fuzzy tracking control strategy, which is independent of the initial state of the system and does not rely on precise modeling of the system and actuators. We apply the approximation capabilities of fuzzy logic systems to handle the unknown nonlinear functions and unidentified actuator faults in the system. The piecewise controller and adaptive law constructed based on piecewise prescribed time-varying function and backstepping technique method establish the theoretical framework of practical prescribed-time tracking control, and extend the range of prescribed-time tracking control to infinity. Regardless of the initial conditions, the proposed control strategy can guarantee that all signals remain uniformly bounded within the practical prescribed time in the presence of unknown nonlinear item and time-varying actuator faults. Simulation example is presented to demonstrate the effectiveness of the proposed control strategy.</p></div>","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"3 1","pages":"Pages 40-49"},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S294985542300059X/pdfft?md5=52a438279e20d3abf3d23f3b83fbb7fa&pid=1-s2.0-S294985542300059X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140160757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Event-triggered H∞ PI state estimation for delayed switched neural networks","authors":"Yuzhong Wang , Changyun Wen , Xiaolei Li","doi":"10.1016/j.jai.2024.02.002","DOIUrl":"https://doi.org/10.1016/j.jai.2024.02.002","url":null,"abstract":"<div><p>On state estimation problems of switched neural networks, most existing results with an event-triggered scheme (ETS) not only ignore the estimator information, but also just employ a fixed triggering threshold, and the estimation error cannot be guaranteed to converge to zero. In addition, the state estimator of non-switched neural networks with integral and exponentially convergent terms cannot be used to improve the estimation performance of switched neural networks due to the difficulties caused by the nonsmoothness of the considered Lyapunov function at the switching instants. In this paper, we aim at overcoming such difficulties and filling in the gaps, by proposing a novel adaptive ETS (AETS) to design an event-based <span><math><msub><mrow><mi>H</mi></mrow><mrow><mi>∞</mi></mrow></msub></math></span> switched proportional–integral (PI) state estimator. A triggering-dependent exponential convergence term and an integral term are introduced into the switched PI state estimator. The relationship among the average dwell time, the AETS and the PI state estimator are established by the triggering-dependent exponential convergence term such that estimation error asymptotically converges to zero with <span><math><msub><mrow><mi>H</mi></mrow><mrow><mi>∞</mi></mrow></msub></math></span> performance level. It is shown that the convergence rate of the resultant error system can be adaptively adjusted according to triggering signals. Finally, the validity of the proposed theoretical results is verified through two illustrative examples.</p></div>","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"3 1","pages":"Pages 26-33"},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2949855424000030/pdfft?md5=ca0dfc3b892317269c5114552323be59&pid=1-s2.0-S2949855424000030-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140160230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wenjing Wang , Juanjuan Xu , Huanshui Zhang , Minyue Fu
{"title":"Exact controllability of rational expectations model with multiplicative noise and input delay","authors":"Wenjing Wang , Juanjuan Xu , Huanshui Zhang , Minyue Fu","doi":"10.1016/j.jai.2024.01.001","DOIUrl":"10.1016/j.jai.2024.01.001","url":null,"abstract":"<div><p>This paper considers the rational expectations model with multiplicative noise and input delay, where the system dynamics rely on the conditional expectations of future states. The main contribution is to obtain a sufficient condition for the exact controllability of the rational expectations model. In particular, we derive a sufficient Gramian matrix condition and a rank condition for the delay-free case. The key is the solvability of the backward stochastic difference equations with input delay which is derived from the forward and backward stochastic system.</p></div>","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"3 1","pages":"Pages 19-25"},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2949855424000017/pdfft?md5=7b66d98e9a13b338d24d969156a3900d&pid=1-s2.0-S2949855424000017-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139821817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Adaptive predictor-based control for a helicopter system with input delays: Design and experiments","authors":"S. Schlanbusch, Jing Zhou","doi":"10.1016/j.jai.2024.02.001","DOIUrl":"https://doi.org/10.1016/j.jai.2024.02.001","url":null,"abstract":"","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"53 26","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139827415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wenjing Wang, Juanjuan Xu, Huanshui Zhang, Minyue Fu
{"title":"Exact controllability of rational expectations model with multiplicative noise and input delay","authors":"Wenjing Wang, Juanjuan Xu, Huanshui Zhang, Minyue Fu","doi":"10.1016/j.jai.2024.01.001","DOIUrl":"https://doi.org/10.1016/j.jai.2024.01.001","url":null,"abstract":"","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"16 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139881749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A generic framework for qualifications of digital twins in maintenance","authors":"Jie Liu, Xingheng Liu, Jørn Vatn, Shen Yin","doi":"10.1016/j.jai.2023.07.002","DOIUrl":"10.1016/j.jai.2023.07.002","url":null,"abstract":"<div><p>Digital twins have emerged as a promising technology for maintenance applications, enabling organizations to simulate and monitor physical assets to improve their performance. In Operation and Maintenance (O&M), digital twin facilitates the diagnosis and prognosis of critical assets, forming the basis for smart maintenance planning and reducing downtime. However, there is a lack of standardized approaches for the qualifications of digital twins in maintenance, leading to low trustworthiness and limiting its application. This paper proposes a novel framework for the qualifications of digital twins in maintenance based on five pillars, namely fidelity, smartness, timeliness, integration, and standard compliance. We demonstrate the effectiveness of the framework through two case studies, showing how it can be implemented on digital twins for preventive maintenance and condition-based maintenance. Our proposed framework can help organizations across different industrial domains develop and implement digital twins in maintenance more effectively and efficiently, leading to significant benefits in terms of cost reduction, performance improvement, and sustainability.</p></div>","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"2 4","pages":"Pages 196-203"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S294985542300031X/pdfft?md5=a83844e12c5df9bce1296ec251ee4b59&pid=1-s2.0-S294985542300031X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81664900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Event-based performance guaranteed tracking control for constrained nonlinear system via adaptive dynamic programming method","authors":"Xingyi Zhang, Zijie Guo, Hongru Ren, Hongyi Li","doi":"10.1016/j.jai.2023.11.002","DOIUrl":"10.1016/j.jai.2023.11.002","url":null,"abstract":"<div><p>An optimal tracking control problem for a class of nonlinear systems with guaranteed performance and asymmetric input constraints is discussed in this paper. The control policy is implemented by adaptive dynamic programming (ADP) algorithm under two event-based triggering mechanisms. It is often challenging to design an optimal control law due to the system deviation caused by asymmetric input constraints. First, a prescribed performance control technique is employed to guarantee the tracking errors within predetermined boundaries. Subsequently, considering the asymmetric input constraints, a discounted non-quadratic cost function is introduced. Moreover, in order to reduce controller updates, an event-triggered control law is developed for ADP algorithm. After that, to further simplify the complexity of controller design, this work is extended to a self-triggered case for relaxing the need for continuous signal monitoring by hardware devices. By employing the Lyapunov method, the uniform ultimate boundedness of all signals is proved to be guaranteed. Finally, a simulation example on a mass–spring–damper system subject to asymmetric input constraints is provided to validate the effectiveness of the proposed control scheme.</p></div>","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"2 4","pages":"Pages 239-247"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2949855423000473/pdfft?md5=e6a0affcc6d203edf03ab9613e063578&pid=1-s2.0-S2949855423000473-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138616887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A comprehensive survey of robust deep learning in computer vision","authors":"Jia Liu , Yaochu Jin","doi":"10.1016/j.jai.2023.10.002","DOIUrl":"https://doi.org/10.1016/j.jai.2023.10.002","url":null,"abstract":"<div><p>Deep learning has presented remarkable progress in various tasks. Despite the excellent performance, deep learning models remain not robust, especially to well-designed adversarial examples, limiting deep learning models employed in security-critical applications. Therefore, how to improve the robustness of deep learning has attracted increasing attention from researchers. This paper investigates the progress on the threat of deep learning and the techniques that can enhance the model robustness in computer vision. Unlike previous relevant survey papers summarizing adversarial attacks and defense technologies, this paper also provides an overview of the general robustness of deep learning. Besides, this survey elaborates on the current robustness evaluation approaches, which require further exploration. This paper also reviews the recent literature on making deep learning models resistant to adversarial examples from an architectural perspective, which was rarely mentioned in previous surveys. Finally, interesting directions for future research are listed based on the reviewed literature. This survey is hoped to serve as the basis for future research in this topical field.</p></div>","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"2 4","pages":"Pages 175-195"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S294985542300045X/pdfft?md5=4ec3b4ce82d2aa24d2e48cd35edc7071&pid=1-s2.0-S294985542300045X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139050418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}