Pub Date : 2025-01-08DOI: 10.1109/TSMC.2024.3520526
Yanchi Li;Dongcheng Li;Wenyin Gong;Qiong Gu
Multiobjective multitask optimization (MO-MTO) aims to exploit the similarities among different multiobjective optimization tasks through knowledge transfer (KT), facilitating their simultaneous resolution. The effective design of KT techniques embedded in multiobjective evolutionary optimizers is crucial for enhancing the performance of multiobjective multitask evolutionary algorithms (MO-MTEAs). However, a significant limitation of existing KT techniques in MO-MTEAs is their equal treatment of particles/individuals for transferred knowledge reception, which can negatively impact the balance of diversity and convergence in population evolution. To remedy this limitation, this article proposes a new MO-MTEA, named MTEA-DCK, which incorporates diversity-oriented KT (DKT) and convergence-oriented KT (CKT) techniques tailored for different particles in the population. MTEA-DCK utilizes a strength-Pareto-based competitive mechanism to divide particles into winners and losers: 1) for winners, DKT is conducted via an intertask domain alignment approach to enhance population diversity and 2) for losers, CKT is executed within the unified search space to improve convergence. Additionally, to ensure robust performance on complex task combinations, we introduce two automatic parameter control strategies specifically designed for these KT techniques. MTEA-DCK was performed on 39 benchmark MO-MTO problems and demonstrated superior performance compared to eight state-of-the-art MO-MTEAs and six multiobjective evolutionary algorithms. Finally, we present three real-world MO-MTO application cases, where our approach also yielded better results than other algorithms.
{"title":"Multiobjective Multitask Optimization via Diversity- and Convergence-Oriented Knowledge Transfer","authors":"Yanchi Li;Dongcheng Li;Wenyin Gong;Qiong Gu","doi":"10.1109/TSMC.2024.3520526","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3520526","url":null,"abstract":"Multiobjective multitask optimization (MO-MTO) aims to exploit the similarities among different multiobjective optimization tasks through knowledge transfer (KT), facilitating their simultaneous resolution. The effective design of KT techniques embedded in multiobjective evolutionary optimizers is crucial for enhancing the performance of multiobjective multitask evolutionary algorithms (MO-MTEAs). However, a significant limitation of existing KT techniques in MO-MTEAs is their equal treatment of particles/individuals for transferred knowledge reception, which can negatively impact the balance of diversity and convergence in population evolution. To remedy this limitation, this article proposes a new MO-MTEA, named MTEA-DCK, which incorporates diversity-oriented KT (DKT) and convergence-oriented KT (CKT) techniques tailored for different particles in the population. MTEA-DCK utilizes a strength-Pareto-based competitive mechanism to divide particles into winners and losers: 1) for winners, DKT is conducted via an intertask domain alignment approach to enhance population diversity and 2) for losers, CKT is executed within the unified search space to improve convergence. Additionally, to ensure robust performance on complex task combinations, we introduce two automatic parameter control strategies specifically designed for these KT techniques. MTEA-DCK was performed on 39 benchmark MO-MTO problems and demonstrated superior performance compared to eight state-of-the-art MO-MTEAs and six multiobjective evolutionary algorithms. Finally, we present three real-world MO-MTO application cases, where our approach also yielded better results than other algorithms.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"55 3","pages":"2367-2379"},"PeriodicalIF":8.6,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143465569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The application of automated guided vehicle (AGV) greatly improves the production efficiency of workshop. However, machine flexibility and limited logistics equipment increase the complexity of collaborative scheduling, and frequent dynamic events bring uncertainty. Therefore, this article proposes a real-time scheduling method for dynamic flexible job shop scheduling problem with AGVs using multiagent reinforcement learning (MARL). Specifically, a real-time scheduling framework is proposed in which a multiagent scheduling architecture is designed for achieving task selection, machine allocation and AGV allocation. Then, an action space and an efficient action decoding algorithm are proposed, which enable agents to explore in the high-quality solution space and improve the learning efficiency. In addition, a state space with generalization, a reward function considering machine idle time and a strategy for handling four disturbance events are designed to minimize the total tardiness cost. Comparison experiments show that the proposed method outperforms the priority dispatching rules, genetic programming and four popular reinforcement learning (RL)-based methods, with performance improvements mostly exceeding 10%. Furthermore, experiments considering four disturbance events demonstrate that the proposed method has strong robustness, and it can provide appropriate scheme for uncertain manufacturing system.
{"title":"Real-Time Scheduling for Flexible Job Shop With AGVs Using Multiagent Reinforcement Learning and Efficient Action Decoding","authors":"Yuxin Li;Qingzheng Wang;Xinyu Li;Liang Gao;Ling Fu;Yanbin Yu;Wei Zhou","doi":"10.1109/TSMC.2024.3520381","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3520381","url":null,"abstract":"The application of automated guided vehicle (AGV) greatly improves the production efficiency of workshop. However, machine flexibility and limited logistics equipment increase the complexity of collaborative scheduling, and frequent dynamic events bring uncertainty. Therefore, this article proposes a real-time scheduling method for dynamic flexible job shop scheduling problem with AGVs using multiagent reinforcement learning (MARL). Specifically, a real-time scheduling framework is proposed in which a multiagent scheduling architecture is designed for achieving task selection, machine allocation and AGV allocation. Then, an action space and an efficient action decoding algorithm are proposed, which enable agents to explore in the high-quality solution space and improve the learning efficiency. In addition, a state space with generalization, a reward function considering machine idle time and a strategy for handling four disturbance events are designed to minimize the total tardiness cost. Comparison experiments show that the proposed method outperforms the priority dispatching rules, genetic programming and four popular reinforcement learning (RL)-based methods, with performance improvements mostly exceeding 10%. Furthermore, experiments considering four disturbance events demonstrate that the proposed method has strong robustness, and it can provide appropriate scheme for uncertain manufacturing system.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"55 3","pages":"2120-2132"},"PeriodicalIF":8.6,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438448","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-07DOI: 10.1109/TSMC.2024.3522968
Yuhan Wang;Zhuping Wang;Hao Zhang;Huaicheng Yan
This article investigates the optimal group consensus problem (GCP) in multiagent systems (MASs). To address this problem, a novel distributed optimal control policy is designed in the framework of off-policy reinforcement learning (RL). First, a framework for multiagent differential graphical games is formulated. Second, a min-max strategy is then introduced to ensure the achievement of group consensus through a data-driven value iteration (VI) approach. Finally, the presented consensus control policy is extended to address the group formation tracking problem (GFTP) of nonholonomic mobile robots, with a numerical example to illustrate the efficacy of the proposed results. Compared with the existing literature, this article has the following contributions: 1) A group of agents are decomposed into multiple subgroups to accomplish different consensus objectives; 2) the prior knowledge of agents’ dynamics and initial stabilizing control gains can be eliminated; and 3) the performance index function (PIF) for each agent is designed to integrate not only its individual control policy but also that of its neighboring agents.
{"title":"Optimal Group Consensus of Multiagent Systems in Graphical Games Using Reinforcement Learning","authors":"Yuhan Wang;Zhuping Wang;Hao Zhang;Huaicheng Yan","doi":"10.1109/TSMC.2024.3522968","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3522968","url":null,"abstract":"This article investigates the optimal group consensus problem (GCP) in multiagent systems (MASs). To address this problem, a novel distributed optimal control policy is designed in the framework of off-policy reinforcement learning (RL). First, a framework for multiagent differential graphical games is formulated. Second, a min-max strategy is then introduced to ensure the achievement of group consensus through a data-driven value iteration (VI) approach. Finally, the presented consensus control policy is extended to address the group formation tracking problem (GFTP) of nonholonomic mobile robots, with a numerical example to illustrate the efficacy of the proposed results. Compared with the existing literature, this article has the following contributions: 1) A group of agents are decomposed into multiple subgroups to accomplish different consensus objectives; 2) the prior knowledge of agents’ dynamics and initial stabilizing control gains can be eliminated; and 3) the performance index function (PIF) for each agent is designed to integrate not only its individual control policy but also that of its neighboring agents.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"55 3","pages":"2343-2353"},"PeriodicalIF":8.6,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143465577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Epileptor model is a mathematical framework utilized for simulating the transition from interictal to ictal local field potential (LFP) activity in the brain, with the aim of predicting and preventing epileptic seizures. This article introduces a novel approach integrating Lyapunov and Poincaré–Bendixson methods to analyze the stability of limit cycles in nonlinear systems, specifically focusing on Epileptors with a two-state dynamic. Our method accurately delineates the limit cycle boundary through eigenvalue-based analysis, facilitating precise assessment of stability properties and identification of critical regions linked to seizure initiation and termination. Through the investigation of the two-state dynamics of Epileptors, we gain deeper insights into the transition between low activity and seizure states, consequently improving our understanding of epileptic seizures. Our approach can be employed to establish stability conditions and determine the existence of limit cycles in Epileptor models, which can further aid in predicting and preventing epileptic seizures by identifying critical regions associated with seizure initiation and termination. The simulations conducted in this study demonstrate that the model under investigation exhibits stable limit cycle behavior and manifests bifurcation, with significant implications for the development of targeted interventions and more effective prediction and treatments for epilepsy. The findings indicate that the suggested approach establishes that external stimulation should not surpass 10.8 mA. Moreover, the initial normal state lies within the range of −1.6 to −0.1 ictal LFP. On the other hand, the LaSalle and eigenvalue methods individually cannot precisely determine the limit cycle region.
{"title":"New Eigenvalue-Based Analysis for Precise Limit Cycle Stability Assessment in a Two-State Epileptor Model","authors":"Samaneh-Alsadat Saeedinia;Mohammad-Reza Jahed-Motlagh;Nikola Kirilov Kasabov;Abbas Tafakhori","doi":"10.1109/TSMC.2024.3517620","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3517620","url":null,"abstract":"The Epileptor model is a mathematical framework utilized for simulating the transition from interictal to ictal local field potential (LFP) activity in the brain, with the aim of predicting and preventing epileptic seizures. This article introduces a novel approach integrating Lyapunov and Poincaré–Bendixson methods to analyze the stability of limit cycles in nonlinear systems, specifically focusing on Epileptors with a two-state dynamic. Our method accurately delineates the limit cycle boundary through eigenvalue-based analysis, facilitating precise assessment of stability properties and identification of critical regions linked to seizure initiation and termination. Through the investigation of the two-state dynamics of Epileptors, we gain deeper insights into the transition between low activity and seizure states, consequently improving our understanding of epileptic seizures. Our approach can be employed to establish stability conditions and determine the existence of limit cycles in Epileptor models, which can further aid in predicting and preventing epileptic seizures by identifying critical regions associated with seizure initiation and termination. The simulations conducted in this study demonstrate that the model under investigation exhibits stable limit cycle behavior and manifests bifurcation, with significant implications for the development of targeted interventions and more effective prediction and treatments for epilepsy. The findings indicate that the suggested approach establishes that external stimulation should not surpass 10.8 mA. Moreover, the initial normal state lies within the range of −1.6 to −0.1 ictal LFP. On the other hand, the LaSalle and eigenvalue methods individually cannot precisely determine the limit cycle region.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"55 3","pages":"2062-2072"},"PeriodicalIF":8.6,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-06DOI: 10.1109/TSMC.2024.3519347
Jianghong Zhou;Jun Luo;Huayan Pu;Yi Qin
Aiming at the large differences between tasks in continuous remaining useful life (RUL) prediction and the limited information capturing capability of the existing continuous learning (CL) methods, this article develops a novel multibranch horizontal augmentation network (MBHAN). First, a hierarchical self-attention (HSA) mechanism is proposed to capture the local degradation features and dependencies at different scales and enhance the representation capacity of RUL prediction model. Based on HSA and temporal convolutional network (TCN), a time-frequency fusion TCN (TFFTCN) is designed to mine the hidden degradation information from the time-domain and frequency-domain data. Then, a memory weight constraint (MWC) regularization term is built to control the update of important parameters for pervious tasks during the learning of new task. A horizontal network augmentation rule based on the task similarity and MWC is proposed, including the augmentation of a task branch network for small task difference and the augmentation of a feature extraction backbone network for large task difference. On this basis, the MBHAN is proposed to continuously predict RUL of machinery. Finally, the experimental results on the life-cycle bearing and gear datasets demonstrate that TFFTCN achieve an average accuracy of 93% across both datasets, surpassing the existing prediction methods.
{"title":"Multibranch Horizontal Augmentation Network for Continuous Remaining Useful Life Prediction","authors":"Jianghong Zhou;Jun Luo;Huayan Pu;Yi Qin","doi":"10.1109/TSMC.2024.3519347","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3519347","url":null,"abstract":"Aiming at the large differences between tasks in continuous remaining useful life (RUL) prediction and the limited information capturing capability of the existing continuous learning (CL) methods, this article develops a novel multibranch horizontal augmentation network (MBHAN). First, a hierarchical self-attention (HSA) mechanism is proposed to capture the local degradation features and dependencies at different scales and enhance the representation capacity of RUL prediction model. Based on HSA and temporal convolutional network (TCN), a time-frequency fusion TCN (TFFTCN) is designed to mine the hidden degradation information from the time-domain and frequency-domain data. Then, a memory weight constraint (MWC) regularization term is built to control the update of important parameters for pervious tasks during the learning of new task. A horizontal network augmentation rule based on the task similarity and MWC is proposed, including the augmentation of a task branch network for small task difference and the augmentation of a feature extraction backbone network for large task difference. On this basis, the MBHAN is proposed to continuously predict RUL of machinery. Finally, the experimental results on the life-cycle bearing and gear datasets demonstrate that TFFTCN achieve an average accuracy of 93% across both datasets, surpassing the existing prediction methods.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"55 3","pages":"2237-2249"},"PeriodicalIF":8.6,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-06DOI: 10.1109/TSMC.2024.3521369
Tássio M. Linhares;Eduardo S. Tognetti;Taís R. Calliero
This work addresses the problem of designing dynamic output feedback controllers for Takagi-Sugeno (T-S) fuzzy systems subjected to inexact measurements of premise variables. Instead of assuming that the premise variables are precisely available for the controller, this work provides linear matrix inequalities (LMIs) conditions to design controller gains depending on premise variables with additive uncertainties. This uncertainty model includes inexact measurements of the premise variables due to sensor devices or an approximate representation in the T-S modeling, which can assume the form of absolute uncertainties in the membership functions. Numerical examples illustrate the robustness of the approach.
{"title":"Output Feedback Control With Inexact Premise Variables of T-S Fuzzy Systems","authors":"Tássio M. Linhares;Eduardo S. Tognetti;Taís R. Calliero","doi":"10.1109/TSMC.2024.3521369","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3521369","url":null,"abstract":"This work addresses the problem of designing dynamic output feedback controllers for Takagi-Sugeno (T-S) fuzzy systems subjected to inexact measurements of premise variables. Instead of assuming that the premise variables are precisely available for the controller, this work provides linear matrix inequalities (LMIs) conditions to design controller gains depending on premise variables with additive uncertainties. This uncertainty model includes inexact measurements of the premise variables due to sensor devices or an approximate representation in the T-S modeling, which can assume the form of absolute uncertainties in the membership functions. Numerical examples illustrate the robustness of the approach.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"55 3","pages":"2380-2386"},"PeriodicalIF":8.6,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143465566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This article proposes a stabilizing control scheme based on partial-state decomposition to exponentially stabilize multi-input and multioutput nonminimum phase nonlinear systems in a general normal form with a general relative degree. The scheme reveals that partial-state variables can play an essential role in stabilizing the whole system. Specifically, partial-state variables are decomposed into a sum of two vector signals s and N. Then, setting s as the output vector, a new normal form is derived. For the new normal form, N and an auxiliary signal are designed to exponentially stabilize the unstable zero/internal dynamics of the auxiliary system; and the real input is designed to ensure that $s $ is exponentially stable. In particular, the zero/internal dynamics dependence on the input is fully considered in this article, and the proposed method ensures global stabilization of the closed-loop system without relying on the existence condition of Lyapunov functions. Finally, a high fidelity hypersonic vehicle model is given to show the design procedure and verify the feasibility and validity of the proposed stabilizing control scheme.
本文提出了一种基于偏态分解的稳定控制方案，以指数方式稳定具有一般相对度的一般正态形式的多输入和多输出非最小相位非线性系统。该方案揭示了偏态变量在稳定整个系统中的重要作用。具体来说，部分状态变量被分解为两个矢量信号 s 和 N 之和。对于新的正态形式，N 和辅助信号的设计是为了指数稳定辅助系统不稳定的零点/内部动态；而实际输入的设计是为了确保 $s $ 是指数稳定的。特别是，本文充分考虑了零点/内部动力学对输入的依赖性，提出的方法无需依赖李亚普诺夫函数的存在条件就能确保闭环系统的全局稳定。最后，文章给出了一个高保真高超音速飞行器模型，以展示设计过程并验证所提稳定控制方案的可行性和有效性。
{"title":"Partial-State Decomposition-Based Control of MIMO Nonminimum Phase Nonlinear Systems With Application to a Hypersonic Vehicle Model","authors":"Xinhao Zhang;Yanjun Zhang;Jianliang Ai;Yeguang Wang;Xuelin Zhang","doi":"10.1109/TSMC.2024.3521380","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3521380","url":null,"abstract":"This article proposes a stabilizing control scheme based on partial-state decomposition to exponentially stabilize multi-input and multioutput nonminimum phase nonlinear systems in a general normal form with a general relative degree. The scheme reveals that partial-state variables can play an essential role in stabilizing the whole system. Specifically, partial-state variables are decomposed into a sum of two vector signals s and N. Then, setting s as the output vector, a new normal form is derived. For the new normal form, N and an auxiliary signal are designed to exponentially stabilize the unstable zero/internal dynamics of the auxiliary system; and the real input is designed to ensure that <inline-formula> <tex-math>$s $ </tex-math></inline-formula> is exponentially stable. In particular, the zero/internal dynamics dependence on the input is fully considered in this article, and the proposed method ensures global stabilization of the closed-loop system without relying on the existence condition of Lyapunov functions. Finally, a high fidelity hypersonic vehicle model is given to show the design procedure and verify the feasibility and validity of the proposed stabilizing control scheme.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"55 3","pages":"2289-2301"},"PeriodicalIF":8.6,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143465576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-03DOI: 10.1109/TSMC.2024.3520823
Xiaobing Nie;Boqiang Cao;Wei Xing Zheng;Jinde Cao
This work explores the issue of multistability for a competitive neural network (NN) class with sigmoidal activation functions (AFs) involving state-dependent switching and fractional-order derivative. Specifically, first, we consider three different switching point locations, and establish some sufficient criteria ensuring that NNs with n-neurons can have, and only have, $5^{n_{1}}cdot 3^{n_{2}}$ equilibrium points (EPs) with $n_{1}+n_{2}=n$ , by utilizing the geometric features of the sigmoidal functions, the fixed point theorem, the Filippov’s EP definition, and the contraction mapping theorem. Then, based on novel Lyapunov functions and by applying the fractional-order calculus theory, it is demonstrated that $3^{n_{1}}cdot 2^{n_{2}}$ out of $5^{n_{1}}cdot 3^{n_{2}}$ total EPs are locally stable. This work’s investigation reveals that competitive NNs with switching afford more storage capacity compared to the nonswitching case. Additionally, our results are valid for the integer-order and fractional-order switched NNs, improving and generalizing current works. Furthermore, two numerical examples and an application example of associative memory are provided to validate the effectiveness of the theoretical findings, and the way various fractional orders affect the NNs’ convergence speed is shown through simulations.
{"title":"Multistability Analysis of Fractional-Order State-Dependent Switched Competitive Neural Networks With Sigmoidal Activation Functions","authors":"Xiaobing Nie;Boqiang Cao;Wei Xing Zheng;Jinde Cao","doi":"10.1109/TSMC.2024.3520823","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3520823","url":null,"abstract":"This work explores the issue of multistability for a competitive neural network (NN) class with sigmoidal activation functions (AFs) involving state-dependent switching and fractional-order derivative. Specifically, first, we consider three different switching point locations, and establish some sufficient criteria ensuring that NNs with n-neurons can have, and only have, <inline-formula> <tex-math>$5^{n_{1}}cdot 3^{n_{2}}$ </tex-math></inline-formula> equilibrium points (EPs) with <inline-formula> <tex-math>$n_{1}+n_{2}=n$ </tex-math></inline-formula>, by utilizing the geometric features of the sigmoidal functions, the fixed point theorem, the Filippov’s EP definition, and the contraction mapping theorem. Then, based on novel Lyapunov functions and by applying the fractional-order calculus theory, it is demonstrated that <inline-formula> <tex-math>$3^{n_{1}}cdot 2^{n_{2}}$ </tex-math></inline-formula> out of <inline-formula> <tex-math>$5^{n_{1}}cdot 3^{n_{2}}$ </tex-math></inline-formula> total EPs are locally stable. This work’s investigation reveals that competitive NNs with switching afford more storage capacity compared to the nonswitching case. Additionally, our results are valid for the integer-order and fractional-order switched NNs, improving and generalizing current works. Furthermore, two numerical examples and an application example of associative memory are provided to validate the effectiveness of the theoretical findings, and the way various fractional orders affect the NNs’ convergence speed is shown through simulations.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"55 3","pages":"2106-2119"},"PeriodicalIF":8.6,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-03DOI: 10.1109/TSMC.2024.3522116
Shubo Wang;Chuanbin Sun;Qiang Chen;Haoran He
Robot systems, due to their unique flexibility and economy, are widely used in modern industry and intelligent manufacturing. The parameters of the system are unknown, and traditional parameter estimation methods are difficult to achieve fixed time convergence, which leads to extremely position tracking control problem. In addition, the transient and steady-state performance of the robot system is difficult to specify in advance. In this article, a novel composite learning fixed-time (FxT) control strategy is proposed for the robotic systems to deal with these issues. The funnel control (FC) is utilized to transform the original error system into a new error dynamics with transient performance constraints. The two-phase nonsingular FxT sliding mode surface is constructed to avoid the singularity problem. Then, the filter operation is introduced to obtain the expression of parameter estimation error and is used to design the composite learning law. To achieve parameter estimation, a FxT composite learning law based on online historical data and regression extension is proposed, where the interval excitation (IE) is considered in the adaptive law. Finally, the designed adaption is incorporated into the nonsingular FxT sliding mode control to achieve tracking control. Moreover, the comparison of three different controllers is made to demonstrate the benefits of the developed control strategy.
{"title":"Composite Learning Fixed-Time Control for Nonlinear Servo Systems With State Constraints and Unknown Dynamics","authors":"Shubo Wang;Chuanbin Sun;Qiang Chen;Haoran He","doi":"10.1109/TSMC.2024.3522116","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3522116","url":null,"abstract":"Robot systems, due to their unique flexibility and economy, are widely used in modern industry and intelligent manufacturing. The parameters of the system are unknown, and traditional parameter estimation methods are difficult to achieve fixed time convergence, which leads to extremely position tracking control problem. In addition, the transient and steady-state performance of the robot system is difficult to specify in advance. In this article, a novel composite learning fixed-time (FxT) control strategy is proposed for the robotic systems to deal with these issues. The funnel control (FC) is utilized to transform the original error system into a new error dynamics with transient performance constraints. The two-phase nonsingular FxT sliding mode surface is constructed to avoid the singularity problem. Then, the filter operation is introduced to obtain the expression of parameter estimation error and is used to design the composite learning law. To achieve parameter estimation, a FxT composite learning law based on online historical data and regression extension is proposed, where the interval excitation (IE) is considered in the adaptive law. Finally, the designed adaption is incorporated into the nonsingular FxT sliding mode control to achieve tracking control. Moreover, the comparison of three different controllers is made to demonstrate the benefits of the developed control strategy.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"55 3","pages":"2332-2342"},"PeriodicalIF":8.6,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143465568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-03DOI: 10.1109/TSMC.2024.3518513
Rongqiang Tang;Peng Shi;Xinsong Yang;Guanghui Wen;Lei Shi
Considering the memory property of the fractional calculus and the potential diverging state of the open-loop mode, existing analysis methods are difficult to solve the finite-time issue of intermittently controlled fractional-order systems (FOSs). This article studies the finite-time synchronization of coupled FOSs with nonlinearity via fuzzy intermittent quantized control and two novel fractional-order differential inequalities. An interval-type 2 Takagi-Sugeno fuzzy technique is introduced, which not only facilitates the handling of the nonlinear term in the error dynamic system, but also greatly simplifies the control design. Synchronization conditions in form of linear matrix inequalities are provided by designing a novel Lyapunov function on the basis of ellipsoidal norm. Moreover, two corollaries show the generality of the new analysis framework. Compared with existing results, it is amazing that the decreasing magnitude of Lyapunov function on the control intervals can be smaller than its increasing magnitude on the subsequent noncontrol interval. Finally, Chua’s system is used to clarify the effectiveness of theoretical outcomes.
{"title":"Finite-Time Synchronization of Coupled Fractional-Order Systems via Intermittent IT-2 Fuzzy Control","authors":"Rongqiang Tang;Peng Shi;Xinsong Yang;Guanghui Wen;Lei Shi","doi":"10.1109/TSMC.2024.3518513","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3518513","url":null,"abstract":"Considering the memory property of the fractional calculus and the potential diverging state of the open-loop mode, existing analysis methods are difficult to solve the finite-time issue of intermittently controlled fractional-order systems (FOSs). This article studies the finite-time synchronization of coupled FOSs with nonlinearity via fuzzy intermittent quantized control and two novel fractional-order differential inequalities. An interval-type 2 Takagi-Sugeno fuzzy technique is introduced, which not only facilitates the handling of the nonlinear term in the error dynamic system, but also greatly simplifies the control design. Synchronization conditions in form of linear matrix inequalities are provided by designing a novel Lyapunov function on the basis of ellipsoidal norm. Moreover, two corollaries show the generality of the new analysis framework. Compared with existing results, it is amazing that the decreasing magnitude of Lyapunov function on the control intervals can be smaller than its increasing magnitude on the subsequent noncontrol interval. Finally, Chua’s system is used to clarify the effectiveness of theoretical outcomes.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":"55 3","pages":"2022-2032"},"PeriodicalIF":8.6,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：