IEEE Transactions on Cybernetics最新文献_第8页

Knowledge Learning-Based Dimensionality Reduction for Solving Large-Scale Sparse Multiobjective Optimization Problems 解决大规模稀疏多目标优化问题的基于知识学习的降维方法

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-18 DOI: 10.1109/TCYB.2025.3558354

Shuai Shao;Ye Tian;Yajie Zhang;Xingyi Zhang

{"title":"Knowledge Learning-Based Dimensionality Reduction for Solving Large-Scale Sparse Multiobjective Optimization Problems","authors":"Shuai Shao;Ye Tian;Yajie Zhang;Xingyi Zhang","doi":"10.1109/TCYB.2025.3558354","DOIUrl":"10.1109/TCYB.2025.3558354","url":null,"abstract":"Large-scale sparse multiobjective optimization problems (LSMOPs) are of great significance in the context of practical applications, such as critical node detection, feature selection, and pattern mining. Since many LSMOPs are pursued based on large datasets, they involve a large number of decision variables, resulting in a huge search space that is challenging to explore efficiently. To rapidly approximate sparse Pareto optimal solutions, some evolutionary algorithms have been proposed to reduce the dimensionality of LSMOPs. However, their adaptability to different LSMOPs remains limited due to their reliance on fixed dimensionality reduction schemes, which can potentially lead to local optima and inefficient utilization of function evaluations. To address this issue, a knowledge learning-based dimensionality reduction approach is proposed in this article. First, in the early stages of evolution, the impact of different dimensionality reduction schemes on the sparse distribution of the population is evaluated. Then, the multilayer perceptron is employed to learn the accumulated knowledge from the evolutionary process, thereby constructing a mapping model between the sparse features of the evolutionary process and the candidate dimensionality reduction schemes. Finally, the model recommends the best dimensionality reduction scheme in each generation, achieving a good balance between exploration and exploitation. Experimental evaluations on both benchmark and real-world LSMOPs demonstrate that an evolutionary algorithm incorporating the proposed knowledge learning-based dimensionality reduction approach outperforms most existing evolutionary algorithms.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 7","pages":"3471-3484"},"PeriodicalIF":9.4,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143849807","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}

引用次数: 0

Quality Control in Extrusion-Based Additive Manufacturing: A Review of Machine Learning Approaches 基于挤压的增材制造质量控制：机器学习方法综述

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-18 DOI: 10.1109/TCYB.2025.3558515

Adailton Gomes Pereira;Gustavo Franco Barbosa;Moacir Godinho Filho;Sidney Bruce Shiki;Andrea Lago da Silva

{"title":"Quality Control in Extrusion-Based Additive Manufacturing: A Review of Machine Learning Approaches","authors":"Adailton Gomes Pereira;Gustavo Franco Barbosa;Moacir Godinho Filho;Sidney Bruce Shiki;Andrea Lago da Silva","doi":"10.1109/TCYB.2025.3558515","DOIUrl":"10.1109/TCYB.2025.3558515","url":null,"abstract":"Additive manufacturing (AM) revolutionizes product creation with its unique layer-by-layer construction method but faces obstacles in widespread industrial use due to quality assurance and defect challenges. Integrating machine learning (ML) into AM quality control (QC) systems presents a viable solution, utilizing ML’s ability to autonomously detect patterns and extract important data, reducing the reliance on manual intervention. This study conducts an in-depth literature review to scrutinize the role of ML in augmenting QC mechanisms within extrusion-based AM processes. Our primary objective is to pinpoint ML models that excel in monitoring manufacturing activities and facilitating instantaneous defect corrections via parameter adjustments. Our analysis highlights the efficacy of convolutional neural networks (CNNs) models in defect detection, leveraging camera-based systems for an in-depth examination of printed parts. For 1-D data processing, support vector machines (SVMs) and long short-term memory (LSTM) networks have shown significant application and effectiveness. Furthermore, the study classifies various sensors and defects that can effectively benefit from ML-driven QC approaches. Our findings accentuate the essential role of ML, especially CNNs, in detecting and rectifying production flaws and also detail the synergy between different sensor technologies in creating a comprehensive monitoring framework. By integrating ML with a multisensor approach and employing real-time corrective strategies, such as dynamic parameter adjustments and the use of advanced control systems, this research underscores ML’s transformative potential in elevating AM QC. Thus, our contribution lays the groundwork for harnessing ML technologies to ensure superior quality parts production in AM, paving the way for its broader industrial adoption.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 6","pages":"2522-2534"},"PeriodicalIF":9.4,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143849734","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}

引用次数: 0

Distributed Practical Fixed-Time Resource Allocation Algorithm for Disturbed Multiagent Systems: An Integrated Framework 扰动多智能体系统的分布式实用固定时间资源分配算法：一个集成框架

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-18 DOI: 10.1109/TCYB.2025.3558787

Qingxiang Ao;Cheng Li;Ben Niu;Zhiliang Zhao;Jiaxin Yuan;Sen Chen;Xiaole Yang

{"title":"Distributed Practical Fixed-Time Resource Allocation Algorithm for Disturbed Multiagent Systems: An Integrated Framework","authors":"Qingxiang Ao;Cheng Li;Ben Niu;Zhiliang Zhao;Jiaxin Yuan;Sen Chen;Xiaole Yang","doi":"10.1109/TCYB.2025.3558787","DOIUrl":"10.1109/TCYB.2025.3558787","url":null,"abstract":"The practical fixed-time resource allocation problem is investigated for multi-input-multi-output nonlinear uncertain multiagent systems with disturbed dynamics, subject to global equality and local inequality constraints. Due to the coexistence of distributed high-order dynamics system within agents and decision-making constraints, decision variables in resource allocation optimization problems cannot be directly obtained from the system. Existing strategies are insufficient to solve such complex fixed-time optimization control problems with coupled decision-making constraints. To address these challenges, a novel integrated framework is proposed, fusing symbolic-function-based fixed-time control theory with gradient consistency. The proposed algorithm is implemented through an output-feedback backstepping design process, which involves two stages. First, in the output-feedback design stage, a fixed-time high-order extended state observer estimates the uncertain dynamics and disturbances. Second, in the backstepping design stage, a time-switching controller is developed. This controller’s virtual control law has two components: the first employs the proportional-integral control method to satisfy the equality constraints, while the second uses gradient information from the <inline-formula> <tex-math>$epsilon $ </tex-math></inline-formula>-exact penalty function to address the inequality constraints. Using the Lyapunov stability criterion, the proposed algorithm can ensure that all signals remain practical fixed-time stable, and that the error between the outputs of all agents and the optimal solution is maintained within a neighborhood of the origin. Finally, simulations are presented to demonstrate the effectiveness of the approach.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 6","pages":"2820-2832"},"PeriodicalIF":9.4,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143849810","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}

引用次数: 0

Asynchronous Control of Cyber–Physical Systems With Quantized Measurements and Stochastic Multimode Attacks 基于量化测量和随机多模攻击的信息物理系统异步控制

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-18 DOI: 10.1109/TCYB.2025.3555396

Yuan Wang;Huaicheng Yan;Ju H. Park;Yunsong Hu;Hao Shen

{"title":"Asynchronous Control of Cyber–Physical Systems With Quantized Measurements and Stochastic Multimode Attacks","authors":"Yuan Wang;Huaicheng Yan;Ju H. Park;Yunsong Hu;Hao Shen","doi":"10.1109/TCYB.2025.3555396","DOIUrl":"10.1109/TCYB.2025.3555396","url":null,"abstract":"This article is concerned with the observer-dependent asynchronous control problem in cyber-physical systems (CPSs) vulnerable to multimode attacks, with a specific focus on addressing the significant challenge posed by the surreptitious nature of attack behaviors. First, in view of band-limited communication channels in CPSs, the quantizer is used to quantize the measured output. Second, owing to the open and shared network of CPSs, the data transmission process is more susceptible to attacks. A multichannel transmission framework is constructed under the assumption that each transmitted data element is susceptible to potential attacks. The switching dynamics among various attack forms launched by the adversary on the transmission channel are governed by a semi-Markov chain. The analysis of multimode attacks with stealth characteristics is conducted within the framework of a hidden semi-Markov jump mode, which is achieved by establishing a dual-layer stochastic process comprising a multimode sequence and an observed mode sequence. Leveraging emission probability, we design an observed-mode-dependent controller capable of stabilizing the system even in the absence of direct access to the actual attack patterns and in the presence of information loss. The simulations involving a single-channel unmanned ground vehicle system and a mass-spring–damper system with two channels are provided to validate the feasibility and efficacy of our proposed methodology.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 7","pages":"3390-3402"},"PeriodicalIF":9.4,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143849811","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}

引用次数: 0

Distributed Resilient Secondary Control Strategy Considering Economic Dispatch for DC Microgrids: A Dynamic Event-Triggered Mechanism 考虑经济调度的直流微电网分布式弹性二次控制策略：动态事件触发机制

IF 11.8 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-18 DOI: 10.1109/tcyb.2025.3554751

Daduan Zhao, Yan Li, Xiangyang Cao, Yue Sun, Chenghui Zhang

引用次数: 0

Cooperative Multiagent Learning and Exploration With Min–Max Intrinsic Motivation 最小-最大内在动机下的合作多智能体学习与探索

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-18 DOI: 10.1109/TCYB.2025.3557694

Yaqing Hou;Jie Kang;Haiyin Piao;Yifeng Zeng;Yew-Soon Ong;Yaochu Jin;Qiang Zhang

{"title":"Cooperative Multiagent Learning and Exploration With Min–Max Intrinsic Motivation","authors":"Yaqing Hou;Jie Kang;Haiyin Piao;Yifeng Zeng;Yew-Soon Ong;Yaochu Jin;Qiang Zhang","doi":"10.1109/TCYB.2025.3557694","DOIUrl":"10.1109/TCYB.2025.3557694","url":null,"abstract":"In the field of multiagent reinforcement learning (MARL), the ability to effectively explore unknown environments and collect information and experiences that are most beneficial for policy learning represents a critical research area. However, existing work often encounters difficulties in addressing the uncertainties caused by state changes and the inconsistencies between agents’ local observations and global information, which presents significant challenges to coordinated exploration among multiple agents. To address this issue, this article proposes a novel MARL exploration method with Min-Max intrinsic motivation (E2M) that promotes the learning of joint policies of agents by introducing surprise minimization and social influence maximization. Since the agent is subject to unstable state changes in the environment, we introduce surprise minimization by computing state entropy to encourage the agents to cope with more stable and familiar situations. This method enables surprise estimation based on the low-dimensional representation of states obtained from random encoders. Furthermore, to prevent surprise minimization from leading to conservative policies, we introduce mutual information between agents’ behaviors as social influence. By maximizing social influence, the agents are encouraged to interact to facilitate the emergence of cooperative behavior. The performance of our proposed E2M is testified across a range of popular StarCraft II and Multiagent MuJoCo tasks. Comprehensive results demonstrate its effectiveness in enhancing the cooperative capability of the multiple agents.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 6","pages":"2852-2864"},"PeriodicalIF":9.4,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143849813","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}

引用次数: 0

Dynamic Locomotion Synchronization and Fuzzy Control of a Lower Limb Exoskeleton With Body Weight Support for Active Following Human Operator 负重支撑下肢外骨骼动态运动同步与模糊控制

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-18 DOI: 10.1109/TCYB.2025.3558616

Guoxin Li;Jiacheng Xu;Zhijun Li;Rong Song;Yu Kang

{"title":"Dynamic Locomotion Synchronization and Fuzzy Control of a Lower Limb Exoskeleton With Body Weight Support for Active Following Human Operator","authors":"Guoxin Li;Jiacheng Xu;Zhijun Li;Rong Song;Yu Kang","doi":"10.1109/TCYB.2025.3558616","DOIUrl":"10.1109/TCYB.2025.3558616","url":null,"abstract":"Despite remarkable progress in robotic exoskeletons, exoskeletons are still far from matching human-level guidance and locomotion performance in gait training or movement enhancement. A desirable exoskeleton would first provide a standard gait profile by learning from human operators while requiring body weight support with active human-following to govern dynamic locomotion synchronization. To address these issues, in this article, we propose a human operator-involved dynamic locomotion synchronization control framework for the lower limb exoskeleton actively following gait training with gravity-supporting. First, we designed a human motion capture system based on a five-link model for the locomotion of a human operator. To reproduce human-level motor skills, we use whole-body teleoperation to leverage human control intelligence to command the locomotion of a robotic exoskeleton system. Specifically, using the linear inverted pendulum (LIP) model, the human operator’s divergent component of motion (DCM) is obtained by the human motion capture system. The dynamic similarity is used to generate a reference DCM for the robotic exoskeleton to synchronize the human operator’s movement. Finally, a fuzzy-based adaptive controller is designed to track the synchronous trajectory for the exoskeleton in the presence of robotic dynamics uncertainties with input saturation. Experiments on the human subject are carried out to demonstrate the effectiveness of the proposed method.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 6","pages":"2792-2805"},"PeriodicalIF":9.4,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143849783","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}

引用次数: 0

On Consensus Control of Uncertain Multiagent Systems Based on Two Types of Interval Observers 基于两类区间观测器的不确定多智能体系统的一致控制

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-18 DOI: 10.1109/TCYB.2025.3559110

Yuchen Qian;Zhonghua Miao;Jin Zhou;Xiaojin Zhu

引用次数: 0

Robust Reconstructed Neural Network With Spectral Reshaping Activation 采用频谱重塑激活的鲁棒重构神经网络

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-16 DOI: 10.1109/TCYB.2025.3557397

Honggui Han;Zecheng Tang;Xiaolong Wu;Hongyan Yang;Junfei Qiao

引用次数: 0

Intermittent Observer for Chaotic Lur’e Systems With Multi-Nondifferentiable Delay and Partially Limited Output Channels and Its Application to Secure Communication 具有多不可微延迟和部分受限输出信道的混沌Lur系统间歇观测器及其在保密通信中的应用

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-16 DOI: 10.1109/TCYB.2025.3557539

Kui Ding;Quanxin Zhu;Tingwen Huang

{"title":"Intermittent Observer for Chaotic Lur’e Systems With Multi-Nondifferentiable Delay and Partially Limited Output Channels and Its Application to Secure Communication","authors":"Kui Ding;Quanxin Zhu;Tingwen Huang","doi":"10.1109/TCYB.2025.3557539","DOIUrl":"10.1109/TCYB.2025.3557539","url":null,"abstract":"This study focuses on the state tracking problems of chaotic Lur’e systems with nondifferentiable delay and partial channel restriction via intermittent observer. Different from the results obtained by existing chaotic Lur’e systems, the time delay involved in the chaotic Lur’e system explored in this study does not require that the time delay must be differentiable and there is no limit that the time delay must be bounded, which is more in accordance with the operating situation in practical engineering. Subsequently, aiming at the inevitable cyber-attack in the communication network environment, an intermittent observer based on the loss of partial measurement information induced by cyber-attack is constructed. Especially, in the operation process of the designed intermittent estimator, it breaks through the strict requirement that the observation width must be greater than the upper limit of the delay in the existing work, which intuitively reflects the wider application range and has more exploratory significance. Moreover, a meaningful lemma is designed, which effectively overcomes the invalidity of existing Lyapunov function or Lyapunov–Krasovskii functional methods for nondifferentiable systems, and develops novel criteria for partial information loss and nondifferentiable systems, presenting an important theoretical guidance for related topics. Numerical simulations are provided to verify the effectiveness of the proposed intermittent observer mechanism and the stabilization criteria of the error system. Finally, an application of the proposed intermittent observation result for two identical chaotic systems to a secure communication approach is provided.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 7","pages":"3306-3319"},"PeriodicalIF":9.4,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143841481","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}

引用次数: 0