Pub Date : 2024-07-18DOI: 10.1109/TSMC.2024.3417394
Hongyu Sun;Bo Yuan;Neal N. Xiong;Jiao Song;Wensi Ding;Qiang Liu
In this article, a novel system based on the simultaneous iterative reconstructive technique (SIRT) and multiagent deep reinforcement learning is proposed for detection of anomalous geological structures in coal mines. The system employs the SIRT optimization inversion method to construct a computational model for channel wave signal imaging. Then, the back projection technique (BPT) was introduced to the system. By utilizing the BPT algorithm to provide initial values for the SIRT, the channel wave signals can be prescreened, improving the ability of the SIRT algorithm to suppress model noise and enhancing its resolution. Furthermore, we employ multiagent reinforcement learning method for image feature classification of anomalous geological structures. Moreover, we conduct two-dimensional and three-dimensional imaging of four types of changes and energy fluctuations. The results demonstrate a high degree of concordance between the computed channel wave results and the slowness of the measured channel wave signals. Experimental findings validate the exceptional computational accuracy of this novel system, with relative errors and coefficient of deviation both within 1%, surpassing traditional SIRT inversion methods, damped least-squares methods, conjugate gradient methods, and classical algebraic reconstruction methods. These discoveries demonstrate the feasibility and superiority of utilizing transmission tomography imaging technology for the detection of anomalous structures in coal seams, offering new perspectives for underground exploration in coal mines.
{"title":"MDRL-ETT: A Multiagent Deep Reinforcement Learning-Enhanced Transmission Tomography System to Detect Anomalous Geological Structures","authors":"Hongyu Sun;Bo Yuan;Neal N. Xiong;Jiao Song;Wensi Ding;Qiang Liu","doi":"10.1109/TSMC.2024.3417394","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3417394","url":null,"abstract":"In this article, a novel system based on the simultaneous iterative reconstructive technique (SIRT) and multiagent deep reinforcement learning is proposed for detection of anomalous geological structures in coal mines. The system employs the SIRT optimization inversion method to construct a computational model for channel wave signal imaging. Then, the back projection technique (BPT) was introduced to the system. By utilizing the BPT algorithm to provide initial values for the SIRT, the channel wave signals can be prescreened, improving the ability of the SIRT algorithm to suppress model noise and enhancing its resolution. Furthermore, we employ multiagent reinforcement learning method for image feature classification of anomalous geological structures. Moreover, we conduct two-dimensional and three-dimensional imaging of four types of changes and energy fluctuations. The results demonstrate a high degree of concordance between the computed channel wave results and the slowness of the measured channel wave signals. Experimental findings validate the exceptional computational accuracy of this novel system, with relative errors and coefficient of deviation both within 1%, surpassing traditional SIRT inversion methods, damped least-squares methods, conjugate gradient methods, and classical algebraic reconstruction methods. These discoveries demonstrate the feasibility and superiority of utilizing transmission tomography imaging technology for the detection of anomalous structures in coal seams, offering new perspectives for underground exploration in coal mines.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142275008","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 : 2024-07-18DOI: 10.1109/TSMC.2024.3418950
Di Yang;Weijun Liu;Zhiwu Li
This article proposes a new adaptive neural control scheme with guaranteed performance for mechanical systems under dynamic uncertainties and uncertain initial conditions. Employing the novel time-varying neuron (TVN) approach and a shifting function, the control method developed in this article can systematically solve two crucial problems: one is how to construct a variable structure network to improve the approximation ability while the online tuning parameters do not increase with the number of neurons, and the other is how to achieve the predetermined tracking performance for multi-input multi-output (MIMO) mechanical systems under any bounded initial tracking errors. To approximate uncertain dynamics, the TVN approach is first presented to instruct the process of adding new neurons for better-learning capability, where the online updating parameters in the neural network (NN) unit are compressed by the vector projection technique, yielding an NN approximator with low-computational burden. By virtue of a shifting function, the uncertain initial tracking error is converted to zero such that a speed function with predetermined convergence performance can be efficiently employed to constrain the tracking trajectory without considering the initial condition. Moreover, to obviate the differentiation operation for the virtual stabilizing function, the dynamic surface technique is adopted to derive the presented control scheme for facilitating practical implementation. Finally, the effectiveness and benefits of the presented control are verified via theoretical analysis and a two-link manipulator.
本文针对动态不确定性和不确定初始条件下的机械系统，提出了一种性能有保证的新型自适应神经控制方案。通过采用新颖的时变神经元（TVN）方法和移位函数，本文提出的控制方法可以系统地解决两个关键问题：一是如何构建可变结构网络以提高逼近能力，同时在线调谐参数不随神经元数量的增加而增加；二是如何在任何有界初始跟踪误差条件下实现多输入多输出（MIMO）机械系统的预定跟踪性能。为了逼近不确定的动力学，首先提出了 TVN 方法来指导新神经元的添加过程，以获得更好的学习能力，其中神经网络（NN）单元中的在线更新参数通过向量投影技术进行了压缩，从而产生了一种低计算负担的 NN 近似器。通过移位函数，不确定的初始跟踪误差被转换为零，从而可以有效地使用具有预定收敛性能的速度函数来约束跟踪轨迹，而无需考虑初始条件。此外，为了避免对虚拟稳定函数进行微分运算，采用了动态曲面技术来推导所提出的控制方案，以方便实际应用。最后，通过理论分析和双链操纵器验证了所提出的控制方案的有效性和优势。
{"title":"Adaptive Neural Control With Guaranteed Performance for Mechanical Systems Under Uncertain Initial Conditions: A Time-Varying Neuron Approach","authors":"Di Yang;Weijun Liu;Zhiwu Li","doi":"10.1109/TSMC.2024.3418950","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3418950","url":null,"abstract":"This article proposes a new adaptive neural control scheme with guaranteed performance for mechanical systems under dynamic uncertainties and uncertain initial conditions. Employing the novel time-varying neuron (TVN) approach and a shifting function, the control method developed in this article can systematically solve two crucial problems: one is how to construct a variable structure network to improve the approximation ability while the online tuning parameters do not increase with the number of neurons, and the other is how to achieve the predetermined tracking performance for multi-input multi-output (MIMO) mechanical systems under any bounded initial tracking errors. To approximate uncertain dynamics, the TVN approach is first presented to instruct the process of adding new neurons for better-learning capability, where the online updating parameters in the neural network (NN) unit are compressed by the vector projection technique, yielding an NN approximator with low-computational burden. By virtue of a shifting function, the uncertain initial tracking error is converted to zero such that a speed function with predetermined convergence performance can be efficiently employed to constrain the tracking trajectory without considering the initial condition. Moreover, to obviate the differentiation operation for the virtual stabilizing function, the dynamic surface technique is adopted to derive the presented control scheme for facilitating practical implementation. Finally, the effectiveness and benefits of the presented control are verified via theoretical analysis and a two-link manipulator.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142275010","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 : 2024-07-18DOI: 10.1109/TSMC.2024.3429685
{"title":"TechRxiv: Share Your Preprint Research with the World!","authors":"","doi":"10.1109/TSMC.2024.3429685","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3429685","url":null,"abstract":"","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10604668","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141725678","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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}
Pub Date : 2024-07-18DOI: 10.1109/TSMC.2024.3429679
{"title":"Information For Authors","authors":"","doi":"10.1109/TSMC.2024.3429679","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3429679","url":null,"abstract":"","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10604673","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141725645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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}
Pub Date : 2024-07-18DOI: 10.1109/TSMC.2024.3429675
{"title":"TechRxiv: Share Your Preprint Research with the World!","authors":"","doi":"10.1109/TSMC.2024.3429675","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3429675","url":null,"abstract":"","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10604684","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141725649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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}
Pub Date : 2024-07-18DOI: 10.1109/TSMC.2024.3417977
Yingkang Xie;Qian Ma;Choon Ki Ahn
This study explores finite-time adaptive neural tracking control for output-constrained nonlinear systems. An improved command filter was utilized to simplify the controller, and a compensation system ensured that the filter error converged in finite time. To avoid singularities during the controller design process, a novel switch function was employed in the command filter, including a compensation system and virtual controller, which guaranteed the second-order derivability of the virtual controller. Furthermore, to reduce the communication burden, an improved Zeno-free event-triggered condition was introduced. The control strategy ensured that all the closed-loop system variables remained bounded and that the reference trajectory could be well-tracked in finite time. Finally, a simulation example was given to support our control strategy.
{"title":"Finite-Time Adaptive Tracking Control for Output-Constrained Nonlinear Systems: An Improved Command Filter Approach","authors":"Yingkang Xie;Qian Ma;Choon Ki Ahn","doi":"10.1109/TSMC.2024.3417977","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3417977","url":null,"abstract":"This study explores finite-time adaptive neural tracking control for output-constrained nonlinear systems. An improved command filter was utilized to simplify the controller, and a compensation system ensured that the filter error converged in finite time. To avoid singularities during the controller design process, a novel switch function was employed in the command filter, including a compensation system and virtual controller, which guaranteed the second-order derivability of the virtual controller. Furthermore, to reduce the communication burden, an improved Zeno-free event-triggered condition was introduced. The control strategy ensured that all the closed-loop system variables remained bounded and that the reference trajectory could be well-tracked in finite time. Finally, a simulation example was given to support our control strategy.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142246408","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 : 2024-07-18DOI: 10.1109/TSMC.2024.3418428
Tiantian Gai;Jian Wu;Francisco Chiclana;Mingshuo Cao;Ronald R. Yager
In social network group decision making (SN-GDM), overlapping communities are special community structures that can assist opinion interaction to reach group consensus. However, the specific mechanisms of how overlapping structures facilitate community interaction need to be further explored. In addition, the compromise behavior of decision makers (DMs) is conducive to group consensus, but it is usually fixed at the same value, and then it need further research the characteristic of the dynamics compromise limits. To this end, the overlapping community structures under DMs’ trust network is detected. Then, the effect of community overlap in social networks on community interaction is explored. Meanwhile, a limited compromise function is built based on prospect theory to describe the dynamic compromise behavior of communities. Hence, a dynamic compromise behavior driven bidirectional feedback mechanism with overlapping communities is proposed in the context of SN-GDM, and an illustrative example with comparative analysis is provided to testify the advantages of proposed method. It is proved that overlapping communities can improve the compromise willingness compared to nonoverlapping communities, indicating that overlapping communities can serve as a bridge to facilitate interaction, and the dynamic compromise behavior can more realistically describe the real behavior of DMs. In general terms, the proposed method provides a solution to the consensus reaching issue of SN-GDM from a new perspective. Specifically, it can be applied to real-life application scenarios, such as group recommendation to recommend acceptable solutions for social network group users.
{"title":"Dynamic Compromise Behavior Driven Bidirectional Feedback Mechanism for Group Consensus With Overlapping Communities in Social Network","authors":"Tiantian Gai;Jian Wu;Francisco Chiclana;Mingshuo Cao;Ronald R. Yager","doi":"10.1109/TSMC.2024.3418428","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3418428","url":null,"abstract":"In social network group decision making (SN-GDM), overlapping communities are special community structures that can assist opinion interaction to reach group consensus. However, the specific mechanisms of how overlapping structures facilitate community interaction need to be further explored. In addition, the compromise behavior of decision makers (DMs) is conducive to group consensus, but it is usually fixed at the same value, and then it need further research the characteristic of the dynamics compromise limits. To this end, the overlapping community structures under DMs’ trust network is detected. Then, the effect of community overlap in social networks on community interaction is explored. Meanwhile, a limited compromise function is built based on prospect theory to describe the dynamic compromise behavior of communities. Hence, a dynamic compromise behavior driven bidirectional feedback mechanism with overlapping communities is proposed in the context of SN-GDM, and an illustrative example with comparative analysis is provided to testify the advantages of proposed method. It is proved that overlapping communities can improve the compromise willingness compared to nonoverlapping communities, indicating that overlapping communities can serve as a bridge to facilitate interaction, and the dynamic compromise behavior can more realistically describe the real behavior of DMs. In general terms, the proposed method provides a solution to the consensus reaching issue of SN-GDM from a new perspective. Specifically, it can be applied to real-life application scenarios, such as group recommendation to recommend acceptable solutions for social network group users.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142235880","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 : 2024-07-18DOI: 10.1109/TSMC.2024.3429669
{"title":"IEEE Transactions on Systems, Man, and Cybernetics publication information","authors":"","doi":"10.1109/TSMC.2024.3429669","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3429669","url":null,"abstract":"","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10604670","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141729907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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}
Pub Date : 2024-07-18DOI: 10.1109/TSMC.2024.3429671
{"title":"IEEE Systems, Man, and Cybernetics Society Information","authors":"","doi":"10.1109/TSMC.2024.3429671","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3429671","url":null,"abstract":"","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10604686","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141725648","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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}
Pub Date : 2024-07-18DOI: 10.1109/TSMC.2024.3429683
{"title":"IEEE Transactions on Systems, Man, and Cybernetics publication information","authors":"","doi":"10.1109/TSMC.2024.3429683","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3429683","url":null,"abstract":"","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10604690","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141732500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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}
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：