Journal of Automation and Intelligence最新文献_第4页

Privacy-preserving distributed consensus over directed networks with limited communication 在有限通信的定向网络上保持隐私的分布式共识

Journal of Automation and Intelligence Pub Date : 2025-12-01 Epub Date: 2025-08-26 DOI: 10.1016/j.jai.2025.08.004

Yang Song , Jian Guo , Jimin Wang

引用次数: 0

Distributed optimal formation control of heterogeneous Euler–Lagrange multi-agent systems 异构欧拉-拉格朗日多智能体系统的分布式最优编队控制

Journal of Automation and Intelligence Pub Date : 2025-12-01 Epub Date: 2025-03-27 DOI: 10.1016/j.jai.2025.03.007

Mengmeng Duan, Fengping Huang, Shanying Zhu, Ziwen Yang, Cailian Chen

引用次数: 0

CLAD: Criterion learner and attention distillation for automated CNN prunning CLAD: CNN自动剪枝的标准学习器和注意蒸馏

Journal of Automation and Intelligence Pub Date : 2025-12-01 Epub Date: 2025-08-26 DOI: 10.1016/j.jai.2025.08.002

Zheng Li , Jiaxin Li , Shaojie Liu , Bo Zhao , Derong Liu

{"title":"CLAD: Criterion learner and attention distillation for automated CNN prunning","authors":"Zheng Li , Jiaxin Li , Shaojie Liu , Bo Zhao , Derong Liu","doi":"10.1016/j.jai.2025.08.002","DOIUrl":"10.1016/j.jai.2025.08.002","url":null,"abstract":"<div><div>Filter pruning effectively compresses the neural network by reducing both its parameters and computational cost. Existing pruning methods typically rely on pre-designed pruning criteria to measure filter importance and remove those deemed unimportant. However, different layers of the neural network exhibit varying filter distributions, making it inappropriate to implement the same pruning criterion for all layers. Additionally, some approaches apply different criteria from the set of pre-defined pruning rules for different layers, but the limited space leads to the difficulty of covering all layers. If criteria for all layers are manually designed, it is costly and difficult to generalize to other networks. To solve this problem, we present a novel neural network pruning method based on the Criterion Learner and Attention Distillation (CLAD). Specifically, CLAD develops a differentiable criterion learner, which is integrated into each layer of the network. The learner can automatically learn the appropriate pruning criterion according to the filter parameters of each layer, thus the requirement of manual design is eliminated. Furthermore, the criterion learner is trained end-to-end by the gradient optimization algorithm to achieve efficient pruning. In addition, attention distillation, which fully utilizes the knowledge of unpruned networks to guide the optimization of the learner and improve the pruned network performance, is introduced in the process of learner optimization. Experiments conducted on various datasets and networks demonstrate the effectiveness of the proposed method. Notably, CLAD reduces the FLOPs of ResNet-110 by about 53% on the CIFAR-10 dataset, while simultaneously improves the network’s accuracy by 0.05%. Moreover, it reduces the FLOPs of ResNet-50 by about 46% on the ImageNet-1K dataset, and maintains a top-1 accuracy of 75.45%.</div></div>","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"4 4","pages":"Pages 254-265"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145799792","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}

引用次数: 0

Stackelberg game-based optimal secure control against hybrid attacks for networked control systems 基于Stackelberg博弈的网络控制系统抗混合攻击最优安全控制

Journal of Automation and Intelligence Pub Date : 2025-09-01 Epub Date: 2025-03-29 DOI: 10.1016/j.jai.2025.03.006

Wei Xiong , Yi Dong , Liubin Zhou

引用次数: 0

Human–AI interactive optimized shared control 人机交互优化共享控制

Journal of Automation and Intelligence Pub Date : 2025-09-01 Epub Date: 2025-01-09 DOI: 10.1016/j.jai.2025.01.001

Junkai Tan , Shuangsi Xue , Hui Cao , Shuzhi Sam Ge

{"title":"Human–AI interactive optimized shared control","authors":"Junkai Tan , Shuangsi Xue , Hui Cao , Shuzhi Sam Ge","doi":"10.1016/j.jai.2025.01.001","DOIUrl":"10.1016/j.jai.2025.01.001","url":null,"abstract":"<div><div>This paper presents an optimized shared control algorithm for human–AI interaction, implemented through a digital twin framework where the physical system and human operator act as the real agent while an AI-driven digital system functions as the virtual agent. In this digital twin architecture, the real agent acquires an optimal control strategy through observed actions, while the AI virtual agent mirrors the real agent to establish a digital replica system and corresponding control policy. Both the real and virtual optimal controllers are approximated using reinforcement learning (RL) techniques. Specifically, critic neural networks (NNs) are employed to learn the virtual and real optimal value functions, while actor NNs are trained to derive their respective optimal controllers. A novel shared mechanism is introduced to integrate both virtual and real value functions into a unified learning framework, yielding an optimal shared controller. This controller adaptively adjusts the confidence ratio between virtual and real agents, enhancing the system’s efficiency and flexibility in handling complex control tasks. The stability of the closed-loop system is rigorously analyzed using the Lyapunov method. The effectiveness of the proposed AI–human interactive system is validated through two numerical examples: a representative nonlinear system and an unmanned aerial vehicle (UAV) control system.</div></div>","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"4 3","pages":"Pages 163-176"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145108734","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}

引用次数: 0

Fault-tolerant control for swarm systems: A geometric-based PDE planning approach 群系统容错控制：一种基于几何的PDE规划方法

Journal of Automation and Intelligence Pub Date : 2025-09-01 Epub Date: 2025-03-18 DOI: 10.1016/j.jai.2025.03.002

Yacun Guan , Bin Jiang , Youmin Zhang , Yun Chen

引用次数: 0

Dynamic hedging of 50ETF options using Proximal Policy Optimization 基于近端策略优化的50ETF期权动态套期保值

Journal of Automation and Intelligence Pub Date : 2025-09-01 Epub Date: 2025-04-09 DOI: 10.1016/j.jai.2025.04.001

Lei Liu , Mengmeng Hao , Jinde Cao

引用次数: 0

Densely-connected Decoder Transformer for unsupervised anomaly detection of power electronic systems 用于电力电子系统无监督异常检测的密集连接解码器变压器

Journal of Automation and Intelligence Pub Date : 2025-09-01 Epub Date: 2025-05-30 DOI: 10.1016/j.jai.2025.05.002

Zhichen Zhang, Gen Qiu, Yuhua Cheng, Min Wang

{"title":"Densely-connected Decoder Transformer for unsupervised anomaly detection of power electronic systems","authors":"Zhichen Zhang, Gen Qiu, Yuhua Cheng, Min Wang","doi":"10.1016/j.jai.2025.05.002","DOIUrl":"10.1016/j.jai.2025.05.002","url":null,"abstract":"<div><div>Reliable electricity infrastructure is critical for modern society, highlighting the importance of securing the stability of fundamental power electronic systems. However, as such systems frequently involve high-current and high-voltage conditions, there is a greater likelihood of failures. Consequently, anomaly detection of power electronic systems holds great significance, which is a task that properly-designed neural networks can well undertake, as proven in various scenarios. Transformer-like networks are promising for such application, yet with its structure initially designed for different tasks, features extracted by beginning layers are often lost, decreasing detection performance. Also, such data-driven methods typically require sufficient anomalous data for training, which could be difficult to obtain in practice. Therefore, to improve feature utilization while achieving efficient unsupervised learning, a novel model, Densely-connected Decoder Transformer (DDformer), is proposed for unsupervised anomaly detection of power electronic systems in this paper. First, efficient label-free training is achieved based on the concept of autoencoder with recursive-free output. An encoder–decoder structure with densely-connected decoder is then adopted, merging features from all encoder layers to avoid possible loss of mined features while reducing training difficulty. Both simulation and real-world experiments are conducted to validate the capabilities of DDformer, and the average FDR has surpassed baseline models, reaching 89.39%, 93.91%, 95.98% in different experiment setups respectively.</div></div>","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"4 3","pages":"Pages 217-226"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145108717","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}

引用次数: 0

Multiplayer Pareto optimal control with H∞ constraint for nonlinear stochastic system via online synchronous reinforcement learning 基于在线同步强化学习的非线性随机系统H∞约束多人Pareto最优控制

Journal of Automation and Intelligence Pub Date : 2025-09-01 Epub Date: 2025-06-03 DOI: 10.1016/j.jai.2025.05.004

Li Wang , Xiushan Jiang , Dongya Zhao , Bor-Sen Chen

{"title":"Multiplayer Pareto optimal control with H∞ constraint for nonlinear stochastic system via online synchronous reinforcement learning","authors":"Li Wang , Xiushan Jiang , Dongya Zhao , Bor-Sen Chen","doi":"10.1016/j.jai.2025.05.004","DOIUrl":"10.1016/j.jai.2025.05.004","url":null,"abstract":"<div><div>This paper investigates a multiplayer Pareto game for affine nonlinear stochastic systems disturbed by both external and the internal multiplicative noises. The Pareto cooperative optimal strategies with the <span><math><msub><mrow><mi>H</mi></mrow><mrow><mi>∞</mi></mrow></msub></math></span> constraint are resolved by integrating <span><math><mrow><msub><mrow><mi>H</mi></mrow><mrow><mn>2</mn></mrow></msub><mo>/</mo><msub><mrow><mi>H</mi></mrow><mrow><mi>∞</mi></mrow></msub></mrow></math></span> theory with Pareto game theory. First, a nonlinear stochastic bounded real lemma (SBRL) is derived, explicitly accounting for non-zero initial conditions. Through the analysis of four cross-coupled Hamilton–Jacobi equations (HJEs), we establish necessary and sufficient conditions for the existence of Pareto optimal strategies with the <span><math><msub><mrow><mi>H</mi></mrow><mrow><mi>∞</mi></mrow></msub></math></span> constraint. Secondly, to address the complexity of solving these nonlinear partial differential HJEs, we propose a neural network (NN) framework with synchronous tuning rules for the actor, critic, and disturbance components, based on a reinforcement learning (RL) approach. The designed tuning rules ensure convergence of the actor–critic-disturbance components to the desired values, enabling the realization of robust Pareto control strategies. The convergence of the proposed algorithm is rigorously analyzed using a constructed Lyapunov function for the NN weight errors. Finally, a numerical simulation example is provided to demonstrate the effectiveness of the proposed methods and main results.</div></div>","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"4 3","pages":"Pages 207-216"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145108735","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}

引用次数: 0

On the stability criteria for constrained switched linear systems with multiple faults 多故障约束切换线性系统的稳定性判据

Journal of Automation and Intelligence Pub Date : 2025-09-01 Epub Date: 2025-04-23 DOI: 10.1016/j.jai.2025.04.002

Tianyu Tan , Kunwu Zhang , Keyong Shao , Songlin Zhuang , Yang Shi

{"title":"On the stability criteria for constrained switched linear systems with multiple faults","authors":"Tianyu Tan , Kunwu Zhang , Keyong Shao , Songlin Zhuang , Yang Shi","doi":"10.1016/j.jai.2025.04.002","DOIUrl":"10.1016/j.jai.2025.04.002","url":null,"abstract":"<div><div>Switched systems play an imperative role in modeling many real industrial systems with abrupt changes. Due to possible exposure to unreliable and complex physical environments, switching dynamics may simultaneously face multiple faults, including the unexpected controller disconnect, the temporary mismatch between subsystems and desired corresponding controllers, and the intermittent disordering of mode transitions. These commonly arising faults may result in severe and detrimental impacts on the reliability and convergence of the closed-loop solution, thereby bringing significant yet challenging issues to be tackled. This paper provides the first attempt to investigate the stabilization problem for a class of constrained switched linear systems with multiple faults under mode-dependent dwell time (MDT). From a set-theory perspective, we demonstrate a critical necessary and sufficient stability condition for switched systems without uncertainties. Moreover, the non-conservative stability criterion is further extended to the perturbed switched systems with rigorous proof. A switching communication network example verifies the validity of the theoretical result and demonstrates their advantages.</div></div>","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"4 3","pages":"Pages 185-197"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145108736","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}

引用次数: 0