检索结果-内蒙古大学图书馆

One-Variable Attack on the Industrial Fault Classification System and Its Defense

engineering 2022年第12期19卷 240-251页

作者： Yue Zhuo Yuri A.W.Shardt Zhiqiang Ge State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhou 310027China Department of Automation Engineering Technische Universität IlmenauIlmenau D-98684Germany

Recently developed fault classification methods for industrial processes are mainly ***,models based on deep neural networks have significantly improved fault classification accuracy owing to the inclusion of a large number of data ***,these data-driven models are vulnerable to adversarial attacks;thus,small perturbations on the samples can cause the models to provide incorrect fault *** recent studies have demonstrated the vulnerability of machine learning methods and the existence of adversarial *** paper proposes a black-box attack method with an extreme constraint for a safe-critical industrial fault classification system:Only one variable can be perturbed to craft adversarial ***,to hide the adversarial samples in the visualization space,a Jacobian matrix is used to guide the perturbed variable selection,making the adversarial samples in the dimensional reduction space invisible to the human *** the one-variable attack(OVA)method,we explore the vulnerability of industrial variables and fault types,which can help understand the geometric characteristics of fault classification *** on the attack method,a corresponding adversarial training defense method is also proposed,which efficiently defends against an OVA and improves the prediction accuracy of the *** experiments,the proposed method was tested on two datasets from the Tennessee–Eastman process(TEP)and steel plates(SP).We explore the vulnerability and correlation within variables and faults and verify the effectiveness of OVAs and defenses for various classifiers and *** industrial fault classification systems,the attack success rate of our method is close to(on TEP)or even higher than(on SP)the current most effective first-order white-box attack method,which requires perturbation of all variables.

关键词： Adversarial samples Black-box attack Industrial data security Fault classification system

来源：评论

学校读者我要写书评

暂无评论

Fusing Multi-scale Binary Convolution with Joint Attention Face Expression Recognition Algorithm 19th

Fusing Multi-scale Binary Convolution with Joint Attention ...

引用

19th Chinese Intelligent Systems Conference, CISC 2023

作者： Qin, Minbo Li, Lin Automation Division Department of Control Science and Engineering University of Shanghai for Science and Technology Shanghai200093 China

ISBN: (纸本)9789819968855

Addressing the challenges of wild facial expression datasets being affected by illumination and pose variations, and the expression features being dispersed across multiple easily overlooked facial regions, this paper proposes a facial expression recognition network called Binary and Joint Attention Network. Firstly, The multi-scale binary convolution module integrates texture features of different granularities. Subsequently, the proposed Multi-head Joint Attention module focusing on multiple distinct facial areas through multiple attention heads. Lastly, the inter-attention map loss is designed to prevent attention overlap while assisting in classification. Experimental results on multiple datasets, including SFEW2.0, RAF-DB, FER2013, demonstrate that the proposed network can effectively recognize various facial expressions. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Bayesian Filtering for High-Dimensional State-Space Models With State Partition and Error Compensation

引用

IEEE/CAA Journal of Automatica Sinica 2024年第5期11卷 1239-1249页

作者： Ke Li Shunyi Zhao Biao Huang Fei Liu Key Laboratory of Advanced Process Control for Light Industry(Ministry of Education) Institute of AutomationJiangnan UniversityWuxi 214122China Department of Chemical and Materials Engineering University of AlbertaEdmonton AB T6G 2G6Canada

In the era of exponential growth of data availability,the architecture of systems has a trend toward high dimensionality,and directly exploiting holistic information for state inference is not always computationally *** paper proposes a novel Bayesian filtering algorithm that considers algorithmic computational cost and estimation accuracy for high-dimensional linear *** high-dimensional state vector is divided into several blocks to save computation resources by avoiding the calculation of error covariance with immense *** that,two sequential states are estimated simultaneously by introducing an auxiliary variable in the new probability space,mitigating the performance degradation caused by state ***,the computational cost and error covariance of the proposed algorithm are analyzed analytically to show its distinct features compared with several existing *** results illustrate that the proposed Bayesian filtering can maintain a higher estimation accuracy with reasonable computational cost when applied to high-dimensional linear systems.

关键词： filtering estimation error

来源：评论

学校读者我要写书评

暂无评论

Proximity Estimation with Position Adjustment for Autonomous Industrial Inspection

Proximity Estimation with Position Adjustment for Autonomous...

引用

2024 International Conference on Artificial Intelligence of Things and Systems, AIoTSys 2024

作者： Zhou, Ziyi Huang, Ping Zheng, Song Xu, Zhezhuang Zhuang, Zixiong College of Electrical Engineering and Automation Fuzhou Univ. and Key Lab. of Industrial Automation Control Technology and Information Processing Education Department of Fujian Province Fuzhou350000 China

ISBN: (纸本)9798331507886

Due to the similarity in appearance and dense deployment of devices in industrial environments, relying solely on machine vision makes it challenging for inspection robots to accurately identify similar devices. Although wireless signals from industrial internet of things (IoT) can serve as identification features, signal fluctuations impact the accuracy and efficiency of recognition. To address this issue, this paper proposes a proximity estimation algorithm with position adjustment for autonomous industrial inspection. The algorithm considers the spatial relationships between nodes and the topological relationship between the signal strength and variations among the nodes. By analyzing the topological relationship between the signal strength and variations among the nodes, the robot autonomously adjusts its position and selects the proximal node based on the spatial topology relationship between them. We have built an inspection platform using quadruped robots to evaluate the effectiveness of the experiments. The experimental results demonstrate that the algorithm further improves the efficiency of identifying proximal devices while ensuring the estimation accuracy of the algorithm. © 2024 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Optimal Multi-agent Collision-Free Path Planning with Temporal Logic Constraints 5th

Optimal Multi-agent Collision-Free Path Planning with Tempo...

引用

5th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2021

作者： Zheng, Yiwei Liu, Zhaocong Lai, Aiwen Yu, Xiao Lan, Weiyao Department of Automation Xiamen University Fujian Xiamen361005 China The Science and Technology on Space Intelligent Control Laboratory Beijing Institute of Control Engineering Beijing100094 China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9789811939976

In this paper, we present a novel optimal multi-agent collision-free path planning algorithm (OMPATL) for the problem of multi-robot path planning with temporal logic constraints. Given a high-level mission specification in the form of linear temporal logic (LTL), OMPATL can automatically synthesize a set of trajectories for the multi-agent system (MAS), which achieves the collision avoidance among agents and minimizes the cost of the maximum traveling time between successive satisfactions. To synthesize the optimal trajectories, the motion of all agents, together with the mission area, is modeled as a weighted team transition system (TS) with a set of atomic propositions (APs). If the collision avoidance were not required, the optimal trajectories would be easily synthesized by an algorithm such as shortest paths. However, once the multi-agent systems are required to be safety-critical and collision-free, these trajectories may become infeasible. In OMPATL, a strategy is proposed for adding a set of transitions including "wait" and "go-back" to each individual TS based on the optimal run which does not consider collision avoidance. Then, the states and transitions with collisions can be removed such that the optimal collision-free trajectories are founded by the synthesis algorithm. The synthesized run balances collision avoidance, mission fulfillment, and optimality. The optimal run is synthesized offline and online adjustments are not needed. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Topography Modeling of Surface Grinding Based on Random Abrasives and Performance Evaluation

引用

Chinese Journal of Mechanical engineering 2024年第5期37卷 126-148页

作者： Yanbin Zhang Peng Gong Lizhi Tang Xin Cui Dongzhou Jia Teng Gao Yusuf Suleiman Dambatta Changhe Li Key Lab of Industrial Fluid Energy Conservation and Pollution Control Qingdao University of TechnologyMinistry of EducationQingdao 266520China School of Materials Science and Engineering Xi’an University of TechnologyXi’an 710048China College of Mechanical Engineering and Automation Liaoning University of TechnologyJinzhou 121001China Mechanical Engineering Department Ahmadu Bello UniversityZaria 810106Nigeria

The surface morphology and roughness of a workpiece are crucial parameters in grinding *** prediction of these parameters is essential for maintaining the workpiece’s surface ***,the randomness of abrasive grain shapes and workpiece surface formation behaviors poses significant challenges,and accuracy in current physical mechanism-based predictive models is *** address this problem,by using the random plane method and accounting for the random morphology and distribution of abrasive grains,this paper proposes a novel method to model CBN grinding wheels and predict workpiece surface ***,a kinematic model of a single abrasive grain is developed to accurately capture the three-dimensional morphology of the grinding ***,by formulating an elastic deformation and formation model of the workpiece surface based on Hertz theory,the variation in grinding arc length at different grinding depths is ***,a predictive model for the surface morphology of the workpiece ground by a single abrasive grain is *** model integrates the normal distribution model of abrasive grain size and the spatial distribution model of abrasive grain positions,to elucidate how the circumferential and axial distribution of abrasive grains influences workpiece surface ***,by integrating the dynamic effective abrasive grain model,a predictive model for the surface morphology and roughness of the grinding wheel is *** examine the impact of changing the grit size of the grinding wheel and grinding depth on workpiece surface roughness,and to validate the accuracy of the model,experiments are *** indicate that the predicted three-dimensional morphology of the grinding wheel and workpiece surfaces closely matches the actual grinding wheel and ground workpiece surfaces,with surface roughness prediction deviations as small as 2.3%.

关键词： Surface topography prediction Grinding Grinding wheel model Random plane method

来源：评论

学校读者我要写书评

暂无评论

Dynamic Event-Triggered Fixed-Time Consensus Analysis of Multi-Agent Systems Under Input Delays and Switching Topologies 3

Dynamic Event-Triggered Fixed-Time Consensus Analysis of Mul...

引用

3rd IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2024

作者： Zhang, Yu Li, Yajing Ran, Guangtao Yu, Hao Ma, Guangfu Department of Automation Shenzhen518055 China Shanghai Institute of Aerospace System Engineering Shanghai200241 China Harbin Institute of Technology Department of Control Science and Engineering Harbin150001 China School of Automation Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9798331540319

This paper proposes a dynamic event-triggered control method for first-order multi-agent systems with input delays and disturbances under switching topologies. The controller design and its properties of dynamic event-triggered fixed-time consensus are presented in detail. Furthermore, agents can achieve consensus in a fixed time for any initial conditions and topologies that comply with the control protocol. Zeno behavior is avoided. Simulation examples demonstrate the effectiveness of the proposed algorithm and simulate scenarios in which the communication environment deteriorates due to external disturbances affecting the MASs. © 2024 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fault-Tolerant control for Stochastic High-Order Fully Actuated Systems with Local Faults

Adaptive Fault-Tolerant Control for Stochastic High-Order Fu...

引用

2023 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes, SAFEPROCESS 2023

作者： Liu, Xueqing Chen, Maoyin Sheng, Li Zhou, Donghua Tsinghua University Department of Automation Beijing China College of Control Science and Engineering Qingdao China Shandong University of Science and Technology College of Electrical Engineering and Automation Qingdao China

ISBN: (纸本)9798350337754

This paper portrays a class of local faults, whose basic characteristic is that the fault occurs only when the system is in a certain state domain. In engineering practice, such faults are prevalent and could affect efficiency greatly. To accurately tolerate these local faults, a novel control strategy is proposed. The globally asymptotical stability in probability is guaranteed by using time-varying gains on pre-divided fields. Finally, a numerical example is presented to demonstrate the effectiveness of the proposed framework. © 2023 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Higher-order properties and extensions for indirect MRAC and APPC of linear systems

引用

Science China(Information Sciences) 2024年第4期67卷 218-238页

作者： Yanjun ZHANG Zhipeng ZHANG Jian SUN Lei WANG Kangkang ZHANG National Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of Technology School of Automation Beijing Institute of Technology Beijing Institute of Technology Chongqing Innovation Center College of Control Science and Engineering Zhejiang University Department of Electrical and Electronic Engineering Imperial College London KIOS Research and Innovation Center of Excellence University of Cyprus

Recently, a reference derived some new higher-order output tracking properties for direct model reference adaptive control（MRAC） of linear time-invariant（LTI） systems: limt→∞ e（i）（t） = 0, i = 1,..., n*-1, where n*and e（i）（t） denote the relative degree of the system and the i-th derivative of the output tracking error, respectively. However, a naturally arising question involves whether indirect adaptive control（including indirect MRAC and indirect adaptive pole placement control） of LTI systems still has higher-order tracking properties. Such properties have not been reported in the literature. Therefore, this paper provides an affirmative answer to this question. Such higher-order tracking properties are new discoveries since they hold without any additional design conditions and, in particular, without the persistent excitation condition. Given the higher-order properties, a new adaptive control system is developed with stronger tracking features.（1） It can track a reference signal with any order derivatives being unknown.（2） It has higher-order exponential or practical output tracking properties.（3） Finally, it is different from the usual MRAC system, whose reference signal's derivatives up to the n*order are assumed to be known. Finally, two simulation examples are provided to verify the theoretical results obtained in this paper.

关键词： higher-order tracking indirect adaptive control model reference adaptive control adaptive pole placement control

来源：评论

学校读者我要写书评

暂无评论

Multi-agent Reinforcement Learning Algorithm Based on Role Parameter Sharing 1

引用

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Zhang, Hui Xu, Chi Zhang, Ting-Ting Zhang, Ya School of Automation Southeast University Nanjing210096 China High-Tech Department Jiangsu Automation Research Institute Lianyungang222061 China School of Command and Control Engineering Army Engineering University Jiangsu Nanjing210017 China

ISBN: (数字)9789819733361

ISBN: (纸本)9789819733354

In multi-agent reinforcement learning, scalability is a significant challenge. Applying reinforcement learning algorithms in large-scale multi-agent systems requires consideration of algorithm efficiency. This paper attempts to reduce network parameter quantity and training time from the perspective of parameter sharing. However, parameter sharing may also bring some disadvantages, such as policy similarity, which may limit the formation of cooperative policies and affect the efficiency of the entire system. To address the problems caused by parameter sharing, this paper proposes a multi-agent reinforcement learning algorithm with role parameter sharing (R-PS). By dynamically dividing roles and selecting objects for parameter sharing, R-PS automatically identifies intelligent agents that may generate beneficial parameter sharing and conducts partial parameter sharing within the roles. Meanwhile, intrinsic rewards are introduced to increase the diversity of agent strategies. Experimental results show that R-PS can effectively divide roles, benefit from partial parameter sharing, and form diverse policies through intrinsic rewards. It also reduces training time, produces excellent performance and collaboration. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：