检索结果-内蒙古大学图书馆

第三十八届中国控制会议

作者： Ya-Li Wu Guo-Ting Li Yu-Long Fu Xiao-Peng Wang School of Automation and Information Engineering Xi'an University of Technology Shaanxi Province Key Laboratory of Complex System Control and Intelligent Information Processing

Compared with traditional machine learning, intrusion detection based on deep learning has the advantage of feature extraction. Auto-encoders, owing to having good feature extraction and dimensionality reduction ability, are known for the superior performance. However, the network structure selection is time-consuming and laborious. The essential features cannot be automatically extracted according to different distribution characteristics of the data set. Moreover, the existing data pre-processing method fails to adapt the model better. Based on the stack sparse auto-encoders(SSAE), we propose a new intrusion detection model named DBSO-SSAE. The algorithm is based on difference brain storm optimization(DBSO) which automatically adapts to selection network framework. Meanwhile, a new normalization strategy is introduced to further improve the accuracy of the model. The simulation results show that DBSO-SSAE greatly reduces the complexity of manual tuning and increases the adaptability of the network model.

关键词： intrusion detection feature extraction SSAE deep learning difference brain storm optimization

来源：评论

学校读者我要写书评

暂无评论

Evasion strategies of a three-player lifeline game

引用

Science China(information Sciences) 2018年第11期61卷 144-154页

作者： Fan ZHANG Wenzhong ZHA School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex System Information Science Academy China Electronics Technology Group Corporation

This study examines a multi-player pursuit-evasion game, more specifically, a three-player lifeline game in a planar environment, where a single evader is tasked with reaching a lifeline prior to capture. A decomposition method based on an explicit policy is proposed to address the game qualitatively from two main aspects:(1) the evader's position distribution to guarantee winning the game(i.e., the escape zone),which is based on the premise of knowing the pursuers' positions initially, and(2) evasion strategies in the escape zone. First, this study decomposes the three-player lifeline game into two two-player sub-games and obtains an analytic expression of the escape zone by constructing a barrier, which is an integration of the solutions of two sub-games. This study then explicitly partitions the escape zone into several regions and derives an evasion strategy for each region. In particular, this study provides a resultant force method for the evader to balance the active goal of reaching the lifeline and the passive goal of avoiding capture. Finally,some examples from a lifeline game involving more than one pursuer are used to verify the effectiveness and scalability of the evasion strategies.

关键词： lifeline game three-player pursuit-evasion game barrier evasion strategy game of kind

来源：评论

学校读者我要写书评

暂无评论

Predicting Remaining Useful Life of Industrial Equipment Based on Multivariable Monitoring Data Analysis

Predicting Remaining Useful Life of Industrial Equipment Bas...

引用

2018 Chinese Automation Congress, CAC 2018

作者： Li, Xin Xie, Guo Liu, Han Wang, Wenqing Information Processing Xi 'An University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Xi'an China

ISBN: (纸本)9781728113128

Modern industrial equipment plays a vital role in the operation of large industrial systems. Accurate prediction of its remaining useful life will greatly reduce the possibility of unsafe accidents. The internal structure of modern industrial equipment is very complex, and a variety of state monitoring data affect the remaining useful life of the equipment, and the mutual influence between different monitoring data has greatly increased the difficulty of remaining useful life prediction. In this paper, the long short-term memory network in deep learning is used to solve this problem. The long short-term memory network has many advantages in time series prediction. The remaining useful life prediction model of industrial equipment based on long short-term memory network and multivariable monitoring data is established, and aiming at the characteristics of multivariable monitoring data, Mini-batch Gradient Descent algorithm (MBGD) is adopted to train the network. Finally, the engine monitoring data set provided by the NASA prediction center is used to verify the algorithm. The data set is divided into training set and test set, the training set is put into the long short-term memory network to get the prediction model, and then the remaining useful life prediction is carried out by the test set. The prediction accuracy and generalization ability of the algorithm are verified by predicting the remaining useful life of three different turbofan engines. © 2018 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Data Based Fault Diagnosis of Hot Axle for High-Speed Train

Data Based Fault Diagnosis of Hot Axle for High-Speed Train

引用

2018 Chinese Automation Congress, CAC 2018

作者： Sun, Lanlan Hei, Xinhong Xie, Guo Qian, Fueai Wang, Zhuxin Liu, Ran System Control and Intelligent Information Processing University of Technology Xi'An Shaanxi Key Laboratory of Complex Xi'an China

ISBN: (纸本)9781728113128

The axle temperature is an important performance index for high-speed train axle, and many types of high-precision detection device have been developed. However, because the existing hotbox detection system works by comparing the measured value with fixed and experiential temperature thresholds, without considering the dynamic influence of running environment, the rates of fault and failure alarm are still high. Regarding this problem, this paper is to realize high precision fault diagnosis. Firstly, the characteristics of the temperature rising rates of all axles, the axles on the same side of a carriage, the axles on the same side of a whole train are analyzed. Secondly, the support vector machine (SVM) is employed to establish a data-based fault diagnosis model, and the model is optimized using genetic algorithm. Finally, the proposed method is applied to an actual running data, the analysis results demonstrated the effectiveness and feasibility. © 2018 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Trajectory optimisation design of robot based on artificial intelligence algorithm

引用

International Journal of Wireless and Mobile Computing 2019年第1期16卷 35-40页

作者： Huang, Li Zhang, Kai Hu, Wei Li, Chengcheng College of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan430081 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Hubei Wuhan430081 China Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and Technology Hubei Wuhan430081 China

Artificial intelligence has attracted more and more attention and has been widely used in all walks of life, especially in the education industry;artificial intelligence has gradually become the core. Aiming at the problem of robot trajectory planning in artificial intelligence, this paper applies the project teaching method to the course of artificial intelligence, regards trajectory planning as a project, analyses and studies it, uses ant colony algorithm to find the optimal planning path. Through the teaching of the project, the students will understand the ant colony algorithm more deeply. The algorithm is programmed independently to achieve the final trajectory optimisation. Students become the main body of the classroom, give full play to the initiative and enthusiasm of the students, through the operation of the project to train the students' innovative ability and cooperation ability, and improve the overall quality of the college students. Copyright © 2019 Inderscience Enterprises Ltd.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Policy iteration based Q-learning for linear nonzero-sum quadratic differential games

引用

Science China(information Sciences) 2019年第5期62卷 195-213页

作者： Xinxing LI Zhihong PENG Li LIANG Wenzhong ZHA School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex System Information Science Academy China Electronics Technology Group Corporation

In this paper, a policy iteration-based Q-learning algorithm is proposed to solve infinite horizon linear nonzero-sum quadratic differential games with completely unknown dynamics. The Q-learning algorithm, which employs off-policy reinforcement learning(RL), can learn the Nash equilibrium and the corresponding value functions online, using the data sets generated by behavior policies. First, we prove equivalence between the proposed off-policy Q-learning algorithm and an offline PI algorithm by selecting specific initially admissible polices that can be learned online. Then, the convergence of the off-policy Qlearning algorithm is proved under a mild rank condition that can be easily met by injecting appropriate probing noises into behavior policies. The generated data sets can be repeatedly used during the learning process, which is computationally effective. The simulation results demonstrate the effectiveness of the proposed Q-learning algorithm.

关键词： adaptive dynamic programming ADP Q-learning reinforcement learning RL linear nonzerosum quadratic differential games policy iteration PI off-policy

来源：评论

学校读者我要写书评

暂无评论

Model analysis and experimental research on hydraulic high-speed impact system 8

Model analysis and experimental research on hydraulic high-s...

引用

8th IEEE International Conference on Fluid Power and Mechatronics, FPM 2019

作者： Wang, Shoukun Shi, Mingxin Chen, Zhihua Beijing Institute of Technolog Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing China Key Laborator Yof Servo Motion System Drive and Control Ministry of Industry and Information Technology School of Automation Beijing Institute of Technology Beijing China

ISBN: (数字)9781728103112

ISBN: (纸本)9781728103112

High-speed impact simulation test is an important test method to study the fatigue properties or limit parameters of materials. With the advantages of great impact energy, good program control and convenient test operation, hydraulic impact is widely used in high-speed impact field. A hydraulic high speed impact simulation system is designed in this paper, which uses high pressure accumulator to supply oil and converts hydraulic energy into impact energy through servo valve controlled cylinder system. This system can simulate dynamic change process of impact velocity and acceleration of projectile, and has impact angle adjustment and end buffer function. First, the composition and working principle of this hydraulic impact simulation system is introduced, as well as the analysis of the hydraulic impact mechanism. Second, the system dynamics model of servo valve controlled cylinder based on accumulator oil is built, and the simplified model and its basic characteristics are analyzed. Then, the Influences of various parameters in impact dynamic model on impact process are also discussed. Finally, the simulation system and physical prototype system of hydraulic impact is presented, the simulation and actual impact test data and corresponding analysis conclusions are also given. © 2019 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

An improved distributed nonlinear observer for leader-following consensus via differential geometry approach

arXiv

引用

arXiv 2020年

作者： Xu, Haotian Wang, Jingcheng Wang, Bohui Wang, Hongyuan Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 Autonomous Systems and Intelligent Control International Joint Research Center Xi'an Technological University Xi'an Shaanxi710021 China School of Aerospace Science and Technology Xidian University Xi'an710071 China

This paper is concerned with the leader-following output consensus problem in the framework of distributed nonlinear observers. In stead of certain hypotheses on the leader system, a group of geometric conditions is put forward to develop a novel distributed observer strategy with less conservatism, thereby definitely improving the applicability of the existing results. To be more specific, the improved distributed observer can precisely handle consensus problems for some nonlinear leader systems which are invalid for the traditional strategies with the certain assumption, such as Elastic Shaft Single Linkage Manipulator (ESSLM) systems and most of first-order nonlinear systems. We prove the sufficient conditions for the exponential stability of our distributed observer's error dynamic by proposing two pioneered lemmas to show the relationship between the maximum eigenvalues of two matrices appearing in Lyapunov type matrices. Then, a partial feedback linearization method with zero dynamic proposed in differential geometry is employed to design a purely decentralized control law for the affine nonlinear multiagent system. With this advancement, the existing results can be regarded as a specific case owing to that the followers can be chosen as an arbitrary minimum phase affine smooth nonlinear system. At last, the novel distributed observer and the improved purely decentralized control law are applied in the distributed control framework to construct a closed-loop system. We also prove the stability of closed-loop system to achieve leader-following consensus, i.e., the distributed control framework is proved to satisfy certainty equivalence principle. Our method is illustrated by ESSLM system and Van der Pol system as leader. Copyright © 2020, The Authors. All rights reserved.

关键词： Feedback linearization

来源：评论

学校读者我要写书评

暂无评论

Optimization of Missile Path Planning Based on APMO-HV Algorithm

Optimization of Missile Path Planning Based on APMO-HV Algor...

引用

2019 IEEE International Conference on Unmanned systems, ICUS 2019

作者： Zhang, Hu Wang, Shuai Liu, Tonglin Zhou, Aimin Zhang, Yi Beijing Electro-mechanical Engineering Institute Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China Changzhou University School of Mechanical Engineering Changzhou China East China Normal University Shanghai Key Laboratory of Multidimensional Information Processing School of Computer Science and Technology Shanghai China

ISBN: (纸本)9781728137926

In this paper, with considerations of low efficiency of missile path planning (MPP) by traditional aggregation technology, it uses affinity propagation based multi-objective evolutionary algorithm with hypervolume environment selection (APMO-HV) to solve the problem of MPP after establishing the MPP model. The experimental part compares and analyzes APMO-HV with six state-of-the-art algorithms, and applies it to address the MPP problem. The experimental results show that compared with the other six algorithms, APMO-HV has achieved the best solution performance in both the GLT test suite and MPP problem. This not only validates the effect of the proposed algorithm, but also enriches and improves the research results of MPP. © 2019 IEEE.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Fault-Tolerant Cooperative Motion Planning of Connected and Automated Vehicles at a Signal-Free and Lane-Free Intersection

引用

IFAC-PapersOnLine 2018年第24期51卷 60-67页

作者： Li, Bai Zhang, Youmin Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an710048 China Department of Mechanical Industrial and Aerospace Engineering Concordia University Montreal Canada

Compared with a conventional intersection, a signal-free and lane-free intersection enables the vehicles to drive more flexibly, thereby to promote the throughput and to reduce congestions. This work proposes a fault-tolerant cooperative motion planning method for a number of connected and automated vehicles (CAVs) which are passing through a signal-free and lane-free intersection. Partial loss of actuator effectiveness is considered as the fault type. Even a subtle fault may significantly affect the overall team performance. Thus correctly judging whether each faulty/healthy CAV can still achieve its original goal is impossible until a corresponding motion replanning problem turns out to be solvable or not. To maximize the completeness of the original task, we propose a parallel computation framework, wherein the fault-recovery motion replanning problems in multiple levels of task completeness are tried simultaneously. Concretely, i) each faulty/healthy CAV should accomplish its original goal; ii) only each healthy CAV is required to accomplish its original goal; and iii) all the faulty/healthy CAVs try to stop safely without the need to achieve any original goals. Problems iii), ii), and i) are ranking with increasing computational difficulty. Among all the three problems, the achievable solution to the most difficult one is implemented as the fault-recovery strategy. © 2018

关键词： Motion planning Automation Fault tolerance Vehicles Automated vehicles Co operative control connected Intersection managements Optimal controls

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：