检索结果-内蒙古大学图书馆

Use of multi-agent system for industrial production control

IFAC-PapersOnLine 2024年第9期58卷 205-210页

作者： J. Jirsa F. Zezulka P. Marcoň T. Pečinka L. Nováček V. Kaczmarczyk J. Arm Department of Technical Studies College of Polytechnics Jihlava Tolsteho 1556 586 01 Jihlava Czech Republic Department of Theoretical and Experimental Electrical Engineering Faculty of Electrical Engineering and Communication Brno University of Technology Technická 3082/12 Brno 616 00 Czech Republic Department of Control and Instrumentation Faculty of Electrical Engineering and Communication Brno University of Technology Technická 3082/12 Brno 616 00 Czech Republic

This paper describes specific implementation of Asset Administration Shell technology used for an industrial distributed control system. The base of this control system is a multiagent system of digital twins which was created by AAS. This multiagent system was developed for a specific platform CP Factory (mainly based on Simatic PLC) but the implementation is y portable to each common platform. Digital twin of several types of components of typical industrial production process are described in this paper with the implementation of active and passive administration shell. The main focus is on describing the way of integrating digital twins into the production system and the necessary SW tools. Industry 4.0 language was used as a common communication protocol as well as OPC UA and MQTT.

关键词： Multiagent system Asset administration shell digital twin OPC UA MQTT

来源：评论

学校读者我要写书评

暂无评论

Fast Informer-Based Time Series Detection

Fast Informer-Based Time Series Detection

引用

International Symposium on Antennas, Propagation and EM Theory (ISAPE)

作者： Weiguo Shen Tianhao Xia Dongwei Xu Qi Xuan Yun Lin Wei Wang Science and Technology on Communication Information Security Control Laboratory Jiaxing China Zhejiang University of Technology College of Information Engineering Institute of Cyberspace Security Binjiang Institute of Artificial Intelligence HangZhou China Zhejiang University of Technology Institute of Cyberspace Security Binjiang Institute of Artificial Intelligence HangZhou China College of Information and Communication Engineering Harbin Engineering University Binjiang Institute of Artificial Intelligence Harbin China

ISBN: (数字)9798350353129

ISBN: (纸本)9798350353136

Time series data are pivotal in modern technology and industrial applications,but they are frequently impacted by anomalies due to system failures,cyberattacks,or unexpected events. Therefore,swift and accurate anomaly detection in time series is crucial. This paper introduces ‘TransIDS’,an intrusion detection method that focuses on the efficient extraction and detection of time series features. TransIDS uses the Informer model to capture temporal features within data frames more effectively,improving detection performance and reducing runtime. We also fine-tune the Informer model and introduce an automatic anomaly threshold selection method,optimizing it for anomaly detection tasks. We validate TransIDS through experiments on various datasets and compare it with three existing methods. The results show that TransIDS outperforms the compared models in detection performance.

关键词： Runtime Accuracy Antenna theory Time series analysis Intrusion detection Predictive models Feature extraction Transformers Data models Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of A Missile Guidance and control System Model for Precise Target Tracking

Performance Analysis of A Missile Guidance and Control Syste...

引用

Applied Intelligence and Computing (AIC), IEEE World Conference on

作者： Rituraj Bhattacharjee Subhradip Mukherjee Department of Instrumentation & Control Engineerig Manipal Institute of Technology Manipal Academy of Higher Education Manipal Karnataka India Electronics and Communication Department MVJ College of Engineering Bangalore India

ISBN: (数字)9798350384598

ISBN: (纸本)9798350384604

A missile navigation system model is developed and analyzed in this work. The flight command structure is a crucial component which improves the efficiency of the system. It has a major impact on both the accuracy of the strike and precise control over the missile's performance. The goal of the flight command structure is to instruct the missile to follow the steering directive produced by the control system. The system's representation is determined by how well it establishes the flying course required to intercept the target and sends the commands to the attitude control system required to keep the missile on course while taking the airframe's dynamics and relevant aerodynamic characteristics into account. The missile is guided to attack the target after it has been tracked, and its trajectory is determined by the homing guidance loop utilizing the PID controller-based autopilot mode. In the MATLAB simulation environment, dynamic performance of the missile guidance system is simulated using a step response technique based on time.

关键词： Analytical models Tracking loops Target tracking Navigation Aerodynamics Mathematical models Missile guidance Trajectory Performance analysis MATLAB

来源：评论

学校读者我要写书评

暂无评论

A Generic Layer Pruning Method for Signal Modulation Recognition Deep Learning Models

引用

IEEE Transactions on Cognitive communications and Networking 2024年

作者： Lu, Yao Zhu, Yutao Li, Yuqi Xu, Dongwei Lin, Yun Xuan, Qi Yang, Xiaoniu Zhejiang University of Technology Binjiang Institute of Artificial Intelligence Hangzhou310056 China Chinese Academy of Sciences Institute of Computing Technology Beijing China Harbin Engineering University College of Information and Communication Engineering Harbin China Zhejiang University of Technology Institute of Cyberspace Security College of Information Engineering Hangzhou China Peng Cheng Laboratory PCL Research Center of Networks and Communications Shenzhen518000 China Hangzhou310056 China Science and Technology on Communication Information Security Control Laboratory Jiaxing China

With the successful application of deep learning in communications systems, deep neural networks are becoming the preferred method for Automatic Modulation Recognition (AMR). Although these AMR models yield impressive results, they often come with high computational complexity and large model sizes, which hinders their practical deployment in communication systems. To address this challenge, we propose a novel layer pruning method, PSR. Specifically, we decompose the AMR model into several consecutive blocks, each containing consecutive layers with similar semantics. Then, we identify layers that need to be preserved within each block based on their contribution. Finally, we reassemble the pruned blocks and fine-tune the compact model. Extensive experiments on five datasets demonstrate the efficiency and effectiveness of PSR over a variety of state-of-the-art baselines, including layer pruning and channel pruning methods. © 2015 IEEE.

关键词： Signal modulation

来源：评论

学校读者我要写书评

暂无评论

Reliability Allocation of Cruise Ship Automation System Based on BBWM-AHP

Reliability Allocation of Cruise Ship Automation System Base...

引用

System Reliability and Safety engineering (SRSE), International Conference on

作者： Jiaxin Xiang Yongquan Sun Hao Wang Hongke Chen School of Measurement and Control Technology and Communication Engineering Harbin University of Science and Technology Harbin China China Institute of Marine Technology & Economy Beijing China School of Mechanical and Electrical Engineering & Automation Xiamen University Tan Kah Kee College Zhangzhou China

ISBN: (数字)9798350356083

ISBN: (纸本)9798350356090

Limited reliability data during the development of cruise ship automation systems often leads to subjective weight allocation. This paper proposes an reliability allocation method based on the Bayesian best-worst method and analytic hierarchy process to address this challenge. By considering the system reliability indices, influencing factors, and units need to be allocated, a hierarchical model is established for reliability allocation based on the analytic hierarchy process. The Bayesian best-worst method compares elements in each layer, generating best and worst matrices based on decision-makers. These matrices determine optimal weights for each layer’s elements. The analytic hierarchy process determines relative importance weights among the system reliability index, influencing factors, and units. Consequently, the derived optimal weights are converted into allocation factors, which enable the allocation of reliability for cruise ship automation systems. This fusion-based approach presents a novel and effective method for optimizing reliability allocation during the development stage of complex systems.

关键词： Automation Analytic hierarchy process Reliability engineering Bayes methods Safety Reliability Resource management Indexes Marine vehicles Matrix converters

来源：评论

学校读者我要写书评

暂无评论

Interpretable DRL-based Maneuver Decision of UCAV Dogfight

arXiv

引用

arXiv 2024年

作者： Han, Haoran Cheng, Jian Lv, Maolong School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu611731 China Air Traffic Control and Navigation College Air Force Engineering University Xi’an710051 China College of Aeronautics Engineering Air Force Engineering University Xi’an710038 China

This paper proposes a three-layer unmanned combat aerial vehicle (UCAV) dogfight frame where Deep reinforcement learning (DRL) is responsible for high-level maneuver decision. A four-channel low-level control law is firstly constructed, followed by a library containing eight basic flight maneuvers (BFMs). Double deep Q network (DDQN) is applied for BFM selection in UCAV dogfight, where the opponent strategy during the training process is constructed with DT. Our simulation result shows that, the agent can achieve a win rate of 85.75% against the DT strategy, and positive results when facing various unseen opponents. Based on the proposed frame, interpretability of the DRL-based dogfight is significantly improved. The agent performs yo-yo to adjust its turn rate and gain higher maneuverability. Emergence of"Dive and Chase" behavior also indicates the agent can generate a novel tactic that utilizes the drawback of its opponent. © 2024, CC0.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Electrochemical Energy Storage technology and Its Application Analysis 5

Electrochemical Energy Storage Technology and Its Applicatio...

引用

5th IEEE Conference on Energy Internet and Energy System Integration, EI2 2021

作者： Li, Jianlin Tan, Yuliang Li, Yaxin Xu, Dezhi Ma, Suliang Energy Storage Technology Engineering Research Center North China University of Technology Beijing China College of Communication and Control Engineering Jiangnan University Jiangsu Province Wuxi China

ISBN: (纸本)9781665434256

With the increasing maturity of large-scale new energy power generation and the shortage of energy storage resources brought about by the increase in the penetration rate of new energy in the future, the development of electrochemical energy storage technology and the construction of demonstration applications are imminent. In view of the characteristics of different battery media of electrochemical energy storage technology and the technical problems of demonstration applications, the characteristics of different electrochemical energy storage media and the structure of energy storage systems are summarized. On this basis, different demonstration applications are analyzed by examples and their internal structures are analyzed. And the role played in the power grid, and finally the development of electrochemical energy storage technology was summarized and prospected. © 2021 IEEE

关键词： Energy storage

来源：评论

学校读者我要写书评

暂无评论

Vehicle state parameter estimation based on improved adaptive observer

Vehicle state parameter estimation based on improved adaptiv...

引用

Conference on Vehicle control and Intelligence (CVCI)

作者： Lianbing Wang Xu Zhao Juncheng Wan Hongyan Guo Yiming Zhang State Key Laboratory of Automotive Simulation and Control and the College of Communication Engineering Jilin University Changchun China College of Communication Engineering Jilin University Changchun China Department of Aircraft Control and Information Engineering Jilin Institute of Chemical Technology Changchun China SAIC Motor R&D Innovation Headquarter Shanghai China

To accurately obtain the state parameters during vehicle driving, this paper designs an adaptive nonlinear observer for vehicle state parameters to mitigate the influence of measurement noise within the framework of extended Kalman filtering. Based on the vehicle nonlinear three degree of freedom, a dead zone observer was designed to accurately estimate the sideslip angle, yaw rate, and longitudinal velocity of the vehicle in answer to the problem of significant noise in lateral acceleration. According to the output variable error, determine the dead zone boundary of the observed state variables at each time based on observation errors, limiting the estimation error within the dead zone boundary and improving noise suppression performance. The validity of this method is validated through a variety of different simulation conditions and by comparison to the EKF algorithm. Results demonstrate that the improved algorithm significantly enhances the estimation precision compared to Extended Kalman Filter algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IMPROVED GNSS-IR HEIGHT measureMENT METHOD BASED ON LOCALLY WEIGHTED REGRESSION 9

IMPROVED GNSS-IR HEIGHT MEASUREMENT METHOD BASED ON LOCALLY ...

引用

9th International Symposium on Test Automation and Instrumentation, ISTAI 2022

作者： Luo, Zhaowang Shang, Junna Li, Fangzhou Pang, Run Wang, Yiteng College of Telecommunication Engineering Hangzhou Dianzi University Hangzhou310018 China Science and Technology on Communication Information Security Control Laboratory Jiaxing314033 China The 36th Research Institute of China Electronics Technology Group Corporation Jiaxing314033 China

ISBN: (纸本)9781839538391

Global Navigation Satellite System Interferometric reflectance measurement (GNSS-IR) is a new remote sensing technology which uses satellite reflectance signals for monitoring. Aiming at the problems that the current GNSS-IR altimetry in land scenes is rarely applied and the accuracy of the traditional method is low under the reflection surface with high roughness, the traditional GNSS-IR altimetry is improved based on the local weighted regression method. A general navigation receiver method is proposed here, and does not need to use expensive special receiver or geodesic receiver. The local weighted regression method is used to separate the reflected signals to solve the problem of low local fitting accuracy of traditional methods when dealing with complex SNR changes in land scenes. The normalized Lomb-Scargle is used for spectrum analysis to improve the stability when there are few valid observations. The simulation and test results show that the proposed method has a significant improvement in the measurement accuracy compared with the traditional GNSS-IR method in the high-roughness ground scene. The single satellite measurement accuracy can reach within 10cm, and the root mean square error of the dual-frequency and multi-satellite combined altimetry measurement result is 2.62cm. © 2022 IET Conference Proceedings. All rights reserved.

关键词： Reflection

来源：评论

学校读者我要写书评

暂无评论

Recent patents for the motorized spindle preload mechanism

引用

Recent Patents on Mechanical engineering 2021年第3期14卷 329-341页

作者： Dai, Ye Wen, Wan-Jian Xuan, Li-Yu Yu, Xiao-Yang Wang, Gang Key Laboratory of Advanced Manufacturing and Intelligent Technology Ministry of Education School of Mechanical and Power Engineering Harbin University of Science and Technology Harbin150080 China School of College of Measurement and Control Technology and Communication Engineering Harbin University of Science and Technolo-gy Harbin150080 China Ningbo Skync Five Axis Numerical Control Tech Co. Ltd Yuyao315400 China

Background: The motorized spindle preload technology is one of the motorized spindle key technologies, and adjusting the preload according to the working conditions can effectively improve the dynamic performance of the motorized spindle and enhance the machining accuracy. Objectives: Review the preload mechanism development, introduce various preload mechanisms, and show research status in recent years. Then to explore and predict the future development of preload technology through the analysis of the overall preload mechanism. Methods: Search for different kinds of patents and literature about spindle preload structure in recent years. Through structural research and comparison with the traditional preload mechanism, to review the structure principle of various preload mechanisms at the present stage, then shown the advantages and disadvantages of each structure. Result: According to the patents and research of the preload mechanism in recent years, classification introduced the piezoelectric ceramic preload device, electromagnetic preload device, and hydraulic preload device, and so on. Introduce their advantages and existing problems in detail, then comprehensively compare the advantages and disadvantages of various mechanisms in control and mechanism. Finally, discuss the prospects and development directions of preload technology. Conclusion: With the further development of technology, high-precision products have higher requirements for machine tools, such as low latency, low heat generation, high efficiency, and long life. People use electromagnetic force, air pressure, hydraulic pressure, and other methods, to control the magnitude of the preload, maintain the performance of the motorized spindle at a high level. Compared with the traditional quantitative preload, their applicable working conditions are more extensive and accuracy is higher. However, various new preload methods still have certain shortcomings and need further improvement. © 2021 Bentham Sci

关键词： Machine tools

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：