检索结果-内蒙古大学图书馆

IEEE Conference on Decision and control

作者： Yi Zhang GuoLian Hou Baojiang Wu College of light Industry Hebei Polytechnic University Tangshan Hebei China Department of Automation North China Electric Power University Beijing China College of Computer and Automatic Control Hebei Polytechnic University Tangshan Hebei China

ISBN: (纸本)9781424438716

The paper described a novel method for detecting and identifying faults that occur in the actuator of control systems with input and output signals related to the component itself. The diagnosis algorithm consists of three steps: firstly, generalized morphological filter with multi-structure elements is designed to filter the random noise and impulse noise in actuator's input and output signals. And secondly, wavelet transform, which has been proposed for sensor's fault diagnosis some years ago, is developed for actuator's fault diagnosis. To effectively extract the abruptly fault characteristic, wavelet transform was used to analyze the filtered signals in this paper. By the Multi Resolution Analyzing (MRA), the faults can be detected accurately. Thirdly, according to calculating the Lipschitz Exponent (LE) at the fault's point, the fault type can be identified. The several typical faults such as fix, gain, bias have been studied. The effectiveness of the proposed approach is demonstrated by the means of experimental results and simulations.

关键词： Actuators Fault detection Fault diagnosis Filters Multiresolution analysis Wavelet transforms control systems Signal processing Signal design Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Improved Ant Colony Algorithm with Pheromone Mutation and its Applications in Flow-shop Problems

Improved Ant Colony Algorithm with Pheromone Mutation and it...

引用

World Congress on Intelligent control and Automation (WCICA)

作者： Bing Li Xuemei Song Tangshan Teacher''s College Tangshan China School of Computer and Automatic Control Hebei Polytechnic University Tangshan China

Ant colony algorithm (ACA) has the disadvantages such as easily relapsing into local optimization and stagnation. Aimed at improving this problem existed in ACA, several new betterments are proposed and evaluated. In particular, pheromone mutation and stochastic search strategy were inducted. Then an improved ant colony algorithm with pheromone mutation was put forward. It was tested by a set of benchmark travelling salesman problems from the travelling salesman problem library. And the results of the examples show that it can not easily run into the local optimum and can converge at the global optimum. The improved algorithm was used to solve the flow-shop problems. It performs better than the other algorithms such as genetic algorithm

关键词： Genetic mutations Traveling salesman problems Application software Educational institutions automatic control Ant colony optimization Stochastic processes Benchmark testing Libraries Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

On-Device Learning with Raspberry Pi for GCN-Based Epilepsy EEG Classification

On-Device Learning with Raspberry Pi for GCN-Based Epilepsy ...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： He, Zhuoli Wang, Chuansheng Huang, Jiayan Grau, Antoni Guerra, Edmundo Yan, Jiaquan Fuzhou University College of Computer and Big Data Fuzhou China Polytechnic University of Catalonia Department of Automatic Control Barcelona Spain Putian University College of New Engineering Industry Putian China Minjiang University School of Computer and Big Data Fuzhou China

ISBN: (纸本)9798350386226

Epilepsy is a chronic brain disease characterized by recurrent and transient seizures, which is accompanied by super-synchronous abnormal discharge of electroencephalogram (EEG) signals. As a non-invasive auxiliary diagnostic technique, EEG is currently important means of seizure detection. However, due to ignoring the spatial topological relationship between electrodes, existing data-driver methods fail to fully reflect the interaction between signals. Meanwhile, their models usually be designed with a large number of redundant parameters, making it difficult to deploy to micro-embedded devices with limited-resources. In this paper, we propose a on-device learning with edge device for epilepsy EEG classification network based on GCN (oDLGCN-EEG). Specifically, to analyze the spatial relationships between various electrodes and their temporal dependencies, we design a Brain Topology Network (BTN) for the spatiotemporal dependency feature map construction. To capture the internal activity during epilepsy seizures, we design a Neural Feature Extraction Module (NFEM) for the neural activity feature map construction. Besides, we propose a pruning scheme to optimize the model, which successfully deploys the optimized oDLGCN-EEG on the embedded Raspberry Pi device for efficient and low-power consumption intelligent epilepsy classification. Experiments in comparison with state-of-the-art methods show that oDLGCN-EEG achieves the best classification accuracy and with the smallest parameter number on baseline EEG dataset. The code is available at https://***/cathnat/Epileptic-Classification. © 2024 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Improved Elman Neural network with Ant Colony Algorithm and its Applications in Fault Diagnosis

Improved Elman Neural network with Ant Colony Algorithm and ...

引用

2010 International Conference on computer and Communication Technologies in Agriculture Engineering(计算机与通信技术在农业工程国际会议 CCTAE 2010)

作者： Guohuan Lou Zheng Yao Qingxin Zhao College of Computer and Automatic Control Hebei Polytechnic University Tangshan China Tangshan Mine Kailuan Group Tangshan China

ISBN: (纸本)9781424469444;9781424469451

In the power plant, the blower fans running conditions related to the power plant production directly, as well as the security situation. This article introduced embedded system monitoring to the Auxiliary power plant machinery diagnostics systems. An on-line mechanical fault diagnosis system was developed based on ant colony algorithm and Elman neural network. This system integrated data acquisition, signal processing, network communications, on-line fault diagnosis and other functions into one. Experiments show that this method is simple and effective. It can also be applied to other fault diagnosis of complex systems and has certain portability.

关键词： fault diagnosis Ant Colony Algorithm Elman neural network

来源：评论

学校读者我要写书评

暂无评论

A Stability Determining Algorithm on Fuzzy Rules Based on the Theory of Phase Track

A Stability Determining Algorithm on Fuzzy Rules Based on th...

引用

International Symposium on Intelligent Information Technology Application, IITA

作者： Zhigang Li Zhenlei Wang Zhongkui Sun Yu Lv College of Computer and Automatic Control Hebei Polytechnic University Tangshan Hebei China College of Light Industry Hebei Polytechnic University Tangshan Hebei China Department of Architectural Design Xindi Energy Engineering Limited Langfang Hebei China

Phase plane analyzing approach is an intuitive graphical way for the analysis of fuzzy control system, and it can invert the movement of a first and second order system into the track of position and velocity in the phase plane, which is very important to further improve the whole system. However, it can't go without expertise and it is vague in the phase track drawing for stability determination. In the paper, an algorithm based on phase plain analyzing approach will be put forward to achieve the determination of fuzzy control stability automatically.

关键词： Fuzzy control Fuzzy systems Stability analysis automatic control Algorithm design and analysis control systems Tracking Educational institutions Fuzzy sets Information analysis

来源：评论

学校读者我要写书评

暂无评论

The Design of the Ultrasonic Liquid Density Measuring Instrument

The Design of the Ultrasonic Liquid Density Measuring Instru...

引用

International Conference on Measuring Technology and Mechatronics Automation, ICMTMA

作者： Wang Haiqun Cao Yi Zhang Yugui Chen Zhikun College of Computer and Automation Control Hebei Polytechnic University Tangshan Hebei China

ISBN: (纸本)9781424490103

In the present discussion, it is described for the work principle of the ultrasonic liquid density meter. The center frequency of the ultrasonic transducer is 1MHz. The paper gives the design of the hardware and the program flow diagram. Under laboratory conditions, we detect 90# gasoline and the experimental result shows that it is consistent with the theoretical result.

关键词： Acoustics Transmitters Ultrasonic variables measurement Receivers Ultrasonic transducers Density measurement Petroleum

来源：评论

学校读者我要写书评

暂无评论

On smart selection of clustering algorithms

On smart selection of clustering algorithms

引用

International Conference on computer Science and Information Technology (CSIT)

作者： Zhigang Li Kunpeng Li Weijia Guo College of Computer and Automatic Control Hebei Polytechnic University Tangshan China School of Computer and Information Technology Beijing Jiaotong University Beijing China

Currently, a large number of clustering algorithms are available for data mining. But it will be difficult for people who to a large extent know little about data mining to select an appropriate clustering algorithm. In order to solve this problem, in this paper, we first comprehensively analyze a number of clustering algorithms, then summarize their evaluation criteria and apply the so-called fuzzy comprehensive evaluation to smart comprehensive evaluation for clustering algorithm. Finally, we propose a smart choice of specific data mining algorithm to help the users who lacks the corresponding expertise.

关键词： Scalability Algorithm design and analysis Heuristic algorithms Stability analysis Clustering algorithms Power system stability

来源：评论

学校读者我要写书评

暂无评论

Real-time reading recognition of digital display instrument based on BP neural network

Real-time reading recognition of digital display instrument ...

引用

International Conference on control and Automation (ICCA)

作者： Ruikun Gong kui Yuan Shanpo Nian Lei Chen Guangxiang Zhang Yansong Tian College of Computer and Automatic Control Hebei Polytechnic University Tangshan 063009 China Academic Affairs Department Hebei Polytechnic University Tangshan 063009 China Graduate School Hebei Polytechnic University Tangshan 063009 China

In many chemical industries, the metallurgy, a number of digital real-time monitoring instruments are used. The manual method will bring the problems of inefficient and misjudge. To recognize digital display instrument's real-time reading, a BP neural network is designed, an improved BP algorithm and fifteen feature extraction method is proposed. The image of instrument board is obtained by an digital camera firstly, then transmitted to PC, and an image preprocessing is carried through. The image preprocessing includes vertical tilt correction, binary, gray processing, grads sharp, noise point removal, character segmentation, character unitary adjustment, character contraction and feature extraction. Character features are extracted by n dimensions feature extraction method. Finally real-time recognize the reading by the BP neural network. The experiment results show that the recognition accurate rate is greater than 98%. And the time of recognizing for one instrument image is less than 0.5 second.

关键词： Displays Instruments Neural networks Feature extraction Chemical industry Monitoring Algorithm design and analysis Digital cameras Image segmentation Image recognition

来源：评论

学校读者我要写书评

暂无评论

Optimize and design fieldbus network based embedded systems

Optimize and design fieldbus network based embedded systems

引用

International Conference on Industrial and Information Systems, IIS

作者： Shengnan Hao Zheng Yao Zhaohua Wang College of Computer and Automatic Control Hebei Polytechnic University Tangshan China Department of Computer Science and Technology Tangshan Teacher''s College Tangshan China

To promote the information technology development of the enterprise, achieve information integration and data share between different fieldbuses, by means of analyzing communication bus of industrial control system, the principle of the fieldbus protocol conversion is discussed. According to the basic construction of network, a scheme of fieldbus conversion is designed to accomplish the communication. The structure model was designed via the techniques of database, network, and communication, etc.; the embedded monitor system based on industrial control fieldbus is suitable for existing fieldbus network. As proved by practice, system can run stably, and its functions should take care of industrial control and information development of the enterprise needs.

关键词： Logic gates Iterative closest point algorithm Monitoring Protocols Biological system modeling Industries Universal Serial Bus

来源：评论

学校读者我要写书评

暂无评论

Research on Neural Network Model Based on Subtraction Clustering and Its Applications

引用

Physics Procedia 2012年 25卷 1642-1647页

作者： Zhang Tie-jun Chen Duo Sun Jie Department of Computer Science and Technology Tangshan CollegeTangshan Hebei Province China School of Computer and Control Hebei Polytechnic University Tangshan Hebei Province China

This paper takes advantage of the integration of subtraction clustering and fuzzy c-means clustering algorithm to obtain precise number of clusters and the degree of membership, and establishes the neural network model based on the multiple criterion information fusion and the fuzzy technology. Collecting a variety of data in actual underground mining process and integrating them as a whole, the simulations are performed. Experimental results indicate that the proposed method is valid.

关键词： subtractive clustering fuzzy c-means clustering fuzzy neural network

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：