Application of Signal Processing and Pattern Recognition Theory in Fault Diagnosis of Electrical System

Yutao Guo

doi:10.62051/81fmxb22

Authors

Yutao Guo

DOI:

https://doi.org/10.62051/81fmxb22

Keywords:

Electrical System; Fault Diagnosis; Signal Processing; Pattern Recognition; Multi-source Information Fusion.

Abstract

The application of signal processing and pattern recognition theory in fault diagnosis of electrical system is discussed in this paper. Due to the continuous expansion of the scale and complexity of the power system, the traditional fault diagnosis methods have been unable to meet the modern needs. This study first introduces the common types and characteristics of electrical system faults, and then focuses on the analysis of the role of signal processing technology in fault signal extraction and feature analysis, covering Fourier transform, wavelet transform and empirical mode decomposition. Then, the application of pattern recognition theory in fault classification and identification is discussed, with emphasis on algorithms such as support vector machine, artificial neural network and fuzzy logic. After comparing the advantages and disadvantages of different signal processing and pattern recognition methods in electrical system fault diagnosis, a comprehensive fault diagnosis method based on multi-source information fusion is proposed. The effectiveness of the proposed method is verified by a case study and future research directions, such as the potential application of deep learning and big data analysis in fault diagnosis of electrical systems, are discussed. This study provides theoretical basis and technical support for improving the accuracy and real-time performance of electrical system fault diagnosis, which is of great significance to ensure the safe and stable operation of power system.

Downloads

Download data is not yet available.

References

[1] Shao Wen-jun; Application of Fuzzy Theory Based on Multi-source Information Fusion in Fault Diagnosis of bleed air System [J]. Journal of Sichuan Ordnance Industry,2014 (04):145-148.

[2] Tan Derong, Han Gabong. Fault Diagnosis Pattern Recognition of Vehicle System Based on BP [J]. Journal of Shandong University of Technology (Natural Science Edition),2003 (03):8-12.

[3] Wang Dongxiao. Research on Fault Diagnosis Method of Robot RV Reducer Based on Internal Parameters [D]. Kunming University of Science and Technology,2023.

[4] Jin Futao. Fault Diagnosis Method of Rolling Bearing Support Vector Machine Based on Signal Decomposition and Multi-scale Entropy [D]. East China Jiaotong University,2023.

[5] Li Jingyao. Research on State Recognition and Fault Diagnosis Method of Agricultural Machinery [D]. Tarim University,2023.

[6] Quan Zhenya. Research on Weak Fault Signal Enhancement Recognition and Diagnosis of Rolling Bearing for health condition Monitoring [D]. Taiyuan University of Science and Technology,2023.

[7] Zhang Yilan. Research on Bearing fault diagnosis Method Based on voiceprint recognition and Transfer Learning [D]. Shandong University,2023.

[8] Li H X. Research on Rotating Machinery Running State Recognition Method Based on improved D-S Evidence Theory [D]. Jilin University,2023.

[9] Zhang Qixiang. Low-rank Dynamic Mode Decomposition Theory and Its Application in Mechanical Fault Diagnosis [D]. Wuhan University of Science and Technology,2023.

[10] Li Yougen. Vibration Fault Diagnosis and Experimental Verification of Multi-stage Centrifugal Pump Based on SVM [D]. Chongqing University of Technology,2023.

[11] Zhang Xiaolong. Research on Fault Diagnosis of Aviation Hydraulic Pipe-clamp Based on Improved Kernel Principal Component Analysis [D]. Liaoning University of Science and Technology,2023.

[12] Zheng Wenjie. Research on Multi-condition Current Diagnosis Based on Slewing Bearing [D]. Anhui University of Science and Technology,2023.

[13] Yuan Zicheng. Construction and Verification of Rolling Bearing Fault Diagnosis Model Based on Vibration Signal Analysis [D]. Harbin University of Science and Technology,2023.

[14] Yuan Ruibo. Research on Feature Extraction and Fault Clustering Identification Method of Rolling Bearing Based on Information Entropy [D]. Lanzhou University of Technology,2023.

[15] Yang Di. Feature Space Weighted Redundant Attribute Projection Method and its Application in Mechanical Fault Diagnosis [D]. Wuhan University of Science and Technology,2022.

[16] Chen Qing. Research on Deep Learning Method of Rotating Machinery Fault Warning and Diagnosis Based on Axis Trajectory Image [D]. Dalian University of Technology,2022.

[17] Wen Peitian. Fault Feature Extraction and intelligent Recognition of Rolling Bearing Based on Generative Adversarial Network [D]. East China Jiaotong University,2022.

[18] Xu Xuemei. Research on intelligent diagnosis method of rolling bearing Imbalance Based on data enhancement and feature enhancement [D]. Soochow University,2022.