高压电器2018，Vol.54Issue(2)：12-19,8.DOI:10.13296/j.1001-1609.hva.2018.02.003
基于ReliefF特征量优化及BP神经网络识别的高压隔离开关故障类型与位置诊断方法
Fault Type and Position Diagnosis Method of High-voltage Disconnectors Based on ReliefF Characteristic Quantity Optimization and BP Neural Network Recognition
张一茗 1李少华 1陈士刚 2高群伟 1宋亚凯 1张文涛 1李洪涛 3关永刚4
作者信息
- 1. 平高集团有限公司,河南平顶山467001
- 2. 北京交通大学电气工程学院,北京100044
- 3. 国网江苏省电力公司电力科学研究院,南京211103
- 4. 清华大学电机系电力系统及发电设备控制和仿真国家重点实验室,北京100084
- 折叠
摘要
Abstract
Aiming at the problem of the type and the location of mechanical failure of high-voltage disconnectors are difficult to be effectively identified,a fault diagnosis method based on ReliefF algorithm is proposed to optimize the multi-channel vibration characteristics and utilize BP neural network fusion decision.First,simulating the failure through the tests and the install multi-point vibration sensors in the disconnectors body and the operating mechanism to collect the vibration signals of different locations.Then the vibration signals collected by a plurality of sensors are conducted with EMD to obtain the intrinsic modal function.And calculating the energy moment and integrating the energy-moment of the multi-channel signals.Finally,the ReliefF algorithm is used for extracting the principal components to construct the input feature vector of the BP neural network,so as to realize the fault type and the position diagnosis.The experimental results show that the multi-channel sensor feature fusion has a better adaptability and classification ability for the different faults of disconnectors than the single-channel signal feature extraction has,which can diagnose the type and the location of the fault and improve the diagnostic accuracy.关键词
高压隔离开关/能量矩/特征融合/ReliefF优化/BP神经网络Key words
high voltage disconnectors/energy moment/feature fusion/ReliefF optimization/BP neural network引用本文复制引用
张一茗,李少华,陈士刚,高群伟,宋亚凯,张文涛,李洪涛,关永刚..基于ReliefF特征量优化及BP神经网络识别的高压隔离开关故障类型与位置诊断方法[J].高压电器,2018,54(2):12-19,8.
