小波模糊神经网络在绝缘子污秽在线监测中的应用  

Application of Wavelet Fuzzy Neural Network to Contamination On-line Monitoring of Insulators

作　　者：岳良顺[1] 刘念[1] 梁杉[1] 张欢[1] 

机构地区：[1]四川大学电气信息学院,成都610065

出　　处：《高电压技术》2010年第10期2483-2487,共5页High Voltage Engineering

摘　　要：为了实现电气设备在线监测的智能化和自动化,提出了基于小波模糊神经网络的绝缘子在线监测的方法。鉴于模糊神经网络具有良好的学习性及其很强的模式识别能力以及小波对含噪泄漏电流信号有很好的去噪能力,故提出了小波理论和模糊神经网络相结合的小波模糊神经网络。在实验室模拟实验和现场实测数据的基础上,分析了环境因素对不同污秽程度绝缘子外部电气特性的影响,通过选择环境温度和湿度,泄漏电流有效值,泄漏电流峰值及泄漏电流脉冲频率等变量作为其输入变量,并将其用于对绝缘子污秽程度在线监测结果的模糊综合评定。同时也介绍了基于小波模糊神经网络的污秽评定模型的构建过程,通过部分实验数据验证了该方法的可行性。通过此方法,监控人员可以实时在线监测变电站实时绝缘状况,同时可减少电网因绝缘问题引起的故障,在保证电网安全运行方面有突出贡献。To realize the intelligently and automatically monitoring electric equipment,a method for online monitoring of insulators based on wavelet fuzzy neural network is put forward.The fuzzy neural network with the robust learning and pattern has identification ability and wavelet transform has preferable de-noising ability,so a wavelet fuzzy neural network which is combined with the wavelet and fuzzy neural network is proposed.Based on simulation experiments and on-site data,the influence of environmental factors on the exterior electrical characteristics of insulators with different contamination conditions is analyzed.Moreover,the principle of the integrative evaluation on the online detection results in the surface contamination states of the transmission line insulators is put forward by using wavelet fuzzy neural network whose input variables are chosen as the r.m.s,the peak value,the amplitude and times of the pulses of leakage current,the environmental temperature,and humidity.The model establishment of the contamination evaluation based on wavelet fuzzy neural network method is mentioned,and the feasibility of method is proved by experiments in laboratory.In this way,the dispatcher can remotely online monitor the insulated status of the substation,and this system can decrease the fault of power system caused by fault of insulation.It is very important for the power system to insure the safe operation of the power system.

关 键 词：小波模糊神经网络 绝缘子 小波变换 模糊神经网络 小波神经网络 模糊综合评定 

分 类 号：TM855[电气工程—高电压与绝缘技术] TM216[一般工业技术—材料科学与工程]