摘要
将概率神经网络引入到电力变压器的故障诊断中,并提出了利用模糊数学的知识对神经网络输入进行预处理的方法。采用改良的三比值方法来实现故障诊断,建立了基于模糊输入的神经网络故障诊断模型。通过对神经网络模型的实例训练及仿真,证明了此方法有较好的收敛性,提高了故障诊断的有效性和准确性。
Probabilistic Neural Network is used in fault diagnosis of power transformer. A method using fuzzy math theory to deal with the data of the neural network input is proposed. Fault diagnosis of power transformer based on improved three ratio method is realized. And a fault diagnosis model of neural network based on fuzzy input is constituted. The simulation diagnosis demonstrates the effectiveness, astringency and veracity of the proposed algorithm.
出处
《电气应用》
北大核心
2007年第7期28-30,共3页
Electrotechnical Application
基金
吉林省科技厅项目(200505263)
关键词
概率神经网络
模糊
故障诊断
气相色谱分析法
probabilistic neural network fuzzy fault diagnosis dissolved gas analysis
