基于人工鱼群算法的变压器故障诊断研究  

Research on Transformer Fault Diagnosis Based on Artificial Fish Algorithm

作　　者：苗强 

机构地区：[1]中煤科工集团上海研究院检测中心,上海201401

出　　处：《煤炭技术》2015年第4期291-292,共2页Coal Technology

摘　　要：针对变压器在故障诊断时复杂难辨的问题,提出了一种基于人工鱼群算法优化BP神经网络的故障诊断方法。该方法首先将所得的样本进行预处理,然后通过归一化后的故障特征量样本和目标期望输出,对建立的模型进行样本训练,最后将验证数据进行诊断测试。诊断结果表明,采用该方法可以满足变压器故障诊断的需要,具有很强的实用价值。Aimed at the complexity of the transformer fault diagnosis, puts forward a kind of based on artificial fish algorithm to optimize the BP neural network fault diagnosis methods. Firstly,this method will process the sample, normalize the sample and target characteristics of desired output. Establish the model of sample training. Finally, diagnostic tests with the verifying data. Diagnostic results show that can meet the needs of transformer fault diagnosis by using this method, and has a strong practical value.

关 键 词：人工鱼群算法 BP神经网络 故障诊断 变压器 

分 类 号：TM407[电气工程—电器] TP18[自动化与计算机技术—控制理论与控制工程]