Transformer Fault Diagnosis Based On Hybrid Immune Intelligent Algorithm

Large power transformer is very important transformation equipment in power system, which running state directly affects security of system, so that on line measure and diagnosis transformer conditions have very important function on system stability. Artificial immune system is a new intelligent algorithm which is inspired by biological immune, which is highly parallel adaptive system with capability in learning, memory acquisition, and pattern recognition and so on. This paper presents two methods on fault diagnosis of power transformer: the artificial immune RBF neural network use immune clustering algorithm to immune clustering algorithm, which can reduce the training computational complexity of neural networks and improve capacity of network generalization; the hybrid intelligent algorithm of immune support vector machines pre-selected the data with the immune clustering algorithm, and the Support Vector Machine is used for Transformer Fault Diagnosis. Through examples analysis and Comparison results show that the two methods of fault diagnosis can be evidently improved.