Fault Diagnosis System Of Gas Chromatograph In Transformer Oil Based On Artificial Neural Network

Power transformer, one of the most important devices, has a very significant influence to the security and stability of power system.In this paper, presents the principle and solution of fault diagnosis system with eigenvalue of gas solved in oil, presents that ANN is suitable for transformer fault diagnosis.Such as standard BP algorithm,additional momentum method,adapt learn rate method and L-M rule are used to train the same Neural net,and a conclusion that L-M ruleare is better. On this foundation,discussed the consistency of the mixed gases based on neural net mode identify.And combined an real example,and aimed at every algorithm's shortages of the restrain speed and the train accuracy,used L-M rule to identify the mixed gases,at the same time,gived the results of the training.The result expressed that the L-M algorithm greatly improved the net's refrain speed and train accuracy.At last,taked the air's component as the importation,take the fault's nature as the exportation,give a real example of transfer fault diagnosis.Under different numbers of neural units,combined the study refrain speed and the diagnosis results of artificial neural networks.The result expressed that aiming at the same fault ,using neural net diagnosis method is puperior to other judge method.Neural net has a very big potential in transfer fault diagnosis,select fit net modle,continuously renew study sample,can acquire the increasingly perfect Result.