Fault diagnosis is essentially a kind of data mining. In order to meet the requirements of rapid diagnosis and fault-tolerance for Substation Fault Diagnosis, a combination of the improved Kohonen neural network and the BP network is presented in this paper. Considering that the fault information vector should be centered around the main fault device, we modified the distance function of Kohonen network. Fault data are classified through a modified Kohonen network, achieving initial classification by bring similar information together. Then, it is precisely determined through the BP sub-network. Experiments showed that, compared with single BP network, the combination network has a higher diagnosis ability and good fault-tolerance.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
'/%3e%3cuse xlink:href='%23a' transform='rotate(144 450 300)'/%3e%3cuse xlink:href='%23a' transform='rotate(216 450 300)'/%3e%3cuse xlink:href='%23a' transform='rotate(288 450 300)'/%3e%3c/svg%3e)