Because the transformer is one of the most important equipments in power system, the technology of fault diagnosis for transformer is always taken into account by savants all over the world. The negative selection algorithm has much advantage for some faults which lack a great deal of training sample data in the power transformer faults. However, the existing negative selection algorithm also has some shortages. For these shortages, this paper researches a mutation based negative selection algorithm, which join the thought of the mutation in the generative process of the detector, promising the diversity of the antibody. In the paper, another kind of immune algorithm will be used in transformer fault diagnosis. This is a fuzzy immune network classification algorithm which combines idiotypic immune network theory with fuzzy logic. Experiments show that the immune algorithm's diagnostic performance is good. It has a higher accuracy and feasibility, and has a good prospect in transformer fault diagnosis.
|