Skip to Main Content
A genetic programming based fuzzy mapping functions (GPFMF) model is proposed in this paper to diagnose the insulation fault types of power transformers. The proposed GPFMF model constructs the fuzzy relationship between input and output fuzzy variables by genetic programming algorithms. The fuzzy relationship is represented as one of candidates which have the form of tree-like combinations of series of fuzzy implication operators with fuzzy input variables. Then the best fuzzy mapping function is evolved by genetic operations and evolution. Based on the proposed GPFMF model, an insulation fault diagnosis system for power systems is designed to detect the insulation fault types of power transformers. Compared with the normal fuzzy IEC code method, the GPFMF models can generate fuzzy mapping functions from fuzzy input and output examples and has higher performance than normal fuzzy method.