Equipment fault diagnosis method and system of electric power system

摘要: The invention discloses an equipment fault diagnosis method of electric power system. comprises the steps segmenting infrared image by utilizing a two-dimensional fuzzy-partition maximal entropy, and performing noise reduction target segmentation on collected thermogram point equipment; classifying storing all targets artificial neural network; finally comparing separated or prediction with carrying out fusion analyzing according to stage model, so as obtain result; data conventional empirical detected data, thus obtaining final result predicted position equipment. By integrating multiple algorithms, precise are formulated, modularization systematic design is adopted, that complete precision way for diagnosing system established, running reliability stability can be improved.