Model Research On Multi-Layer Intelligent Diagnosis Based On Genetic Programming

Intelligent fault diagnosis is a new approach in fault diagnosis technique. With the development of AI, more and more new methods have been found. It is an important task for researchers to work out how to apply the methods to fault diagnosis and form new intelligent fault diagnosis methods.Genetic programming (GP) is a new technology for optimization, which simulates inherit and evolution in the nature and gets optimal solutions through reproduction, crossover and mutation operations. In this thesis, built on the fault diagnosis of power transformers, modeling methods of GP-classifier are discussed. A new multi-layer intelligent diagnosis based on GP is proposed. Meanwhile, the fault diagnosis model of power transformer is established and simulated.This thesis focuses on the application of GP-classifier to fault diagnosis. The main research contribution of the thesis can be summarized as follows:1, Binary classification based on GP is analyzed. A new algorithm for binary classification based on GP with probabilistic model is proposed. Meanwhile, using 3σ-rule to make a dynamic range in binary classification improves the diagnosis accuracy. 2, The method of conversion from two-class to multi-class was analyzed. Program classification map model is introduced. Combining the hierarchical clustering and the decision tree, we establish the classification model of multi-layer GP with hierarchical clustering and probabilistic model. 3 , We implement an emulation experiment in fault diagnosis of power...