Study On The Method In Fault Intelligent Diagnosis Of Power Transformer

Power transformer is one of the most important electrical equipments in the electric system,and is also one of the electrical equipments resulting in most electric system accidents.Its operating state affects system's security level directly.It is an important issue for electrical department to find the potential faults of the transformer, to keep it operating safely, and to improve the reliability of power supply.Therefore,it is of great realistic significance to study the fault diagnosis technology of transformer and to increase the operating and maintaining level of transformer.Due to the fact that the relevant fault symptom space and fault space have complicated non-linear relations, the mathematical models of diagnosis system are dificult to build up. However, Artificial Neural Networks (ANN) provides a new technique for this issue in view of its advantages, such as parallel processing, self-adaptation, self-study, association memory,non-linear mapping,etc.Thereby,ANN and Dissolved Gases Analysis(DGA) are applied to fault diagnosis system in the paper.The transformer faults and the diagnosis technology in the round were analyzed and researched in this paper first. Then the basic theory, operation mechanism and each advantage, disadvantage of genetic algorithm, artificial neural network and wavelet transform were analyzed synthetical.This paper has studied and designed a kind of faults diagnosis model based on genetic algorithm wavelet neural network (GA-WANN)to the concrete problem. This mode first adopted improved genetic algorithm to optimize the parameter of wavelet network, then adopted BP algorithm to train the network.We put GA-WANN which has been trained into power transformer fault diagnosis. Simulation result indicates this algorithm solves the problem that wavelet network will fall into local small extremum so easily,and overcomes the shortcoming that the speed is too slow if use genetic algorithm to train neural network independently, at the same time the diagnosis accuracy improves to some extent too.A fault diagnosis method of transformer is imporved based on the quantum neural network. This mothod uses the thought of quantum state superimposition of quantum theory in neural network to form a quantum neural network which has multi-layer activation function, which gives the quantum neural network an inherent fuzziness and well solves the pattern recognition problems of cross-data in fault modes during the transformer fault diagnosis. We put the quantum neural network which has been trained into power transformer fault diagnosis.The simulation results show that this mothod has very high rate and low error rate of fault diagnosis.Quantum genetic algorithm as a fault diagnosis method of transformer is imporved in this paper in the end.Quantum genetic algorithm is based on the concept of quantum computing, the theory of evolution algorithm, which uses quantum coding characterization of chromosomes.It can be expressed a linear superposition state to obtain better population diversity, faster convergence speed and global optimization capacity. We use the trained quantum genetic algorithm for power transformer fault diagnosis, simulation results show that the quantum genetic algorithm has higher accuracy than the traditional quantum neural network.