A method of inverter circuit fault diagnosis based on BP neural network and D-S evidence theory

With the study and analysis on intelligent fault diagnosis for inverting circuit, an improved diagnosis method combined BP neuron network and D-S evidence theory was proposed. Each measuring point was extracted by BP neural network to obtain the local diagnosis, which is adopted to design the belief function of D-S evidence theory. Multiple monitoring points´ information is fused to receive the comprehensive global diagnosis result. The experimental results show that this method has the better feasibility and effectiveness on fault diagnosis in inverter´s key components-inverting circuit.