Audio Fault Diagnosis for Motor Based on D-S Evidence Theory
GU Ai-yu · Computer Knowledge and Technology · 2010
In this paper,a new efficient audio fault diagnosis system based on information fusion technology and neural network was pre-sented,the background of wavelet transform was given.In data fusion level,multi-neural networks are used to carry on fusion in motor feature level and carry on local motor fault diagnosis,in order to acquire independent evidence each other.Then D-S evidence theory and fusion algorithm are used to fuse evidence.The results show that the proposed method was effective,improved the diagnostic precision and satisfy the requirement for real time.