DETECTION OF SURGING SOUND WITH WAVELET TRANSFORM AND NEURAL NETWORKS

An acoustic diagnosis technique for the blower by wavelet transform an d neural networks is described. It is important for this diagnosis to detect surging phenomena, which lead to the destruction of the blower. Dyadic wavelet transform is used as the pre-processing method. A mult i-layered neural network is used as the discrimination method. Experim ent is per formed for a blower. The results show that the neural netwo rk with wavelet transform can detect surging sound well.