A gas regulator fault detecting method based on acoustic emission technology

摘要

In this paper, a new method of gas pressure regulator fault diagnosis is proposed. The wavelet packet decomposition is used for feature extraction of the acoustic emission signal. Then, based on the model obtained in the BP neural network, early regulator fault can be detected. The experimental results prove the feasibility of this method. It can effectively improve the accuracy of the fault diagnosis of the regulator. In addition, the millisecond diagnostic cycle also makes this method have a high engineering value.