Abnormal diagnosis of acoustic emission pipeline working conditions based on PSO-LSTM-DAE

Abstract

Abstract To solve the problem of difficult identification of pipeline working conditions, acoustic emission was used to extract abnormal pipeline data, and a PSO-Lstm-DAE model was proposed to classify and identify abnormal working conditions of acoustic emission pipelines. The algorithm took advantage of the timing characteristics of LSTM and the noise reduction ability of DAE and set the optimal superparameters through PSO. In this paper, four commonly used abnormal condition detection data sets were collected, and algorithm tests were carried out on the data sets and compared with other anomaly detection algorithms. The classification accuracy of the proposed PSO-LSTM-DAE model was 95.68%. The results of multiple indexes show that the PSO-LSTM-DAE model proposed in this paper has significant advantages in the diagnosis of abnormal pipeline conditions.