An Adaptive Multisensor Fault Diagnosis Method for High-Speed Train Traction Converters

Abstract

Traction converters are safety-critical parts of traction drive systems on high-speed trains. Considering the complicated interconnections in the traction converter, it is imperative to utilize multisensors rather than single-sensor for fault diagnosis. However, the multisensor-based traction converter fault diagnosis is barely discussed by now. Concerning this issue, this article proposes a novel intelligent diagnosis method based on long short-term memory network, which deals with extracting long-term dependencies in time series effectively and learns hidden fault characteristics from traction converter multisensor signals adaptively, without needs of expert knowledge or system modeling. Experiments were designed to verify the model's sensitivity on different signals as single-sensor respectively, and as multisensors integrally. Ten kinds of measured signals from actual high-speed trains in operation were utilized for verification. Results show that the proposed method has the highest sensitivity to different signals compared to conventional models, and the crucial fault modes were identified accurately, which implies the high reliability of multifault identification. In addition, experiments on different scales of training sets also suggest that the model accuracy can be improved by increasing the training data scale appropriately. Besides, this method can be further applied to other train systems with similar data characteristics in the future.