Research on intelligent fault diagnosis for railway point machines using deep reinforcement learning

Abstract

The advanced diagnosis of faults in railway point machines is momentous to ensure the efficient and stable operation of the turnout conversion system. Numerous mature deep learning methods have been extensively applied in this domain. While robust perception has yielded excellent diagnostic outcomes, the deficiency in decision-making capability has led to a lack of overall intelligence. To deal with this, this study proposes an end-to-end deep reinforcement learning (DRL) framework for diagnosing faults in railway point machines. Firstly, a one-dimensional convolutional neural network (1DCNN) is used for the automatic extraction of features from the current signal. Subsequently, the deep Q network (DQN) algorithm is introduced as the core of the diagnostic framework. This involves designing an interactive environment for fault classification and optimizing the agent training network. Finally, leveraging fault data, the agent and the environment engage in continuous interactive learning to produce the ideal classification policy. Multiple comparative experiments are conducted to validate the proposed method. The results demonstrate that the diagnostic accuracy reaches 98.41%, and the average accuracy after many iterations is as high as 99.12%. Notably, this research introduces a creative application of DRL to address the challenge of diagnosing faults in railway point machines. The incorporation of decision thought effectively enhances the intelligence of fault diagnosis.