With the continuous improvement of railway speed and the continuous increase of operating mileage, automatic fault detection technology of railway vehicle equipment is becoming more and more meaningful. As a key component of the rail vehicle, the running state of bearing directly affects the safe operation of trains. Since bearing faults are closely related to the increase of axles’ temperature during the running process, bearing temperature detection has become an important method for bearing fault diagnosis. This paper presents a data-driven bearing temperature prediction framework based on the deep neural network LSTM for rail vehicle to predict the bearing temperature during operation. The data used in this study are derived from the sensor data generated by the rail vehicle during the actual operation. The accuracy of the experimental results indicates that the framework provided in this paper is a feasible prediction method of axle temperature.
CITATION STYLE
Yang, X., Dong, H., Man, J., Chen, F., Zhen, L., Jia, L., & Qin, Y. (2020). Research on Temperature Prediction for Axles of Rail Vehicle Based on LSTM. In Lecture Notes in Electrical Engineering (Vol. 639, pp. 685–696). Springer. https://doi.org/10.1007/978-981-15-2866-8_65
Mendeley helps you to discover research relevant for your work.