Bearing temperature prediction and alarm diagnosis method based on LSTM model

Abstract

The invention discloses a bearing temperature prediction and alarm diagnosis method based on an LSTM model. Firstly, a bearing temperature prediction model is generated, model input data is obtained according to the real-time monitoring temperature, and then target shaft position temperature data is predicted; and finally, the running state of the bearing is judged according to a temperature alarmmechanism and an alarm result is output. According to the invention, temperature prediction of the target shaft position is carried out through the auxiliary shaft position temperature value; a long-short-term memory network model is adopted; the bearing fault alarm system based on the temperature sensor is prevented from being disturbed by temperature jump and temperature keeping unchanged in the using process, false alarm and missing alarm are avoided, the incidence relation in the time sequence can be analyzed, the trend of time sequence data is predicted, and meanwhile the defect that other neural networks cannot be predicted for a long time is overcome. And temperature alarm can be carried out more accurately.

Description

technical field [0001] The invention relates to the technical field of railway transportation safety monitoring and train fault detection, in particular to a research on temperature prediction and temperature alarm mechanism of bogie rolling bearings based on LSTM recursive neural network model. Background technique [0002] With the rapid development of my country's high-speed, heavy-duty railways and urban rail transit, it poses challenges to the operation and maintenance of rail transit vehicles, and rolling bearings are one of the key components of train bogies, and their operating status directly affects the stability and safety of trains Therefore, breaking through the health status monitoring and online fault diagnosis technology of key components of high-speed trains is an important way to ensure the safe and efficient operation of high-speed trains. In the bogie rolling bearing fault monitoring system developed by several companies, temperature sensors are used to co...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is: false alarms caused by sensor damage, electromagnetic interference, etc. in the existing bogie fault diagnosis system, and temperature alarm problems caused by reducing normal shaft temperature rises such as locomotive high-power operation, etc., bearing alarm system Accuracy and stability are not enough

Images