Fault prediction method and device of electric sliding plug door

Abstract

The invention provides a fault prediction method and device of an electric sliding plug door, wherein the method comprises the steps of: obtaining transverse and vertical stress signal data of the electric sliding plug door, and acquiring motor current signal data output by a door controller corresponding to the electric sliding plug door; and performing fault prediction according to the transverse and vertical stress signal data, the motor current signal data and a pre-trained hidden Markov model to obtain a fault prediction result of the electric sliding plug door, therefore, by performing the fault prediction on the electric sliding plug door by combining the hidden Markov models of two fault factors of the transverse and vertical stress signal data and the motor current signal data, the state of the electric sliding plug door can be accurately predicted, and the fault prediction accuracy of the electric sliding plug door is improved.

Description

technical field [0001] The invention relates to the technical field of urban rail transit, in particular to a fault prediction method and device for an electric sliding door. Background technique [0002] With the development of urban rail transit, higher requirements are put forward for the operation, use and maintenance of urban rail transit related equipment such as subways and light rails. [0003] In the operation process of urban rail transit vehicles, the door is a relatively common door system driving form, and its operation reliability and safety will directly affect the normal and safe operation of urban rail transit vehicles. [0004] At present, door failure prediction methods in related technologies can be divided into two methods based on physical models and intelligent algorithm models based on data analysis in terms of prediction models, among which: [0005] The fault prediction method based on the physical model only performs fault prediction for a single ...

AI Technical Summary

Problems solved by technology

However, since this model is based on experimental data, in the actual operation of rail equipment, due to various causes of failure, the effect of failure prediction in actual operation is very limited

[0007] Based on the above description, it can be seen that the above two types of fault prediction methods have a common shortcoming, which is that they can only target one fault cause, and the health management and fault prediction effects of the actual operation of the door system are not ideal.

Images