Method and system for constructing and predicting service life prediction model of key component of wheel set

Abstract

The invention provides a method and a system for constructing and predicting a service life prediction model of a key component of a wheel set. The method comprises the following steps: determining input parameters of the model as environment temperature, driving speed and driving mileage, and determining an output parameter as wheel diameter residual abrasion loss; the current environment temperature, the running speed and the running mileage of the wheel set are obtained in real time, and turning repair data of the wheel set are obtained to serve as sample data; preprocessing the sample data; model construction is carried out on the preprocessed sample data, and finally the model with the highest verification sample accuracy rate is selected as the optimal prediction model of the current wheel set. And the wheel residual life is estimated and predicted by combining the wheel geometric part abrasion data and the development trend with the mileage, and the prediction precision is high.

Description

technical field [0001] The invention belongs to the technical field of prediction, and in particular relates to the construction of a life prediction model for key components of a wheel set, a prediction method and a system. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] The wheel set is one of the key components of the EMU, which plays a vital role in the actual operation of the EMU. Wheel sets play a vital role in the operation of EMUs. Wheel set failures not only endanger the driving safety of trains, but also bring huge impact and damage to railway lines and bridges, and aggravate the fatigue damage of vehicle structures. Increased maintenance costs. The traditional method of checking wheel set failures is static inspection, that is, when the vehicle is undergoing regular maintenance, the wheel set is disassembled and then measured ...

AI Technical Summary

Problems solved by technology

[0007] Because the model-based method needs to determine the distribution law, it is difficult to achieve in the actual rail transit operation, and the model needs a failure physical model, which is generally a mechanism model obtained in the experimental environment. In the actual environment operation, it is affected by various The impact of these factors is relatively large, which greatly reduces the prediction effect of the final model

[0008] From the perspective of mechanism research, the mechanism model requires precise mathematical formulas to prove the principle. Under the current technical conditions, some models cannot be established or there is no breakthrough in mechanism research, which leads to some faults. Object monitoring

Images