Train suspension system failure isolation method based on LDA method

Abstract

The invention relates to a train suspension system failure isolation method based on an LDA method. The train suspension system failure isolation method is based on data feature extraction of the Fisher discriminatory analysis method and the application of the Fisher discriminatory analysis method in a train suspension system failure diagnosis. Diagnosis discrimination functions are obtained by collecting and training simulated normal data and all types of failure data so that new test data can be discriminated and diagnosed. According to the train suspension system failure isolation method based on the LDA method, a precise mathematical model is not required, and any requirement for overall distributed situations is not made; a large number of characteristic variables are reduced to several linear combinations, so that smaller dimensionalities are formed for convenient expression; meanwhile, a test unit is simple in structure and not prone to being interfered by external factors, and therefore the reliability of a device is high.

Description

technical field [0001] This patent belongs to the technical field of railway transportation, and in particular relates to a fault separation method for a train suspension system based on a linear discriminant method. Background technique [0002] The dynamic characteristics of the train suspension system have coupling effects in the vertical and lateral directions, coupled with the nonlinearity of the suspension components of the train, the flexible structure of the car body and many other factors, it is difficult to obtain an accurate mathematical model of the train suspension system. Model. Therefore, there are many limiting factors in the model-based fault diagnosis method, such as modeling error, complicated process, and large computational burden. Data-driven fault diagnosis methods have received extensive attention and research in recent years, and have made great progress. The fault diagnosis method based on Fisher's discriminant analysis method is one of the very i...

AI Technical Summary

Problems solved by technology

[0002] The dynamic characteristics of the train suspension system have coupling effects in the vertical and lateral directions, coupled with the nonlinearity of the suspension components of the train, the flexible structure of the car body and many other factors, it is difficult to obtain an accurate mathematical model of the train suspension system. Model

Therefore, the model-based fault diagnosis method has many limiting factors such as modeling error, complex process, and large computational burden.

Images