Intelligent Fault Detection Method for Air Braking Devices of Railway Freight Cars

Abstract

The invention relates to the technical field of railway freight car brake detection, and relates to an intelligent fault detection method for an air brake device of a railway freight car, comprising the following steps: 1. Obtaining the air pressure supplied to the sensor under normal and different damage conditions of various components The measurement data constitutes the training data set; 2. Divide the accumulated pressure measurement data collected by the sensor into a single different braking state data, and the different braking states include braking, pressure holding and relief; 3. Judging according to the cumulative difference function Braking state, and data feature extraction; 4. Build a random forest, input the extracted data features for model parameter training. The invention can preferably detect the fault type and damage degree of the air brake device of the railway freight car.

Description

technical field [0001] The invention relates to the technical field of railway freight car brake detection, in particular to an intelligent fault detection method for an air brake device of a railway freight car. Background technique [0002] The components of the air brake system of railway freight cars include brake supervisors, auxiliary air cylinders, brake cylinders, 120 valves, etc. The brake supervisor provides compressed air for each vehicle. When the air pressure in the pipe decreases, the train will brake, and the air pressure will increase to relieve the train. The 120 valve is the core of the brake device. The brake main pipe, brake cylinder and auxiliary air cylinder are all connected to the 120 valve. It adjusts the position of the internal slide valve and throttle valve according to the change of the air pressure of the brake main pipe to open or block the relevant passages. , to realize the control of train braking or mitigation. The auxiliary air cylinder ...

AI Technical Summary

Problems solved by technology

Due to the dependence and coupling relationship of each component in the air brake system, it is difficult to find faults, and there is a strong ambiguity between fault symptoms and causes, which brings great difficulties to fault diagnosis and location

[0003] At present, the detection system generally uses an over-limit alarm mechanism to monitor the air brake system of railway freight cars. This type of fault is usually caused by serious leakage. It cannot be well monitored for the performance degradation caused by the deterioration of the brake system status components.

Although fault detection methods such as fault tree theory, expert system, and fuzzy theory can achieve the effect of brake fault diagnosis to a certain extent, the accuracy of fault diagnosis, fault location accuracy, and fault diagnosis efficiency are all low, and the interpretation of fault occurrence is relatively low. Not strong

Traditional models are generally based on expert knowledge and experience, which cannot accurately reflect the facts. At the same time, after the model is built, it is not easy to change, and it is not easy to accept external information and human-computer interaction.

Images