Fault Diagnosis Method Based on I/O Measuring Point Fault Dependency Matrix

Abstract

The invention discloses a fault diagnosis method based on an I / O measuring point fault dependency matrix, comprising the following steps: S1: obtaining vehicle door state data; S2: structured data processing; S3: selecting test points; S4: constructing a fault test dependency matrix ; S5: fault diagnosis reasoning. The invention uses a data-based mathematical modeling method to structurally process the control signal data of the door controller and model the fault test, so that accurate correlation can be established between the test result and the fault, the data collection is convenient, and the method is applicable Wide; the selection of test points is based on the structural and functional characteristics of the car door, and the normal car door data is used as a benchmark to formulate standard selection of test points and filter data to make the selection of test points more reasonable. Considering the difference in collection time, relative time is used As a standard to establish a faulty test interval for testing.

Description

technical field [0001] The invention relates to the field of urban rail transit, in particular to a fault diagnosis method based on an I / O measuring point fault dependency matrix. Background technique [0002] Urban rail transit has many advantages such as large capacity, high efficiency, low energy consumption, intensification, convenient ride, safety and comfort, etc. It is an important way to solve the problem of urban traffic congestion, realize the adjustment of urban spatial layout and the balanced development of the city. Automation is also one of the development trends in the industry. Computer control and system security control will improve the automation of subway operations. While the functions of the subway are becoming more and more perfect, the structure, components and signal transmission system of the vehicle system are developing rapidly, which makes the types of faults more complicated. In particular, the doors of the subway are opened and closed hundreds ...

AI Technical Summary

Problems solved by technology

While the functions of the subway are becoming more and more perfect, the structure, components and signal transmission system of the vehicle system are developing rapidly, which makes the types of faults more complicated. In particular, the doors of the subway are opened and closed hundreds of times a day. The degradation process of the door system is faster, coupled with the influence of environmental and human factors, the frequency of failure of the door system increases

At present, the intelligent diagnosis algorithm for car door faults is not perfect enough, and it is still necessary to manually go to the scene to detect a large number of parameters related to the car door, and to find out the cause of the fault, which is time-consuming and labor-intensive.

[0003] At present, fault diagnosis methods are mainly divided into three categories: model-based, knowledge-based, and data-driven. Among them, the model-based method is mainly suitable for objects that can establish mathematical models. Due to the complex structure of the car door, it is difficult to construct an accurate analytical model, so it is not Not suitable for diagnosing car door faults; knowledge-based diagnosis methods, divided into expert systems and symbolic directed graphs, are suitable for objects that cannot be modeled and the number of sensors is insufficient, but the cost of diagnosis for systems with large amounts of data is too high; expert systems In-depth professional knowledge and long-term accumulation of experience are required, and the types of subway door faults are complex, so the expert system is not fully applicable in actual operation; the main fault diagnosis method is still based on the data-driven fault diagnosis method, through the online and Analyze and process offline data to realize fault diagnosis

Images