Method and device for ground fault diagnosis of dc600v train power supply system

Abstract

The invention discloses a grounding fault diagnosing method and apparatus of a DC 600V train power supply system. The method includes the steps of obtaining fault waveform sets of the DC600V train power supply system when different types of ground faults occur, wherein each fault waveform sample set corresponds to one ground fault type, training each fault waveform set to obtain a fault classification model, and acquiring current fault waveform on a real-time basis when a grounding fault occurs to a target DC600V train power supply system and diagnosing the grounding fault type corresponding to the current fault waveform according to the fault classification model. The apparatus comprises a classification model training module and a fault diagnosing module. The method and apparatus have the advantages of simple realization operation, high diagnosis efficiency and precision, high universality, good expansion performance and easy execution and maintenance.

Description

technical field [0001] The invention relates to the technical field of electric locomotives, in particular to a ground fault diagnosis method and device suitable for a power supply system of a DC600V train. Background technique [0002] The DC600V train power supply system is widely used in air-conditioned trains. The ground fault protection device in the power supply system is an important part of ensuring the operation of the train and the personal safety of passengers, and plays an important role in ensuring the operation of the electric locomotive train. The key to the realization of the ground fault protection device lies in the identification and detection of the ground fault waveform and the separation of different fault modes, that is, the ground fault diagnosis. Ground fault diagnosis is divided into two main steps: fault detection and fault separation. Fault detection is to judge whether a ground fault occurs in the system, so as to respond quickly to reduce the lo...

AI Technical Summary

Problems solved by technology

[0003] There are many types of ground faults in the DC600V power supply system and it is difficult to accurately locate them. First, the power supply system is mainly divided into rectifier units, DC power supply units, and inverter output units. Changes in type and load will lead to changes in fault waveforms, that is, fault waveforms are likely to be unstable on vehicles such as complex working conditions, different batches, and load changes, and the electromagnetic environment on electric locomotives and bullet trains is very complicated. The detailed features are also unreliable under the action of ground faults, which will bring great troubles to the positioning and separation of ground faults

[0004] At present, there are few relevant studies on the ground fault diagnosis of DC600V power supply system, and there is no effective diagnosis method. The existing fault diagnosis methods are usually designed based on some local characteristics of the fault waveform to realize waveform recognition, Fault diagnosis, and the diagnosis method based on the local characteristics of the fault waveform has the following problems:

[0005] ① Incomplete identification features and inaccurate diagnosis

Especially in new road conditions and new load environments, many problems such as unrecognized, misjudged, and missed judgments are likely to occur, making there still hidden safety hazards and unable to effectively meet engineering needs;

[0006] ② poor versatility

The above-mentioned methods and algorithms for local features are usually difficult to generalize. It is necessary to optimize parameters for each working condition, as well as feature selection, algorithm design, and even re-design of the algorithm for each fault. When there are many failure modes and the working environment is complex, often hard to accomplish;

[0007] ③ Poor maintenance

When the power supply system changes and the external environment changes, it takes a lot of energy to adjust parameters or even redesign the algorithm. When a new failure mode appears, it is difficult to maintain, and in actual engineering applications, it is often necessary to perform specific algorithm processing for different locomotives. It is very difficult to maintain and upgrade the above method;

[0008] ④Large workload required

The method based on the local characteristics of the fault waveform requires characteristic analysis and algorithm design for each fault mode, which is inefficient, requires a large amount of work, and takes a lot of time

[0009] ⑤ poor robustness

Identification algorithms based on local features have poor generalization characteristics, and it is difficult to stably identify and separate faults in complex environments

Images