Train anomaly detection method and system with deep detection function

Abstract

The invention provides a train abnormality detection method and a train abnormality detection system with a deep detection function, wherein the method comprises the following steps that a train number and the current image of a train are acquired; a reference image of the train which corresponds to the train number is searched in a preset image library, and the reference image of the train and the current image of the train respectively include gray level information and depth information; the current image of the train and the reference image of the train are in alignment, and the gray level information of corresponding areas in the current image of the train and the reference image of the train is compared; and the depth information of areas in the current image of the train and the reference image of the train with inconsistent gray level is compared, the areas with inconsistent depth information are determined as the abnormal areas of the train, and the abnormal alarm information of the train is output. According to the scheme, the problem that the abnormality detection is inaccurate due to the interference of light, dust, water spots and other outside environments to the image of the train can be solved, so that the accuracy in the abnormality detection to the image of the train through a computer is improved, and finally the error alarm rate is reduced.

Description

technical field [0001] The invention relates to a train fault detection technology, in particular to a train abnormality detection method and system with a deep detection function. Background technique [0002] Railway transportation occupies a relatively important position in the field of transportation due to the advantages of large transportation volume, fast speed, high safety and reliability. [0003] As the core part of railway transportation, trains may experience abnormalities in car body parts during operation. The occurrence of abnormal parts will endanger the running safety of the train. Therefore, comprehensive, accurate and fast train anomaly detection is very important to the safe operation of the railway. [0004] However, traditional train anomalies are usually detected manually, which has the following defects: [0005] 1. The train is in motion most of the time, and it is only inspected after the train enters the station or completes the operating kilome...

AI Technical Summary

Problems solved by technology

[0005] 1. The train is in motion most of the time, and it is only inspected after the train enters the station or completes the operating kilometer and enters the warehouse. This leads to the abnormality of the train that cannot be detected and repaired in time, and ultimately increases the difficulty of manual inspection and the missed inspection of abnormal trains. probability

[0006] 2. Even if the train enters the station or enters the warehouse, due to the complex structure of the train (including freight cars, passenger cars, EMUs and other types of trains), there are many parts, it is difficult for the maintenance personnel to remember the normal state of each part, and there is a gap between the parts. There are occlusions and visual blind spots, which not only further increases the probability of missed detection of train anomalies, but also further reduces the efficiency and accuracy of anomaly detection

[0008] In order to overcome the defects of manual detection, although there is also the use of computer automatic anomaly detection methods to assist manual detection, which also achieves the purpose of reducing the difficulty of work and the probability of missed detection, but due to the large number of train parts, the type of fault is difficult to predict, and The train image acquired during the computer automatic anomaly detection process is easily disturbed by external environments such as light, dust, water stains, etc., which leads to the fact that the train image cannot accurately reflect the true state of each component of the train, and ultimately affects the detection results of the train anomaly, resulting in High false alarm rate

Images