Method and system for detecting abnormal state of railway overhead line system bolt

Abstract

The embodiment of the invention provides a method and system for detecting the abnormal state of a railway overhead line system bolt. The method comprises: acquiring an image of a to-be-detected railway contact network bolt; and based on the trained image generation model and the multiple spatial mapping model, carrying out anomaly detection analysis on the to-be-detected railway contact network bolt image to obtain a railway contact network bolt abnormal state detection result. According to the embodiment of the invention, based on an unsupervised learning algorithm, the problems of poor generalization, difficulty in defining abnormal categories and great reduction of accuracy of unseen abnormal samples of an existing detection algorithm are solved, and the unsupervised learning algorithmdoes not need to define the abnormal categories in detail, so that the data annotation amount is greatly reduced, and the working intensity of detection personnel is reduced.

Description

technical field [0001] The invention relates to the technical field of railway detection, in particular to a method and system for detecting abnormal states of railway catenary bolts. Background technique [0002] In the daily maintenance of railway catenary, there are a large number of abnormal detection tasks of railway catenary images. Since the bolts are typical small-sized parts with a large number and type, the probability of abnormal state is high and the number of abnormal samples that can be collected is relatively small. This makes the bolt state anomaly detection task the most difficult. High-speed rail is a typical complex system. Due to its functional characteristics, bolts are widely used in railway catenary equipment. The detection of its abnormal state is of great significance to maintain the normal operation of high-speed rail. At present, the catenary bolt state abnormality detection task mainly relies on professionals to carry out image screening. The sho...

AI Technical Summary

Problems solved by technology

[0009] The embodiment of the present invention provides a method and system for detecting the abnormal state of bolts in the railway catenary, which is used to solve the problem that the supervised learning algorithm used in the prior art for bolt abnormal detection needs to rely on a large number of labeled samples. When the abnormal difference is small Problems that can easily lead to poor detection results

Images