Train operation fault automatic detection system and method based on binocular stereoscopic vision

Abstract

The invention discloses a train operation fault automatic detection system and method based on binocular stereoscopic vision, and the method comprises the steps: collecting left and right camera images of different parts of a train based on a binocular stereoscopic vision sensor; achieving the synchronous precise positioning of various types of target regions where faults are liable to happen based on the deep learning theory of a multi-layer convolution neural network or a conventional machine learning method through combining with the left and right image consistency fault (no-fault) constraint of the same part; carrying out the preliminary fault classification and recognition of a positioning region; achieving the synchronous precise positioning of multiple parts in a non-fault region through combining with the priori information of the number of parts in the target regions; carrying out the feature point matching of the left and right images of the same part through employing the technology of binocular stereoscopic vision, achieving the three-dimensional reconstruction, calculating a key size, and carrying out the quantitative description of fine faults and gradually changing hidden faults, such as loosening or playing. The method achieves the synchronous precise detection of the deformation, displacement and falling faults of all big parts of the train, or carries out the three-dimensional quantitative description of the fine and gradually changing hidden troubles, and is more complete, timely and accurate.

Description

technical field [0001] The invention relates to the technical field of train operation fault detection, in particular to an automatic detection system and method for train operation faults based on binocular stereo vision. Background technique [0002] With the rapid development of China's high-speed railway, the construction of a train operation safety monitoring system is particularly important. The existing monitoring system lacks dynamic monitoring during operation. This will cause the train to travel sick for a long distance, increasing the probability of accidents. Due to the long-term transmission force and braking force of the train running at high speed, different degrees of loosening may occur, which will cause safety hazards to continue high-speed operation. [0003] In terms of automatic detection of train operation faults, some scholars have proposed some fault detection methods for certain specific operation faults. Liu Shuoyan and others proposed a method f...

AI Technical Summary

Problems solved by technology

[0004] At present, most of the existing automatic detection algorithms for train operation faults are mainly based on manual feature extraction, and algorithms need to be designed for different types of faults. However, due to the complexity of the train structure, the fault mechanisms and fault manifestations of different train components are not the same. , there are often huge differences in the different detection and diagnosis methods adopted, which makes the generalization of the algorithm not strong, and the effect of multi-fault detection is not good.

Moreover, the existing train operation fault detection algorithms are only based on the two-dimensional image processing of the train from a single shooting angle, which lacks depth information. Gradual changes hide faults, and the detection effect is not ideal. It can only describe whether a fault occurs qualitatively in two dimensions, but cannot quantitatively describe the fault in three dimensions to characterize the degree of fault occurrence.

This makes the maintenance of the train set incomplete, untimely, inaccurate, and there are problems of "insufficient maintenance" or "excessive maintenance" and inappropriate maintenance timing, thus failing to ensure that train failures are effectively prevented and increasing maintenance costs

Images