Cascade classifier-based state detection method of poor falling off of hexagonal nuts of double-sleeve connector of high-speed rail overhead line system

Abstract

The invention discloses a cascade classifier-based state detection method of poor falling off of hexagonal nuts of a double-sleeve connector of a high-speed rail overhead line system. The detection method comprises steps of: firstly establishing a sample library related to parts of the double-sleeve connector, extracting HOG features of samples to train cascaded AdaBoot classifiers; on this basis, and training a support vector machine, thereby achieving positioning of parts of the double-sleeve connector; then, using the Hough conversion to achieve extraction of oblique angles of flat cantilevers and oblique cantilevers connected to the double sleeves in a target image, and rotating the flat cantilevers to the horizontal direction, thereby, achieving segmentation of the flat cantilevers and the connector; and rotating the oblique cantilevers to the vertical direction, thereby achieving segmentation of the oblique cantilevers and the connector. During fault determination, in the extracted connector image, transverse base lines are set according to positions of light spots, a transverse gray level singular value is detected and precise judgment is made for the falling-off faults of the big hexagonal nuts of the double-sleeve connector.

Description

technical field [0001] The invention relates to the field of fault detection of high-speed railway catenary, in particular to a method for detecting the bad state of falling off of a hexagonal nut of a double-sleeve connector of a high-speed railway catenary based on a cascade classifier Background technique [0002] In the L-shaped wrist arm support device of the high-speed rail catenary, the double-sleeve connector is an important load-bearing component. In order to ensure the safety of the train, the construction quality of this component has strict requirements. For double ferrule connectors, the hexagon nut is an important fastener. Vibration or construction defects during long-term operation of the train may cause the large nut of the casing to fall off, which reduces the bearing capacity of the wrist arm, reduces the mechanical strength of the catenary, and increases the possibility of accidents. The 4C system technical specification promulgated by the former Ministr...

AI Technical Summary

Problems solved by technology

Since the images of catenary support and suspension devices collected on site are generally complex, and the fasteners in the photos are easily affected by reflections, it is difficult to use image processing technology to detect them. At present, there are no relevant reports on this aspect of research.

Images