The invention discloses an abnormal detection method and
system for a splayed anti-loosening line of a rail
train, and relates to the technical field of
rail traffic detection, and the method comprises the steps: image collection and
processing: shooting an image of a fixed point region containing the anti-loosening line, and preprocessing the image to obtain a target image; line integrity judgment: extracting a bolt, a bolt marking line and an anti-loosening line through an analysis model to form a target area graph, and judging whether the anti-loosening line is complete or not according to
line segment continuity and form; performing line deformation depth analysis, and synchronously obtaining the position of an anti-loosening line intersection point and deformation data through the model in combination with the loosening angle of the bolt marking line when the line deformation is complete; performing line deformation safety judgment, setting a safety threshold
group based on historical data, and comparing deformation data to output a
signal; after line deformation abnormity judgment and comparison
signal receiving, actual data are compared with theoretical data output by the mechanical model, and abnormal or normal signals are output. The anti-loose line full-dimension high-precision detection is achieved,
automation and real-time performance are improved, and
train operation safety is guaranteed.