A method for matching hooks and ladle lugs based on deep learning

Abstract

The invention provides a method for matching hooks and ladle lugs based on deep learning, comprising the following steps: S1, using a camera to take images of the crane hook and ladle lugs; S2, using RetinaNet to detect the Hook and lug; S3. Using camera calibration technology, establish a three-dimensional coordinate system for the hook and lug detected in S2; S4. Calculate the horizontal and vertical coordinates of the hook and lug through the coordinate system obtained in S3. Coordinate difference in the vertical direction, adjust the position of the hook so that the hook is in contact with the lifting lug; S5, calculate the rotation angle of the hook through the information collected by the sensor, and calculate the center of mass of the hook and the center of mass of the lifting lug in the horizontal direction When the distance Δx on Δx is less than the predetermined threshold, it is a reliable match, otherwise it is an unreliable match. When the match is unreliable, the position of the hook is constantly adjusted to make Δx less than the predetermined threshold. It solves the problems in the prior art that the matching between the hook and the lifting lug is not firm, which leads to the tipping of the steel ladle and the like.

Description

technical field [0001] The invention relates to the technical field of ladle transfer safety, in particular to a method for matching a hook and a ladle lug based on deep learning. Background technique [0002] The iron (steel) ladle is the main container for the transportation, transfer and smelting of molten iron (steel) in the steelmaking area. The hoisting of the iron (steel) ladle is mainly realized by the crane hook and the trunnion. The method of whether the iron ladle is safe mainly relies on manual visual inspection on both sides of the ladle. With the continuous acceleration of the current steelmaking production rhythm, lifting operations are becoming more and more frequent, and manual visual inspection is sometimes affected by poor night vision and poor mental state. Influenced by factors such as weak sense of responsibility, etc., the crane lifting bag is not strong, the hook and trunnion do not match, and when the bag is placed out of position, the iron (steel) h...

AI Technical Summary

Problems solved by technology

[0003] Aiming at the deficiencies in the prior art, the present invention provides a method for matching the hook and the ladle lifting lug based on deep learning, which solves the problems in the prior art that the matching between the hook and the lifting lug is not firm enough to cause the ladle to tilt Flip and other issues

Images