Lifting hook and steel ladle lifting lug matching method based on deep learning

Abstract

The invention provides a lifting hook and steel ladle lifting lug matching method based on deep learning. The lifting hook and steel ladle lifting lug matching method comprises the following steps ofS1, shooting images of a crane lifting hook and a steel ladle lifting lug by utilizing a camera; S2, detecting the lifting hook and the lifting lug in the images obtained in the step S1 by utilizing RetinaNet; S3, establishing a three-dimensional coordinate system for the lifting hook and the lifting lug detected in the step S2 by using a camera calibration technology; S4, calculating coordinate differences between the lifting hook and the lifting lug in the horizontal direction and the vertical direction according to the coordinate system obtained in the step S3, and adjusting the position ofthe lifting hook to enable the lifting hook to be in contact with the lifting lug; and S5, calculating the rotation angle of the lifting hook according to information acquired by a sensor, calculating the distance delta x between the mass center of the lifting hook and the mass center of the lifting lug in the horizontal direction, determining that matching is reliable if the delta x is smaller than a preset threshold value, otherwise, determining that matching is unreliable, and continuously adjusting the position of the lifting hook to enable the delta x to be smaller than the preset threshold value if matching is unreliable. The lifting hook and steel ladle lifting lug matching method solves the problems that in the prior art, a lifting hook and a lifting lug are not firmly matched, and consequently a steel ladle is overturned.

Description

technical field [0001] The invention relates to the technical field of ladle transfer safety, in particular to a deep learning-based method for matching hooks and ladle lugs. Background technique [0002] The iron (steel) ladle is the main container for the transportation, transfer and smelting of molten iron (molten steel) in the steelmaking area. The method of whether the iron ladle is safe is mainly to rely on manual visual inspection on both sides of the ladle. With the continuous acceleration of the pace of steelmaking production, the lifting operation is becoming more frequent, and manual visual inspection is sometimes affected by poor vision at night and poor mental state. Influenced by factors such as poor sense of responsibility and weak sense of responsibility, the hanging bag of the crane is not firm, the hook and the trunnion do not match, and the position is not aligned when putting the bag, resulting in the tipping of the heavy iron (steel) bag, and the tipping...

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