The invention relates to a
machine vision detection method for
helical gear wear. The method comprises the following steps: step 1,
image acquisition: acquiring a gear image; the main direction of the
tooth surface is detected in real time through Hough transformation, a direction-adjustable
Gabor filter bank is constructed, dynamic deformation of the gear is compensated, and relevant abrasion characteristics are highlighted; step 3, multi-resolution feature decoupling is carried out; 4,
physical field constraint
deep learning: inputting the enhanced image and strain
field data into ResNet-101, and outputting a wear probability thermodynamic diagram; 5, dynamic deformation sensing registration: calculating three-dimensional deformation, using the three-dimensional deformation as a rigid constraint term of an ICP
algorithm to compensate dynamic deformation, and carrying out
point cloud adaptive alignment registration; 6, working condition self-
adaptive decision making: calculating the membership degree of the current working condition, calculating a dynamic threshold value, and combining a probability graph threshold value, a
physical field residual error and a deformation abnormal value to carry out comprehensive
decision making; and step 7, health state evaluation and early warning: calculating an abrasion index.