Quantification of wear on gear cutting tools using computer vision methods

Gears are commonly soft machined using manufacturing processes with a geometrically defined cutting edge, with the aim of balancing workpiece quality and manufacturing costs by controlling tool wear. Early detection of critical tool wear is therefore a key factor. In this paper, an algorithm for detecting and quantifying tool wear on gear cutting tools using computer vision methods is presented. For this, the suitability of traditional and deep learning-based computer vision methods for tool wear detection is compared. Traditional methods used include binary thresholding, edge detection and contour detection. The suitability of different convolutional neural network architectures for the application of deep learning-based computer vision methods is compared. Using U‑Net with EfficientNet as the backbone, an Intersection over Union score of IoU = 0.65 and a loss of l = 0.05 is achieved on the training data and an IoU score of IoU = 0.64 and a loss of l = 0.06 is achieved on the validation data after 60 epochs. The convolutional neural network for identifying the worn area on gear cutting tools is then integrated into a wear quantification algorithm. To quantify the tool wear the mean and maximum wear width VB<inf>m</inf> and VB<inf>max</inf>, and the worn area VB<inf>area</inf> are calculated. To ensure the performance of the algorithm, a manually measured wear curve and an algorithm-generated wear curve from bevel gear cutting and gear hobbing wear trials are compared. Overall, good agreement is achieved between the algorithm-generated and manually measured wear curves with an average absolute difference of ∆VB<inf>max</inf> = 7.99 µm for bevel cutting and ∆VB<inf>max</inf> = 19.95 µm for gear hobbing.