Defect detection method applied to motor coil based on cascade expansion FCN network

Abstract

The invention relates to a defect detection method applied to a motor coil based on a cascade expansion FCN network, and the method comprises the following steps: 1), collecting a sample image, i.e.,a big image, of a target region needing defect detection; 2) traversing all the sample images, and marking the defect position of each image; 3) performing sliding image segmentation on the large image by adopting a window sliding method, and segmenting the marked large image into small images with fixed sizes for training; 4) performing data enhancement on the small graph cut from the sliding window, and expanding the cut small graph; 5) applying the expanded small graph to the training of a network model, evaluating the defect detection effect, and adjusting parameters; and 6) obtaining a feature map output by the last layer of the network model, i.e., a segmentation position of the defect, i.e., a final output result. According to the method, the trained model can be added to an industrial production machine, whether the product has the defect or not can be automatically recognized, the defective product can be automatically shunted, the detection efficiency can be improved, and thelabor cost can be reduced.

Description

technical field [0001] The invention relates to the technical field of computer vision image processing, in particular to a defect detection method applied to motor coils based on a cascaded expanded FCN network. Background technique [0002] Deep neural network model is a kind of multi-layer network model that can construct high-level features from low-level features to learn feature hierarchy. Usually, trainable filters and local neighborhood pooling operations alternately act on the original input data, during which a series of abstract and complex features are output; then the features extracted by the deep neural network are upsampled and fused to predict the category of pixels In order to realize the detection of defects. [0003] At present, for the defect detection of electric motor coils, the traditional method is to design feature extraction processing methods for each defect in the electric motor coil, but the features extracted by manual design are limited to sp...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a defect detection method based on cascaded expanded FCN network applied to motor coils, which solves the disadvantages of traditional defect detection methods relying on feature selection and extraction, and can automatically learn to extract effective features; at the same time, it effectively avoids the drawbacks of the existing deep learning segmentation model, which is easy to overkill at the edge of the defect

Images