Recognition of grinding surface roughness grade based on adversarial domain adaptation under variable illumination

Abstract

Deep learning can realize the self-extraction of grinding surface features so that end-to-end roughness measurement can be realized. Still, due to the grinding surface texture being random, the features are weak, the self-extracted grinding surface features of the same surface under different lighting environments are different, and the training data and the test data when the lighting environments are inconsistent with the recognition of the measurement of the accuracy of the lower. To address these issues, this paper proposes an adversarial domain self-adaptation (NMDANN) based visual measurement method for grinding surface roughness under variable illumination. An improved residual network is used as a generator to extract more effective metastable features, and multi-head attention is introduced into the domain discriminator to enhance its domain adaptive capability. The experimental results show that the method can recognize different grades of roughness on the grinding surface under changing light environments, laying the foundation for online visual measurement of grinding surface roughness under variable light environments.