Visual Measurement of Grinding Surface Roughness Based on GE-MobileNet

Grinding surface texture is random and feature information is weak, so it is difficult to extract effective features by deep learning network. In addition, the existing deep learning methods mostly adopt a large parameter model in grinding surface roughness recognition task, and the cost of deployment in embedded end is high. In order to solve these problems, a new lightweight network model GE-MobileNet (Ghost-ECA-MobileNetV3) is proposed. Based on MobileNetV3, a feature extractor is introduced into the shallow network part of the model to enhance the ability of the network to extract and suppress the surface texture feature and noise. At the same time, SE (Squeeze-and-Excitation) attention mechanism is replaced with ECA (Efficient Channel) attention mechanism with stronger performance. Finally, the deep network layer is removed to reduce the model size. The experimental results show that the accuracy of GE-MobileNet-based grinding surface roughness measurement model on test set is 94.97%, which is better than other networks. This study proves the effectiveness of the roughness measurement method based on GE-MobileNet.