A Convolution Neural Network-Based Approach for Metal Surface Roughness Evaluation

Abstract

Metal surface roughness detection is an essential step of quality control in the metal processing industry. Due to the high manual involvement and poor efficiency of traditional roughness testing, rapid automated vision detection has received increasing attention in product quality control. Many methods have focused on extracting features related to roughness from images by means of mathematical statistics. However, these methods often rely on extensive experiments and complex calculations, while being sensitive to external environmental disturbances. Metal surface roughness detection is an essential step of quality control in the metal processing industry. Due to the high manual involvement and poor efficiency of traditional roughness testing, the rapid automated vision detection has received increasing attention in product quality control. Many methods have focused on extracting features related to roughness from images by means of mathematical statistics. However, these methods often rely on extensive experiments and complex calculations, while being sensitive to external environmental disturbances. In this paper, a convolution neural network-based approach for metal surface roughness evaluation has been proposed. The convolutional neural network was initialized using a transfer learning strategy, and the data augmentation technique was applied to the benchmark dataset for sample expansion. To evaluate this approach, samples of 4 types of roughness classes were prepared. The samples were divided into a training set, validation set, and test set in the ratio of 7:2:1. The accuracy of the neural network on the test set was found to be above 86%. In this paper, we propose a convolution neural network-based approach for metal surface roughness evaluation. We applied migration learning to initialize the convolutional neural network and used data augmentation techniques for sample expansion on the benchmark dataset. The effectiveness of the proposed approach and its superiority over manual detection have been demonstrated in the experiments. No more