Image classification and analysis during the additive manufacturing process based on deep convolutional neural networks

Abstract

In the advanced industrial manufacturing (3D printing), the assembly quality of parts has a tight relationship with the strength and the stiffness of products. Deep convolutional neural network for the image classification is an effective analysis approach for controlling the surface quality of parts and monitoring defects during this process. In this paper, a novel Artificial Intelligence (AI) method to classify and analyze numerous metal images during the manufacturing process is proposed. We exploit the visual-based feature classification method and deep convolutional neural network (DCNN) to analyze the quality of manufacturing parts, which is widely used in the defect detection for Additive Manufacturing. Two types of self-made industrial manufacturing datasets are collected, based on which we train the DCNN model to run the image classification tasks. Experiment results show that this method can achieve the state-of-art classification accuracy.