Real-time Defect Detection for Fused Deposition Modeling based on Machine Learning

FDM (Fused Deposition Modeling) 3D printing technology, as a type of additive manufacturing technology, is widely used in industrial production and scientific research and education. However, many potential problems in the printing process, such as nozzle clogging and material supply interruption, often lead to printing failure, which seriously affects productivity. In order to solve these problems, this paper proposes an artificial intelligence model RAN based on ResNet_50, which realizes the integration of ResNet_50 and Alex net model for detecting defects in the FDM 3D printing process. By introducing the time window strategy in the RAN model, the prediction level is smoother by modifying the model to improve the accuracy on the one hand and at the same time by introducing the time window strategy in the RAN model. Finally, the classification ability of the two types of images in the data is compared, pointing out the deficiencies in the model, and future models can be more diversified to collect information in order to have better classification ability.