Real-Time 3D Surface Measurement in Additive Manufacturing Using Deep Learning

Abstract

Layer-wise 3D surface morphology information is critical for the quality monitoring and control of additive manufacturing (AM) processes. However, most of the existing 3D scan technologies are either contact or time consuming, which are not capable of obtaining the 3D surface morphology data in a real-time manner during the process. Therefore, the objective of this study is to achieve real-time 3D surface data acquisition in AM, which is achieved by a supervised deep learning-based image analysis approach. The key idea of this proposed method is to capture the correlation between 2D image and 3D point cloud, and then quantify this relationship by using a deep learning algorithm, namely, convolutional neural network (CNN). To validate the effectiveness and efficiency of the proposed method, both simulation and real-world case studies were performed. The results demonstrate that this method has strong potential to be applied for real-time surface morphology measurement in AM, as well as other advanced manufacturing processes.

Adaptive 3D Printing for In Situ Adjustment of Mechanical Properties

“…[1][2][3][4][5][6][7][8][8][9][10][11][12][13][14] Given the varied range of possible errors that can occur in FDM 3D printing, there are multiple different methods to approach the detection of specific issues. Machine vision is one of the popular methods [1][2][3][4][5][6]8,[10][11][12][13][14][15][16][17] to detect errors present in printing such as clogged nozzles or layer shifts, while machine learning has been utilized to compare the current operating state of the printer to the desired state. [5,6,8,[11][12][13]18,19] The combined method with these allows users to detect whether the correction is needed for the print or not.…”