“…For example, M. Abdelrahman [ 18 ] and others, utilized a high-resolution optical imaging monitoring system to photograph the powder bed before and after laser scanning, which used multiple light sources from different directions to construct the image, and then created a binary template from a sliced 3D model of the part, which was utilized to index the optical image data to the part geometry, which ultimately allowed for the detection of defects in the part defects in the area of the part; B. Shi et al [ 19 ], proposed to build a powder bed inspection system using an industrial camera and multiple illumination sources, and proposed a better illumination strategy by investigating the expression of defective features under different illumination, and also utilized image feature enhancement and adaptive threshold segmentation algorithm based on the grayscale features of the powder bed image for separating defective regions and based on the three convolutional neural network algorithms, namely, AlexNet, RexNet50, and VGG16—three kinds of convolutional neural network algorithms on the current powder layer exist in the stripe, ultra-high and incomplete powder laying three types of defective regions were experimentally compared and analyzed, and the results showed that the three kinds of defective data are prone to overfitting under the complex model. Other scholars have identified and detected defects in the powder laying process by using industrial cameras, infrared cameras, thermal cameras, and other devices combined with depth algorithms [ 20 , 21 , 22 , 23 , 24 ]. The above research has realized the acquisition of scraper motion signals and powder bed images in the powder spreading process by installing piezoelectric accelerometers on the scraper, installing industrial cameras, etc.…”