The 3D sand printing (3DSP), by binder jetting technology for rapid casting, has a pivotal role in promoting the development of the traditional casting industry as a result of producing high-quality and economical sand molds. This work presents an approach for monitoring and analyzing powder sand-bed images to serve as a realtime control system in a 3DSP machine. A deep residual network (ResNet) is used to classify the defects occurring during the powder spreading stage of the process. Firstly, a pre-trained network was applied as the initial parameter; then it was fine-tuned on the labelled defective sample dataset to accomplish the task, which defines the sand-bed defects induced in the 3DSP processing. Furthermore, the recognition and positioning of sand-bed defects were readily achieved by dividing the sand-bed images into blocks. Experiments show that the fine-tuned network has a 98.7% classification accuracy on the validation dataset of sand-bed defects and 95.4% recognition accuracy for the sandbed images.