Abstract
Additive manufacturing (AM) has gained increasing attention over the past years due to its fast prototype, easier modification, and possibility for complex internal texture devices when compared to traditional manufacture processing. However, potential internal defects are occurring during AM processes, and it requires real-time inspections to minimize the costs by either aborting the processing or repairing the defect. In order to perform the defects inspection, first the defects database NEU-DET is used for training. Then, a convolution neural network (CNN) is applied to perform defects classification. For real-time purposes, Field Programmable Gate Arrays (FPGAs) are utilized for acceleration. A binarized neural network (BNN) is proposed to best fit the FPGA bit operations. Finally, for the image labeled with defects, the selective search and non-maximum algorithms are implemented to help locate the coordinates of defects. Experiments show that the BNN model on NEU-DET can achieve 97.9% accuracy in identifying whether the image is defective or defect-free. As for the image classification speed, the FPGA-based BNN module can process one image within 0.5 s. The BNN design is modularized and can be duplicated in parallel to fully utilize logic gates and memory resources in FPGAs. It is clear that the proposed FPGA-based BNN can perform real-time defects inspection with high accuracy and it can easily scale up to larger FPGA implementations.
Highlights
Additive manufacturing (AM), involving components production layer by layer, allows users to create a product directly from a 3D computer model, while the conventional subtractive processing is the result of removal of material, formative processes, and joining processes [1,2,3]
For the image labeled with defects, the selective search and non-maximum algorithms are implemented to help locate the coordinates of defects
Experiments show that the binarized neural network (BNN) model on Northeast University surface defect database (NEU-DET) can achieve 97.9% accuracy in identifying whether the image is defective or defect-free
Summary
Additive manufacturing (AM), involving components production layer by layer, allows users to create a product directly from a 3D computer model, while the conventional subtractive processing is the result of removal of material, formative processes, and joining processes [1,2,3]. While reaching the defects classification goal with high accuracy and promising inference time, were all CPU-based and GPUs were used for acceleration purposes. Nakahara et al [17] implemented a multi-scale sliding window-based object detector on an FPGA. They trained the VGG11-based binarized convolutional neural network (BCNN). The researchers did a comparison between their proposed ARM-FPGA detector and the well-known YOLOv2 CPU-GPU version Their proposed FPGA-based solution could achieve 82.20% accuracy, 28 ms inference time, and consume only 2.5 W. The proposed multi-scale sliding window is time-consuming and many defect-free sub-images are generated unnecessarily. We propose an FPGA-based embedded design to perform AM defects identification and classification in real time.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
