Metal Additive Manufacturing Parts Inspection Using Convolutional Neural Network

Abstract

Metal additive manufacturing (AM) is gaining increasing attention from academia and industry due to its unique advantages compared to the traditional manufacturing process. Parts quality inspection is playing a crucial role in the AM industry, which can be adopted for product improvement. However, the traditional inspection process has relied on manual recognition, which could suffer from low efficiency and potential bias. This study presented a convolutional neural network (CNN) approach toward robust AM quality inspection, such as good quality, crack, gas porosity, and lack of fusion. To obtain the appropriate model, experiments were performed on a series of architectures. Moreover, data augmentation was adopted to deal with data scarcity. L2 regularization (weight decay) and dropout were applied to avoid overfitting. The impact of each strategy was evaluated. The final CNN model achieved an accuracy of 92.1%, and it took 8.01 milliseconds to recognize one image. The CNN model presented here can help in automatic defect recognition in the AM industry.

Artificial Intelligence Applications for Increasing Resource Efficiency in Manufacturing Companies—A Comprehensive Review

“…Thus, defects can be detected early on within the manufacturing system, and processes can be adapted. Using CNN, Cui et al [94] analyzed the product quality of additive manufactured metal parts, considering the lack of fusion, crack, and porosity. Li et al [95] applied CNN to evaluate the product quality during the assembly process.…”

“…-Predictive Maintenance [57,59,69,70,80,83,84,86,95,113]; -Production planning [52,54,61,65,72,77,78,101,102]; -Fault detection and prediction/predictive quality [58,62,74,82,87,89,93,94,110,111,115,118]; -Increasing energy efficiency in production [56,63,85,99,100,103,108,114,119] and facility management [53,67,76,107,109].…”

FPGA-Based Acceleration on Additive Manufacturing Defects Inspection

“…Resolutions beyond that, however, will tremendously increase the size of the neural networks and slow down the training and prediction speed. When the image resolution is higher, a common practice is to split the image into sub-blocks and use the sub-images for training the CNN model to perform defect inspection in metal AM [ 11 ]. The 200 × 200 image size used in our paper is comparable to literature with CPU-GPU approaches, and is considered the state-of-the-art comparing to other FPGA-based implementations (e.g., 28 × 28 in [ 16 ], 32 × 32 and 48 × 48 in [ 17 ]).…”

“…Huang et al [ 10 ] introduced a novel compact CNN model with low computation and memory cost and achieved 100% accuracy and 29 ms inference time on the NEU dataset with Intel i3-4010U CPU. Cui et al [ 11 ] presented a CNN model which achieved an accuracy of 92.1% within 8.01 ms. The experiments were conducted with AMD Ryzen 52600 processor and Nvidia 1070 GPU.…”

Laser Metal Deposition of an AlCoCrFeNiTi0.5 High-Entropy Alloy Coating on a Ti6Al4V Substrate: Microstructure and Oxidation Behavior

“…As a promising surface modification technology, laser metal deposition (LMD) has introduced a number of capabilities unparalleled by conventional process [3,[6][7][8][9][10][11]. LMD achieves layer-by-layer fabrication of near net-shaped deposition onto the substrate by introducing a powder stream into a laser beam.…”