Image classification and analysis during the additive manufacturing process based on deep convolutional neural networks

In the advanced industrial manufacturing (3D printing), the assembly quality of parts has a tight relationship with the strength and the stiffness of products. Deep convolutional neural network for the image classification is an effective analysis approach for controlling the surface quality of parts and monitoring defects during this process. In this paper, a novel Artificial Intelligence (AI) method to classify and analyze numerous metal images during the manufacturing process is proposed. We exploit the visual-based feature classification method and deep convolutional neural network (DCNN) to analyze the quality of manufacturing parts, which is widely used in the defect detection for Additive Manufacturing. Two types of self-made industrial manufacturing datasets are collected, based on which we train the DCNN model to run the image classification tasks. Experiment results show that this method can achieve the state-of-art classification accuracy.

[1]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[2]  M. J. Highsmith,et al.  3D printed tooling for thermoforming of medical devices , 2011 .

[3]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[4]  I. Yadroitsava,et al.  Selective laser melting of Ti6Al4V alloy for biomedical applications: Temperature monitoring and microstructural evolution , 2014 .

[5]  G. Tapia,et al.  A Review on Process Monitoring and Control in Metal-Based Additive Manufacturing , 2014 .

[6]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[7]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[9]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[10]  A. Uriondo,et al.  The present and future of additive manufacturing in the aerospace sector: A review of important aspects , 2015 .

[11]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[14]  Luis Perez,et al.  The Effectiveness of Data Augmentation in Image Classification using Deep Learning , 2017, ArXiv.

[15]  Frank Hutter,et al.  Fixing Weight Decay Regularization in Adam , 2017, ArXiv.

[16]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[17]  Seung Ki Moon,et al.  Process monitoring and inspection systems in metal additive manufacturing: Status and applications , 2017 .

[18]  Ehsan Malekipour,et al.  Common defects and contributing parameters in powder bed fusion AM process and their classification for online monitoring and control: a review , 2018 .