One Dimensional Fourier Transform on Deep Learning for Industrial Welding Quality Control

This paper presents a method for industrial welding quality control. It focuses on the detection of Lack of Fusions (LoF) in joined parts produced in a rotational welding process. The solutions are based on the LeNet and AlexNet networks that are extended with previous convolutional layers based on 1D-pDFT (1D Polar Discrete Fourier Transform) and Gabor filters. The new layers add to the network the ability to deal with the images by means of knowledge arising from the physical process. In this paper a detailed description of the optical setup and the procedure to obtain defectives samples is also given.

[1]  Investigation of hidden periodic structures on SEM images of opal-like materials using FFT and IFFT. , 2014, Scanning.

[2]  D. Donoho,et al.  Fast and accurate Polar Fourier transform , 2006 .

[3]  Kincho H. Law,et al.  Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning , 2018, Smart and sustainable manufacturing systems.

[4]  C. T. Sun,et al.  Defect Detection on Randomly Textured Surfaces by Convolutional Neural Networks , 2018, 2018 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM).

[5]  Jian Zhang,et al.  Automatic Pearl Classification Machine Based on a Multistream Convolutional Neural Network , 2018, IEEE Transactions on Industrial Electronics.

[6]  Shin Ando,et al.  Deep Over-sampling Framework for Classifying Imbalanced Data , 2017, ECML/PKDD.

[7]  Joshua B. Tenenbaum,et al.  Human-level concept learning through probabilistic program induction , 2015, Science.

[8]  Patrick O. Kanold,et al.  Spatial pattern of intra-laminar connectivity in supragranular mouse auditory cortex , 2014, Front. Neural Circuits.

[9]  Neha Sharma,et al.  An Analysis Of Convolutional Neural Networks For Image Classification , 2018 .

[10]  Ting Liu,et al.  Recent advances in convolutional neural networks , 2015, Pattern Recognit..

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

[12]  Guosheng Lin,et al.  CRF Learning with CNN Features for Image Segmentation , 2015, Pattern Recognit..

[13]  Moncef Gabbouj,et al.  Real-Time Fault Detection and Identification for MMC Using 1-D Convolutional Neural Networks , 2019, IEEE Transactions on Industrial Electronics.

[14]  Andrew J. R. Simpson.  Over-Sampling in a Deep Neural Network , 2015, ArXiv.

[15]  José García Rodríguez,et al.  A survey on deep learning techniques for image and video semantic segmentation , 2018, Appl. Soft Comput..

[16]  Wei Xu,et al.  CNN-RNN: A Unified Framework for Multi-label Image Classification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).