Edge computing accelerated defect classification based on deep convolutional neural network with application in rolling image inspection

Jiayu Huang, Nurretin Sergin, Akshay Dua, Erfan Bank Tavakoli, Hao Yan, Fengbo Ren, Feng Ju

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper develops a unified framework for training and deploying deep neural networks on the edge computing framework for image defect detection and classification. In the proposed framework, we combine the transfer learning and data augmentation with the improved accuracy given the small sample size. We further implement the edge computing framework to satisfy the real-time computational requirement. After the implement of the proposed model into a rolling manufacturing system, we conclude that deep learning approaches can perform around 30-40% better than some traditional machine learning algorithms such as random forest, decision tree, and SVM in terms of prediction accuracy. Furthermore, by deploying the CNNs in the edge computing framework, we can significantly reduce the computational time and satisfy the real-time computational requirement in the high-speed rolling and inspection system. Finally, the saliency map and embedding layer visualization techniques are used for a better understanding of proposed deep learning models.

Original languageEnglish (US)
Title of host publicationManufacturing Processes; Manufacturing Systems; Nano/Micro/Meso Manufacturing; Quality and Reliability
PublisherAmerican Society of Mechanical Engineers
ISBN (Electronic)9780791884263
DOIs
StatePublished - 2020
EventASME 2020 15th International Manufacturing Science and Engineering Conference, MSEC 2020 - Virtual, Online
Duration: Sep 3 2020 → …

Publication series

NameASME 2020 15th International Manufacturing Science and Engineering Conference, MSEC 2020
Volume2

Conference

ConferenceASME 2020 15th International Manufacturing Science and Engineering Conference, MSEC 2020
CityVirtual, Online
Period9/3/20 → …

ASJC Scopus subject areas

  • Safety, Risk, Reliability and Quality
  • Materials Science (miscellaneous)
  • Control and Optimization
  • Industrial and Manufacturing Engineering
  • Mechanical Engineering

Fingerprint Dive into the research topics of 'Edge computing accelerated defect classification based on deep convolutional neural network with application in rolling image inspection'. Together they form a unique fingerprint.

Cite this