Electronic Circuit Assessment using Machine Learning (ML)


EOI: 10.11242/viva-tech.01.04.96

Download Full Text here



Citation

Nilesh Ohol, Pratik Vishwakarma, Hitesh Rawat, Aakash Yadav, "Electronic Circuit Assessment using Machine Learning (ML)", VIVA-IJRI Volume 1, Issue 4, Article 96, pp. 1-8, 2021. Published by Computer Engineering Department, VIVA Institute of Technology, Virar, India.

Abstract

Traditionally after installing all the electronics on the circuit board part, a worker make sure the circuits are working properly. Motive is to build machines that can replace the repetitive function of Human and Test Electronic Circuit Performance using Computer Vision which is one of the advancements using machine learning. Printed circuit board (PCB) testing has been a critical process in electrical production industry to ensure product quality and reliability, reduce production costs and increase production. PCB testing involves the detection of errors on a PCB and the segmentation of those errors to identify the roots of errors. The proposed algorithm is broadly divided into five categories, feature detection and feature classification. The algorithm is able to perform tests even if the image is captured rotating, measuring and translating according to a template that performs algorithm rotation, scale and translation they are different. The newness of the algorithm is still at the beginning of analyzing the feature with its unique appearance as well firmness. In addition to this, the algorithm only takes 2,528 s to scan a PCB image. Performance of the proposed algorithm is verified by performing experiments on various PCB images and shows that the proposed algorithms suitable for automatic PCB view testing

Keywords

Computer Vision, Defect Classifier, Machine Learning, Neural Network, Open CV, Printed Circuit Board, Python, Raspberry Pi, VGG16, YOLO.

References

  1. Lijun Yu, Weijie Sun, Hui Wang,Qiang Wang and Chaoda Liu ,” The Design of Single Moving Object Detection and Recognition System Based on OpenCV”, 2018 IEEE International Conference on Mechatronics and Automation
  2. Vikas Chaudhary,1 Ishan R. Dave2 and Kishor P. Upla3,” Automatic Visual Inspection of Printed CircuitBoard for Defect Detection and Classification”, IEEE WiSPNET 2017 conference.
  3. Dev P. Desai ,Dr. D.M. Patel and BE Student,” Design of Control Unit for CNC Machine Tool using Arduino based Embedded System”, 2015 International Conference on Smart Technologies and Managementfor Computing, Communication, Controls, Energy and Materials (ICSTM), May 2015. pp.443-448.
  4. Joseph Redmon*, Santosh Divvala, Ross Girshick, Ali Farhadi,” Unified, Real-Time Object Detection”, 2016 IEEE Conference on Computer Vision and Pattern Recognition.
  5. Shuyan Ren,Liu Lu,Li Zhao,Hailong Duan ,” Circuit Board Defect Detection based on Image Processing ”, 2015 8th International Congress on Image and Signal Processing (CISP 2015) .
  6. Shenghui Wang, Leilei Niu, and Nan Li.,” esearch on Image Recognition of Insulators Based on YOLO Algorithm, 2018 international conference of power system technology.
  7. Fa’Iq Raihan ,Win Ce,“PCB Defect Detection USING OPENCV with Image Subtraction Method”, 2017 International Conference on Information Management and Technology (ICIMTech), Bina Nusantara University, Jakarta, Indonesia 11480.
  8. Zhenyu Lu, Jia Lu, Quanbo Ge and Tianming zhan,“multi object detection method based on YOLO and resent hybrid network”,2019 IEEE 4th International Conference on Advanced Robotics and Mechatronics (ICARM).