Poka Yoke system based on image analysis and object recognition

Modern Technologies in Industrial Engineering 2015

Belu, N.^1 ; Ionescu, L.M.^2 ; Misztal, A.^3 ; Mazre, A.^2

University of Piteti, Faculty of Mechanics and Technology, Department of Manufacturing and Industrial Management, Targu din Vale Street, no. 1, Arges, Pitesti

110040, Romania^1

University of Pitesti, Faculty of Electronics Communcations and Computers, Department of Electronics, Computers and Electrical Engineering, Str. Targu din Vale, nr.1, Pitesti

110040, Romania^2

Poznan University of Technology, Faculty of Engineering Management, 60-965 Poznan, ul, Strzelecka

11, Poland^3

关键词: Analog-to-digital;    Associative memory;    Cost of disposal;    Different equipment;    Hopfield Networks;    Mistake proofing;    Production process;    Toyota Production System;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/95/1/012138/pdf
DOI  :  10.1088/1757-899X/95/1/012138

来源: IOP

【 摘 要 】

Poka Yoke is a method of quality management which is related to prevent faults from arising during production processes. It deals with "fail-sating" or "mistake-proofing". The Poka-yoke concept was generated and developed by Shigeo Shingo for the Toyota Production System. Poka Yoke is used in many fields, especially in monitoring production processes. In many cases, identifying faults in a production process involves a higher cost than necessary cost of disposal. Usually, poke yoke solutions are based on multiple sensors that identify some nonconformities. This means the presence of different equipment (mechanical, electronic) on production line. As a consequence, coupled with the fact that the method itself is an invasive, affecting the production process, would increase its price diagnostics. The bulky machines are the means by which a Poka Yoke system can be implemented become more sophisticated. In this paper we propose a solution for the Poka Yoke system based on image analysis and identification of faults. The solution consists of a module for image acquisition, mid-level processing and an object recognition module using associative memory (Hopfield network type). All are integrated into an embedded system with AD (Analog to Digital) converter and Zync 7000 (22 nm technology)..