Industrial parts change recognition model using machine vision, image processing in the framework of industrial information integration

This paper presents the industrial parts change recognition model using machine vision image processing in the framework of industrial information integration and it is applied research's category. Therefore, this study implements a new industrial information integration engineering (IIIE)system by combining components that have previously been expressed separately by previous research to develop inspection of industrial parts and improve its quality and accuracy of human visual inspection status and this is the innovative aspect of this research. We used machine vision to improve human vision in change recognition in objects such as cracks, fractures… and that has been the research issue. So, this study aims to aggregate different tools identified by other researchers in change recognition in different parts because human vision is weak, and current mechanical tools such as sensors have several problems such as calibration and accurate maintenance and repair and errors. The proposed model can be used in two fields, first, recognition of the difference between family-made industrial parts with the standard sample in the production lines online, second, monitoring and controlling changes in the working industrial parts such as moving rails, train wheels, brake discs, clutch plates, various motor parts, etc. In the first case, every manufacturer needs to produce parts, such as the standard prototype for the production line. Therefore, if the machinery of the production line is out of calibration for any reason, products will be made out of standard, which would mean a reduction in the quality or an increase in production costs. Therefore, online monitoring of production lines with the help of machine vision is important in reducing production costs. In the second case, recognition of the timely change in the working industrial parts can also prevent accidents. In other words, timely detection of failure can be effective in preventing accidents in addition to reducing costs. For example, the timely detection of a train wheel or train rail wear and its timely repair or replacement will prevent the occurrence of a rail accident, which is one of the applications of the proposed model. Since the results of this study are compared with those of industrial parts with standard samples, the results are sufficiently valid. The study was conducted by the authors and no organization was involved.