Home > Published Issues > 2021 > Volume 10, No. 4, July 2021 >

A Mobile Production Monitoring System Based on Internet of Thing (IoT) and Random Forest Classification

Qiu Yu Wong and Yih Bing Chu
Centre for Autonomous Systems and Robotics Research, Faculty of Engineering and Technology, Tunku Abdul Rahman University College, Malaysia

Abstract—Production variations are crucial factors that cause the reduction of production efficiency. These variations are often unpredictable and difficult to be interpreted directly from the production activity of the working station. Automated diagnostic of the causes to variations is therefore the key to overcome the issue. The system should also detect and diagnose variations for all the machines which are placed in the same manufacturing line at the same instance to prevent misaligned of production volume. To achieve this, Internet of thing (IoT) technology is proposed. The technology enables automatic data transfer without the need of human intervention. Through IoT, manufacturers are able to keep track the production activity and resolve problems encountered immediately. In addition, a typical random forest classification model is developed to analyze the production patterns and subsequently identify the causes to the unwanted variations. To the best of authors’ knowledge, this paper presents a first-time work on implementation of a mobile production monitoring system based on IoT and random forest classification. The methodology and technical matter to realize the implementation are highlighted and discussed. Overall, the proposed system has been tested accordingly and visualized through a developed mobile application.

 
Index Terms—Internet of Thing (IoT), Mobile monitoring, production control chart, production monitoring, random forest classification

Cite: Qiu Yu Wong and Yih Bing Chu, "A Mobile Production Monitoring System Based on Internet of Thing (IoT) and Random Forest Classification," International Journal of Electrical and Electronic Engineering & Telecommunications, Vol. 10, No. 4, pp. 243-250, July 2021. Doi: 10.18178/ijeetc.10.4.243-250

Copyright © 2021 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.