<p>The use of information and communication technologies (ICT) for supporting production processes&nbsp;is a trend that has been increased throughout the time, from the emergence&nbsp;of computers and their use in organizations, especially in manufacturing industries.&nbsp;One of those information and communication technologies&nbsp;is the Manufacturing Execution System (MES), which is a system that connects businesses functions between&nbsp;direct process control systems and uses the information generated in the manufacturing processes to provide visibility, control and real-time data for decision-making for interested parties. Although, there are different MES functionalities for suporting manufacturing processes based on normative organizations and documentation, the one focused in this work is related with quality management. Since manufacturing processes can provide a huge amount of data, most of times interpreting and manage it in real time can&nbsp;be a difficult task. Besides that, the cost of having a MES from the current market for small and medium organizations is not attainable, because they are expensive. The proposed MES developed in this work as been designed to manage large amount of data &nbsp;using a&nbsp;statistical and matemathical tool that is frequently used in social sciences, and is&nbsp;part of structural equation models:&nbsp;factor analysis. The&nbsp;discrete data generated in a conceptual simulated production line of the manufacturing process of steel tubes has been used to test the proposed MES. The simulated production line is compromised by nine operations: cutting tube, tube forming reduction, turning tube, drilling a hole, splint assembly in the tube, valve assembly in the hole, hose and rivet assembly rivet, leakage test and pull test. Using Matlab Simulink environment, the simulated production line generated random parameters&nbsp;data of measurement of twelve features throughout the operation stations. That data then is transferred to a Python environment for further analysis.&nbsp;A factor analysis module has been programmed in Python to analyze the random data generated&nbsp;by Simulink environment. By applying factor analysis in the random data, the proposed MES is capable to identify latent and observed variables or factors that could cause a defect in subsequent operations,&nbsp;and classify potential and observed variables in the parameters data and measurement. In order to test the efficacy and reliability&nbsp;of the model proposed, a Machine Learning tool has been applied. Benefits, advantages and limitations&nbsp;of using the proposed MES are disscussed. This work could lead to future research in applying factor analysis for interpreting data in manufacturing environments.&nbsp;</p>

Design of a Manufacturing Execution System Based on Factor Analysis of Discrete Data for Diagnostic and Classification Defects in a Simulated Production Line

Paper Proceedings: https://asmedigitalcollection.asme.org/IMECE/IMECE2021/volume/85543

ASME 2021 International Mechanical Engineering Congress and Exposition (IMECE2021)

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.