A Total Productivity PCA Model for Assessment and Improvement of Electrical Manufacturing Systems

Abstract

This study presents a framework for assessment of electrical manufacturing systems based on a total machine productivity approach and multivariate analysis. Furthermore, the total model is developed by Principle Component Analysis (PCA) and validated and verified by Numerical Taxonomy (NT) and non-parametric correlation methods, namely, Spearman correlation experiment and Kendall Tau. To achieve the objectives of this study, a comprehensive study was conducted to locate the most important economic and technical indicators which influence machine performance. These indicators are related to machine productivity, efficiency, effectiveness and profitability. Six major electrical machinery sectors are selected according to the format of International Standard for Industrial Classification of all economic activities (ISIC). Then, a comparative study is conducted through PCA among the electrical machinery sectors by considering the six sectors. This in turn shows the weak and strong points of electrical machinery and apparatus manufacturing sectors with respect to machine productivity. Furthermore, PCA identified which machine indicators have the major impacts on the performance of electrical machinery sectors. The modeling approach of this study could be used for ranking and analysis of other electrical sectors. This study is the first to introduce a total productivity model for assessment and improvement of total machine performance in electrical manufacturing sectors.