Overall Equipment Effectiveness-related Assembly Pattern Catalogue based on Machine Learning

Abstract

Nowadays, a lot of data is generated in production and also in the domain of assembly, from which different patterns can be extracted using machine learning methods with the support of data mining. With the help of the revealed patterns, the assembly operations and processes can be further optimized, thus the profit achieved can be increased. This article attempts to explore the patterns related to the most used Key Performance Indicator (KPI) in manufacturing, the Overall Equipment Effectiveness (OEE) metric. The patterns and relationships discovered will be sorted into Assembly Pattern Catalogue (APC). Firstly, a literature review demonstrates scientific relevance. Secondly, it examines the circumstances and methods of samples in the Manufacturing Execution System (MES) data source and Enterprise Resource Planning (ERP) systems. In the third section, the detailed pattern catalogue is defined in the area of assembly. The novelty of the article is that beyond the generalization of patterns, it characterizes the pattern catalogue with mentioning practical industrial examples.