Der Einfluss von Predictive Maintenance auf interne Einflussfaktoren der Overall Equipment Effectiveness (OEE)

Abstract

This thesis examines the impact of Predictive Maintenance on Overall Equipment Effectiveness (OEE) in industrial production environments. The starting point is the observation that many companies still struggle with inefficient maintenance processes, unplanned downtimes, and quality losses, even though technological tools for preventive maintenance have long been available. The aim of the paper was therefore to identify key internal factors influencing OEE and to investigate to what extent Predictive Maintenance can contribute to improving availability, performance, and quality rate. To this end, five research questions were formulated, focusing on direct and indirect influencing factors, the effect of predictive maintenance on machine availability, performance, and quality, as well as effective technologies and methods. To address the problem, a comprehensive theoretical foundation was first established, defining and distinguishing key terms such as OEE, maintenance strategies, and Predictive Maintenance, in order to subsequently analyze in detail the influence of Predictive Maintenance on the three OEE factors – machine availability, performance, and quality rate. The methodology was based on a qualitative analysis of relevant literature, current studies, and industry case examples. The results show that Predictive Maintenance can significantly increase machine availability by reducing unplanned downtimes and optimally scheduling maintenance activities. Performance is also positively influenced by avoiding micro-stoppages and ensuring more stable process conditions. The quality rate particularly benefits from the early detection of critical conditions, thereby preventing defective production. To achieve the resulting improvement in OEE, technologies such as AIbased analytics models, condition monitoring, and digital twins are highlighted in the literature as particularly effective. In summary, Predictive Maintenance can be regarded as a key tool for optimizing OEE. However, its success strongly depends on data quality, technological infrastructure, and acceptance within the company. Looking ahead, it is expected that intelligent, connected maintenance systems will play a key role in the digital transformation of industrial processes.

Date of Award	2025
Original language	German (Austria)
Supervisor	Roland Braune (Supervisor)