Total Productive Maintenance in an Industry 4.0 Framework

Abstract

Maintenance is a key operation function that is required to improve business performance by avoiding equipment breakdown. In 1971, Total Productive Maintenance (TPM), a lean manufacturing approach, has been developed and widely used as a maintenance strategy to gain a competitive advantage in industry. However, with the advent of new technology and the internet of things, manufacturing process are subject to evolve from the old traditional ways of manufacturing to digitalized manufacturing. In this stage, the utilization of data for understanding current operating conditions and detecting faults and failures is an important topic to research. However, that alone is not enough to ensure long term survival and success in the market. Today, with the applications and technologies of Industry 4.0, components and systems are able to gain self-awareness and self-predictiveness which will provide management with more insight on the status of the factory. Systems are able to make use of both historical and live data which was not possible before. In this context, this thesis aims on developing a framework for productive and efficient maintenace with the use of Industry 4.0 technologies. The thesis discusses the new benefits that predictive maintenance has the potential of providing and it discusses several machine learning algorithms that are promising in the field of maintenacne. Throughout the thesis several models are developed and discussed to provide a framework that would ease the transition of mainentance from the old traditional ways to the newly emerging concept of a smart factory in Industry 4.0.