Digital Transformation in Maintenance Management

Abstract

The relationship between technology and maintenance is mutually beneficial since technology is continuously improving with consequent substantial advancements in the field of maintenance. Maintenance management may be effectively modernized through digitalization. Developing advanced technologies promotes indeed the possibility of maintaining a competitive and long-term position in this field. Digitalization is consistently transforming organizations by allowing them to use suitable technologies for collecting data automatically. Various equipment and components are nowadays capable of collecting their operating data over an extended period, which may yield a plethora of intriguing insights employing digitalization. However, to achieve effective prediction of any type of failure, maintenance management requires several smart technologies which offer wider applications for digitalization, including artificial intelligence (AI), big data, Internet of Things (IoT), digital twins, novel sensor technologies, data collection and distribution from various smart sensors, and investigating a lot of data utilizing machine/deep learning. Smart sensors facilitate the collection of large amounts of data to be effectively evaluated for enabling maintenance management and decision-making of more complex systems. The focus of this study is to investigate which type of data should have to be digitally collected for effectively implementing predictive maintenance policies. This can be identified by studying the latest trends of digitalization in maintenance management. Moreover, this study aims to elaborate a decision-making model supporting the implementation of maintenance management policies. This will be done by first identifying critical factors for maintenance management and secondly analyzing their mutual relationships in a structured way. In detail, a Fuzzy Cognitive Map (FCM) will be built to model such relations, in order to identify those factors having a greater influence on all the other ones. In this direction, this study may have positive impacts on economic, social, and environmental factors.