The Future of Maintenance

In this book, a number of perspectives on predictive and proactive maintenance have been presented that were developed during the course of EU/ECSEL project MANTIS in the years 2015–2018. At the start of the project, a number of developments heralded things to come: The Big Data and data science revolution, internet of things (IoT), advances in machine learning, improvements in wireless connectivity, sensor technologies and available computing power. At the level of software, cloud computing, software services, semantic interoperability and multi-tiered architectures all displayed a fast-moving field. This final chapter takes a step back and presents some views towards the future. Whether one deals with PM on a manufacturing process or a fleet of machines, in logistics or construction, the potential gains from improving the maintenance policies can be substantial. With a daily yield of 30% of a particular production process, an improvement of only 3 percentage points due to improved maintenance policies constitutes an improvement of 10% on the status quo. In maintenance services for customers of a leased fleet of machines, the statistical analysis of customer usage patterns allows a company to design services, adapted to the wear & tear patterns that are typical for different customer groups and provide economically attractive solutions (e.g., ‘bronze, silver and gold’ maintenance service levels). With this in mind, it is surprising that maintenance is sometimes considered as a liability. In the biological world, the praying mantis will clean its body and sensors, autonomously. For cyber-physical systems of the near future, one would hope that at least part of such behaviors is controlled on the basis of intrinsic feedback loops. This should ideally be realized in a cost-effective manner, i.e., with minimal human intervention at all levels of control, ranging from analytics to decision making, corrective interventions and preventive actions at the physical level. Only an integrated design of primary and secondary system functions of cyber-physical system will lead to efficient and resilient systems. When NASA rovers were sent to Mars, it quickly became clear that in spite of the impressive technological advances, a ‘minor’ aspect was overlooked: Dust was accumulating on the solar panels, the camera lenses and the color-calibration disk for true-color adjustments [KinchMarsDust, 2007]. Unlike its biological counterparts on earth, e.g., insects, the Mars rover did not have actuators, neither for cleaning its essential photovoltaic energy-harvesting system, nor its sensors.