ABSTRACT
ABSTRACT Transportation infrastructure assets are designed to meet pre-specified reliability, availability, maintainability and safety (RAMS) requirements. Electrical and mechanical components are critical elements with respect to the RAMS-criteria. Unplanned failure of these components lead to societal impact, unsafe situations or costs. The trend in asset management is to apply data-driven, predictive maintenance. In various fields, novel techniques are used to monitor performance and predict behaviour of electrical and mechanical components. These techniques combine insights and methods from different fields, such as computer and data science with knowledge about the assets. They include data collection techniques, protocols for aggregation, transport and storage of data, fast algorithms to handle and analyse (real time) big data, resulting in early warning systems and decision support techniques for the required maintenance actions. This paper attempts to answer: which technologies fit to the Rijkswaterstaat assets and which steps need to be taken to include relevant technologies to the maintenance and organizational processes in order to move towards predictive maintenance practice? This paper firstly analyses Rijkswaterstaat’ systems (its assets, the characteristics and the state of the art of the maintenance strategy). It secondly scans other industries’ predictive maintenance & monitoring techniques; their characteristics and similarities to the Rijkswaterstaat characteristics and their possible applicability). The paper finally defines a roadmap in order to apply relevant techniques and provide a stepwise application and implementation strategy for Rijkswaterstaat and ends up with conclusion and recommendations.
