Understanding what to measure, and how to model it, to deliver value in railway predictive maintenance
The goal of this project is to shift the current condition assessment and monitoring paradigm for railways. This proposal aims to exploit the power harnessed from on board monitoring data obtained in a continual fashion from in-service trains for more accurately diagnosing condition and faults of railway infrastructure, as well as providing complementary information regarding the state of the rolling stock. We propose two interlaced tracks: determine what quantities need be measured, i.e., which data is actually needed, complemented with mathematical/statistical models of the interacting system (pillar I), in order to determine processes and critical parameters that enable reduction in life cycle costs and performance improvement of the railway transport system (pillar II).
We aim to redefine the digital modelling of operations by moving from readily available measurements (push strategy), to quantities that reveal latent, yet salient, information on system performance (pull strategy). The primary goal lies in ensuring maximal efficiency, i.e., maximizing availability and customer satisfaction while reducing life-cycle costs, at no compromise for safety. Our vision lies in defining monitoring strategies of the future, where data is merged with models of interaction of the vehicle/rail infrastructure, thereby maximizing our current understanding of the system, and our ability to assess it. The SBB structure offers unique platform to accomplishing the envisioned research, which is unparalleled to any railway company in Europe or elsewhere, as it features a vertical integration between infrastructure and operations.