Keywords: track, singular points, artificial intelligent, railway, energy, maintenance.

Globally, the railway is considered a sustainable and energy-efficient mode of transport. Recently, the utilisation of road transport has increased manifold due to loss of trust in railway transport. The situation is further aggravated by the inefficient use of resources, budgetary constraints, climate change, etc. Hence, there is a need to increase the capacity and punctuality of railway transport. Therefore, this paper proposes a framework that can benefit the railway sector by facilitating the transition towards an energy-efficient railway system. This framework will achieve this by reducing unplanned stoppages, leading to increased punctuality, capacity, trust, and good governance. One of the key challenges in achieving this goal is the ability to distinguish between a singular point (regular designed elements, like turnouts and joints) and actual track defects when using vibration measurements. To address this challenge, this paper focuses on applying Artificial Intelligent based techniques to identify and detect the existence of such regular designed elements. This paper presents a case study of a measurement system installed in Sweden that provides a proof-of-concept for data fusion and data analytics using AI for improving the detection capability and thus increasing the prediction accuracy.

download the full-text of this paper (PDF, 10 pages, 826 Kb)

go to the previous paper
go to the next paper
return to the table of contents
return to the volume description