Abstract
Many railway assets suffer increasing wear and tear during operation. Prognostics can assist diagnosis by assessing the current health of a system and predicting its remaining life based on features that capture the gradual degradation in a system’s operational capabilities. Prognostics are critical to improve safety, plan successful work, schedule maintenance, and reduce maintenance costs and down time. Unlike fault diagnosis, prognosis is a relatively new area, but it has become an important part of Condition-based Maintenance (CBM) of systems.
As there are many prognostic techniques, usage must be attuned to particular applications. Broadly stated, prognostic methods are either data-driven or model-based. Each has advantages and disadvantages; consequently, they are often combined in hybrid applications. A approach hybrid model can combine some or all model types (data-driven, and phenomenological); thus, more complete information can be gathered, leading to more accurate recognition of the fault state.
This approach is especially relevant in railway systems where the maintainer and operator know some of the failure mechanisms, but the complexity of the infrastructure and rolling stock is huge that there is no way to develop a complete model-based approach. Therefore, hybrid models are extremely useful for accurately estimating the Remaining Useful Life (RUL) of railway systems. The paper addresses the process of data aggregation into a hybrid model to get RUL values within logical confidence intervals so that the life cycle of railway assets can be managed and optimised.
