Hybrid models for PHM deployment techniques in railway

Many railway assets exhibit increasing wear and tear of equipment during operation. Prognostics are viewed as an add-on capability to diagnosis; they assess the current health of a system and predict its remaining life based on features that capture the gradual degradation in the operational capabilities of a system. Prognostics are critical to improve safety, plan successful missions, schedule maintenance, reduce maintenance cost and down time. Unlike fault diagnosis, prognosis is a relatively new area and became an important part of Condition-based Maintenance (CBM) of systems. Currently, there are many prognostic techniques; their usage must be tuned for each application. The prognostic methods can be classified as being associated with one or more of the following two approaches: data-driven and model-based. Each of these approaches has its own advantages and disadvantages, and consequently, they are often used in combination in many applications called hybrid. A hybrid model could combine some or all of model types (data-driven, and phenomenological), so that more complete information allows for more accurate recognition of the fault state. This approach is especially relevant in railway where the maintainer and operator know some of the failure mechanisms, but the complexity of the infrastructure and rolling stock is huge so no way to develop a complete model based approach that is why development of hybrid models becomes necessary to estimate RUL of railway systems in a more accurate way. The paper address this process of data aggregation into the hybrid model in order to get RUL values within logical confidence intervals so railway assets life cycle can be managed and optimized.