Data-driven prognostic models have been extensively utilized in current structural health monitoring (SHM) practices. They are designed to provide the health indicator (HI) - a representation of the system’s current health state - through sensor data. To enhance performance, online learning is often used to take care of uncertainties that arise from the run-to-failure process. The inverse solution, though demonstrated in online uncertainty quantification applications, remains unexplored in the context of online data-driven prognostics. Therefore, this work proposes a generic inverse solution for a deep prognostic model to online address uncertainties. The proposed method is tested using the open-access XJTU-SY bearing datasets, showcasing its capacity to online enhance the performance of a given model.

Prognostic methods broadly fall into two categories—model-based and data-driven—both of which have shown effectiveness across a range of engineering applications. Model-based approaches require an explicit representation of the degradation process, defining failure as the point when the physical damage state exceeds a predetermined threshold. Data-driven methods, on the other hand, leverage sensor data to directly predict end-of-life (EOL) or related prognostic information. Although both approaches offer insights that could be complementary and potentially fused, most existing fusion methods either combine the outputs from multiple methods or adopt a data-driven method to assist the model-based method. To further enhance the prognostic performance, this study proposes a fusion-based prognostic approach in which the output of one method is actively used to update the model of the other through either the crossover operator or the likelihood function. The proposed approach is validated using both an aluminum fatigue dataset and the Prognostics and Health Management (PHM) 2010 cutter wear dataset, demonstrating improved prognostic accuracy compared to either method used independently.