Prognostics and health management (PHM) has become a prominent field with an emphasis on the analysis of dynamic system degradation, with the objective of enhancing decision making for contingency improvement. The fusion of data-driven and model-based approaches have caused applications of PHM to require extensive concentration in forecasting and filtering techniques. In recent studies, the combination of dynamic system modeling and filtering methods have shown to be extremely effective for PHM applications. Moreover, methods utilizing artificial intelligence (AI) for system modeling, combined with a filtering method for estimation, have shown promising results. This study aims to provide insight to the optimal method of modeling and estimation particularly for PHM concentrations and develop a general prognostics platform using advanced filtering techniques coupled with artificial intelligence based dynamic system modelers. The specific application is a battery dynamic system, with the parameters of interest being state of charge (SOC) and state of health (SOH).