Deterioration and other sources of changing operating conditions make systems reliability evolve over time and efficient approaches for describing this evolution are indispensable. Methods particular to learning multi-event reliability in the context of fragility analysis are discussed here. Beyond learning, in the case of already learned models, parametric and state updates need to also be possible based on new information. For this problem, two basic mathematical components are required: a model describing the dynamics of system states and parameters in time, and a model describing the way we can access these dynamics.

Based on these two components, as new measurements and observations are collected (e.g. from inspections and monitoring), the knowledge about the reliability of the system can be updated through a model-based prediction of the probabilistic system configuration at the next step (prediction step), followed by a likelihood-weighted adjustment of that prediction based on the received observation (estimation step). The two steps can be efficiently accounted for through filtering of Dynamic Bayesian Networks (DBNs).

​

Leveraging the Markovian (in-time) properties of a DBN, allows us to recursively perform the above computations. As discussed in the projects related to decision-making optimization, DBNs form the core around which global decision optimization formulations such as partially observable Markov decision processes can be wrapped to apply control.

​

​