In the context of modern engineering, environmental, and societal concerns, there is an increasing demand for methods able to identify rational management strategies for civil engineering systems, minimizing structural failure risks while optimally planning inspection and maintenance (I&M) processes. Most available methods simplify the I&M decision problem to the component level, often assuming statistical, structural, or cost independence among components, due to the computational complexity associated with global optimization methodologies under joint system-level state descriptions. In this paper, we propose an efficient algorithmic framework for inference and decision-making under uncertainty for engineering systems exposed to deteriorating environments, providing optimal management strategies directly at the system level. In our approach, the decision problem is formulated as a factored partially observable Markov decision process, whose dynamics are encoded in Bayesian network conditional structures. The methodology can handle environments under equal or general, unequal deterioration correlations among components, through Gaussian hierarchical structures and dynamic Bayesian networks, decoupling the originally joint system state space to component networks conditional on shared random variables. In terms of policy optimization, we adopt a deep decentralized multi-agent actor-critic (DDMAC) reinforcement learning approach, in which the policies are approximated by actor neural networks guided by a critic network. By including deterioration dependence in the simulated environment, and by formulating the cost model at the system level, DDMAC policies intrinsically consider the underlying system-effects. This is demonstrated through numerical experiments conducted for both a 9-out-of-10 system and a steel frame under fatigue deterioration. Results demonstrate that DDMAC policies offer substantial benefits when compared to state-of-the-art heuristic approaches. The inherent consideration of system-effects by DDMAC strategies is also interpreted based on the learned policies.

Efficient planning of inspection and maintenance (I&M) actions in civil and maritime environments is of paramount importance to balance management costs against failure risk caused by deteriorating mechanisms. Determining I&M policies for such cases constitutes a complex sequential decision-making optimization problem under uncertainty. Addressing this complexity, Partially Observable Markov Decision Processes (POMDPs) provide a principled mathematical methodology for stochastic optimal control, in which the optimal actions are prescribed as a function of the entire, dynamically updated, state probability distribution. As shown in this paper, by integrating Dynamic Bayesian Networks (DBNs) with POMDPs, advanced algorithmic schemes of probabilistic inference and decision optimization under uncertainty can be uniquely combined into an efficient planning platform. To demonstrate the capabilities of the proposed approach, POMDP and heuristic-based I&M policies are compared, with emphasis on an offshore wind substructure subject to fatigue deterioration. Results verify that POMDP solutions offer substantially reduced costs compared to their counterparts, even in traditional problem settings.