Structural shape optimization plays an important role in the design of windsensitive structures. The numerical evaluation of aerodynamic performance for each shape search and update during the optimization process typically involves significant computational costs. Accordingly, an effective shape optimization algorithm is needed. In this study, the reinforcement learning (RL) method with deep neural network (DNN)-based policy is utilized for the first time as a shape optimization scheme for aerodynamic mitigation of wind-sensitive structures.In addition, "tacit" domain knowledge is leveraged to enhance the training efficiency. Both the specific direct-domain knowledge and general cross-domain knowledge are incorporated into the deep RL-based aerodynamic shape optimizer via the transfer-learning and meta-learning techniques, respectively, to reduce the required datasets for learning an effective RL policy. Numerical examples for aerodynamic shape optimization of a tall building are used to demonstrate that the proposed knowledge-enhanced deep RL-based shape optimizer outperforms both gradient-based and gradient-free optimization algorithms. How to cite this article: Li S, Snaiki R, Wu T. A knowledge-enhanced deep reinforcement learning-based shape optimizer for aerodynamic mitigation of wind-sensitive structures. Comput

No abstract

Hurricanes and their cascading hazards have been responsible for widespread damage to life and property, and are the largest contributor to insured annual losses in coastal areas of the U.S.A. Such losses are expected to increase because of changing climate and growing coastal population density. An effective methodology to assess hurricane wind and surge hazard risks to coastal bridges under changing climate conditions is proposed. The influence of climate change scenarios on hurricane intensity and frequency is explored. A framework that couples the hurricane tracking model (consisting of genesis, track, and intensity) with a height-resolving analytical wind model and a newly developed machine learning-based surge model is used for risk assessment. The proposed methodology is applied to a coastal bridge to obtain its traffic closure rate resulting from the observed (historical) and future (projected) hurricane winds and storm surges, demonstrating the effects of changing climate on the civil infrastructure in a hurricane-prone region.

No abstract