Search for: All records

Abstract Structural design synthesis considering discrete elements can be formulated as a sequential decision process solved using deep reinforcement learning, as shown in prior work. By modeling structural design synthesis as a Markov decision process (MDP), the states correspond to specific structural designs, the discrete actions correspond to specific design alterations, and the rewards are related to the improvement in the altered design’s performance with respect to the design objective and specified constraints. Here, the MDP action definition is extended by integrating parametric design grammars that further enable the design agent to not only alter a given structural design’s topology, but also its element parameters. In considering topological and parametric actions, both the dimensionality of the state and action space and the diversity of the action types available to the agent in each state significantly increase, making the overall MDP learning task more challenging. Hence, this paper also addresses discrete design synthesis problems with large state and action spaces by significantly extending the network architecture. Specifically, a hierarchical-inspired deep neural network architecture is developed to allow the agent to learn the type of action, topological or parametric, to apply, thus reducing the complexity of possible action choices in a given state. This extended framework is applied to the design synthesis of planar structures considering both discrete elements and cross-sectional areas, and it is observed to adeptly learn policies that synthesize high performing design solutions. 

Abstract The study compared the life cycle environmental impacts of three coastal flood management strategies: grey infrastructure (levee), green–grey infrastructure (levee and oyster reef), and a do-nothing scenario, considering the flood damage of a single flooding event in the absence of protection infrastructure. A case study was adopted from a New Orleans, Louisiana residential area to facilitate the comparison. Hazus software, design guidelines, reports, existing projects, and literature were utilized as foreground data for modelling materials. A process-based life cycle assessment was used to assess environmental impacts. The life cycle environmental impacts included global warming, ozone depletion, acidification, eutrophication, smog formation, resource depletion, ecotoxicity, and various human health effects. The ecoinvent database was used for the selected life cycle unit processes. The mean results show green–grey infrastructure as the most promising strategy across most impact categories, reducing 47% of the greenhouse gas (GHG) emissions compared to the do-nothing strategy. Compared to grey infrastructure, green–grey infrastructure mitigates 13%–15% of the environmental impacts while providing equivalent flood protection. A flooding event with a 100-year recurrence interval in the study area is estimated at 34 million kg of CO₂equivalent per kilometre of shoreline, while grey and green–grey infrastructure mitigating such flooding is estimated to be 21 and 18 million kg, respectively. This study reinforced that coastal flooding environmental impacts are primarily caused by rebuilding damaged houses, especially concrete and structural timber replacement, accounting for 90% of GHG emissions, with only 10% associated with flood debris waste treatment. The asphalt cover of the levee was identified as the primary contributor to environmental impacts in grey infrastructure, accounting for over 75% of GHG emissions during construction. We found that there is an important interplay between grey and green infrastructure and optimizing their designs can offer solutions to sustainable coastal flood protection.