Shape optimization of aluminium alloy spherical reticulated shells considering nonlinearities

This study proposes a shape optimization method for K6 aluminum alloy spherical reticulated shells with gusset joints,considering geometric,material,and joint stiffness nonlinearities.The optimization procedure adopts a genetic algorithm in which the elastoplastic non-linear buckling load is selected as the objective function to be maximized.By confinement of the adjustment range of the controlling points,optimization results have enabled a path toward achieving a larger elastoplastic non-linear buckling load without changing the macroscopic shape of the structure.A numerical example is provided to demonstrate the effectiveness of the proposed method.In addition,the variation in structural performance during optimization is illustrated.Through parametric analysis,practical design tables containing the parameters of the optimized shape are obtained for aluminum alloy spherical shells with common geometric parameters.To explore the effect of material nonlinearity,the optimal shapes obtained based on considering and not considering material non-linear objective functions,the elastoplastic and elastic non-linear buckling loads,are compared.

Deep reinforcement learning-based critical element identification and demolition planning of frame structures

This paper proposes a framework for critical element identification and demolition planning of frame structures.Innovative quantitative indices considering the severity of the ultimate collapse scenario are proposed using reinforcement learning and graph embedding.The action is defined as removing an element,and the state is described by integrating the joint and element features into a comprehensive feature vector for each element.By establishing the policy network,the agent outputs the Q value for each action after observing the state.Through numerical examples,it is confirmed that the trained agent can provide an accurate estimation of the Q values,and handle problems with different action spaces owing to utilization of graph embedding.Besides,different behaviors can be learned by varying hyperparameters in the reward function.By comparing the proposed method and the conventional sensitivity index-based methods,it is demonstrated that the computational cost is considerably reduced because the reinforcement learning model is trained offline.Besides,it is proved that the Q values produced by the reinforcement learning agent can make up for the deficiencies of existing indices,and can be directly used as the quantitative index for the decision-making for determining the most expected collapse scenario,i.e.,the sequence of element removals.