In this paper,a new algorithm combining the features of bi-direction evolutionary structural optimization(BESO)and reinforcement learning(RL)is proposed for continuum structural topology optimization(STO).In contrast ...In this paper,a new algorithm combining the features of bi-direction evolutionary structural optimization(BESO)and reinforcement learning(RL)is proposed for continuum structural topology optimization(STO).In contrast to conventional approaches which only generate a certain quasi-optimal solution,the goal of the combined method is to provide more quasi-optimal solutions for designers such as the idea of generative design.Two key components were adopted.First,besides sensitivity,value function updated by Monte-Carlo reinforcement learning was utilized to measure the importance of each element,which made the solving process convergent and closer to the optimum.Second,ε-greedy policy added a random perturbation to the main search direction so as to extend the search ability.Finally,the quality and diversity of solutions could be guaranteed by controlling the value of compliance as well as Intersection-over-Union(IoU).Results of several 2D and 3D compliance minimization problems,including a geometrically nonlinear case,show that the combined method is capable of generating a group of good and different solutions that satisfy various possible requirements in engineering design within acceptable computation cost.展开更多
Owing to advancement in advanced manufacturing technology,the reinforcement design of concrete structures has become an important topic in structural engineering.Based on bi-directional evolutionary structural optimiz...Owing to advancement in advanced manufacturing technology,the reinforcement design of concrete structures has become an important topic in structural engineering.Based on bi-directional evolutionary structural optimization(BESO),a new approach is developed in this study to optimize the reinforcement layout in steel-reinforced concrete(SRC)structures.This approach combines a minimum compliance objective function with a hybrid trusscontinuum model.Furthermore,a modified bi-directional evolutionary structural optimization(M-BESO)method is proposed to control the level of tensile stress in concrete.To fully utilize the tensile strength of steel and the compressive strength of concrete,the optimization sensitivity of steel in a concrete–steel composite is integrated with the average normal stress of a neighboring concrete.To demonstrate the effectiveness of the proposed procedures,reinforcement layout optimizations of a simply supported beam,a corbel,and a wall with a window are conducted.Clear steel trajectories of SRC structures can be obtained using both methods.The area of critical tensile stress in concrete yielded by the M-BESO is more than 40%lower than that yielded by the uniform design and BESO.Hence,the M-BESO facilitates a fully digital workflow that can be extremely effective for improving the design of steel reinforcements in concrete structures.展开更多
文摘In this paper,a new algorithm combining the features of bi-direction evolutionary structural optimization(BESO)and reinforcement learning(RL)is proposed for continuum structural topology optimization(STO).In contrast to conventional approaches which only generate a certain quasi-optimal solution,the goal of the combined method is to provide more quasi-optimal solutions for designers such as the idea of generative design.Two key components were adopted.First,besides sensitivity,value function updated by Monte-Carlo reinforcement learning was utilized to measure the importance of each element,which made the solving process convergent and closer to the optimum.Second,ε-greedy policy added a random perturbation to the main search direction so as to extend the search ability.Finally,the quality and diversity of solutions could be guaranteed by controlling the value of compliance as well as Intersection-over-Union(IoU).Results of several 2D and 3D compliance minimization problems,including a geometrically nonlinear case,show that the combined method is capable of generating a group of good and different solutions that satisfy various possible requirements in engineering design within acceptable computation cost.
基金This study was supported by the Australian Research Council(FL190100014 and DE200100887).
文摘Owing to advancement in advanced manufacturing technology,the reinforcement design of concrete structures has become an important topic in structural engineering.Based on bi-directional evolutionary structural optimization(BESO),a new approach is developed in this study to optimize the reinforcement layout in steel-reinforced concrete(SRC)structures.This approach combines a minimum compliance objective function with a hybrid trusscontinuum model.Furthermore,a modified bi-directional evolutionary structural optimization(M-BESO)method is proposed to control the level of tensile stress in concrete.To fully utilize the tensile strength of steel and the compressive strength of concrete,the optimization sensitivity of steel in a concrete–steel composite is integrated with the average normal stress of a neighboring concrete.To demonstrate the effectiveness of the proposed procedures,reinforcement layout optimizations of a simply supported beam,a corbel,and a wall with a window are conducted.Clear steel trajectories of SRC structures can be obtained using both methods.The area of critical tensile stress in concrete yielded by the M-BESO is more than 40%lower than that yielded by the uniform design and BESO.Hence,the M-BESO facilitates a fully digital workflow that can be extremely effective for improving the design of steel reinforcements in concrete structures.
