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

作　　者：Shaojun ZHU Makoto OHSAKI Kazuki HAYASHI Shaohan ZONG Xiaonong GUO 

机构地区：[1]College of Civil Engineering,Tongji University,Shanghai 200092,China [2]Department of Architecture and Architectural Engineering,Kyoto University,Kyoto 615-8540,Japan [3]Tongji Lvjian Co.,Ltd.,Shanghai 200092,China

出　　处：《Frontiers of Structural and Civil Engineering》2022年第11期1397-1414,共18页结构与土木工程前沿（英文版）

基　　金：The authors gratefully acknowledge the financial support provided by the China Scholarship Council(CSC)during a visit of Shaojun Zhu to Kyoto University(No.201906260152);The second author acknowledges the support of JSPS KAKENHI(Grant No.JP20H04467);The third author acknowledges the support of Grant-in-Aid for Young Scientists(Start-up)(Grant No.JP21K20461).

摘　　要：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.

关 键 词：progressive collapse alternate load path demolition planning reinforcement learning graph embedding 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]