Journal of Earthquake Engineering ( IF 2.6 ) Pub Date : 2020-10-05 , DOI: 10.1080/13632469.2020.1826371 Yongjia Xu 1 , Xinzheng Lu 2 , Yuan Tian 2 , Yuli Huang 2
ABSTRACT
After earthquakes, an accurate and efficient seismic-damage prediction is indispensable for emergency response. Existing methods face the dilemma between accuracy and efficiency. A real-time and accurate seismic-damage prediction method based on machine-learning algorithms and multiple intensity measures (IMs) is proposed here. 48 IMs are used for representing the ground-motion characteristics comprehensively, and the workload of the nonlinear time-history analysis (NLTHA) method is replaced by model training in the non-urgent stage to promote efficiency. Case studies with various buildings prove the accuracy and efficiency of the proposed method, and corresponding key IMs are identified by iterative optimization.
中文翻译:
基于机器学习的各种地震动强度测量的实时地震损伤预测和比较
摘要
地震发生后,准确、高效的地震破坏预测对于应急响应是必不可少的。现有方法面临着准确性和效率之间的困境。本文提出了一种基于机器学习算法和多强度测量(IM)的实时准确的地震损伤预测方法。48个IM用于全面表示地震动特征,在非紧急阶段用模型训练代替非线性时程分析(NLTHA)方法的工作量,提高效率。各种建筑物的案例研究证明了该方法的准确性和效率,并通过迭代优化确定了相应的关键 IM。