基于PSO-SVM的城市桥梁群体震害预测模型研究

发布时间：2018-06-25 00:49

本文选题：粒子群-支持向量机 + 支持向量机　；参考：《震灾防御技术》2017年01期

【摘要】：本文根据城市桥梁群体的实际震害资料数据,采用粒子群算法(PSO)来优化支持向量机(SVM)参数,选择影响桥梁震害等级的8个因素作为特征输入向量,充分用2种算法的优点建立PSO-SVM的桥梁震害预测模型。通过比较PSO-SVM和SVM模型对桥梁震害的预测能力,发现PSO-SVM模型具有较高预测精度和较高的推广价值。本文的研究成果对桥梁震害等级的预测具有一定的参考价值和指导意义。
[Abstract]:Based on the actual earthquake disaster data of urban bridge population, particle swarm optimization (PSO) algorithm is used to optimize the parameters of support vector machine (SVM), and eight factors affecting the earthquake damage grade of bridge are selected as the characteristic input vector. The bridge damage prediction model of PSO-SVM is established by fully using the advantages of the two algorithms. By comparing the prediction ability of PSO-SVM model and SVM model to bridge earthquake damage, it is found that PSO-SVM model has higher prediction accuracy and higher popularizing value. The research results of this paper have certain reference value and guiding significance for the prediction of bridge earthquake damage grade.
【作者单位】：中国海洋大学工程学院土木工程系;
【分类号】：P315.9;U442.55

【相似文献】