项目网络组织协同治理绩效影响因素分析

为了能够更加准确地判断结构损伤位置和程度，本文提出了基于粒子群优化支持向量机（PSO SVM）方法对斜拉桥主梁进行损伤识别的新方法。该方法以最敏感索张力指标作为损伤识别指标，利用粒子群（PSO）算法寻找支持向量机（SVM）最优参数，建立SVM预测模型，以不同位置、不同损伤程度下最敏感索的张力指标作为SVM的训练和测试输入，由SVM的输出确定损伤位置。通过对实验室的模型斜拉桥的主梁损伤进行了仿真验证，结果表明：采用PSO算法很好地解决了采用SVM方法进行损伤识别时的参数选择随机性难题，实现了对SVM模型参数

Empirical Research on Influencing Factors of Collaborative Governance Performance for Project Network Organization

A new method of damage detection based on particle swarm optimization support vector machine (PSO SVM) is proposed in this paper in order to identify the girder damage of the cable stayed bridge more accurately. The best kernel parameters for support vector machine(SVM) are obtained by particle swarm optimization(PSO) and the testing model of SVM is established. Taking the most sensitivity cable tension indexes as inputs of SVM for both training and testing, damage locations of the main girder for cable stayed bridge are indicated by the outputs of SVM. A numerical example for a test model of a single tower cable stayed bridge is provided to verify the feasibility of the method. It is shown that the automatic optimization of the parameters for SVM can be realized by PSO algorithm and different kinds of damage of the girder for cable stayed bridge can be detected and the identification efficiency is high.