Optimum strain gauges distribution for loading identification following fuzzy pattern recognition and hybrid genetic algorithm
Fuzzy pattern recognition is effective to realize loading identification and genetic algorithm is effective in optimization,therefore an optimization method for strain sensors distribution based on the two methods is presented.The optimal locations to install sensors are called as key nodes.In this study,loads can be discerned through the recognition of strain patterns quickly after the direction connections of the strain patterns and loading conditions are constructed.Following on the variance of all nodes strains and the field conditions,a candidate set of key nodes is established.Then the absolute errors of the values and positions between input loads and recognition results are constructed as an objective function.The optimal key nodes are determined through minimizing the objective function.Numerical investigation results reveal that the proposed approach is efficient in determining the optimal locations of strain sensors and the accuracy of loading identification has been improved significantly.
Loading identification Fuzzy pattern recognition Hybrid genetic algorithm Location optimization of sensors
Li Gongbiao Qu Weilian
Hubei Key Laboratory of Roadway Bridge & Structural Engineering,Wuhan University of Technology,LuoShi Street 122,Wuhan,Hubei,China
国际会议
The World Forum on Smart Materials and Smart Structures Technology(SMSST07)(2007年世界智能材料与智能结构技术论坛)
重庆·南京
英文
2007-05-01（万方平台首次上网日期，不代表论文的发表时间）