Application of Support Vector Machine in Structure Damage Identification

2009 ◽  
Author(s):  
Yan Yang ◽  
Tian-yi Liu
Keyword(s):  
Support Vector Machine ◽  
Damage Identification ◽  
Support Vector ◽  
Structure Damage

scholarly journals Beam Structure Damage Identification Based on BP Neural Network and Support Vector Machine

2014 ◽  
Vol 2014 ◽  
pp. 1-8 ◽  
Author(s):  
Bo Yan ◽  
Yao Cui ◽  
Lin Zhang ◽  
Chao Zhang ◽  
Yongzhi Yang ◽  
...  
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Bp Neural Network ◽  
Damage Identification ◽  
Support Vector ◽  
Single Crack ◽  
Beam Structure ◽  
Strain Mode ◽  
Structure Damage ◽  
Model Based

It is not easy to find marine cracks of structures by directly manual testing. When the cracks of important components are extended under extreme offshore environment, the whole structure would lose efficacy, endanger the staff’s safety, and course a significant economic loss and marine environment pollution. Thus, early discovery of structure cracks is very important. In this paper, a beam structure damage identification model based on intelligent algorithm is firstly proposed to identify partial cracks in supported beams on ocean platform. In order to obtain the replacement mode and strain mode of the beams, the paper takes simple supported beam with single crack and double cracks as an example. The results show that the difference curves of strain mode change drastically only on the injured part and different degrees of injury would result in different mutation degrees of difference curve more or less. While the model based on support vector machine (SVM) and BP neural network can identify cracks of supported beam intelligently, the methods can discern injured degrees of sound condition, single crack, and double cracks. Furthermore, the two methods are compared. The results show that the two methods presented in the paper have a preferable identification precision and adaptation. And damage identification based on support vector machine (SVM) has smaller error results.

Damage Identification for Simply-Supported Bridge Based on SVM Optimized by PSO (PSO-SVM)

2011 ◽  
Vol 80-81 ◽  
pp. 490-494 ◽  
Author(s):  
Han Bing Liu ◽  
Yu Bo Jiao ◽  
Ya Feng Gong ◽  
Hai Peng Bi ◽  
Yan Yi Sun
Keyword(s):  
Support Vector Machine ◽  
Classification Accuracy ◽  
Damage Identification ◽  
Fitness Function ◽  
Support Vector ◽  
Detection Accuracy ◽  
Damage Localization ◽  
Swarm Optimization ◽  
Simply Supported ◽  
Beam Bridge

A support vector machine (SVM) optimized by particle swarm optimization (PSO)-based damage identification method is proposed in this paper. The classification accuracy of the damage localization and the detection accuracy of severity are used as the fitness function, respectively. The best and can be obtained through velocity and position updating of PSO. A simply supported beam bridge with five girders is provided as numerical example, damage cases with single and multiple suspicious damage elements are established to verify the feasibility of the proposed method. Numerical results indicate that the SVM optimized by PSO method can effectively identify the damage locations and severity.

APPLICATION OF GENETIC ALGORITHM-SUPPORT VECTOR MACHINE (GA-SVM) FOR DAMAGE IDENTIFICATION OF BRIDGE

2011 ◽  
Vol 10 (04) ◽  
pp. 383-397 ◽  
Author(s):  
HAN-BING LIU ◽  
YU-BO JIAO
Keyword(s):  
Genetic Algorithm ◽  
Support Vector Machine ◽  
Damage Identification ◽  
Back Propagation ◽  
Support Vector ◽  
Model Parameters ◽  
Simply Supported ◽  
Relative Errors ◽  
Shape Ratio ◽  
Crossover And Mutation

A support vector machine (SVM) optimized by genetic algorithm (GA)-based damage identification method is proposed in this paper. The best kernel parameters are obtained by GA from selection, crossover and mutation, and utilized as the model parameters of SVM. The combined vector of mode shape ratio and frequency rate is used as the input variable. A numerical example for a simply supported bridge with five girders is provided to verify the feasibility of the method. Numerical simulation shows that the maximal relative errors of GA-SVM for the damage identification of single, two and three suspicious damaged elements is 1.84%. Meanwhile, comparative analyzes between GA-SVM and radical basis function (RBF), back propagation networks optimized by GA (GA-BP) were conducted, the maximal relative errors of RBF and GA-BP are 6.91% and 5.52%, respectively. It indicates that GA-SVM can assess the damage conditions with better accuracy.

Study on Identification of Damage to Wind Turbine Blade Based on Support Vector Machine and Particle Swarm Optimization

2015 ◽  
Vol 27 (3) ◽  
pp. 244-250 ◽  
Author(s):  
Guimei Gu ◽  
◽  
Rang Hu ◽  
Yuanyuan Li
Keyword(s):  
Support Vector Machine ◽  
Acoustic Emission ◽  
Particle Swarm Optimization ◽  
Wind Turbine ◽  
Turbine Blade ◽  
Damage Identification ◽  
Particle Swarm ◽  
Support Vector ◽  
Swarm Optimization ◽  
Upper Computer

<div class=""abs_img""> <img src=""[disp_template_path]/JRM/abst-image/00270003/03.jpg"" width=""340"" />Classification results of SVM-PSO</div> In order to identify two failures of crack damage and edge damage to wind turbine blade, a damage identification system was designed by acoustic emission technique. This system took advantage of wireless technique for signal collection and transmission and upper computer for receiving and processing data. This system adopted acoustic emission sensor, NRF905 wireless transmission, upper computer designed by VB language, and the serial communication function of VB for data receiving. Data was firstly normalized after being received. Then, the energy features of data were abstracted by db wavelet. With the abstracted features, support vector machine model was established and verified, and the machine parameters were optimized by particle swarm optimization. Results show that the system is reliable in data collection and transmission, and the correctness of damage identification obviously increases by optimizing the support vector machine with particle swarm. The design provides method to monitor the status of rotating object, so this system can provide model base for subsequent studies.

Sign in / Sign up

Export Citation Format

Share Document