Fuzzy Least Square Support Vector Machine Applied to Detect Damage for Fiber Smart Structures

The research on realizing the self-detecting damage function is one of the main research contents of smart structures, and an important issue related to the self-detecting damage function is the method of damage detection. It has been of an important theoretical meaning and a great practical value for applications of smart structures to research on this issue. Due to the structure damage detectionpsilas essence as pattern recognition or nonlinear regression, damagepsilas nondeterministic attribute, and least square support vector machinepsilas (LS-SVM) excessive sensitivity to isolated data points, fuzzy least square support vector machine (FLS-SVM) is proposed to detect damage locations for fiber smart structures by introducing fuzzy memberships to LS-SVM. The testing results show that, FLS-SVM possesses the higher damage locating accuracy, and the bitter dissemination ability than LS-SVM under the same conditions. And FLS-SVM obtains the better noise immunity, and thus strengthens its own robustness.