Optimal Sensor Placement Based on Parallel Quantum Genetic Algorithm Integrated LS-SVMs for Self-diagnostic Smart Structures

It has been of great practical value to optimize sensors´ locations and number for the self-diagnostic smart structures. Based on damage detection, Least Square Support Vector Machine (LS-SVM) is proposed to establish the performance function of damage detection for the piezoelectric smart structures, and then quantum genetic algorithm (QGA) is applied to optimize the performance function. To enhance the algorithm speed, LS-SVMs adopted as parallel mode are combined with QGA, that is, a parallel QGA integrated LS-SVMs is constructed to realize optimal sensor placement corresponding to its primal sensor placement. For the more sensors´ primal placement, the number of sensors can be reduced effectively through the method of parallel QGA integrated LS-SVMs, and thus leads to cost savings. Compared with traditional GA, QGA possesses the better searching ability and the faster convergence speed.