中文摘要：

基于损伤检测的智能结构传感器优化配置的研究工作较少，问题在于难以找到理想的关联损伤物理力学特征的损伤检测目标函数．提出了一种基于损伤检测的压电智能结构传感器优化配置的遗传神经网络（GANN）方法．该方法采用最小二乘支持向量机（LS-SVM）网络建立损伤检测目标函数，运用改进的遗传算法对目标函数进行优化，从而实现不同数目传感器的优化布置，并综合考虑成本与效益的因素，确定传感器的最优配置数目．论文对该遗传神经网络方法的具体实现过程及其可行性进行了分析，结果表明，该方法是可行的，可用于实现传感器对应于其初始布置模式下的最优配置．对于更多传感器的初始布置模式，采用该方法可有效减少更多传感器的数量，从而降低成本．

英文摘要：

A very small amount of research has been done in optimizing sensor placement based on damage detection for smart structures, because it is difficult to establish the desired performance function of damage detection related to the physical and mechanical characteristics of damages. The method of genetic algorithm integrated neural network （GANN） is proposed to optimize sensor placement based on damage detection for piezoelectric smart structures. In this method, Least Square Support Vector Machine （LSSVM） is adopted as a kind of neural network to establish the performance function based on damage detection, and an improved genetic algorithm is applied to optimize the performance function for searching for the optimal locations of different number of sensors. Considered the cost-effective factor roundly, the optimal number of sensors can be determined through the method. The implementation process and feasibility of the method of genetic algorithm integrated neural network are analyzed. The results show that the method is feasible, and can be applied to realize the 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.