改进粒子群算法在桥梁结构损伤识别传感器优化布设中的应用

Application of improved particle swarm optimization algorithm in sensor optimal placement of bridge structural damage identification

粒子群算法以其强大的搜索能力及较好的适应度已逐步应用到桥梁结构损伤识别领域。针对以损伤识别为目标的传感器优化布设,提出一种基于改进粒子群算法的传感器优化布置方法。首先利用传感器覆盖率概念建立数学模型;其次以联合覆盖率最大构造适应度函数;在确定了监测半径的条件下,利用粒子群算法寻找出传感器的最优数目与位置。为了验证所提方法的有效性,以一三跨桥梁结构为实验对象。实验结果表明,改进的粒子群算法相比于传统粒子群算法,在寻优过程中迭代次数更少,寻找到的最优值更好,且经过融合后的数据损伤识别结果更加真实可靠。

The particle swarm optimization algorithm with strong search ability and perfect robustness is gradually applied to the field of bridge structure damage identification.A sensor optimal placement method based on improved particle swarm optimization(PSO)algorithm is proposed for the sensor optimal placement taking damage identification as the object.The concept of sensor coverage rate is used to establish the mathematical model,and then the maximum joint coverage rate is used to construct the fitness function.After the determination of the monitoring radius,the PSO algorithm is adopted to find out the optimal number and location of sensors.In order to verify the effectiveness of the proposed method,a three-span bridge structure is taken as the experimental object.The experimental results show that,in comparison with the traditional PSO algorithm,the improved PSO algorithm has less iteration number in the optimization process,better optimal value,and more authentic and reliable damage recognition results after data fusion.