不同适应度函数的遗传算法在桥梁结构传感器布设中的应用

从模态振型正交性和模态能量两方面出发设计了3个适应度函数,将其分别应用于改进遗传算法和单亲遗传算法。采用两步法对大跨径桥梁结构传感器布设进行定量和定位分析。通过对两种遗传算法、3个适应度函数及有效独立算法在大跨径拱桥中的对比分析,证实了单亲遗传算法比改进遗传算法更适合于桥梁结构传感器的布设,基于组合评价准则适应度函数比单一评价准则适应度函数布设出的传感器位置更加合理,验证了两步法用于传感器定量及定位计算的有效性。

Sensor placement on bridge structure based on genetic algorithms with different fitness functions

Three fitness functions were designed from the mode orthogonality and the modal energy,and they were used to the improved genetic algorithm and the single parent genetic algorithm.A 2-step method was proposed to determine the number and the location of the sensors on the large-span bridge structures.According to the comparative analyses of these 2 algorithms,3 fitness functions and the effective independence algorithm applied to the large-span arch bridge,the single parent genetic algorithm appeared more suitable to the sensor placement problem than the improved genetic algorithm,and the fitness function designed by the combined evaluation criteria was more reasonable than the one designed by the single evaluation criterion.The effectireness of the 2-step method for the placement of the sensors on the bridge structure is proved.