免疫遗传算法在结构损伤识别中的应用与改进

为了解决结构的多损伤识别问题,提出了基于免疫遗传算法和贝叶斯融合理论的二阶段识别方法。首先将结构的应变能和频率数据作为两种具有互补性质的信息源,通过采用贝叶斯融合理论来初步确定结构的损伤位置,然后通过免疫遗传算法来精确确定结构的损伤位置和程度。考虑到基本免疫遗传算法的搜索效率仍不太高,故提出了疫苗培养、以及双终止条件等改进策略。数值计算结果表明,论文提出的二阶段方法可以有效的识别出结构的损伤位置和程度,而所建议的改进免疫遗传算法明显优于基本免疫遗传算法和简单遗传算法。

Improvement and Application of Immune Genetic Algorithm in Structural Damage Identification

In order to solve structural multi-damage identification problem, a two-stage method based on Bayesian theory and immune genetic algorithm (IGA) is presented. Firstly, structural modal strain energy and frequency are considered as two kinds of information sources, and Bayesian theory is utilized to integrate the two information sources and preliminarily detect structural damage locations. Then, immune genetic algorithm is used to identify structural damage extents. Considering the convergence rate of basic IGA is still not very good, some improved strategies, such as culture vaccine, two termination conditions, are presented. It is shown that the two-stage method can precisely identify structural damage locations and extent, and the calculated results of the proposed improved IGA are obviously better than those of both the basic IGA and simple genetic algorithm.