遗传算法应用于高阶剪切梁结构损伤检测中的效果分析

Analysis of the effect of genetic algorithm applied to structural damage detection of high-order shear beams

梁式结构作为工程项目的主要承重结构,高阶剪切梁在工程领域中具有较为广泛的应用,因此梁式结构的损伤识别是工程质量和生命安全的重要保障。研究为识别梁结构裂纹的位置和深度,将遗传算法与损伤识别模型相结合。该方法利用遗传算法全局寻最优解的能力对反向传播神经网络(Back-propagation neural network,BPNN)进行优化。通过有限元分析获得裂纹梁的固有频率,并以固有频率作为模型的输入,以裂纹位置与深度作为模型输出。通过算例分析,模型的预测误差平方和为5.2,适应度值为0.154。梁的裂纹深度相对误差平均值为4.03%。实验结果表明:提出的模型具有较高的预测精度,能准确识别梁式结构的损伤情况。

As the main load-bearing structure of engineering projects,high-order shear beams have more extensive applications in the engineering field,so the damage identification of beam structures is an important guarantee of engineering quality and life safety.The study combines genetic algorithm with damage identification model in order to identify the location and depth of cracks in beam structures.The method optimizes the Back-propagation neural network(BPNN)using the ability of genetic algorithm to find the optimal solution globally.The intrinsic frequency of the cracked beam is obtained by finite element analysis,and the intrinsic frequency is used as the input of the model,and the crack location and depth are used as the output of the model.The model's prediction error sum of squares is 5.2 and the fitness value is 0.154.The average relative error of crack depth of the beam is 4.03%.The experimental results show that the model proposed in the study has high prediction accuracy and can accurately identify the damage of the beam structure.