基于模态振型和神经网络方法的人防工程结构损伤诊断

随着人防工程建设规模的扩大与发展,对人防工程结构的损伤诊断及其安全性评价已成为亟待解决的重要问题。本文提出了一种基于模态振型与神经网络相结合的人防工程结构损伤诊断方法,构造了以模态振型变化率为输入的BP神经网络。以某人防工程结构为算例,用单元弹性模量E的降低模拟结构的损伤位置和损伤程度,通过给定人防工程结构不同单元不同程度的损伤,计算结构的前3阶振型变化率绝对值之和作为BP神经网络的输入,计算分析表明,利用模态振型与神经网络相结合的方法能够准确地诊断出人防工程结构的损伤位置和损伤程度,能方便、有效地解决地下人防工程结构的损伤诊断问题。

Civil Air Defense Engineering Damage Diagnosis Based on Modal Parameters and Neural Network Technique

As the construction scale of civil air defense engineering expands and develops,it is in urgent need of solving the important problems of damage diagnosis and safety evaluation on the civil air defense engineering.Based on modal parameters and Neural Network to detect the damage of the civil air defense engineering,a new method is proposed in the paper,and the sum of the variation rate of the former three mode' absolute value as the Neural Network's input is established.Using a civil air defense engineering...