基于最小二乘支持向量机算法的高层建筑结构的强震抗毁性估计模型
An Invulnerability Estimation Model of High-rise Buildings under Strong Earthquake Based on Least Squares Support Vector Machine Algorithm

采用现有的估计模型对混凝土建筑结构的抗毁性进行估计时，存在估计精度低、耗时长等问题。为此，提出一种基于最小二乘支持向量机的强震作用下混凝土高层建筑结构的抗毁性估计模型。该模型采用最小二乘支持向量机对混凝土结构强震损伤程度相关数据的训练样本进行训练，创建混凝土结构抗毁性估计模型；为了减少可能存在的模型误差，采用KLASSO调参模型对结构抗毁性估计模型中的参数进行调节和优化，得出可靠、稳定的强震作用下混凝土高层建筑结构抗毁性估计模型。仿真实验证明，该模型估计精度相对较高，可节省估计用时，为更好地提升建筑行业的安全检测工作效率提供很好的依据。
The existing estimation model as a method to estimate the invulnerability of concrete building structures is characterized by some problems, such as low estimation accuracy and long time consumption. Therefore, for high-rise buildings under strong earthquakes, an invulnerability estimation model based on least squares support vector machine is proposed. The least squares support vector machine is used to train the training samples of concrete structures damaged by strong earthquakes; then, an invulnerability estimation model of concrete structures is established. To reduce the possible model errors, the KLASSO parameter adjustment model is used to adjust and optimize the parameters of the invulnerability estimation model. The simulation results show that the model has a high estimation accuracy, and thus, the estimation time can be saved. The study can provide a good basis for improving the safety inspection efficiency of the construction industry