Application of dam deformation prediction based on LSSVR optimized by ASA-ABC

2nd International Symposium on Resource Exploration and Environmental Science

生态环境科学

Feng, Tengfei^1 ; Zhong, Yu^1 ; Liu, Xiaosheng^1 ; Ma, Yuqing^1 ; Liu, Chaohu^1

Jiangxi University of Science and Technology, Ganzhou, China^1

关键词: Adaptive simulated annealing;    Artificial bee colonies;    Artificial bee colony algorithms (ABC);    Least squares support vector regression;    Model-based OPC;    Optimizing parameters;    Prediction accuracy;    Prediction model;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/170/2/022076/pdf
DOI  :  10.1088/1755-1315/170/2/022076

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

In order to improve the prediction accuracy of the dam deformation, aiming at the difficulty to determining the parameters of the least squares support vector regression (LSSVR) and the artificial bee colony algorithm (ABC) is prone to fall into local optimum when optimizing parameters, a self-adaptive simulated annealing mechanism is designed to improve the optimization performance of the ABC algorithm, so that a prediction model based on least squares support vector regression optimized by adaptive simulated annealing artificial bee colony (ASA-ABC-LSSVR) is constructed, and the model is applied to dam deformation prediction. The experimental results show that ASA-ABC effectively solves the difficult to balance the development and exploration capability of ABC. Compared with the prediction model based on the LSSVR and the model based on the LSSVR optimized by ABC (ABC-LSSVR), the ASA-ABC-LSSVR model has higher prediction accuracy and the prediction trend is more practical.