ABC-RBF神经网络在平板坝裂缝开合度监测中的应用  

Application of ABC-RBF Neural Network on monitoring the crack opening degree of concrete slab dam

作　　者：赵鲲鹏[1,2,3] 梁嘉琛 杨景文[1,2,3] 曹睿哲[1,2,3] 胡添翼[1,2,3] 戴波[1,2,3] 何启[1,2,3] 

机构地区：[1]河海大学水利水电学院,江苏南京210098 [2]河海大学水资源高效利用与工程安全国家工程研究中心,江苏南京210098 [3]河海大学水文水资源与水利工程科学国家重点实验室,江苏南京210098

出　　处：《水利水电技术》2015年第10期35-37,58,共4页Water Resources and Hydropower Engineering

基　　金：淮安市水利院士工作站资助;国家自然科学基金项目(51279052;51209077);江苏省杰出青年基金项目(BK20140039;BK2012036);江苏省"333高层次人才培养工程"(2017-B08037)

摘　　要：为提高混凝土平板坝裂缝开合度预测精度,针对混凝土平板坝裂缝开合度监测序列呈非线性以及周期性变化的特点,将基于EMD分解优化的ABC-RBF神经网络模型应用于混凝土平板坝裂缝开合度安全监测中,对比分析普通RBF和ABC-RBF神经网络模型。结果表明,ABC-RBF神经网络模型预测误差相对较小,可用于分析混凝土平板坝裂缝开合度的安全监测。In order to enhanced the prediction accuracy of the crack opening degree of＂ concrete slab dam, the EMD based-de- composed and optimized ABC - RBF neural network model is applied to the monitoring of the crack opening degree of concrete slab dam in accordance with characteristics of the periodic change and the nonlinearity of the order of the crack opening monito- ring on the concrete slab dam, and then the conventional RBF and ABC - RBF neural network models are comparatively ana- lyzed. The result shows that the prediction error from the ABC - RBF neural network model is smaller with a better effect. This method provides a new method for the analysis made on the safety monitoring of the crack opening degree of the concrete slab dam.

关 键 词：混凝土平板坝 裂缝开合度 经验模态分解 ABC—RBF神经网络 

分 类 号：TV698.11[水利工程—水利水电工程]