基于人工蜂群优化小波神经网络的深基坑开挖对既有盾构隧道变形的预测分析  

Prediction Analysis of Existing Shield Tunnel Deformation Induced by Deep Excavation Using Artificial Bee Colony Optimized Wavelet Neural Network

作　　者：张亚辉 彭立飞[2] 刘凯 徐强 樊浩博 ZHANG Yahui;PENG Lifei;LIU Kai;XU Qiang;FAN Haobo(Hebei Urban and Rural Construction School,Shijiazhuang 050030,China;The First Operation Co.,Ltd.of Jinan Rail Transit Group Co.,Ltd.,Jinan 250300,China;Key Laboratory of Roads and Railway Engineering Safety Control of Ministry of Education,Shijiazhuang Tiedao University,Shijiazhuang 050043,China;Shijiazhuang Tiedao University,Shijiazhuang 050043,China)

机构地区：[1]河北城乡建设学校,石家庄050030 [2]济南轨道交通集团第一运营有限公司,济南250300 [3]石家庄铁道大学道路与铁道工程安全保障教育部重点实验室,石家庄050043 [4]石家庄铁道大学,石家庄050043

出　　处：《高速铁路技术》2024年第4期1-7,99,共8页High Speed Railway Technology

基　　金：国家自然科学基金青年基金资助项目(52108378);河北省自然科学基金资助项目(E2020210068);青年人才托举工程(2021QNRC001)。

摘　　要：小波神经网络在对数据预测方面存在收敛速度慢、极易陷入局部最优的缺陷,人工蜂群算法全局寻优能力强、收敛速度快,但其本身也存在寻找到最优解时速度变慢以及后期寻优能力弱的缺点。本文利用人工蜂群算法对小波神经网络进行优化,建立ABC-WNN分析模型,并依托基坑工程实例,对基坑开挖引起的盾构隧道变形量进行预测分析,并将结果与单一的BP神经网络模型、WNN模型进行均方差以及平均绝对误差对比。结果表明:(1)ABC-WNN模型预测值与实际工程数据拟合程度高,相对误差最大仅为2.41×10^(-5),表明该模型预测功能较为可靠;(2)ABC-WNN的各项统计学特征均为最低,分别为0.557和0.563,人工蜂群优化后的小波神经网络模型对变形量预测精度更高、计算稳定性更好、收敛速度更快。研究成果可为类似工程的盾构隧道变形预测提供一种新途径。Wavelet neural networks(WNNs)possess inherent drawbacks in data prediction,such as slow convergence and susceptibility to local optima.Conversely,artificial bee colony(ABC)algorithms exhibit strong global search capability and fast convergence,albeit with a tendency to slow down when approaching optimal solutions and weaker exploration ability in later stages.This study employed the ABC algorithm to optimize a WNN,and constructed an ABCWNN analytical model.With the excavation of foundation pit as the case for study,the model was utilized to predict deformation induced by deep excavation in an existing shield tunnel.Predictions were then compared against those from standalone BP neural network and WNN models in terms of mean squared error and average absolute error.The results reveal that:(1)The ABC-WNN model exhibits high goodness-of-fit with actual engineering data,with a maximum relative error of merely 2.41×10^(-5),indicating reliable predictive capability.(2)Statistical characteristics of the ABCWNN model are the lowest,specifically with values of 0.557 and 0.563,signifying that the ABC-optimized wavelet neural network model provides higher prediction accuracy,improved computational stability,and faster convergence for tunnel deformation quantification.These findings offer a novel approach for predicting shield tunnel deformation in analogous engineering contexts.

关 键 词：盾构隧道 变形预测 人工蜂群 深基坑 小波神经网络 

分 类 号：U455.43[建筑科学—桥梁与隧道工程]