多策略改进的IPOA-CNN-BiGRU模型在基坑降水预测中的应用

doi:10.3973/j.issn.2096-4498.2024.S2.028

隧道建设（中英文） ›› 2024, Vol. 44 ›› Issue (S2): 286-299.DOI: 10.3973/j.issn.2096-4498.2024.S2.028

多策略改进的IPOA-CNN-BiGRU模型在基坑降水预测中的应用

于维鹤¹，黄志强^{2, *}，王乃毅²，张宁²

（1. 中国石油辽宁丹东销售分公司，辽宁丹东 118016; 2. 沈阳工业大学建筑与土木工程学院，辽宁沈阳 110870）

出版日期:2024-12-20 发布日期:2024-12-20
作者简介:于维鹤（1999—），男，辽宁丹东人，2024年毕业于沈阳工业大学，土木水利专业，硕士，主要从事深度学习及地下空间工程研究工作。 E-mail： 657226715@qq.com。*通信作者：黄志强， E-mail： 1843172057@qq.com。

Application of Improved Pelican Optimization Algorithm-Convolutional Neural Networks-Bidirectional Gated Recurrent Unit Model in Predicting Foundation Pit Dewatering

YU Weihe¹, HUANG Zhiqiang^{2, *}, WANG Naiyi², ZHANG Ning²

(1. PetroChina Liaoning Dandong Sales Branch, Dandong 118016, Liaoning, China; 2. School of Architecture and Civil Engineering, Shenyang University of Technology, Shenyang 110870, Liaoning, China)

Online:2024-12-20 Published:2024-12-20

摘要/Abstract

摘要： 为提高基坑降水水位预测精度，加强对基坑降水水位的控制，在标准鹈鹕优化算法（POA）的基础上引入Logistic混沌映射、自适应动态权重因子w及萤火虫扰动最优位置3种优化策略，提出改进鹈鹕优化算法（IPOA）。选取4种基准测试函数对IPOA算法进行仿真测试，并选用其他5种优化算法进行对比分析。以沈阳北站基坑降水工程为实例进行研究，采用IPOA算法优化CNN-BiGRU模型中的隐含层节点个数、初始学习率以及L2正则化系数，形成IPOA-CNN-BiGRU水位预测模型，选用GWO、WOA、POA算法优化CNN-BiGRU模型并搭建Midas GTS NX基坑降水有限元数值模拟模型，进行对比分析，验证本文提出的预测模型在水位预测任务中的优越性。结果表明： 1）IPOA优化算法在单峰及多峰函数的寻优任务中均体现出较好的性能，其在4种基准测试函数中的寻优速度更快，寻优结果要明显优于其余5种算法。2）在水位预测任务中，IPOA-CNN-BiGRU水位预测模型的E_MAE、E_RMSE、E_MAPE分别为0.213 8、0.253 9、0.771 3，预测精度比GWO、WOA、POA优化下的CNN-BiGRU模型分别提高了32.36%、20.96%、15.79%。3）相比Midas GTS NX有限元模型，IPOA-CNN-BiGRU模型的参数依赖性更低，其预测精度提高了80.65%，验证了采用IPOA-CNN-BiGRU模型对基坑降水水位进行预测的可行性。

关键词: 基坑降水预测, 改进鹈鹕优化算法, 超参数优化, 数值模拟, 对比验证

Abstract: To enhance the prediction accuracy of foundation pit dewatering level and strengthen the control of dewatering level, three optimization strategies, Logistic chaos mapping, adaptive dynamic weighting factor w and firefly disturbance optimal position, are introduced to improve standard pelican optimization algorithm (POA). Four benchmark test functions are selected to simulate and test the improved POA (IPOA), and five optimization algorithms are selected for comparison and analysis. Taking a foundation pit in Shenyang North Railway Station as an example, the IPOA algorithm is used to optimize the number of nodes in the hidden layer, the initial learning rate, and the L2 regularization coefficient in the convolutional neural networks (CNN)-bidirectional gated recurrent unit (BiGRU) model to form the IPOA-CNN-BiGRU water level prediction model. Additionally, the grey wolf optimizer (GWO), whale optimization algorithm (WOA), and POA are selected to optimize the CNN-BiGRU model and build the Midas GTS NX finite element numerical simulation model. The comparative results among these models in predicting dewatering level of the foundation pit reveal the following: (1) The IPOA optimization algorithm shows better performance in both single-peak and multi-peak function optimization tasks, and its optimization speed is the fastest in the four benchmark functions, and the optimization results are significantly better than the remaining five algorithms. (2) In the water level prediction task, the E_MAE, E_RMSE, and E_MAPEof the IPOA-CNN-BiGRU model are 0.213 8, 0.253 9, and 0.771 3, respectively, and the prediction performances are 32.36%, 20.96%, and 15.79% higher than those of the CNN-BiGRU model under GWO, WOA, and POA optimization, respectively. (3) The IPOA-CNN-BiGRU model has a low dependence on the parameters compared with the Midas GTS NX finite element model, and its prediction accuracy is improved by 80.65%, which verifies the feasibility of the IPOA-CNN-BiGRU model in predicting dewatering level of the foundation pits.

Key words: foundation pit dewatering prediction, improved pelican optimization algorithm, hyperparameter optimization, numerical simulation, comparative validation

于维鹤, 黄志强, 王乃毅, 张宁. 多策略改进的IPOA-CNN-BiGRU模型在基坑降水预测中的应用[J]. 隧道建设, 2024, 44(S2): 286-299.

YU Weihe, HUANG Zhiqiang, WANG Naiyi, ZHANG Ning.

Application of Improved Pelican Optimization Algorithm-Convolutional Neural Networks-Bidirectional Gated Recurrent Unit Model in Predicting Foundation Pit Dewatering [J]. Tunnel Construction, 2024, 44(S2): 286-299.

[1]	荣传新, 屠卓, 龙伟, 张润泽. 地下水渗流富水砂层竖井冻结温度场时空演化规律及敏感性分析[J]. 隧道建设, 2025, 45(2): 268-283.
[2]	陈利, 刘兵, 曹志, 陈佳佳, 张恒, 张志强. 自然风对竖井排烟特长公路隧道火灾烟气扩散特性的影响[J]. 隧道建设, 2025, 45(2): 315-323.
[3]	甘甜. 协同排烟制式下列车越站对地铁站台排烟的影响研究[J]. 隧道建设, 2025, 45(2): 324-331.
[4]	李明, 王磊, 崔灏, 陈红蕾, 孙长松, 杨哲. 超大直径盾构隧道联络通道冻结法施工交界面温度场研究——以北京东六环改造工程冻结联络通道为例[J]. 隧道建设, 2025, 45(2): 352-360.
[5]	吴森阳, 陈相, 陈棚, 曾瑀韩. 大断面小净距矩形顶管法地铁车站施工风险控制研究——以广州地铁海傍站为例 [J]. 隧道建设, 2025, 45(2): 382-391.
[6]	马永政, 郑义, 朱瑶宏, 周汪, 牛富生, 黄强. 机械法联络通道施工参数全局敏感性影响分析[J]. 隧道建设, 2025, 45(1): 98-108.
[7]	张玉伟, 节金浦, 宋战平, 孙引浩, 成涛. 锚固结构界面失效机制及其界面模型研究进展[J]. 隧道建设, 2024, 44(S2): 36-50.
[8]	朱杰, 杨晨, 崔萌, 付跃有, 贾红岩, 韩萌萌. 基于安全系数的地下水封洞库主洞室围岩稳定性研究[J]. 隧道建设, 2024, 44(S2): 179-191.
[9]	阮恒丰, 梁荣柱, 康成, 李忠超, 曹世安, 丁智. 旁侧基坑开挖对地铁盾构隧道影响的精细化数值模拟研究[J]. 隧道建设, 2024, 44(S2): 245-255.
[10]	宋宏倬, 姜谙男, 阮颖颖, 闵庆华. 基于Hoek-Brown弹塑性HMD耦合模型的富水区隧道施工分析[J]. 隧道建设, 2024, 44(S2): 342-351.
[11]	李守仁, 谢雄耀, 唐亘跻, 李培锋. 膨胀性软岩隧道结构渐进性破坏机制与支护优化研究——以大亮山隧道为例[J]. 隧道建设, 2024, 44(S2): 424-434.
[12]	许万敏, 徐佳信, 徐金峰, 李守仁. 深埋偏压公路隧道非对称大变形控制技术及初期支护优化——以南朗山一号隧道为例[J]. 隧道建设, 2024, 44(S2): 435-444.
[13]	易壮鹏, 桂怡琦, 唐新超, 李宇杰. 椭圆形悬浮隧道管节沉放过程的波激运动特性分析[J]. 隧道建设, 2024, 44(S1): 92-104.
[14]	高峰, 姚海波, 耿英宸, 冯天垚, 庄璐, 于贺. 电力管廊通风规律及结构布局优化研究[J]. 隧道建设, 2024, 44(S1): 156-166.
[15]	郭明, 吴杰, 周轮. 顶部隐伏溶洞对隧道围岩变形特征影响分析——以齐岳山高速公路隧道为例[J]. 隧道建设, 2024, 44(S1): 211-223.

多策略改进的IPOA-CNN-BiGRU模型在基坑降水预测中的应用

Application of Improved Pelican Optimization Algorithm-Convolutional Neural Networks-Bidirectional Gated Recurrent Unit Model in Predicting Foundation Pit Dewatering

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价