基于GPR代理模型和GA-APSO混合优化算法的软基水闸底板脱空反演

PDF(2050 KB)

振动与冲击 ›› 2023, Vol. 42 ›› Issue (14) : 1-10.

论文

李火坤1，柯贤勇1,2，黄伟1，刘双平1,2，唐义员1，方静1

作者信息 +

Inversion study of soft foundation sluice bottom plate emptying based on a GPR surrogate model and a GA-APSO hybrid optimization algorithm

LI Huokun1，KE Xianyong1,2，HUANG Wei1，LIU Shuangping1,2，TANG Yiyuan1，FANG Jing1

Author information +

文章历史 +

摘要

软基水闸底板脱空是水闸在长期服役期间受水流侵蚀等环境因素影响所产生的一种危害极大且难以察觉的病害。由于其病害部位于水下，传统方法难以检测，本文提出一种基于高斯过程回归（Gaussian Process Regression，GPR）代理模型和遗传—自适应惯性权重粒子群（Genetic Algorithm-Adaptive Particle Swarm Optimization，GA-APSO）混合优化算法的水闸底板脱空动力学反演方法，用于检测软基水闸底板脱空。首先，构建表征软基水闸底板脱空参数和水闸结构模态参数之间非线性关系的GPR代理模型；其次，基于GPR代理模型与水闸实测模态参数建立脱空反演的最优化数学模型，将反演问题转化为目标函数最优化求解问题；最后，为提高算法寻优计算的精度，提出一种GA-APSO混合优化算法对目标函数进行脱空反演计算，并提出一种更合理判断反演脱空区域面积和实际脱空区域面积相对误差的指标—面积不重合度。为验证所提方法性能，以一室内软基水闸物理模型为例，对2种不同脱空工况开展研究分析，结果表明，反演脱空区域面积和模型实际设置脱空区域面积的相对误差分别为8.47%、10.77%，相对误差值较小，所提方法能有效反演出水闸底板脱空情况，可成为软基水闸底板脱空反演检测的一种新方法。

Abstract

The floor void of sluice on soft foundation is a very harmful and undetectable disease caused by environmental factors such as water erosion during long-term service of sluice gates. Since the damage area is underwater, it is difficult to be detected by traditional methods. In this paper, a dynamic inversion method based on Gaussian Process Regression(GPR) surrogate model and Genetic Algorithm-Adaptive Particle Swarm Optimization(GA-APSO) hybrid optimization algorithm is proposed to detect the voiding of soft foundation sluice floor.. Firstly, a GPR surrogate model is constructed to characterize the nonlinear relationship between the emptying parameters and the modal parameters of the sluice structure; secondly, an optimization mathematical model for emptying parameter inversion is established based on the GPR surrogate model and the measured modal parameters of the sluice, and the inversion problem is transformed into an objective function optimization solution problem; Finally, in order to improve the accuracy of the algorithm, a GA-APSO hybrid optimization algorithm is proposed to perform the inversion calculation of the objective function for the emptying, and a more reasonable index to judge the relative error between the inversion voiding area and the actual voiding area—area non-coincidence is proposed. In order to verify the performance of the proposed method, the physical model of an indoor soft foundation sluice is used as an example, and two different emptying conditions are set for analysis. The results show that the relative errors of the inverse emptying area and the actual set emptying area of the model are 8.47% and 10.77%, respectively, with smaller relative error values. and the proposed method can effectively inverse perform the emptying of the sluice bottom plate, which can be a new method for inversion detection of soft foundation sluice floor.

导出引用

李火坤1，柯贤勇1,2，黄伟1，刘双平1,2，唐义员1，方静1. 基于GPR代理模型和GA-APSO混合优化算法的软基水闸底板脱空反演[J]. 振动与冲击, 2023, 42(14): 1-10

LI Huokun1，KE Xianyong1,2，HUANG Wei1，LIU Shuangping1,2，TANG Yiyuan1，FANG Jing1. Inversion study of soft foundation sluice bottom plate emptying based on a GPR surrogate model and a GA-APSO hybrid optimization algorithm[J]. Journal of Vibration and Shock, 2023, 42(14): 1-10

参考文献

[1] 沈长松，刘晓青，王润英，等. 水工建筑物[M]. 北京：中国水利水电出版社，2016.
[2] 梁民阳，吴兴龙. 浙东海塘上水闸病害成因分析及对策[J]. 中国农村水利水电，2006(7)：107-108.
[3] 张挺，詹杰民，谢应恩. 软土地基水闸的基础防渗问题及处理[C]. 第一届中国水利水电岩土力学与工程学术讨论会论文集（下册）. 北京：中国水利学会，2006.
[4] Fan X F, Wu Z Y, Liu L J, et al. Analysis of sluicefoundation seepage using monitoring data and numericalsimulation[J]. Advances in Civil Engineering,2019(3):1-15.
[5] 戴呈祥，王士恩. 水闸闸基隐患探测雷达图像特征分析[J]. 地球物理学进展，2003(03)：429-433.
Dai Chenxiang, Wang Shien. Feature analysis on radar pictures for detecting hidden danger of floodgate base[J]. Progress in Geophysics, 2003, 18(3): 429-433.
[6] 安铎，陆新宇，李经纬. 基于探地雷达技术的水闸脱空检测方法研究[J]. 人民长江, 2014，45(S2)：202-205.
An Duo, Lu xinyu, Li jingwei. Research on detection method of sluice void based on ground penetrating radar technology[J]. Yangtze River, 2014, 45(2): 202-205.
[7] 陈鹦. 无损动态检测闸基隐患[J]. 大坝与安全,1994(1):40-46.
Chen Ying. Non-destructive dynamic detection of hidden dangers of gate base[J]. Dam & Safety, 1994(1): 40-46.
[8] 黄锦林，李火坤，邓冰梅. 基于响应面理论的闸基底板脱空区域识别方法[J]. 中国水利水电科学研究院学报，2018，16(4):249-256.
Huang Jinlin, Li Huokun, Deng Bingmei. Identification methods of sluice floor pavement area based on the theory of response surface[J]. Journal of China Institute of Water Resources and Hydropower Research, 2018, 16(4): 249-256.
[9] 李火坤，余杰，王刚，等. 软基水闸底板脱空动力学反演模型构建与试验验证[J]. 农业工程学报，2020，36(21):145-153.
Li Huokun, Yu Jie, Wang Gang, et al. Model construction of dynamic inversion and experimental verification for the void of sluice floor on the soft foundation[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(21):145-153.
[10] 苏怀智，李季，吴中如. 大坝及岩基物理力学参数优化反演分析研究[J]. 水利学报，2007(S1):129-134.
Su Huaizhi, Li Ji, Wu Zhongru. Feedback analysis for mechanical parameters of dam and its foundation with optimization algorithm[J]. Journal of hydraulic engineering, 2007(S1):129-134.
[11] 康飞，李俊杰，许青. 混合蜂群算法及其在混凝土坝动力材料参数反演中的应用[J]. 水利学报，2009，40(06):736-742.
Kang Fei, Li Junjie, Xu Qing. Hybrid simplex artificial bee colony algorithm and its application in material dynamic parameter back analysis of concrete dams[J]. Journal of hydraulic engineering, 2009, 40(06):736-742.
[12] Kang F, Li J J. Displacement model for concrete dam safety monitoring via Gaussian process regression considering extreme air temperature[J], J. Struct. Eng., 146(2020).
[13] Kang F, Wu Y R, Li J J, et al . Dynamic parameter inverse analysis of concrete dams based on Jaya algorithm with Gaussian processes surrogate model[J]. Advanced Engineering Informatics, 49(2021).
[14] 余红玲，王晓玲，王成，等. 贝叶斯框架下大坝渗流参数反演组合代理模型研究[J]. 水利学报，2022，53(03):306-315+324.
Yu Hongling, Wang Xiaoling, Wang Cheng, et al . Research on ensemble surrogate models of dam seepage parameters inversion under Bayesian framework[J]. Journal of hydraulic engineering, 2022, 53(03):306-315+324.
[15] Li H K, Wang G, Wei B W, et al. Dynamic inversion method for the material parameters of a high arch dam and its foundation [J]. Applied Mathematical Modelling, 2019, 71:60-76.
[16] 李火坤，王刚，魏博文，等. 基于敏感性分析与粒子群算法的拱坝原型动弹性模量反演方法[J]. 水利学报，2020，51(11):1401-1411.
Li Huokun, Wang Gang, Wei Bowen, et al. Inversion of prototype dynamic elastic modulus of arch dam based on sensitivity analysis and particle swarm optimization[J]. Journal of hydraulic engineering, 2020, 51(11): 1401-1411.
[17] 李火坤，王刚，余杰，等. 基于模态参数及BAS-PSO优化算法的软基水闸有限元模型参数修正方法[J]. 工程力学，2021，38(09):246-256.
Li Huokun, Wang Gang, Yu Jie, et al. Finite element model
Parameter updating of sluices on a soft foundationbased on modal parameters and BAS-PSO optimization algorithm[J]. Engineering mechanics, 2021, 38(09):246-256.
[18] 刘信恩，肖世富，莫军. 高斯过程响应面法研究[J]. 应用力学学报，2010，27(01):190-195+233.
Liu Xinen, Xiao Shifu, Mo Jun. A new response surface method baesd on gaussian process[J]. Chinese Journal of Applied Mechanics, 2010, 27(01): 190-195+233.
[19] 苏国韶，赵伟，彭立锋，等. 边坡失效概率估计的高斯过程动态响应面法[J]. 岩土力学，2014，35(12):3592-3601.
Su Guoshao, Zhao Wei, Peng Lifeng, et al. Gaussian process-based dynamic response surface method for estimating slope failure probability[J]. Rock and Soil Mechanics, 2014, 35(12): 3592-3601.
[20] 朱彬，裴华富，杨庆. 基于高斯过程回归的响应面法及边坡可靠度分析[J]. 岩土工程学报，2019，41(S1):209-212.
Zhu Bin, Pei Huafu, Yang Qin. Gaussian process regression-based response surface method and reliability analysis of slopes[J]. Chinese Journal of Geotechnical Engineering, 2019, 41(S1): 209-212.
[21] Kennedy J, Eberhart R. Particle swarm optimization [C]. IEEE International Conference onNeural Networks: IEEE, 1995: 1942-1948.
[22] 李爱国，覃征，鲍复民，等. 粒子群优化算法[J]. 计算机工程与应用，2002，(21): 1-3+17.
Li Aiguo, Qin Zheng, Bao Fumin, et al. Particle Swarm Optimization Algorithms[J]. Computer Engineering and Applications, 2002, (21): 1-3+17.
[23] 李新想, 王锡淮, 肖健梅. 基于遗传混沌粒子群混合算法的船舶动力定位推力分配研究[J]. 舰船科学技术，2018，40(23): 99-103.
Li Xinxiang, Wang Xihuai, Xiao Jianmei. Research on thrust allocation of ship dynamic positioning based on genetic chaos particle swarm optimization algorithm[J]. Ship Science and Technology, 2018, 40(23): 99-103.
[24] 陈璐璐，邱建林，陈燕云，等. 改进的遗传粒子群混合优化算法[J]. 计算机工程与设计，2017 ，38(02):395-399.
Cheng Lulu, Qiu Jianlin, Chen Yanyun, et al. Improved hybrid optimization algorithms based on genetic algorithm and particle swarm optimization[J]. Computer Engineering and Design, 2017 , 38(02): 395-399.
[25] 刘双平，柯贤勇，李火坤，等. 软基水闸底板脱空反演的响应面模型优化[J]. 南昌大学学报(工科版)，2021，43(04):333-340+383.
Liu Shuangping, Ke Xianyong, Li Huokun, et al. Optimization of response surface model in the inversion of the void of sluice floor on soft foundation[J]. Journal of Nanchang University(Engineering & Technology), 2021, 43(04): 333-340+383.
[26] 张建伟，康迎宾，张翌娜，等. 基于泄流响应的高拱坝模态参数辨识与动态监测[J]. 振动与冲击，2010，29(09):146-150+249.
Zhang Jianwei, Kang YingBin, Zhang Yina, et al. Modal parameter identification and dynamic monitoring of high arc dam under vibration response induced by flow discharge[J]. Journal of Vibration and Shock. 2010, 29(09): 146-150+249.