一种改进的算术优化算法及其在水文地质参数智能反演中的应用  

An Improved Arithmetic Optimization Algorithm and Its Application to the Intelligent Inversion of Hydrogeological Parameters

作　　者：许振浩[1,2] 范永辉 王文扬 董唯杰 申艳军 潘东东 XU Zhenhao;FAN Yonghui;WANG Wenyang;DONG Weijie;SHEN Yanjun;PAN Dongdong(Geotechnical and Structural Engineering Research Center,Shandong University,Jinan 250061,China;School of Qilu Transportation,Shandong University,Jinan 250061,China;School of Civil Engineering,Shandong University,Jinan 250061,China;Key Laboratory of Transportation Tunnel Engineering of Ministry of Education,Southwest Jiaotong University,Chengdu 610031,China;School of Geology and Environment,Xi'an University of Science and Technology,Xi'an 710054,China;Suzhou Research Institute,Shandong University,Suzhou 215123,China)

机构地区：[1]山东大学岩土与结构工程研究中心,山东济南250061 [2]山东大学齐鲁交通学院,山东济南250061 [3]山东大学土建与水利学院,山东济南250061 [4]西南交通大学交通隧道工程教育部重点实验室,四川成都610031 [5]西安科技大学地质与环境学院,陕西西安710054 [6]山东大学苏州研究院,江苏苏州215123

出　　处：《应用基础与工程科学学报》2024年第3期721-739,共19页Journal of Basic Science and Engineering

基　　金：国家自然科学基金面上项目(52279103,52379103);江苏省自然科学基金青年项目(BK20210114)。

摘　　要：水文地质参数的高效、准确、智能化获取对地下水资源科学管理和地下工程安全建设具有重要意义,因此提出一种新的水文地质参数智能反演方法.首先,提出了改进的算术优化算法(Chaotic Simplex Arithmetic Optimization Algorithm,CSAOA),在搜索空间中使用混沌理论初始化粒子位置,引入随机优化的超参数自适应调整策略,同时使用单纯形法优化粒子位置更新法则,进一步提高算法的局部开发能力和勘探能力,减小算法陷入局部最优的概率.其次,选取8个基准函数进行数值实验,结果表明CSAOA算法在前期勘探收敛速度和后期局部开发收敛精度方面优于其他对比算法.再次,将传统的人工配线法转化为基于优化算法的全局最优化问题,构建基于CSAOA算法的水文地质参数反演模型,提出了基于CSAOA算法的水文地质参数智能反演方法.最后,将该方法应用于泰斯和汉图什井流模型参数反演实例进行验证,快速准确反演得到了水文地质参数,实现了水文地质参数智能识别.结果证实了该方法的可靠性与先进性,为解决水文地质参数反演问题提供了一种新的方案.It is of great significance to acquire hydrogeological parameters efficiently,accurately and intelligently in the scientific management of groundwater resources and the safety construction of underground engineering.In this study,a novel intelligent inversion method of hydrogeological parameters is proposed.First,an improved arithmetic optimization algorithm(Chaotic Simplex Arithmetic Optimization Algorithm,CSAOA)is proposed.Chaos theory is used to initialize the particle positions in the search space.An adaptive adjustment strategy of hyperparameter based on stochastic optimization is introduced.Meanwhile,the simplex method is used to optimize the updating rule of particle positions,which further improves the local exploitation and exploration capability of the algorithm and reduces the probability of the algorithm falling into local optimum Then 8 benchmark functions are selected for numerical experiments.The results show that the CSAOA is superior to other comparison algorithms in early exploration speed and late local exploitation accuracy.In addition,the traditional manual type curve method is transformed into a global optimization problem based on optimization algorithm.The inversion model of hydrogeological parameters based on CSAOA is constructed,and an intelligent inversion method of hydrogeological parameters based on CSAOA is proposed.Finally,the method is validated in the parameter inversion examples of Theis and Hantush well flow models.Hydrogeological parameters are obtained quickly and accurately,and the intelligent identification of hydrogeological parameters is achieved.The results confirm the reliability and advancement of the method,and provide a new scheme for solving the inversion problem of hydrogeological parameters.

关 键 词：算术优化算法 混沌映射 自适应策略 单纯形法 水文地质参数 智能优化 

分 类 号：P641.2[天文地球—地质矿产勘探] TP18[天文地球—地质学]