您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（理学版）》

《山东大学学报(理学版)》 ›› 2024, Vol. 59 ›› Issue (3): 37-50.doi: 10.6040/j.issn.1671-9352.7.2023.3667

•   • 上一篇    下一篇

基于改进蝴蝶算法的水文地质参数优化

韦修喜1(),彭茂松2,黄华娟1,*()   

  1. 1. 广西民族大学人工智能学院, 广西 南宁 530006
    2. 广西民族大学电子信息学院, 广西 南宁 530006
  • 收稿日期:2023-04-25 出版日期:2024-03-20 发布日期:2024-03-06
  • 通讯作者: 黄华娟 E-mail:weixiuxi@163.com;hhj-025@163.com
  • 作者简介:韦修喜(1980—)，男，博士，副教授，硕士生导师，研究方向为机器学习、计算智能及应用. E-mail: weixiuxi@163.com
  • 基金资助:
    国家自然科学基金资助项目(62266007);广西自然科学基金资助项目(2021GXNSFAA220068)

Optimization of hydrogeological parameters based on improved butterfly optimization algorithm

Xiuxi WEI1(),Maosong PENG2,Huajuan HUANG1,*()   

  1. 1. College of Artificial Intelligence, Guangxi Minzu University, Nanning 530006, Guangxi, China
    2. College of Electronic Information, Guangxi Minzu University, Nanning 530006, Guangxi, China
  • Received:2023-04-25 Online:2024-03-20 Published:2024-03-06
  • Contact: Huajuan HUANG E-mail:weixiuxi@163.com;hhj-025@163.com

RichHTML

2

PDF (PC)

182

摘要：

针对水文地质参数求解精度不足以及传统配线法等策略在求参过程中效率低下等的问题, 提出一种基于黄金正弦加权蝴蝶优化算法的水文地质参数优化策略。首先在蝴蝶优化算法的全局与局部搜索阶段引入黄金正弦算子, 缩小算法解空间; 其次引入自适应权重, 调整算法后期种群个体移动步长与搜索方向。通过6个基准测试函数的寻优对比测试结果表明: 黄金正弦加权蝴蝶优化算法的寻优精度较高且收敛速度较快。将该优化策略应用于水文地质参数导水系数与贮水系数的优化以达到最小降深误差, 并与粒子群优化算法、配线法等优化策略进行实验对比。结果表明黄金正弦加权蝴蝶优化算法能有效优化水文地质参数并提高泰斯公式计算性能, 获得更小抽水降深误差, 为后续抽水试验提供了新方法。

关键词: 蝴蝶优化算法, 黄金正弦算子, 自适应权重, 水文地质参数, 抽水试验

Abstract:

In order to solve the problems of insufficient accuracy of hydrogeological parameters and low efficiency of traditional routing methods, an optimization strategy of hydrogeological parameters based on golden sine weighted butterfly optimization algorithm (GSWBOA) is proposed. Firstly, the golden sine operator is introduced in the global and local search phase of butterfly optimization algorithm to reduce the solution space of the algorithm. Secondly, adaptive weights are introduced to adjust the individual moving step size and search direction in the later stage of the algorithm. The comparison test results of 6 benchmark test functions show that the GSWBOA has higher optimization accuracy and faster convergence. The optimization strategy is applied to the optimization of hydrogeological parameters water conductivity coefficient and water storage coefficient to achieve the minimum depth reduction error, and the optimization strategy is compared with particle swarm optimization algorithm, wiring method and other optimization strategies. The results show that the golden sinusoidal weighted butterfly optimization algorithm can effectively optimize the hydrogeological parameters, improve the calculation performance of Theis formula, and obtain a smaller drawdown error, which provides a new method for the subsequent pumping test.

Key words: butterfly optimization algorithm, golden sine operator, adaptive weight coefficient, hydrogeological parameters, pumping test

中图分类号: 

  • TP183

表1

各算法参数"

算法 参数设置
BOA α=0.1, c=0.01, P=0.8
GSWBOA α=0.1, c=0.01, P=0.8, a=-π, b=π,$\tau=(\sqrt{5}-1) / 2$
DGBOA α=0.1, c=0.01, σmax=1.5, σmin=0.4, Pmax=0.8, Pmin=0.3
GWO α, β, δ=+∞
MSBOA C=0.5, αmax=1, αmin=1e-4, δ=1, Pmax=0.9, Pmin=0.6, β=1

表2

测试函数详细信息"

代号 函数表达式 定义域 维度 最优值
F1 $F_1(x)=\sum\limits_{i=1}^n x_i^2$ [-100, 100] 30 0
F2 $F_3(x)=\sum\limits_{i=1}^D\left(10^6\right)^{\frac{i-1}{D-1}} x_i^2$ [-100, 100] 50 0
F3 $F_3(x)=x_1^2+10^6 \sum\limits_{i=2}^D x_i^2$ [-100, 100] 50 0
F4 $F_4(x)=-20 \exp \left(-0.2 \sqrt{\frac{1}{D} \sum\limits_{i=1}^D x_i^2}\right)-\exp \left(\frac{1}{D} \sum\limits_{i=1}^D \cos \left(2 \pi x_i\right)\right)+20+\mathrm{e}$ [-32, 32] 50 8.88E-16
F5 $F_5(x)=\sum\limits_{i=1}^D\left[x_i^2-10 \cos \left(2 \pi x_i\right)+10\right]$ [-5.12, 5.12] 30 0
F6 $F_6(x)=\left[\frac{1}{D-1} \sum\limits_{i=1}^{D-1}\left(\sqrt{s_i}\left(\sin \left(50 s_i^{0.2}\right)+1\right)\right)\right]^2, s_i=\sqrt{x_i^2+x_{i+1}^2}$ [-100, 100] 50 0

表3

不同算法寻优结果"

函数 算法 最差值 最优值 平均值 标准差 运行时间/s
F1 BOA 7.06E+04 1.07E-11 1.08E+03 6.65E+03 0.153 17
MSBOA 4.80E+04 0.00E+00 3.40E+02 3.22E+03 2.388 90
DGBOA 6.65E+04 1.65E-09 9.46E+02 6.07E+03 0.502 14
GSWBOA 3.71E-03 0.00E+00 7.43E-06 1.66E-04 0.168 31
PPSO 3.04E+04 6.03E-05 9.61E+01 1.53E+03 0.135 65
GWO 5.78E+04 3.92E-40 4.42E+02 3.86E+03 0.259 07
F2 BOA 3.56E+09 1.24E-11 2.57E+07 2.44E+08 0.881 89
MSBOA 2.66E+09 0.00E+00 1.18E+07 1.51E+08 6.571 10
DGBOA 3.79E+09 1.51E-09 2.63E+07 2.59E+08 1.289 00
GSWBOA 1.24E+03 0.00E+00 2.47E+00 5.53E+01 0.900 74
PPSO 2.22E+09 4.35E+02 1.54E+07 1.45E+08 0.531 52
GWO 4.92E+09 1.60E-25 2.63E+07 2.76E+08 0.750 64
F3 BOA 9.22E+10 1.36E-11 4.83E+08 5.35E+09 0.195 42
MSBOA 4.27E+10 0.00E+00 1.46E+08 2.09E+09 3.165 60
DGBOA 8.30E+10 1.55E-09 4.35E+08 4.81E+09 0.592 81
GSWBOA 1.06E+04 0.00E+00 2.13E+01 4.75E+02 0.207 82
PPSO 6.28E+10 5.77E+01 3.19E+08 3.77E+09 0.160 43
GWO 1.25E+11 4.38E-23 1.19E+09 8.96E+09 0.409 04
F4 BOA 2.15E+01 5.37E-10 5.47E+00 8.88E+00 0.327 86
MSBOA 2.12E+01 8.88E-16 9.60E+00 1.05E+01 11.450 10
DGBOA 2.14E+01 4.30E-08 7.19E+00 9.68E+00 0.742 90
GSWBOA 2.97E+00 8.88E-16 6.08E-03 1.33E-01 0.278 86
PPSO 2.11E+01 2.00E+01 2.00E+01 4.94E-02 0.200 83
GWO 2.15E+01 2.10E+01 2.10E+01 3.94E-02 0.472 05
F5 BOA 3.84E+02 0.00E+00 1.03E+02 1.15E+02 0.217 50
MSBOA 1.10E+00 0.00E+00 3.17E-02 1.22E-01 17.951 20
DGBOA 3.87E+02 2.84E-12 8.55E+01 1.07E+02 0.562 25
GSWBOA 1.72E+02 0.00E+00 3.44E-01 7.69E+00 0.213 58
PPSO 3.44E+02 9.45E-05 3.20E+00 2.65E+01 0.152 93
GWO 4.54E+02 0.00E+00 1.92E+01 6.25E+01 0.275 94
F6 BOA 1.08E+01 2.38E-06 1.42E+00 2.78E+00 2.357 80
MSBOA 2.54E+00 0.00E+00 2.35E-02 1.59E-01 5.307 70
DGBOA 1.15E+01 1.97E-03 1.32E+00 2.66E+00 2.672 40
GSWBOA 1.00E-01 0.00E+00 2.39E-04 4.54E-03 1.137 50
PPSO 9.31E+00 2.79E-02 1.42E-01 7.40E-01 1.259 90
GWO 1.04E+01 1.39E-08 4.06E-01 1.48E+00 1.487 40

表4

Wilcoxon秩和检验结果p"

GSWBOA BOA MSBOA DGBOA PPSO GWO
F1 2.82E-184 3.42E-117 2.36E-184 8.24E-185 6.73E-182
F2 3.81E-184 3.89E-116 3.96E-184 1.58E-186 4.28E-183
F3 1.19E-180 5.02E-110 1.27E-180 7.78E-183 2.42E-179
F4 2.75E-180 6.36E-64 5.07E-181 3.18E-214 4.58E-202
F5 7.47E-168 2.25E-48 4.29E-184 2.05E-183 5.85E-186
F6 2.33E-181 2.87E-109 3.64E-182 4.73E-182 1.80E-178

图1

F1—F4测试函数的适应度收敛曲线图"

图2

F5、F6测试函数的适应度收敛曲线图"

图3

F1、F2测试函数的箱线图"

图4

F3—F6测试函数的箱线图"

表5

单观测孔数据"

编号 t/min s/m 编号 t/min s/m
1 10 0.16 10 210 1.55
2 20 0.48 11 270 1.70
3 30 0.54 12 330 1.83
4 40 0.65 13 400 1.89
5 60 0.75 14 450 1.98
6 80 1.00 15 645 2.17
7 100 1.12 16 870 2.38
8 120 1.22 17 990 2.46
9 150 1.36 18 1 185 2.54

图5

单孔观测优化对比"

表6

不同策略优化结果对比"

策略 T/(m2/d) S 误差
GSWBOA 219.381 1 0.000 224 79 0.006 195
PSO 198.860 1 0.000 264 69 0.007 639
人工配线法 197.670 0 0.000 298 70 0.009 642
LinWPSO[6] 216.892 2 0.000 229 94 0.007 339

表7

观测孔数据"

抽水试验参数 1 2 3 4 5 6 7 8
距抽水井距离/m 8.8 10.7 13.4 18.3 25.9 30.5 38.1 49.7
s/m 4.54 4.21 3.87 3.57 3.08 2.93 2.62 2.13

图6

多孔观测优化对比"

表8

不同策略优化结果对比"

策略 T/(m2/d) S 误差大小
GSWBOA 225.964 90 0.000 616 78 0.003 091 20
PSO 205.136 60 0.000 936 04 0.007 359 80
人工配线法 237.400 00 0.000 448 41 1.904 250 00
最小二乘法[6] 229.791 70 0.000 604 48 0.005 701 20
1 赵衍杰, 张志超, 王桂林, 等. 基于抽水试验确定含水层水文地质参数计算方法[J]. 山西建筑, 2022, 48 (8): 93- 95.
ZHAO Yanjie , ZHANG Zhichao , WANG Guilin , et al. Discussion on calculation method of determining hydrogeological parameters of aquifer based on pumping test[J]. Shanxi Architecture, 2022, 48 (8): 93- 95.
2 FABBROCINO S, SESSA EB, DE VITA S, et al. A GIS-based hydrogeological approach to the assessment of the groundwater circulation in the Ischia volcanic island (Italy)[J/OL]. Frontiers in Earth Science, 2022[2023-04-25]. https://doi.org/10.3389/feart.2022.883719.
3 AKHTER G , GE Y , HASAN M , et al. Estimation of hydrogeological parameters by using pumping, laboratory data, surface resistivity and thiessen technique in lower bari doab (Indus Basin), Pakistan[J]. Applied Sciences, 2022, 12 (6): 1- 19.
4 SAMADI J. Modelling hydrogeological parameters to assess groundwater pollution and vulnerability in Kashan aquifer: novel calibration-validation of multivariate statistical methods and human health risk considerations[J/OL]. Environmental Research, 2022[2023-04-25]. https://doi.org/10.1016/j.envres.2022.113028.
5 周志芳, 王萍, 李雅冰, 等. 一种求解承压含水层水文地质参数的新配线法[J]. 河海大学学报(自然科学版), 2019, 47 (1): 7- 12.
ZHOU Zhifang , WANG Ping , LI Yabing , et al. A new type curve method for estimating hydrogeological parameters of confined aquifers[J]. Journal of Hohai University (Natural Sciences), 2019, 47 (1): 7- 12.
6 张勇, 党承华, 东栋, 等. 水文地质参数智能优化计算[M]. 北京: 科学出版社, 2019: 120- 135.
ZHANG Yong , DANG Chenghua , DONG Dong , et al. Intelligent optimization calculation of hydrogeological parameters[M]. Beijing: Science Press, 2019: 120- 135.
7 段国荣, 刘元会. 用差异演化-粒子群混合算法确定含水层参数[J]. 西安科技大学学报, 2019, 39 (3): 549- 554.
DUAN Guorong , LIU Yuanhui . Differential evolution-particle swarm optimization mixed algorithm determine aquifer parameters[J]. Journal of Xi̓an University of Science and Technology, 2019, 39 (3): 549- 554.
8 刘淑惠, 肖长来, 梁秀娟. 基于线性、非线性规划的双辽市水文地质参数计算方法[J]. 水电能源科学, 2020, 38 (4): 72- 75.
LIU Shuhui , XIAO Changlai , LIANG Xiujuan . A method for calculating hydrogeological parameters of Shuangliao city based on linear and nonlinear programming[J]. Water Resources and Power, 2020, 38 (4): 72- 75.
9 周念清, 张瑞城, 江思珉, 等. ES-MDA算法融合ERT数据联合反演地下水污染源与含水层参数[J]. 南水北调与水利科技(中英文), 2022, 20 (3): 478- 486.
ZHOU Nianqing , ZHANG Ruicheng , JIANG Simin , et al. Joint inversion of contaminant source and aquifer parameters by assimilating ERT data with the ES-MDA algorithm[J]. South-to-North Water Transfers and Water Science & Technology, 2022, 20 (3): 478- 486.
10 ARORA S , SINGH S . Butterfly optimization algorithm: a novel approach for global optimization[J]. Soft Computing, 2019, 23 (3): 715- 734.
doi: 10.1007/s00500-018-3102-4
11 ARORA S , SINGH S . Node localization in wireless sensor networks using butterfly optimization algorithm[J]. Arabian Journal for Science and Engineering, 2017, 42 (8): 3325- 3335.
doi: 10.1007/s13369-017-2471-9
12 DUBEY A K . Optimized hybrid learning for multi-disease prediction enabled by lion with butterfly optimization algorithm[J]. Sādhanā, 2021, 46 (2): 1- 27.
13 TUBISHAT M , ALSWAITTI M , MIRJALILI S , et al. Dynamic butterfly optimization algorithm for feature selection[J]. IEEE Access, 2020, 8, 194303- 194314.
doi: 10.1109/ACCESS.2020.3033757
14 ARORA S , SINGH S . An improved butterfly optimization algorithm with chaos[J]. Journal of Intelligent & Fuzzy Systems, 2017, 32 (1): 1079- 1088.
15 ARORA S , ANAND P . Learning automata-based butterfly optimization algorithm for engineering design problems[J]. International Journal of Computational Materials Science and Engineering, 2018, 7 (4): 1- 28.
16 陈俊, 何庆. 基于余弦相似度的改进蝴蝶优化算法[J]. 计算机应用, 2021, 41 (9): 2668- 2677.
CHEN Jun , HE Qing . Improved butterfly optimization algorithm based on cosine similarity[J]. Journal of Computer Applications, 2021, 41 (9): 2668- 2677.
17 张小萍, 谭欢. 具有动态方差高斯变异的蝴蝶优化算法[J]. 云南师范大学学报(自然科学版), 2022, 42 (3): 31- 36.
ZHANG Xiaoping , TAN Huan . Butterfly optimization algorithm with dynamic variance Gaussian mutation[J]. Journal of Yunnan Normal University (Natural Sciences Edition), 2022, 42 (3): 31- 36.
18 邱淑伟, 吴亚敏, 柯昱琪, 等. 基于遍历搜索算法的水文地质参数优化求解[J]. 吉林大学学报(地球科学版), 2020, 50 (6): 1854- 1861.
QIU Shuwei , WU Yamin , KE Yuqi , et al. Optimization of hydrogeological parameters based on ergodic search algorithm[J]. Journal of Jilin University (Earth Science Edition), 2020, 50 (6): 1854- 1861.
19 CRAWFORD B , SOTO R , DE LA FUENTE MELLA H , et al. Binary fruit fly swarm algorithms for the set covering problem[J]. Computers, Materials and Continua, 2022, 71 (2): 4295- 4318.
20 TANYILDIZI E , DEMIR G . Golden sine algorithm: a novel math-inspired algorithm[J]. Advances in Electrical and Compu-ter Engineering, 2017, 17 (2): 71- 78.
21 GHASEMI M , AKBARI E , RAHIMNEJAD A , et al. Phasor particle swarm optimization: a simple and efficient variant of PSO[J]. Soft Computing, 2019, 23 (19): 9701- 9718.
22 郝芃斐, 池瑞, 屈志坚, 等. 求解铁路物流配送中心选址问题的改进灰狼优化算法[J]. 计算机应用, 2021, 41 (10): 2905- 2911.
HAO Pengfei , CHI Rui , QU Zhijian , et al. Improved grey wolf optimizer for location selection problem of railway logistics distribution center[J]. Journal of Computer Applications, 2021, 41 (10): 2905- 2911.
23 宁杰琼, 何庆. 混合策略改进的蝴蝶优化算法[J]. 计算机应用研究, 2021, 38 (6): 1718-1723, 1738.
NING Jieqiong , HE Qing . Mixed strategy to improve butterfly optimization algorithm[J]. Application Research of Compu-ters, 2021, 38 (6): 1718-1723, 1738.
[1] 许侃,刘瑞鑫,林鸿飞,刘海峰,冯娇娇,李家平,林原,徐博. 基于异质网络嵌入的学术论文推荐方法[J]. 《山东大学学报(理学版)》, 2020, 55(11): 35-45.
[2] 张超,梁英,方浩汕. 支持隐私保护的社交网络信息推荐方法[J]. 《山东大学学报(理学版)》, 2020, 55(3): 9-18.
[3] 谢小杰,梁英,董祥祥. 社交网络用户敏感属性迭代识别方法[J]. 《山东大学学报(理学版)》, 2019, 54(3): 10-17, 27.
[4] 肖炜茗,王贵君. 基于Bernstein多项式的SISO三层前向神经网络的设计与逼近[J]. 山东大学学报（理学版）, 2018, 53(9): 55-61.
[5] 索春凤, 王贵君. 最大交互数对非齐次T-S模糊系统的潜在影响[J]. 山东大学学报（理学版）, 2015, 50(08): 14-19.
[6] 吴瑞海 董吉文 段琪庆. 变尺度混沌粒子群与小波的地基沉降预测应用[J]. J4, 2009, 44(11): 75-78.
[7] . 一种基于驾驶员学习过程的在线估计算法[J]. J4, 2009, 44(7): 83-88.
[8] 朱世伟,赛 英 . 基于主成分分析和粗径向基神经网络的财务预警模型研究[J]. J4, 2008, 43(11): 48-53 .
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] 孙小婷1,靳岚2*. DOSY在寡糖混合物分析中的应用[J]. J4, 2013, 48(1): 43 -45 .
[2] 任敏1,2,张光辉1. 右半直线上依分布收敛独立随机环境中随机游动的吸收概率[J]. J4, 2013, 48(1): 93 -99 .
[3] 徐俊峰. 关于复代数微分方程亚纯解的增长级[J]. J4, 2010, 45(6): 91 -93 .
[4] 张丽,许玉铭 . σ1-空间及其性质[J]. J4, 2006, 41(5): 30 -32 .
[5] 王刚,许信顺*. 一种新的基于多示例学习的场景分类方法[J]. J4, 2010, 45(7): 108 -113 .
[6] 陆玮洁,主沉浮,宋 翠,杨艳丽 . 中药郁金中无机离子的毛细管电泳法测定[J]. J4, 2007, 42(7): 13 -18 .
[7] 赵君1,赵晶2,樊廷俊1*,袁文鹏1,3,张铮1,丛日山1. 水溶性海星皂苷的分离纯化及其抗肿瘤活性研究[J]. J4, 2013, 48(1): 30 -35 .
[8] 杨永伟1,2,贺鹏飞2,李毅君2,3. BL-代数的严格滤子[J]. 山东大学学报（理学版）, 2014, 49(03): 63 -67 .
[9] 韩亚飞,伊文慧,王文波,王延平,王华田*. 基于高通量测序技术的连作杨树人工林土壤细菌多样性研究[J]. 山东大学学报（理学版）, 2014, 49(05): 1 -6 .
[10] 王红妹,肖敏*,李正义,李玉梅,钱新民 . 转糖基β-半乳糖苷酶产生菌筛选和鉴定及酶催化生成低聚半乳糖[J]. J4, 2006, 41(1): 133 -139 .
版权所有 © 2018 《山东大学学报(理学版)》编辑部　
地址: 山东省济南市山大南路27号山东大学中心校区（250100）　电话: +86-0531-88366917　E-mail: xblxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发