To address the problem of local optima caused by the complexity of the objective function in parameter inversion for groundwater numerical modeling, an improved quantum genetic algorithm (IQGA) was proposed. Based on niche technology and elitist preservation strategy, a simulated binary crossover method varying with the number of iterations to replace the traditional rotation gate strategy was introduced. Furthermore, the improved algorithm was combined with the dynamic time warping (DTW) technique. Population diversity was maintained through the niche mechanism, while global search capability was enhanced by dynamically updating the population using an elite solution set and a crossover strategy that evolved over iterations. Additionally, DTW distance was employed to quantify the morphological similarity between simulated values and time-series observational data, facilitating the selection of globally optimal parameter combinations. The performance of IQGA was evaluated through benchmark functions, a relatively ideal case study (Case 1), and a real-world complex case (Case 2), and was compared with traditional genetic algorithm (GA), differential evolution (DE), particle swarm optimization (PSO), and basic quantum genetic algorithm (QGA). Experimental results show that during the benchmark function tests, the minimum, maximum, and average errors obtained by IQGA are all superior to those of the other algorithms. Convergence stability is significantly improved, and IQGA consistently outperforms the other algorithms in both the ideal and complex case studies. These results indicate that IQGA, through a synergistic optimization mechanism, effectively avoid the trap of local optima and provide a reliable approach for high-precision parameter identification in complex groundwater models.
现利用量子遗传算法本身所具有的特点,结合所关注的地下水反演存在的相关问题,采用精英保留与小生境策略,使得算法能够契合反演需求以给出多组最优解,同时通过实数编码、精英保留策略,并且提出一种随迭代次数改变的模拟二进制交叉方法等效的旋转门,降低算法陷入局部最优的概率,保证算法精度。在改进算法给出多个候选解的基础上,尝试引入动态时间规整(dynamic time warping,DTW)对观测值曲线与模拟值曲线的相似度进行评估,以期在较优解中找寻趋势与观测值曲线最为相近的一组解。
ChenYinghui, MaMiaomiao, LiuYuedong, et al. Hydrochemical characteristics and water quality evaluation of shallow groundwater in Chaixuan Basin, Zhangjiakou[J]. Science Technology and Engineering, 2024, 24(7): 3010-3019.
WangDun, PeiLixin, ZhangLizhong, et al. Research progress and prospect of numerical simulation of groundwater based on bibliometrics in the past two decades[J]. Environmental Engineering, 2023, 41(S1): 240-247.
[5]
欧何东. 基于进化算法的地下水逆问题研究[D]. 徐州: 中国矿业大学, 2022.
[6]
OuHedong. Research on groundwater inverse problem based on evolutionary algorithm[D]. Xuzhou: China University of Mining and Technology, 2022.
GeYuanbo. Identification of DNAPLs contamination source in groundwater based on improved sparrow search algorithm[D]. Changchun: Jilin University, 2023.
ChuJianmin, QiuWenjie, WuJianfeng, et al. Simulation of arsenic pollution reactive transport and source intensity identification of soil-groundwater in a solid waste landfill site[J]. Acta Scientiae Circumstantiae, 2024(2): 237-247.
LiJianhua. Study on groundwater pollution tracing in a chemical park in Northwest China based on simulation-optimization models[D]. Xi’an: Chang’an University, 2023.
GaoWanyu, LuWenxi, PanZidong, et al. Inverse identification of contamination sources in groundwater based on adaptive weighted particle swarm optimization algorithm[J]. China Rural Water and Hydropower, 2022(12): 1-7, 16.
[15]
HouZ, ZhaoK, WangS, et al. Bayesian hybrid-kernel machine-learning-assisted sensitivity analysis and sensitivity-relevant inverse modeling for groundwater DNAPL contamination[J]. Journal of Hydrology, 2024, 633: 131009.
[16]
孙宇辰. 基于禁忌算子的量子遗传算法研究及FGPA实现[D]. 成都: 四川大学, 2024.
[17]
SunYuchen. Research on quantum genetic algorithm based on tabu operator and FPGA implementation[D]. Chengdu: Sichuan University, 2024.
TanJingbin, QiYing, WuXutao. Analysis of LQR control strategy for high speed elevator lateral vibration based on step quantum genetic algorithm[J]. Manufacture & Upgrading Today, 2024(11): 3-5.
XingNingjiang, ZhouWenzheng, LiuYuzhu. Prediction model of gas emission rate based on improved QGA-ELM[J]. Mining Safety & Environmental Protection, 2024(5): 38-45.
HuaCongcong, FengSheng, LiDahua, et al. PV smart building load optimization based on improved quantum genetic algorithm[J]. Computer Applications and Software, 2024, 41(9): 77-82, 105.
LuoChengming, LuWenxi, PanZidong, et al. Inversion and identification of groundwater pollution sources based on surrogate model and flow direction algorithm[J]. China Environment Science, 2023, 43(11): 5823-5832.
WangShuai, GuoYuekai, QuShaohui, et al. Research on pol distribution transportation optimization based on quantum genetic algorithm[J]. Ship Electronic Engineering, 2021, 41(10): 121-125.
XiaXinmao, GuanHonghao, DingPengfei, et al. Capacity allocation and optimization strategy of an energy storage system based on an improved quantum genetic algorithm[J]. Energy Storage Science and Technology, 2019, 8(3): 551-558.
ChenZhiyuan, LeiJianping, ZhangZiqiao. Finite element model modification based on improved double-chain quantum genetic algorithm[J]. Journal of Wuhan University of Technology (Transportation Science & Engineering), 2022, 46(3): 548-551.
WangB. A research on resistance spot welding quality judgment of stainless steel sheets based on revised quantum genetic algorithm and hidden Markov model[J]. Mechanical Systems and Signal Processing, 2025, 223: 111881.
[37]
KongH P, LiN, ShenY Z, et al. Adaptive double chain quantum genetic algorithm for constrained optimization problems[J]. Chinese Journal of Aeronautics, 2015, 28(1): 214-228.
EyalWirsansky. Hands-on genetic algorithms with Python: applying genetic algorithms to solve real-world deep learning and artificial intelligence problems[M]. Wu Husheng, Zhu Li, Jiang Chuan, et al, Translated. Beijing: Tsinghua University Press, 2023.
[40]
XiaW, ChengM X, LiuM D. Improved ISPO algorithm based on Gaussian mutation[J]. Application Research of Computers, 2013, 30(4): 986-985.
[41]
WangX, DingH, TrajcevskiG, et al. Experimental comparison of representation methods and distance measures for time series data[J]. Data Mining and Knowledge Discovery, 2013, 26(2): 275-309.
GaoBochao. Ultrasound anomaly signal identification method based on local similarity feature[J]. Petrochemical Industry Technology, 2024, 31(10): 208-210.
ZhangXuewen, YuXingwei, HouXinyu, et al. Research on space target group matching technology based on time series vector similarity[J]. Big Data and Data Technology, 2024, 43(2): 29-36.
[46]
LangevinC D, HughesJ D, BantaE R, et al. MODFLOW 6:modular hydrologic model[EB/OL]. Reston: U.S. Geological Survey Software. ( 2024-12-19)[2024-12-20]. https://doi.org/10.5066/F76Q1VQV.
[47]
HughesJ, LangevinC, PaulinskiS, et al. FloPy workflows for creating structured and unstructured MODFLOW models[J]. Groundwater, 2024, 62(1): 124-139.
[48]
AyvazM T. A linked simulation-optimization model for solving the unknown groundwater pollution source identification problems[J]. Journal of Contaminant Hydrology, 2010, 117(1): 46-59.
[49]
XingZ, QuR, ZhaoY, et al. Identifying the release history of a groundwater contaminant source based on an ensemble surrogate model[J]. Journal of Hydrology, 2019, 572: 501-516.
[50]
SecciD, MolinoL, ZaniniA. Contaminant source identification in groundwater by means of artificial neural network[J]. Journal of Hydrology, 2022, 611: 128003.