|本期目录/Table of Contents|

[1]张传利,吴 鹏*,李思悦,等. 融合差分进化与粒子群优化的磷化工污染土壤扩散预测方法 [J].武汉工程大学学报,2026,48(03):261-269.[doi:10.19843/j.cnki.CN42-1779/TQ.202603017]
点击复制

融合差分进化与粒子群优化的磷化工污染土壤扩散预测方法

(/HTML)

《武汉工程大学学报》[ISSN:1674-2869/CN:42-1779/TQ]

卷:
48
期数:
2026年03期
页码:
261-269
栏目:
磷化工论坛
出版日期:
2026-06-30

文章信息/Info

Title:
-
文章编号:
1674 - 2869(2026)03 - 0261 - 09
作者:
张传利1吴 鹏*1李思悦2高 峰3李 亮*4
1.湖北数字文旅集团有限公司,湖北 武汉 430061;
2.武汉工程大学环境生态与生物工程学院,湖北 武汉 430205;
3.武汉工程大学校长办公室,湖北 武汉 430205;
4.武汉工程大学化学与环境工程学院,湖北 武汉 430205


Author(s):
-



关键词:
土壤污染磷化工扩散预测差分进化粒子群优化
Keywords:
-
分类号:
X53;X11;TP18
DOI:
10.19843/j.cnki.CN42-1779/TQ.202603017
文献标志码:
A
摘要:
尽管在土壤污染扩散的高精度预测方面已取得一定进展,但如何在复杂环境中有效融合多维度因子并兼顾参数优化的全局搜索与局部精细能力,仍然是提升预测模型性能的关键。针对磷化工污染土壤扩散预测中多环境影响因子建模不足、单一优化算法易陷入局部最优等问题,提出一种融合差分进化(DE)与粒子群优化(PSO)预测方法DE-PSO。该方法通过定期样本采集与传感器实时监测获取多维度数据,采用线性回归与最小二乘法对传感数据进行校准。构建融合土壤温度、湿度、pH值等环境因子的污染扩散机理模型,并设计DE与PSO的交替迭代机制对模型关键参数进行协同优化。实验结果表明:在对镉、氟化物等磷化工典型污染物的扩散预测中,以镉为例,该方法的预测均方根误差(RMSE)低至0.033 9,决定系数达0.971,收敛迭代次数仅为70次,预测精度与计算效率均显著优于单一DE、单一PSO及传统遗传算法。该方法为复杂环境下土壤污染扩散的高精度、实时预测提供了新的技术路径。


Abstract:


参考文献/References:

[ 1 ] ARHOUNI F E, HAKKAR M, OUAKKAS S, et al. Evaluation of the physicochemical, heavy metal and radiological contamination from phosphogypsum discharges of the phosphoric acid production unit on the coast of El Jadida Province in Morocco [J]. Journal of Radioanalytical and Nuclear Chemistry, 2023, 332(10): 4019-4028.
[ 2 ] BOUARGANE B, LAABOUBI K, BIYOUNE M G, et al. Effective and innovative procedures to use phosphogypsum waste in different application domains: review of the environmental, economic challenges and life cycle assessment [J]. Journal of Material Cycles and Waste Management, 2023, 25(3): 1288-1308.
[ 3 ] HUANG M Y, WU T L, CUI P X, et al. Production of hydroxyl radicals (?OH) and its effect on cadmium solubility during soil redox fluctuations [J]. ACS ES&T Water, 2025, 5(4): 1663-1672.
[ 4 ] KOWALSKA J B, MAZUREK R, G SIOREK M, et al. Pollution indices as useful tools for the comprehensive evaluation of the degree of soil contamination:a review [J]. Environmental Geochemistry and Health, 2018, 40(6): 2395-2420.
[ 5 ] 王薇, 曾光明, 秦肖生. 遗传模拟退火算法在水质模型参数估值中的应用研究[J]. 环境工程, 2003, 21(4): 60-62.
[ 6 ] 王伟, 何东之. 基于非线性和遗传变异的灰狼优化算法[J]. 合肥工业大学学报(自然科学版), 2021, 44(2): 199-205.
[ 7 ] 孙士平, 吴建军. 直接搜索模拟退火算法的自适应改进[J]. 计算机工程与应用, 2015, 51(23): 31-37.
[ 8 ] LOCONSOLE D, ELIA M, CONVERSA G, et al. Soil moisture sensing technologies: principles, applications, and challenges in agriculture [J]. Agronomy, 2025, 15(12): 2788.
[ 9 ] 周凤玺, 罗玚, 马强. 温度梯度作用下非饱和土中铅离子迁移机理研究[J]. 岩土工程学报, 2023, 45(9): 1822-1830.
[10] 韩束丹, 田雨波, 李睿, 等. 融合随机因子的协方差自适应进化策略[J]. 江苏科技大学学报(自然科学版), 2022, 36(3): 59-63.
[11] BANERJEE P, BEHERA P, BANSODE S, et al. Performance analysis of soil sensors: accuracy, variability, and repeatability [C]//2025 IEEE Applied Sensing Conference (APSCON). Hyderabad, India: IEEE, 2025: 311-314.
[12] GRENZD?RFFER G J, WIENKEN J S, STEIGER A. Spatial and temporal field-scale accuracy assessment of a multi-sensor spade for in situ soil diagnostics: performance and limitations of the stenon FarmLab for precision agriculture [J]. Sensors, 2025, 25(24): 7430.
[13] SALGOTRA R, CHAUDHARY R, VERMA P, et al. The rise of particle swarm optimization: a systematic bibliometric & thematic review (1995-2025) [J]. Archives of Computational Methods in Engineering, 2026: 10532.
[14] SHARMA R, MATHARU J S, PARMAR K S. A survey on particle swarm optimization: evolution, adaptations and practical implementations [J]. Applied Soft Computing, 2026, 186: 114016.
[15] ABUALIGAH L. Particle swarm optimization: advances, applications, and experimental insights [J]. Computers, Materials & Continua, 2025, 82(2): 1539-1592.
[16] XU H R, DENG Q W, ZHANG Z Y, et al. A hybrid differential evolution particle swarm optimization algorithm based on dynamic strategies [J]. Scientific Reports, 2025, 15: 4518.
[17] OPARA K R, ARABAS J. Differential evolution: a survey of theoretical analyses [J]. Swarm and Evolutionary Computation, 2019, 44: 546-558.
[18] YANG Y, CHEN Y H, WANG Y C, et al. Modelling a combined method based on ANFIS and neural network improved by DE algorithm: a case study for short-term electricity demand forecasting [J]. Applied Soft Computing, 2016, 49: 663-675.
[19] ALJAIDI M, JANGIR P, ARPITA, et al. A two phase differential evolution algorithm with perturbation and covariance matrix for PEMFC parameter estimation challenges [J]. Scientific Reports, 2025, 15: 8676.
[20] 朱武. 基于种群自适应策略的差分演化算法及其应用研究[D]. 上海: 东华大学, 2013.
[21] 辛斌, 陈杰. 粒子群优化与差分进化混合算法的综述与分类[J]. 系统科学与数学, 2011, 31(9): 1130-1150.
[22] YU X B, CAO J, SHAN H Y, et al. An adaptive hybrid algorithm based on particle swarm optimization and differential evolution for global optimization [J]. The Scientific World Journal, 2014, 2014(1): 215472.
[23] SHANG J, LI G Y. A hybrid composite differential evolution and multiobjective particle swarm optimization evolutionary algorithm and its application [J]. IEEE Access,2024,12:74417-74431.
[24] 马乐杰, 邹德旋, 李灿, 等. 融合差分进化和Sine混沌的改进粒子群算法[J]. 计算机工程与应用, 2024, 60(19): 80-96.


相似文献/References:

[1]杨嘉谟,胡玲,程媛媛.磷化工生产节能减排的有效途径[J].武汉工程大学学报,2009,(12):51.
 YANG Jia mo,HU Ling,CHEN Yuan yuan.Effective way of energysaving and pollutant emission reductionin phosphorus chemical industry[J].Journal of Wuhan Institute of Technology,2009,(03):51.
[2]路小彬,张 杰,徐 平,等.高浓度磷氟砷磷化工废水的处理工艺[J].武汉工程大学学报,2017,39(06):633.[doi:10. 3969/j. issn. 16742869. 2017. 06. 019]
 LU Xiaobin,ZHANG Jie,XU Ping,et al.Treatment Process for Phosphorus Chemical Industry Wastewater with High Concentration of Phosphorus, Fluorine and Arsenic[J].Journal of Wuhan Institute of Technology,2017,39(03):633.[doi:10. 3969/j. issn. 16742869. 2017. 06. 019]

备注/Memo

备注/Memo:
收稿日期:2026-03-30
基金项目:湖北省农业微生物产业发展重大专项揭榜挂帅项目(NYWSWZX2025-2027-09)
作者简介:张传利,硕士,工程师。Email:zclsingle@qq.com
*通信作者:吴 鹏,硕士,架构师。Email:wp19851101@163.com
李 亮,博士,高级实验师。Email:LL121789574@163.com

更新日期/Last Update: 2026-06-26