浏览全部资源
扫码关注微信
宁波大学 机械工程与力学学院,浙江 宁波 315211
赵永杰,博士,讲师,研究方向:机器视觉理论与工业研究,E-mail:zhaoyongjie@nbu.edu.cn
收稿日期:2024-08-27,
修回日期:2024-11-14,
纸质出版日期:2025-06-15
移动端阅览
潘涛,赵永杰.基于机器学习的多种重金属离子同时检测[J].分析测试学报,2025,44(06):1066-1074.
PAN Tao,ZHAO Yong-jie.Simultaneous Detection of Multiple Heavy Metal Ions Based on Machine Learning[J].Journal of Instrumental Analysis,2025,44(06):1066-1074.
潘涛,赵永杰.基于机器学习的多种重金属离子同时检测[J].分析测试学报,2025,44(06):1066-1074. DOI: 10.12452/j.fxcsxb.240827346.
PAN Tao,ZHAO Yong-jie.Simultaneous Detection of Multiple Heavy Metal Ions Based on Machine Learning[J].Journal of Instrumental Analysis,2025,44(06):1066-1074. DOI: 10.12452/j.fxcsxb.240827346.
该研究将机器学习技术与方波脉冲振荡伏安法(SWASV)相结合,来提高对Cd
2+
、Pb
2+
、Cu
2+
和Hg
2+
四种重金属离子的同时检测能力。传统的电化学方法在检测重金属离子时主要依赖于在一定浓度范围内寻找线性响应区间,并且在多离子环境下,SWASV曲线常出现干扰,导致准确性降低。该研究使用裸玻碳电极对不同浓度的金属离子溶液进行重复性的SWASV检测,对检测数据进行电流值、峰值电压和峰面积等重要参数进行特征提取,并结合极端梯度提升(XGBoost)和随机森林(RF)构建浓度预测模型,使用支持向量机(SVM)进行分类预测。分类算法中SVR的效果最佳(四种离子的ROC曲线下面积均大于0.95),相较RF模型XGBoost浓度预测模型预测值和真实值间的拟合度(R-Squared)均达到0.95以上。通过结合SWASV和机器学习,能够在复杂的离子混合体系中实现高精度的离子检测,并有效提高了检测结果的可靠性。本研究的成果为多重重金属离子的环境监测和污染控制提供了创新的
解决方案,并在电化学分析领域展示了机器学习的应用潜力。
In this study,we explored the combination of machine learning techniques and square wave anodic stripping voltammetry(SWASV) to improve the simultaneous detection of four heavy metal ions:Cd
2+
,Pb
2+
,Cu
2+
,and Hg
2+
. Traditional electrochemical methods mainly rely on finding a linear response interval within a certain concentration range when detecting heavy metal ions,and in a multi-ionic environment,the SWASV curve often interferes,resulting in reduced accuracy. In this study,bare glassy carbon electrodes were used to detect repeatable SWASV of different concentrations of metal ion solutions,and important parameters such as current value,peak voltage and peak area were extracted from the detection data,and the concentration prediction model was constructed by combining extreme gradient boosting(XGBoost) and random forest(RF),and the support vector machine(SVM) was used. Among the machine learning classification algorithms,the SVR algorithm has the best effect (the area under the ROC curve of the four ions is greater than 0.95),and the fit degree(R-Squared) between the predicted value and the true value of the XGBoost concentration prediction model of the RF model is more than 0.95. By combining SWASV and machine learning,it is possible to achieve high-precision ion detection in complex ion mixing systems and improve the reliability of detection results. The results of this study provide an innovative solution for environmental monitoring and contamination control of multiple heavy metal ions,and demonstrate the application potential of machine learning in the field of electrochemical analysis.
Sun H J . Environ. Dev. (孙华杰. 环境与发展), 2019 , 31 ( 9 ): 57 - 58 .
Guo C , Xiao H , Li B L , Luo H Q , Li L B . Sens. Actuators B , 2016 , 237 : 570 - 574 .
Guo Z , Wang H , Liu G , Wang Z Q . Sens. Actuators B , 2016 , 235 : 67 - 73 .
Kitte S A , Li S P , Nsabimana A , Gao W Y , Lan J P , Liu Z Y , Xun B G . Talanta , 2019 , 191 : 485 - 490 .
Han Y J , Dai Z P , Zheng X F , Guo Y J . Chin . J. Anal. Chem. (韩玉洁,代志鹏,郑晓芳,郭玉晶. 分析化学) , 2022 , 50 ( 2 ): 206 - 216 .
Fan Q J , Du G R , Tu J R . J. Tianjin Univ. (范清杰,杜国荣,涂家润. 天津大学学报) , 2013 , 46 ( 2 ): 145 - 149 .
Liu N , Ye W S , Liu G , Guo Z . Anal. Chim. Acta , 2022 , 1213 : 339956 .
Liu N , Guo Z , Liu G . J. Electroanal. Chem. , 2021 , 889 : 115227 .
Mandal S , Paul D , Saha S , Das P . Environ. Sci. Nano. , 2022 , 9 ( 7 ): 2596 - 2606 .
Ni Y N , Qiu P , Kokot S . Anal. Chim. Acta , 2004 , 516 ( 1/2 ): 7 - 17 .
Ni Y N , Qiu P , Kokot S . Anal. Chim. Acta , 2005 , 537 ( 1/2 ): 321 - 330 .
Ni Y N , Wang Y R , Kokot S . Talanta , 2006 , 69 ( 1 ): 216 - 225 .
Cabanillas A G , Cáceres M I R , Cañas M A M , Burguillos J M O , Díaz T G . Talanta , 2007 , 72 ( 3 ): 932 - 940 .
González M J G , Renedo O D , Martínez M J A . Talanta , 2007 , 71 ( 2 ): 691 - 698 .
Moneeb M S . Talanta , 2006 , 70 ( 5 ): 1035 - 1043 .
Ji Q , Lu L P . Chin. J. Anal. Chem. (纪权,鲁理平. 分析化学), 2023 , 51 ( 12 ): 1915 - 1923 .
Yin Y , Bo J J , Yu H C , Xiong Z Z , Tao K . J. Nucl. Agric. Sci. (殷勇,薄娟娟,于慧春. 核农学报), 2013 , 27 ( 05 ): 641 - 646 .
Feng X R , Qu G Q . Comput . Eng. Des. (冯晓荣,瞿国庆. 计算机工程与设计), 2019 , 40 ( 9 ): 2494 - 2501 .
Wan Y C , Guo Y , Jian W , Zhan Z , Zou H M . J. Basic Sci. Eng. (王迎超,郭崟,姜雯,张政,邹鹤民. 应用基础与工程科学学报), 2024 , 32 ( 4 ): 957 - 971 .
Han X G , Zhang H Y , Ling W S , Zhao Y G , Pu Y Z , Meng J B , Cao C , Miao X . Mod. Manuf. Eng. (韩新港,张海云,林伟盛,赵玉刚,浦业状,孟建兵,曹辰,苗旭. 现代制造工程), 2022 , 45 ( 10 ): 8 - 13 .
Liu Z , Sun L S , Yu J , Lu N , Xu Y , Guo M . Chin . J. Biomed. Eng. (刘哲,孙乐圣,于骏,陆拧,徐莹,郭淼. 中国生物医学工程学报), 2022 , 41 ( 4 ): 452 - 461 .
Zhang Y T , Cheng H H , Li H , Wang X L , Zhou N D . J . Instrum. Anal. (张雨婷,陈灏翰,李惠,王晓丽,周楠迪. 分析测试学报), 2022 , 41 ( 11 ): 1629 - 1635 .
Li X D , Cao K R , Kuang H B . J. Transportation Syst. Eng. Inf. Technol. (李晓东,曹克让,匡海波.交通运输系统工程与信息), 2024 , 24 ( 6 ): 159 - 168 .
Niu Y , Gao Y , Li T , Wang W X , Mo D Y L , Song Y F . Failure Anal. Prev. (牛寅,高扬,李涛,万文轩,穆迪奕龙,宋云飞. 失效分析与预防), 2024 , 19 ( 4 ): 242 - 249 .
Wang Z D , Wang Z F , Li Z Y , Miao P Y , Wu L Y . J. Vib. Shock. (王昭栋,王自法,李兆焱,苗鹏宇,吴禄源. 振动与冲击), 2024 , 43 ( 5 ): 82 - 93 .
0
浏览量
42
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构