基于粒子群算法-支持向量机-激光诱导击穿光谱技术对稻壳中铬元素的定量分析模型

引用本文: 周华茂, 陈添兵, 刘木华, 徐将, 何秀文, 许方豪, 姚明印. 基于粒子群算法-支持向量机-激光诱导击穿光谱技术对稻壳中铬元素的定量分析模型[J]. 分析化学, 2020, 48(6): 811-816. doi: 10.19756/j.issn.0253-3820.191731 shu

Citation: ZHOU Hua-Mao, CHEN Tian-Bing, LIU Mu-Hua, XU Jiang, HE Xiu-Wen, XU Fang-Hao, YAO Ming-Yin. Quantitative Analysis of Chromium in Rice Husks by Laser Induced Breakdown Spectroscopy Based on Particle Swarm Optimization-Support Vector Machine[J]. Chinese Journal of Analytical Chemistry, 2020, 48(6): 811-816. doi: 10.19756/j.issn.0253-3820.191731 shu

基于粒子群算法-支持向量机-激光诱导击穿光谱技术对稻壳中铬元素的定量分析模型

江西农业大学生物光电及应用实验室, 江西省现代农业装备重点实验室, 南昌 330045
基金项目:
本文系国家自然科学基金项目（No.31772072）和江西省教育厅项目（No.GJJ160404）资助

摘要: 为了对稻壳中重金属铬（Cr）含量进行快速测定，利用激光诱导击穿光谱技术（LIBS）获取了江西省鄱阳湖周边24组水田污染区稻壳中Cr元素的等离子体信号光谱数据。通过在422.04~445.94 nm波段范围内构建光谱九点平滑和归一化数据预处理，选择18组数据作为训练样本，另外6组作为测试样本，提出了基于粒子群算法（PSO）的支持向量机（SVM）参数调节优化方法。建立了PSO-SVM智能算法对Cr含量的LIBS定量分析模型，得到测试集均方根误差（RMSE）为7.83 μg/g，平均绝对误差百分比（MAPE）为4.10%，预测值与测定值之间的相关系数为0.9948。在同等条件下，采用联合区间偏最小二乘法（siPLS）预测6组样本浓度，其RMSE为22.58 μg/g，MAPE为6.17%，相关系数为0.9840。结果表明，PSO-SVM回归定量方法可用于LIBS农产品的成分分析，其分析效果优于siPLS。

关键词:

English

Quantitative Analysis of Chromium in Rice Husks by Laser Induced Breakdown Spectroscopy Based on Particle Swarm Optimization-Support Vector Machine

Key Laboratory of Optics-Electrics Application of Biomaterials of Jiangxi Agricultural University, Jiangxi Key Laboratory of Modern Agricultural Equipment, Nanchang 330045, China
Received Date: 11 December 2019
Revised Date: 19 March 2020
Fund Project:
This work was supported by the National Natural Science Foundation of China (No.31460419) and the Project of Jiangxi Education Department (No. GJJ160404).

Abstract: To rapidly determine Cr content in rice husks, laser induced breakdown spectroscopy (LIBS) was used to obtain plasma signal spectral data of Cr elements of rice in 24 groups of polluted paddy fields around Poyang Lake, Jiangxi Province. By constructing nine-point smoothing and normalized spectral pretreatment in the band range of 422.04-445.94 nm, 18 groups were selected as training samples and the other 6 groups as test samples, and thus a support vector machine (SVM) parameter adjustment optimization method based on particle swarm optimization (PSO) was proposed. The LIBS quantitative analysis model of Cr content by PSO-SVM intelligent algorithm was established, and the root mean square error (RMSE) of test set was 7.83 μg/g, the average absolute error percentage (MAPE) was 4.10%, the correlation coefficient between predicted value and true value was 0.9948. Under the same conditions, partial least square method (siPLS) was used to predict the concentration of 6 groups of samples, and it was found that the RMSE was 22.58 μg/g, the MAPE was 6.17%, and the correlation coefficient was 0.9840. The analysis results showed that the PSO-SVM regression quantitative method could be applied to the composition analysis of LIBS agricultural products, and its analysis effect was improved compared with siPLS.

Key words:

Laser induced breakdown spectroscopy
/ Particle swarm optimization-support vector machine
/ Chromium
/ Rice husk

1. [1]
  WANG Xiao-Bo, LI Jian-Guo, LIU Dong-Ying, QIU Yan-Jun, CHEN Rui-Tao. Chinese Journal of Food Hygiene,2015,27(1):75-78 王晓波,李建国,刘冬英,邱艳君,陈锐涛.中国食品卫生杂志,2015,27(1):75-78
2. [2]
  SHENTU Ping-Ping, LUO Jin-Bin, CHEN Gao-Shang, CAO Li-Jun, CHEN Shuang. Zhejiang Journal of Preventive Medicine, 2014,26(2):128-132 申屠平平,罗进斌,陈高尚,曹丽军,陈爽.浙江预防医学,2014,26(2):128-132
3. [3]
  LIU Qiang, HOU Ye-Mao, ZHANG Hu, ZHENG Kun, ZHANG Juan, TIAN Yuan, WANG Shao-Wen. Grain Processing, 2013,38(3):39-42 刘强,侯业茂,张虎,郑坤,张娟,田原,王绍文.粮食加工,2013,38(3):39-42
4. [4]
  SUN Nan, TIAN Wei-Wei, ZHANG Ying, TIAN Jia-Li. Transactions of the Chinese Society of Agricultural Engineering, 2016,32(13):197-205 孙楠,田伟伟,张颖,田佳丽.农业工程学报,2016,32(13):197-205
5. [5]
  CHEN Ya-Ya, LIN Qin-Lu, LUO Fei-Jun. Journal of Cereals & Oils, 2017,30(4):1-4 陈娅娅,林亲录,罗非君.粮食与油脂,2017,30(4):1-4
6. [6]
  Peng J Y, He Y, Jiang J D, Zhao Z F, Zhou F, Liu F. Food Chem., 2019,295:327-333
7. [7]
  Moncayo S, Manzoor S, Rosales J D, Anzano J, Caceres J O. Food Chem., 2017,232:322-328
8. [8]
  Cheng X, Yang X Y, Zhu Z H, Guo L B, Li X Y, Lu Y F, Zeng X Y. Appl. Optics, 2017,56(33):9144-9149
9. [9]
  Sun L X, Yu H B, Cong Z B, Lu H, Cao B, Zeng P, Dong W, Li Y. Spectrochim. Acta B, 2018,142:29-36
10. [10]
  Moncayo S, Trichard F, Busser B, Sabatier-Vincent M, Pelascini F, Pinel N, Motto-Ros V. Spectrochim. Acta B, 2017,133:40-44
11. [11]
  Busser B, Moncayo S, Coll J L, Sancey L, Motto-Ros V. Coordin. Chem. Rev., 2018,358:70-79
12. [12]
  Yuan T B, Wang Z, Li Z, Ni W D, Liu J M. Anal. Chim. Acta, 2014,807:29-35
13. [13]
  CHEN Tian-Bing, LIU Mu-Hua, HUANG Lin, ZHOU Hua-Mao, WANG Cai-Hong, YANG Hui, HU Hui-Qin, YAO Ming-Yin. Chinese J. Anal. Chem., 2016,44(7):1029-1034 陈添兵,刘木华,黄林,周华茂,王彩虹,杨晖,胡慧琴,姚明印.分析化学,2016,44(7):1029-1034
14. [14]
  Li K H, Guo L B, Li C M, Li X Y, Shen M, Zheng Z, Yu Y, Hao R F, Hao Z Q, Zeng Q D. J. Anal. Atom. Spectrom., 2015,30(7):1623-1628
15. [15]
  El Haddad J, Bruyère D, Ismaël A, Gallou G, Laperche V, Michel K, Bousquet B. Spectrochim. Acta B, 2014,97:57-64
16. [16]
  SHA Wen, LI Jiang-Tao, LU Cui-Ping, ZHENG Chun-Hou. Spectroscopy and Spectral Analysis, 2019,39(6):1958-1964 沙文,李江涛,鲁翠萍,郑春厚.光谱学与光谱分析,2019,39(6):1958-1964
17. [17]
  DONG Mei-Rong, WEI Li-Ping, LU Ji-Dong, LI Wen-Bing, LU Sheng-Zi, HUANG Jian-Wei, LI Shi-Shi, LUO Fa-Sheng, NIE Jia-Lang. Spectroscopy and Spectral Analysis., 2019,39(7):2202-2209 董美蓉,韦丽萍,陆继东,黎文兵,陆盛资,黄健伟,李诗诗,骆发胜,聂嘉朗.光谱学与光谱分析, 2019,39(7):2202-2209
18. [18]
  Lu S Z, Dong M R, Huang J W, Li W B, Lu J D, Li J. Spectrochim. Acta B, 2018,140:35-43
19. [19]
  ZHU Yi-Ning, YANG Ping, YANG Xin-Yan, LI Jia-Ming, HAO Zhong-Qi, LI Qiu-Shi, GUO Lian-Bo, LI Xiang-You, ZENG Xiao-Yan, LU Yong-Feng. Chinese J. Anal. Chem., 2017,45(3):336-341 朱毅宁,杨平,杨新艳,李嘉铭,郝中骐,李秋实,郭连波,李祥友,曾晓雁,陆永枫.分析化学,2017,45(3):336-341
20. [20]
  WANG Chun-Long, LIU Jian-Guo, ZHAO Nan-Jing, MA Ming-Jun, WANG Yin, HU Li, ZHANG Da-Hai, YU Yang, MENG De-Shuo, ZHANG Wei, LIU Jing, ZHANG Yu-Jun, LIU Wen-Qing. Acta Optica Sinica, 2013,33(3):314-319 王春龙,刘建国,赵南京,马明俊,王寅,胡丽,张大海,余洋,孟德硕,章炜,刘晶,张玉钧,刘文清.光学学报, 2013,33(3):314-319
21. [21]
  Zhang T L, Wu S, Dong J, Wei J, Wang K, Tang H S, Yang X F, Li H. J. Anal. Atom. Spectrom., 2015,30(2):368-374
22. [22]
  JIN Ye, YANG Kai, WU Yong-Jiang, LIU Xue-Song, CHEN Yong. Chinese J. Anal. Chem., 2012,40(6):925-931金叶,杨凯,吴永江,刘雪松,陈勇.分析化学, 2012,40(6):925-931

扫一扫看文章

计量

PDF下载量: 9
文章访问数: 720
HTML全文浏览量: 79

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

基于粒子群算法-支持向量机-激光诱导击穿光谱技术对稻壳中铬元素的定量分析模型

English

Quantitative Analysis of Chromium in Rice Husks by Laser Induced Breakdown Spectroscopy Based on Particle Swarm Optimization-Support Vector Machine

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

基于粒子群算法-支持向量机-激光诱导击穿光谱技术对稻壳中铬元素的定量分析模型

English

Quantitative Analysis of Chromium in Rice Husks by Laser Induced Breakdown Spectroscopy Based on Particle Swarm Optimization-Support Vector Machine

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南： 你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

文章相关

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs