三维荧光光谱结合IGOA-SVM分类鉴别油类污染物

doi:10.3964/j.issn.1000-0593(2024)04-1031-08

Abstract
References
Related Citation (15)

Download: PDF (9855 KB)
Export: BibTeX | EndNote (RIS)

Abstract Oil spill pollution is a typical form of environmental pollution in today's era of rapid development, which harms biodiversity and human safety through multiple channels. Therefore, given the composition and characteristics of oil pollutants, it is particularly critical to improve the ecological environment and ensure the steady development of the economy and society by using multi-method cross-fusion to detect them in real-time, accurately and efficiently. Three-dimensional fluorescence spectroscopy is widely used in the substance detection field with fluorescence characteristics with its advantages of high detection accuracy, good real-time performance, simple operation and small interference. Three-dimensional fluorescence spectroscopy combined with a support vector machine and other algorithms have achieved good results in material classification and identification and concentration prediction, but there are still defects, such as slow convergence speed and easy fall into local optimum. A new method for the classification and identification of oil pollutants was proposed by combining a three-dimensional fluorescence spectrum with a support vector machine algorithm ( IGOA-SVM ) optimized by an improved grasshopper algorithm. Firstly, with 0.1 mol·L^-1 sodium dodecyl sulfate as a solvent, 0# diesel oil, 95# gasoline and kerosene were prepared into 20 and 18 mixed samples of 0# diesel oil and 95# gasoline, 0# diesel oil and kerosene, and 20 mixed samples of three components. Half of each was taken as a training set and a test set. The fluorescence data of the mixed solution were collected by an F-7000 fluorescence spectrometer. Matlab analyzed the standard solution of the three oils and the mixed solution. It was found that the fluorescence spectra had different degrees of overlap within a certain range, and it could not be accurately identified by spectral detection alone. Finally, the grasshopper optimization algorithm is improved by combining chaotic initialization, elite optimization, and differential evolution algorithms. The fluorescence peak data in the excitation wavelength 270 nm and emission wavelength 270~450 nm are extracted as the input value of training. With three kinds of classification labels as output, the data are input into the grasshopper optimization algorithm support vector machine (GOA-SVM), particle swarm optimization support vector machine (PSO-SVM) and genetic algorithm optimization support vector machine (GA-SVM) for training. The IGOA-SVM model is superior to GOA-SVM, PSO-SVM and GA-SVM in convergence speed, stability and ability to jump out of local optimum, providing a new idea for accurately identifying oil contaminants.

Key words：Three-dimensional fluorescence spectrum;Improved grasshopper optimization algorithm;Support vector machine;Petroleum pollutants

Received: 2022-11-28 Accepted: 2023-06-12

ZTFLH:

O657.3

Corresponding Authors: ZHU Yan-ping E-mail: YanpingZhu2021@163.com

Cite this article:

CHENG Peng-fei,ZHU Yan-ping,PAN Jin-yan, et al. Classification of Oil Pollutants by Three-Dimensional Fluorescence Spectroscopy Combined With IGOA-SVM[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(04): 1031-1038.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2024)04-1031-08 OR https://www.gpxygpfx.com/EN/Y2024/V44/I04/1031

[1] Chen J H，Di Z J，Shi J，et al. Journal of Cleaner Production，2020，273：122978.
[2] Akinwumiju A S，Adelodun A A，Ogundeji S E. Environmental Pollution，2020，267：115545.
[3] Hung C M，Chen C W，Huang C P，et al. Bioresource Technology，2022，355：127246.
[4] CHEN Ying，DUAN Wei-liang，YANG Ying，et al（陈颖，段玮靓，杨英，等）. Acta Optica Sinica（光学学报），2022，42(12)：1230001.
[5] Periasamy S，Ravi K P，Tansey K. Remote Sensing of Environment，2022，279：113144.
[6] WANG Shu-tao，LIU Na，CHENG Qi，et al（王书涛，刘娜，程琪，等）. Spectroscopy and Spectral Analysis（光谱学与光谱分析），2020，40(4)：1149.
[7] Huang W C，Liu H Y，Zhang Y，et al. Applied Soft Computing，2021, 109：107541.
[8] Zhou Y，Liu Y Y，Wang N，et al. Measurement，2022，201：111737.
[9] Zhang J Q，Zhang J，Zhong M，et al. Measurement，2020，163：108067.
[10] SONG Chang-xin，MA Ke（宋长新，马克）. Techniques of Automation and Applications（自动化技术与应用），2022，41(3)：12.
[11] WANG Sheng-sheng，ZHANG Wei，DONG Ru-yi，et al（王生生，张伟，董如意，等）. Journal of Northeastern University(Natural Science)[东北大学学报(自然科学版)]，2020，41(2)：170.
[12] Arrif T，Hassani S，Guermoui M，et al. Renewable Energy，2022，192：745.
[13] YANG Xiao-min（杨晓敏）. Journal of Electronic Measurement and Instrumentation（电子测量与仪器学报），2021，35(3)：211.
[14] Wu Z Q，Shen D D. Optik，2021，247：167979.
[15] WU Zhong-qiang，SHEN Dan-dan，SHANG Meng-yao，et al（吴忠强，申丹丹，尚梦瑶，等）. Acta Metrologica Sinica（计量学报），2020，41(12)：1536.
[16] Ahmad M F，Mat Isa N A，Lim W H，et al. Alexandria Engineering Journal，2022，61(12)：11835.
[17] CHENG Zhen，SI Gan-shang，LI Zhen-gang, et al（程真，司赶上，李振钢，等）. Acta Optica Sinica（光学学报），2022，42(9)：0930004.