An Adaptive Lorentz Peak Fitting Method Based on GA-NSVM to Identify Overlapping Oeaks of Infrared Spectrum Absorption
LI Zhong-bing1,PANG Wei1,2,LIANG Hai-bo3,JIANG Chuan-dong1,DUAN Hong-ming1,LUO Yi4
1. School of Electrical and Information Engineering, Southwest Petroleum University, Chengdu, Sichuan 610500, China
2. Engineering Technology Research Institute, CNPC West Drilling Engineering Co. LTD, Urumqi, Xinjiang 830026, China
3. School of Mechanical and Electrical Engineering, Southwest Petroleum University, Chengdu, Sichuan 610500, China
4. Development Company of Xinjiang Oilfield Company, PetroChina, Karamay, Xinjiang 834000, China
Abstract A genetic algorithm-nonlinear support vector machine (GA-NSVM)-based adaptive Lorentz peak fitting method for infrared spectral overlapping peak identification is proposed. Based on the fundamental difference of the characteristic absorption line patterns of the elemental substance, the mixture spectrum is decomposed into multiple Lorentz single peaks, and the nonlinear support vector machine is used to perform multi-class screening on the multiple fitted single peaks, so as to determine absorption peaks for specific components. The feasibility of this method in the spectral identification and classification of highly similar molecular structures was demonstrated in the collected infrared spectrum data set of 400 alkane mixture samples. The experiment results show that the proposed method can effectively separate the infrared absorption peaks of methane, ethane, and propane in alkanes with good accuracy and robustness, and a stronger parameters interpretation ability. It can accelerate the application of spectral detection technology in the fields of biopharmaceuticals, food chemical industry, oil and gas exploration, etc., especially in analysis and applications containing homologous organic compounds.
LI Zhong-bing,PANG Wei,LIANG Hai-bo, et al. An Adaptive Lorentz Peak Fitting Method Based on GA-NSVM to Identify Overlapping Oeaks of Infrared Spectrum Absorption[J]. Acta Metrologica Sinica, 2023, 44(4): 622-629.
Jia G H, Zhang J J, Zheng H M. Study on Differential Optical Absorption Spectroscopy Data Processing Based on Discrete Spectrum Correction ［J］. Acta Metrologica Sinica, 2021, 42(8): 1081-1086.
Lü H Z, Ma R M, Zhang L, et al. Research on Accurate Measurement of Low Concentration Nitric Oxide in High Temperature Water-containing Flue Gas Based on FTIR Spectrometer ［J］. Acta Metrologica Sinica, 2021, 42(4): 526-531.
［5］
Yang, J D. Chemical ingredients analysis of ruminant Feed based on near infrared spectrum analysis technology ［J］. Agro Food Industry Hi-Tech, 2017, 28(1): 951-956.
Qi R B, Yin X, Yang L, et al. Application of NIR Spectroscopy to Multiple Gas Components Identification ［J］. Spectroscopy and Spectral Analysis, 2008, 28(12): 2855-2858.
Wang L C. Quantitative Method of Fourier Transform Infrared Spectroscopy for Disaster Gases in Coalmine ［J］. Safety of Coal Mines, 2017, 48(3): 13-17.
Liu L X, Huan H T, Mandelis A, et al. Multiple Dissolved Gas Analysis in Transformer Oil Based on Fourier Transform Infrared Photoacoustic Spectroscopy ［J］. Spectroscopy and Spectral Analysis, 2020, 40(3): 684-687.
Shen Y, Shao K M, Wu J, et al. Optical gas detection: key technologies and applications review ［J］. Opto-Electronic Engineering, 2020, 47(4): 3-18.
Wang X, Wang X R, Liu C, et al. Research and Application of Industrial Online Gas Detector Based on STM32F4 ［J］. Instrument Technique and Sensor, 2019,(5): 38-42.
Zhu J, Liu W Q, Liu J G, et al. Quantitative gas analysis using Fourier transform infrared spectroscopy method ［J］. Chinese Journal of Scientific Instrument, 2007,(1): 80-85.
Zhao J H, Gao M L, Wei Z J, et al. Study on the quantitative analysis of multi-component toxic gases based on FTIR ［J］. Journal of Safety and Environment, 2011, 11(1): 131-135.
Zhang A J. Study of Infrared Spectroscopy Quantitative Analysis Method for Methane Gas Based on Data Mining ［J］. Spectroscopy and Spectral Analysis, 2013, 33(10): 2646-2650.
Duan X L, Wang M Q. Quantitative Analysis of Multi-Component Gases in Underground by Improved PSO-SVM Algorithm ［J］. Spectroscopy and Spectral Analysis, 2019, 39(9): 2883-2888.
Yuan J Y, Jiang C H, Wang Y, et al. Analysis Method of Formaldehyde in Nitrogen Gas Reference Material ［J］. Chemical Reagents, 2020, 42(4): 411-415.
Feng F, Wang F B, Xie F, et al. Implementation of Spectral Overlap Resolution Based on Wavelet Transforms and Gaussian Fitting ［J］. Acta Photonica Sinica, 2015, 44(6): 113-118.
Guo S G, Ling F X, Gao X F. Evaluation of Detection Limit and Uncertainty of Determination of Fatty Acid Methyl Esters in Diesel Fuels by Infrared Spectrometric Method ［J］. Acta Metrologica Sinica, 2021, 42(8): 1115-1120.
［17］
Mou Y, Zhou L, Huang H L, et al. Low-rank based infrared spectral feature extraction framework for quantitative analysis ［J］. Optik, 2018, 157: 343-352.
Safronov N I, SkorbovY V. Question of the effect of the background and the overlapping of absorption bands on the accuracy of quantitative infrared spectral analysis ［J］. Journal of Applied Spectroscopy, 1979, 30: 243-245.
Ru B, He S K, Li X T, et al. . Simulation of TDLAS Direct Absorption Based on HITRAN Database ［J］. Spectroscopy and Spectral Analysis, 2015, 35(1): 172-177.
2023, Vol. 44 
