Online adaptive wavelength selection method and its application in gasoline blending process

doi:10.11949/0438-1157.20201300

Abstract

Abstract:

The near-infrared spectroscopy analysis technology has been widely used in industry as a non-invasive analysis method. However, most of the wavelength selection methods of NIR models are established offline, which cannot effectively track the change of process characteristics. In this paper, a new online adaptive wavelength selection method, online adaptive interval Gaussian process regression (AIGPR), is proposed and applied in gasoline blending process. The proposed method can adjust the wavelength structure according to the characteristics of the query samples. In order to reduce the computing cost of online applications, the proposed method is divided into two parts: offline and online. In the offline part, the spectrum is divided into several wavelength intervals, and a local model is established in each wavelength interval to prepare for online application; in the online part, the query samples are segmented according to the division rules and used to calculate the wavelength importance index by the corresponding local model to obtain the optimal wavelength interval. The effectiveness of the method is proved on the gasoline data. Compared with the variable importance in the projection (VIP) method and the improved relation-variance(RV) method, AIGPR has better performance.

Key words: measurement, model, numerical analysis, NIR, wavelength selection, gasoline blending process, Gaussian process regression

摘要：

近红外光谱分析技术作为一种非侵入性的分析手段在工业上得到了广泛应用。然而，大多数近红外模型的波长选择方法是离线建立的，无法有效跟踪过程特性的变化。提出了一种新的在线自适应波长选择方法——在线自适应区间高斯过程回归波长选择方法（adaptive interval Gaussian process regression， AIGPR），并用于汽油调和过程中的近红外模型的建立。该方法可以根据待测样本的特性对波长结构进行调整。为了降低在线应用的计算成本，该方法分为离线和在线两个部分，离线部分将光谱分割成若干个波长区间，并在每个波长区间上建立局部模型，为在线应用做准备；在线部分中根据划分规则将采样得到待测样本光谱进行分割并代入相应的局部模型中计算波长区间重要性指标，获得最优波长区间。在汽油辛烷值的光谱数据上证明了该方法的有效性。与重要变量投影法和改进的相关系数法相比，该方法具有更好的性能。

关键词: 测量, 模型, 数值分析, 近红外光谱分析技术, 波长选择, 汽油调和, 高斯过程回归

CLC Number:

O 657.33

WANG Kai, DU Wenli, LONG Jian. Online adaptive wavelength selection method and its application in gasoline blending process[J]. CIESC Journal, 2021, 72(2): 1059-1066.

汪恺, 杜文莉, 隆建. 在线自适应波长选择方法及其在汽油调和过程中的应用[J]. 化工学报, 2021, 72(2): 1059-1066.

Figures/Tables 6

Fig.1 Online adaptive interval GPR wavelength selection method

Table 1 The prediction results of three methods

方法	R²	RMSEP	计算时间/s
VIP-PLS	0.7916	0.2143	—
RV-PLS	0.8312	0.1929	0.06
AIGPR-PLS	0.8372	0.1917	0.42

Fig.2 Wavelength selection results of three methods

Fig.3 Wavelength selection results of two samples

Table 2 The prediction results of NIR model with different step size

步长z	RMSEP
5	0.4239
10	0.3905
15	0.2743
20	0.2522
25	0.2035
30	0.2126
35	0.2159
40	0.2412
45	0.2602
50	0.2979

Fig.4 The prediction results of NIR model with different step size

References 31

1	雷萌, 李明. 采用KPCA特征提取的近红外煤炭发热量预测模型[J]. 化工学报, 2012, 63(12): 3991-3995.
	Lei M, Li M. NIRS prediction model of calorific value of coal with KPCA feature extract[J]. CIESC Journal, 2012, 63(12): 3991-3995.
2	吴文娟, 李东, 王国祥, 等. 血液在可见光及近红外范围内随温度变化的动态吸收特性[J]. 化工学报, 2013, 64(4): 1157-1162.
	Wu W J, Li D, Wang G X, et al. Dynamic optical absorption characteristic of human blood in visible- and near-infrared light with variable temperature[J]. CIESC Journal, 2013, 64(4): 1157-1162.
3	Marques E J N, de Freitas S T. Performance of new low-cost handheld NIR spectrometers for nondestructive analysis of umbu (Spondias tuberosa Arruda) quality[J]. Food Chem., 2020, 323: 126820.
4	Balabin R M, Safieva R Z. Gasoline classification by source and type based on near infrared (NIR) spectroscopy data[J]. Fuel, 2008, 87(7): 1096-1101.
5	He K X, Zhong M Y, Du W L. Weighted incremental minimax probability machine-based method for quality prediction in gasoline blending process[J]. Chemometrics Intell. Lab. Syst., 2020, 196:103909.
6	Wang Y F, Wang K, Zhou Z, et al. Modeling of oil near-infrared spectroscopy based on similarity and transfer learning algorithm[J]. Front. Chem. Sci. Eng., 2019, 13: 599-607
7	He K X, Cheng H, Du W L, et al. Online updating of NIR model and its industrial application via adaptive wavelength selection and local regression strategy[J]. Chemometrics Intell. Lab. Syst., 2014, 134: 79-88.
8	Liu J, Luan X L, Liu F. Adaptive JIT-Lasso modeling for online application of near infrared spectroscopy[J]. Chemometrics Intell. Lab. Syst., 2018, 183: 90-95.
9	He K X, Qian F, Cheng H, et al. A novel adaptive algorithm with near-infrared spectroscopy and its application in online gasoline blending processes[J]. Chemometrics Intell. Lab. Syst., 2015, 140: 117-125.
10	Agelet L E, Hurburgh C R. A tutorial on near infrared spectroscopy and its calibration[J]. J. Crit. Rev. Anal. Chem., 2010, 40(4): 246-260.
11	Killner M H M, Rohwedder J J R, Pasquini C. A PLS regression model using NIR spectroscopy for on-line monitoring of the biodiesel production reaction[J]. Fuel, 2011, 90(11): 3268-3273.
12	Chen Q, Zhao J, Liu M, et al. Determination of total polyphenols content in green tea using FT-NIR spectroscopy and different PLS algorithms[J]. J. Pharm. Biomed. Anal., 2008, 46(3): 568-573.
13	Cai W, Li Y, Shao X. A variable selection method based on uninformative variable elimination for multivariate calibration of near-infrared spectra[J]. Chemom. Intell. Lab. Syst., 2008, 90(2): 188-194.
14	Arakawa M, Yamashita Y, Funatsu K. Genetic algorithm-based wavelength selection method for spectral calibration[J]. J. Chemometr.. 2011, 25(1): 10-19.
15	Cao H, Zhou Y. Near-infrared spectra quantitative analysis for flue gas of thermal power plant based on wavelength selection[J]. Scientific Research and Essays., 2014, 9(9): 288-292.
16	Chong I G, Jun H C. Performance of some variable selection methods when multicollinearity is present[J]. Chemom. Intell. Lab. Syst., 2005, 78(1/2): 103-112.
17	Deng B C, Yun Y, Liang Y, et al. A novel variable selection approach that iteratively optimizes variable space using weighted binary matrix sampling[J]. Analyst, 2014, 139(19):4836-4845.
18	Wang K, Du W L, Long J. Near-infrared wavelength-selection method based on joint mutual information and weighted bootstrap sampling[J]. IEEE Trans. Ind. Inform., 2020, 16(9): 5884-5894.
19	Shan R, Cai W, Shao X. Variable selection based on locally linear embedding mapping for near-infrared spectral analysis[J]. Chemom. Intell. Lab. Syst., 2014, 131: 31-36.
20	Mehmood T, de Liland K H, Snipen L, et al. A review of variable selection methods in Partial Least Squares Regression[J]. Chemom. Intell. Lab. Syst., 2012, 118: 62-69.
21	Zou X B, Zhao J W, Li Y X. Selection of the efficient wavelength regions in FT-NIR spectroscopy for determination of SSC of ‘Fuji’apple based on BiPLS and FiPLS models[J]. Vib. Spectrosc., 2007, 44(2): 220-227.
22	Wang X F, Bao Y F, Liu G L, et al. Study on the best analysis spectral section of NIR to detect alcohol concentration based on SiPLS[J]. Procedia Engineering, 2012, 29: 2285-2290.
23	Jiang J H, Berry R J, Siesler H W, et al. Wavelength interval selection in multicomponent spectral analysis by moving window partial least-squares regression with applications to mid-infrared and near-infrared spectroscopic data[J]. Anal.Chem., 2002, 74(14): 3555-3565.
24	Deng B, Yun Y, Ma P, et al. A new method for wavelength interval selection that intelligently optimizes the locations, widths and combinations of the intervals[J]. Analyst, 2015, 140(6):1876-1885.
25	Kaneko H, Funatsu K. A new process variable and dynamics selection method based on a genetic algorithm-based wavelength selection method[J]. AIChE J., 2012, 58(6): 1829-1840.
26	Arakawaa M, Yamashitaa Y, Funatsu K. Genetic algorithm-based wavelength selection method for spectral calibration[J]. J. Chemom., 2010, 25(1): 10-19.
27	Rasmussen C E, Williams C K I. Gaussian Processes for Machine Learning[M]//Cambridge, MA: MIT Press, 2006: 67-75.
28	Chen T, Wang B. Bayesian variable selection for Gaussian process regression: application to chemometric calibration of spectrometers[J]. Neurocomputing, 2010, 73(13/14/15): 2718-2726.
29	Ni W, Nørgaard L, Mørup M. Non-linear calibration models for near infrared pectroscopy[J]. Anal. Chim. Acta, 2014, 813: 1-14.
30	Wang B, Shi J. Generalized Gaussian process regression model for non-Gaussian functional data[J]. J. Am. Stat. Assoc., 2014, 109(507): 1123-1133.
31	Le Gratiet L, Garnier J. Asymptotic analysis of the learning curve for Gaussian process regression[J]. Mach. Learn., 2015, 98(3): 407-433.

[1]	Jiahao SONG, Wen WANG. Study on coupling operation characteristics of Stirling engine and high temperature heat pipe [J]. CIESC Journal, 2023, 74(S1): 287-294.
[2]	Mengya LIAN, Yingying TAN, Lin WANG, Feng CHEN, Yifei CAO. Heating performance of air preheated integrated ground water heat pump air-conditioning system [J]. CIESC Journal, 2023, 74(S1): 311-319.
[3]	Zhenghao JIN, Lijie FENG, Shuhong LI. Energy and exergy analysis of a solution cross-type absorption-resorption heat pump using NH₃/H₂O as working fluid [J]. CIESC Journal, 2023, 74(S1): 53-63.
[4]	Hao WANG, Zhenlei WANG. Model simplification strategy of cracking furnace coking based on adaptive spectroscopy method [J]. CIESC Journal, 2023, 74(9): 3855-3864.
[5]	Ke LI, Jian WEN, Biping XIN. Study on influence mechanism of vacuum multi-layer insulation coupled with vapor-cooled shield on self-pressurization process of liquid hydrogen storage tank [J]. CIESC Journal, 2023, 74(9): 3786-3796.
[6]	Xianheng YI, Wu ZHOU, Xiaoshu CAI, Tianyi CAI. Measurable range of nanoparticle concentration using optical fiber backward dynamic light scattering [J]. CIESC Journal, 2023, 74(8): 3320-3328.
[7]	Xudong YU, Qi LI, Niancu CHEN, Li DU, Siying REN, Ying ZENG. Phase equilibria and calculation of aqueous ternary system KCl + CaCl₂ + H₂O at 298.2, 323.2, and 348.2 K [J]. CIESC Journal, 2023, 74(8): 3256-3265.
[8]	Chengying ZHU, Zhenlei WANG. Operation optimization of ethylene cracking furnace based on improved deep reinforcement learning algorithm [J]. CIESC Journal, 2023, 74(8): 3429-3437.
[9]	Linqi YAN, Zhenlei WANG. Multi-step predictive soft sensor modeling based on STA-BiLSTM-LightGBM combined model [J]. CIESC Journal, 2023, 74(8): 3407-3418.
[10]	Guoze CHEN, Dong WEI, Qian GUO, Zhiping XIANG. Optimal power point optimization method for aluminum-air batteries under load tracking condition [J]. CIESC Journal, 2023, 74(8): 3533-3542.
[11]	Jintong LI, Shun QIU, Wenshou SUN. Oxalic acid and UV enhanced arsenic leaching from coal in flue gas desulfurization by coal slurry [J]. CIESC Journal, 2023, 74(8): 3522-3532.
[12]	Yuying GUO, Jiaqiang JING, Wanni HUANG, Ping ZHANG, Jie SUN, Yu ZHU, Junxuan FENG, Hongjiang LU. Water-lubricated drag reduction and pressure drop model modification for heavy oil pipeline [J]. CIESC Journal, 2023, 74(7): 2898-2907.
[13]	Chunyu LIU, Huanyu ZHOU, Yue MA, Changtao YUE. Drying characteristics and mathematical model of CaO-conditioned oil sludge [J]. CIESC Journal, 2023, 74(7): 3018-3027.
[14]	Weiming SHAO, Wenxue HAN, Wei SONG, Yong YANG, Can CHEN, Dongya ZHAO. Dynamic soft sensor modeling method based on distributed Bayesian hidden Markov regression [J]. CIESC Journal, 2023, 74(6): 2495-2502.
[15]	Yanhui LI, Shaoming DING, Zhouyang BAI, Yinan ZHANG, Zhihong YU, Limei XING, Pengfei GAO, Yongzhen WANG. Corrosion micro-nano scale kinetics model development and application in non-conventional supercritical boilers [J]. CIESC Journal, 2023, 74(6): 2436-2446.