Modeling of oil near-infrared spectroscopy based on similarity and transfer learning algorithm

Abstract

Near-infrared spectroscopy mainly reflects the frequency-doubled and total-frequency absorption information of hydrogen-containing groups (O‒H, C‒H, N‒H, S‒H) in organic molecules for near-infrared lights with different wavelengths, so it is applicable to testing of most raw materials and products in the field of petrochemicals. However, the modeling process needs to collect a large number of laboratory analysis data. There are many oil sources in China, and oil properties change frequently. Modeling of each raw material is not only unfeasible but also will affect its engineering application efficiency. In order to achieve rapid modeling of near-infrared spectroscopy and based on historical data of different crude oils under different detection conditions, this paper discusses about the feasibility of the application of transfer learning algorithm and makes it possible that transfer learning can assist in rapid modeling using certain historical data under similar distributions under a small quantity of new data. In consideration of the requirement of transfer learning for certain similarity of different datasets, a transfer learning method based on local similarity feature selection is proposed. The simulation verification of spectral data of 13 crude oils measured by three different probe detection methods is performed. The effectiveness and application scope of the transfer modeling method under different similarity conditions are analyzed.

Graphical abstract

Keywords

near-infrared spectroscopy / transfer learning / similarity / modeling

References

[1] Yan Y L. The Basis and Application of Near Infrared Spectroscopy. Beijing: China Light Industry Press, 2005, 286–564 (in Chinese)

[2] Lu W Z. Modern Near Infrared Spectroscopy Analysis Technology. Beijing: China Petrochemical Press, 2007, 14–26 (in Chinese)

[3] Workman J Jr. A brief review of near infrared in petroleum product analysis. Journal of Near Infrared Spectroscopy, 1996, 4(1): 69

[4] Oja H. Multivariate Linear Regression. New York: Springer, 2010, 183–200

[5] Tormod N, Harald M. Principal component regression in NIR analysis: Viewpoint, background details and selection of components. Journal of Chemometrics, 1988, 2(2): 155–167

[6] Geladi P, Kowalski B R. Partial least-squares regression: a tutorial. Analytica Chimica Acta, 1985, 185(86): 1–17

[7] He Y, Li X, Deng X. Discrimination of varieties of tea using near infrared spectroscopy by principal component analysis and BP model. Journal of Food Engineering, 2007, 79(4): 1238–1242

[8] Shimodaira H. Improving predictive inference under covariate shift by weighting the log-likelihood function. Journal of Statistical Planning and Inference, 2000, 90(2): 227–244

[9] He Y. Modelling of near-infrared spectroscopy based on semi-supervised learning and transfer learning. Dissertation for the Doctor Degree. Shandong: Ocean University of China, 2012

[10] Pan S J, Yang Q. A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10): 1345–1359

[11] Weiss K, Khoshgoftaar T M, Wang D D. A survey of transfer learning. Journal of Big Data, 2016, 3(1): 9

[12] Tan B, Song Y, Zhong E, Yang Q. Transitive transfer learning. Acm Sigkdd International Conference on Knowledge Discovery & Data Mining, 2015, 1155–1164

[13] Tan B, Zhang Y, Pan S J, Yang Q. Distant domain transfer learning. Association for the Advance of Artificial Intelligence, 2017, 2604–2610

[14] Gao J. The application of near infrared spectroscopy in oil quality analysis. Dissertation for the Master Degree. Jiangsu: Nanjing Tech University, 2005, 11–12

[15] Karstang T V, Valheim K. Multivariate prediction and background correction using local modeling and derivative spectroscopy. Analytical Chemistry, 1996, 63(8): 767–772

[16] Zhao C H, Tian M H, Li J W. Research progress on spectral similarity metrics. Journal of Harbin Engineering University, 2017, 38(8): 1179–1189 (in Chinese)

[17] Wang C, Gong M, Zhang M, Chan Y. Unsupervised hyperspectral image band selection via column subset selection. IEEE Geoscience and Remote Sensing Letters, 2015, 12(7): 1411–1415

[18] Schlamm A, Messinger D. Improved detection clustering of hyperspectral image date by preprocessing with a euclidean distance transformation. WHISPERS, 2011, 1(2): 1–4

[19] Zhong Y, Lin X, Zhang L. A support vector conditional random fields classifier with a Mahalanobis distance boundary constraint for high spatial resolution remote sensing imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(4): 1314–1330

[20] Kruse F A, Lefkoff A B, Boardman J W, Heidebrecht K B, Shapiro A T, Barloon P J. The spectral image processing systems (SIPS)-interactive visualization and analysis of imaging spectrometer data. Aip Conference, 1993, 283(1): 192–201

[21] Chang C I. Spectral information divergence for hyperspectral image analysis. IEEE International Geoscience & Remote Sensing Symposium, 1999, 509–511

[22] Pan S J, Kwok J T, Yang Q, Pan J J. Adaptive localization in a dynamic WiFi environment through multi-view learning. Association for the Advance of Artificial Intelligence, 2007, 1108–1113

[23] Granahan J C, Sweet J N. An evaluation of atmospheric correction techniques using the spectral similarity scale. IEEE International Geoscience & Remote Sensing Symposium, 2001, 2022–2024

[24] Pan S J, Tsang I W, Kwok J T, Yang Q. Domain adaptation via transfer component analysis. IEEE Transactions on Neural Networks, 2011, 22(2): 199–210

[25] Breiman L. Bagging predictors. Machine Learning, 1996, 24(2): 123–140

[26] Dai W Y, Yang Q, Xue G R, Yu Y. Boosting for transfer learning. International Conference on Machine Learning, Corvalis, 2007, 238(6): 193–200

[27] Freund Y, Schapire R E. A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 1997, 55(1): 119–139

[28] Zhou S H, Du W L. Modeling of ethylene cracking furnace yields based on transfer learning. CIESC Journal, 2014, 65(12): 4921–4928

Acknowledgements

The financial supports from the National Natural Science Foundation of China (Major Program, Grant No. 61590923), National Science Fund for Distinguished Young Scholars (No. 61725301), the Fundamental Research Funds for the Central Universities and the Programme of Introducing Talents of Discipline to Universities (the 111 Project) under Grant B17017 are gratefully acknowledged.

RIGHTS & PERMISSIONS

2019 Higher Education Press and Springer-Verlag GmbH Germany, part of Springer Nature