Near Infrared Spectroscopy Analysis of Moisture in Engine Oil
LIU Ge1, CHEN Bin2*, SHANG Zhi-xuan2, QUAN Yu-xuan2
1. Hebei Key Laboratory of Hazardous Chemicals Safety and Control Technology, School of Chemical and Environmental Engineering, North China Institute of Science and Technology, Yanjiao 065201, China
2. School of Environmental Engineering, Hebei Key Laboratory of Safety Monitoring of Mining Equipment，North China Institute of Science and Technology, Yanjiao 065201, China
Abstract：Engine oil is the core component of the engine. It is easy to mix with water in the engine oil, which can easily accelerate the deterioration and deterioration of the engine oil, and then harms the safe operation of the engine. Detecting water in the engine oil is an important indicator to ensure the quality of the engine oil. Moisture is easy to accelerate the deterioration and degradation of engine oil, and it is harmful to the safe operation of the engine, and its detection is an important index to ensure the quality of engine oil. Therefore, near-infrared (NIR) spectroscopy combined with partial least squares (PLS) regression method was used to detect engine oil with different water content. Firstly, the mechanism of 931, 1 195~1 212 and 1 391~1 430 nm wavelengths with strong absorption peaks were analyzed according to the NIR characteristics of water-containing engine oil. Orthogonal signal correction (OSC) and several other spectral pretreatment methods were used to construct the PLS regression model, and the characteristic wavelength was selected according to the regression coefficient. The results showed that the PLS model pretreated by OSC had the better predictive ability, while the pretreated by MSC and SNV reduced the correction ability of the model. The 166 feature wavelengths were selected, accounting for 32.42% of the spectrum. The fourteen oil samples in the prediction set were predicted using the established near-infrared full spectrum PLS model and the characteristic wavelength selected PLS model. Both models can achieve good prediction, and the standard deviation of prediction is 0.000 7 and 0.000 6, respectively. The PLS model selected by characteristic wavelength had the most robust prediction and the best performance index (R2P was 0.993 0, R2CV was 0.988 7, RMSECV and RMSEP were 3.140 1×10-4 and 2.419 0×10-4, RPD was 11.988 4). Compared with the full-spectrum model, the PLS model with characteristic wavelength selection can eliminate much useless information in the full spectrum, predict the water content of engine oil most robustly and have the best performance index so that the performance of the model has been significantly improved. The prediction set of oil samples was verified according to the established full-spectrum PLS model after OSC pretreatment and the PLS model for characteristic wavelength selection. The prediction effect of the PLS model after characteristic wavelength selection was good, and the predicted value of each oil sample was closer to the measured value. It indicates that the PLS model established after characteristic wavelength selection does not reduce the accuracy and prediction ability of the model, but eliminates the information of unrelated variables, making the model more generalized. Therefore, the near-infrared spectroscopy technology has good accuracy and reliability in detecting moisture in engine oil, which provides a feasible solution for engine condition monitoring.
Key words：Engine oil; Moisture; Near infrared spectroscopy; Characteristic wavelength
[1] Al Sheikh Omar A, Motamen Salehi F, Farooq U, et al. Tribology International, 2021, 160(13): 107050.
[2] Kr Singh D, Kurien J, Villayamore A. Materials Today: Proceedings, 2021, 44: 3976.
[3] Zhou F, Yang K. IOP Conference Series. Materials Science and Engineering, 2021, 1043(5): 52054.
[4] Johns M L, Lisabeth K W. Measurement Science & Technology, 2016, 27(10): 105501.
[5] Abdulmunaim A M, Reuter M, Abdulmunem O M, et al. Transactions of the Asabe, 2016, 59: 795.
[6] Liu J, Han J, Zhang Y, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2018, 204: 33.
[7] Basati Z, Jamshidi B, Rasekh M, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2018, 203: 308.
[8] Liu C, Tang X, Yu T, et al. Optik, 2020, 224: 165694.
[9] Holland T, Abdul-Munaim A, Watson D, et al. Lubricants, 2019, 6(2): 35.
[10] CHEN Bin, LIU Ge（陈 彬, 刘 阁）. High Voltage Engineering(高电压技术), 2020, 46 (4): 1405.
[11] Holzki M, Fouckhardt H, Klotzbücher T. Sensors and Actuators A: Physical, 2012, 184: 93.
[12] CHEN Bin, LIU Ge(陈 彬, 刘 阁). Acta Photonica Sinica（光子学报），2014, 43(2): 0230001-1.
[13] Rudnitskaya A, Rocha S M, Legin A, et al. Analytica Chimica Acta, 2010, 662(1): 82.
