隨著現今工業技術的發展，對於高性能和穩定性高的機器設備的需求越來越高，因此潤滑油的重要性也日益的提高。潤滑油更是在機器運行中起著關鍵的作用，且被廣泛的應用在各種領域當中，而使用品質良好的潤滑油是設備良好運行和維持機器使用壽命的關鍵。然而傳統的潤滑油更換標準太過於籠統不夠精確，根據不同的設備和使用方式，潤滑油的更換頻率和更換標準可能都不同。因此本研究開發了一個以RC放電訊號為主要分析依據之創新之潤滑油品質預測之系統，透過擷取放電訊號時域及頻域中的多種特徵指標，搭配方差膨脹因子、逐步迴歸與主成分分析等特徵處理方法挑除特徵間的共線性。接著使用交叉驗證對潤滑油初期不同公里數下的黏度，及特定波段下傅立葉紅外線光譜儀的吸收度峰值變化，使用一般線性迴歸、非線性迴歸與隨機森林迴歸等方法進行建模。並透過校正判定係數(R_adj^2)與正規化均方根誤差(NRMSE)等性能指標為依據，比較模型的擬合表現。結果指出不管使用何種特徵挑選方法，經過十折交叉驗證的隨機森林迴歸相較於其他迴歸方法，對潤滑油的黏度與內部成份變化的預測都有較好的擬合結果。

Lubricating oil holds a significant position in the industrial and mechanical sectors, playing an indispensable role in ensuring machinery's regular operation and protection. With the advancements in industrial technology, there is an increasing demand for high-performance and stable machinery, thus elevating the importance of lubricating oil. Lubricating oil is crucial in the smooth functioning of machines and finds extensive applications in various fields. It is an essential element for maintaining equipment longevity, reducing friction and wear, and providing cooling and sealing functions.
As the demand for high-quality lubricating oil grows, the conventional standards for oil replacement have proven to be vague and imprecise. The oil replacement frequency and criteria may vary depending on different equipment and usage scenarios. In response, this study has developed an innovative system for predicting lubricating oil quality based primarily on RC discharge signals. By extracting various feature indicators from the time domain and frequency domain of the discharge signals and applying feature processing methods such as variance inflation factor, stepwise regression, and principal component analysis, collinearity between features is effectively addressed, Furthermore, linear regression, nonlinear regression, and random forest regression methods are employed to model the changes in viscosity and absorption peak values in specific spectral bands of Fourier Transform Infrared (FTIR) spectroscopy, using cross-validation and performance metrics such as R_adj^2 and NRMSE for model evaluation. Results indicate that regardless of the feature selection method employed, the random forest regression model, validated using a 10-fold cross-validation, outperforms other regression methods in predicting viscosity and internal composition variations of lubricating oil.

[1] B. J. Hamrock, B. J. Schmid, and B. O. Jacobson, Fundamentals of fluid film lubrication. CRC press, 2004.
[2] S. Hurley, P. Cann, and H. Spikes, "Lubrication and reflow properties of thermally aged greases," Tribology Transactions, vol. 43, no. 2, pp. 221-228, 2000.
[3] T. Giannakopoulos and A. Pikrakis, Introduction to audio analysis: a MATLAB® approach. Academic Press, 2014.
[4] C. Besser et al., "Generation of engine oils with defined degree of degradation by means of a large scale artificial alteration method," Tribology International, vol. 132, pp. 39-49, 2019.
[5] B. Jakoby, M. Scherer, M. Buskies, and H. Eisenschmid, "An automotive engine oil viscosity sensor," IEEE Sensors Journal, vol. 3, no. 5, pp. 562-568, 2003.
[6] M. K. A. Ali and H. Xianjun, "Improving the heat transfer capability and thermal stability of vehicle engine oils using Al2O3/TiO2 nanomaterials," Powder Technology, vol. 363, pp. 48-58, 2020.
[7] J. Sentanuhady, W. Saputro, and M. A. Muflikhun, "Metals and chemical compounds contaminants in diesel engine lubricant with B20 and B100 biofuels for long term operation," Sustainable Energy Technologies and Assessments, vol. 45, p. 101161, 2021.
[8] S. Zzeyani, M. Mikou, J. Naja, and A. Elachhab, "Spectroscopic analysis of synthetic lubricating oil," Tribology International, vol. 114, pp. 27-32, 2017.
[9] M. Sejkorová, B. Šarkan, P. Veselík, and I. Hurtová, "FTIR spectrometry with PLS regression for rapid TBN determination of worn mineral engine oils," Energies, vol. 13, no. 23, p. 6438, 2020.
[10] A. Wolak, W. Krasodomski, and G. Zając, "FTIR analysis and monitoring of used synthetic oils operated under similar driving conditions," Friction, vol. 8, pp. 995-1006, 2020.
[11] P. Rawson and G. Morris, Fourier transform infrared (FTIR) based oil condition monitoring for synthetic turbine oils. DSTO Aeronautical and Maritime Research Laboratory, 2003.
[12] B. Pavoni, N. Rado, R. Piazza, and S. Frignani, "FT‐IR Spectroscopy and Chemometrics as a Useful Approach for Determining Chemical‐Physical Properties of Gasoline, by Minimizing Analytical Times and Sample Handling," Annali di Chimica: Journal of Analytical, Environmental and Cultural Heritage Chemistry, vol. 94, no. 7‐8, pp. 521-532, 2004.
[13] F. Van De Voort, J. Sedman, V. Yaylayan, C. S. Laurent, and C. Mucciardi, "Quantitative determination of moisture in lubricants by Fourier transform infrared spectroscopy," Applied spectroscopy, vol. 58, no. 2, pp. 193-198, 2004.
[14] M. J. Adams, M. J. Romeo, and P. Rawson, "FTIR analysis and monitoring of synthetic aviation engine oils," Talanta, vol. 73, no. 4, pp. 629-634, 2007.
[15] S. Kumar, P. Mukherjee, and N. Mishra, "Online condition monitoring of engine oil," Industrial lubrication and tribology, vol. 57, no. 6, pp. 260-267, 2005.
[16] N. Dörr, A. Agocs, C. Besser, A. Ristić, and M. Frauscher, "Engine oils in the field: a comprehensive chemical assessment of engine oil degradation in a passenger car," Tribology Letters, vol. 67, pp. 1-21, 2019.
[17] M. D. Brouwer, L. A. Gupta, F. Sadeghi, D. Peroulis, and D. Adams, "High temperature dynamic viscosity sensor for engine oil applications," Sensors and Actuators A: Physical, vol. 173, no. 1, pp. 102-107, 2012.
[18] G. Rilling, P. Flandrin, and P. Goncalves, "On empirical mode decomposition and its algorithms," in IEEE-EURASIP workshop on nonlinear signal and image processing, 2003, vol. 3, no. 3: Grado: IEEE, pp. 8-11.
[19] L. Lin and J. Hongbing, "Signal feature extraction based on an improved EMD method," Measurement, vol. 42, no. 5, pp. 796-803, 2009.
[20] N. E. Huang et al., "The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis," Proceedings of the Royal Society of London. Series A: mathematical, physical and engineering sciences, vol. 454, no. 1971, pp. 903-995, 1998.
[21] H. Ding, Z. Huang, Z. Song, and Y. Yan, "Hilbert–Huang transform based signal analysis for the characterization of gas–liquid two-phase flow," Flow measurement and instrumentation, vol. 18, no. 1, pp. 37-46, 2007.
[22] R. Yan and R. X. Gao, "Hilbert–Huang transform-based vibration signal analysis for machine health monitoring," IEEE Transactions on Instrumentation and measurement, vol. 55, no. 6, pp. 2320-2329, 2006.
[23] C. Lee and D. A. Landgrebe, "Feature extraction based on decision boundaries," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 4, pp. 388-400, 1993.
[24] D. Tkach, H. Huang, and T. A. Kuiken, "Study of stability of time-domain features for electromyographic pattern recognition," Journal of neuroengineering and rehabilitation, vol. 7, no. 1, pp. 1-13, 2010.
[25] J.-F. Bercher and C. Vignat, "Estimating the entropy of a signal with applications," IEEE transactions on signal processing, vol. 48, no. 6, pp. 1687-1694, 2000.
[26] B. Chen, L. Chen, and Y. Chen, "Efficient ant colony optimization for image feature selection," Signal processing, vol. 93, no. 6, pp. 1566-1576, 2013.
[27] G. Dougherty, Pattern recognition and classification: an introduction. Springer Science & Business Media, 2012.
[28] S. García, J. Luengo, and F. Herrera, Data preprocessing in data mining. Springer, 2015.
[29] T. Ahmad and M. N. Aziz, "Data preprocessing and feature selection for machine learning intrusion detection systems," ICIC Express Lett, vol. 13, no. 2, pp. 93-101, 2019.
[30] R. Zebari, A. Abdulazeez, D. Zeebaree, D. Zebari, and J. Saeed, "A comprehensive review of dimensionality reduction techniques for feature selection and feature extraction," Journal of Applied Science and Technology Trends, vol. 1, no. 2, pp. 56-70, 2020.
[31] N. Sharma and K. Saroha, "Study of dimension reduction methodologies in data mining," in International Conference on Computing, Communication & Automation, 2015: IEEE, pp. 133-137.
[32] H. R. Kanan and K. Faez, "An improved feature selection method based on ant colony optimization (ACO) evaluated on face recognition system," Applied Mathematics and Computation, vol. 205, no. 2, pp. 716-725, 2008.
[33] I. Guyon and A. Elisseeff, "An introduction to variable and feature selection," Journal of machine learning research, vol. 3, no. Mar, pp. 1157-1182, 2003.
[34] H. Zhou, Z. Deng, Y. Xia, and M. Fu, "A new sampling method in particle filter based on Pearson correlation coefficient," Neurocomputing, vol. 216, pp. 208-215, 2016.
[35] J. Kittler, "Feature set search algorithms," Pattern recognition and signal processing, 1978.
[36] X. Huang, L. Zhang, B. Wang, F. Li, and Z. Zhang, "Feature clustering based support vector machine recursive feature elimination for gene selection," Applied Intelligence, vol. 48, pp. 594-607, 2018.
[37] A. L. Blum and P. Langley, "Selection of relevant features and examples in machine learning," Artificial intelligence, vol. 97, no. 1-2, pp. 245-271, 1997.
[38] R. Tibshirani, "Regression shrinkage and selection via the lasso," Journal of the Royal Statistical Society Series B: Statistical Methodology, vol. 58, no. 1, pp. 267-288, 1996.
[39] L. Breiman, "Random forests," Machine learning, vol. 45, pp. 5-32, 2001.
[40] B. Mahesh, "Machine learning algorithms-a review," International Journal of Science and Research (IJSR).[Internet], vol. 9, no. 1, pp. 381-386, 2020.
[41] X. J. Zhu, "Semi-supervised learning literature survey," 2005.
[42] V. Rodriguez-Galiano, M. Sanchez-Castillo, M. Chica-Olmo, and M. Chica-Rivas, "Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines," Ore Geology Reviews, vol. 71, pp. 804-818, 2015.
[43] X. Xie et al., "Comparison of random forest and multiple linear regression models for estimation of soil extracellular enzyme activities in agricultural reclaimed coastal saline land," Ecological Indicators, vol. 120, p. 106925, 2021.
[44] T. Benkedjouh, K. Medjaher, N. Zerhouni, and S. Rechak, "Health assessment and life prediction of cutting tools based on support vector regression," Journal of intelligent manufacturing, vol. 26, pp. 213-223, 2015.
[45] S. A. Abdul-Wahab, C. S. Bakheit, and S. M. Al-Alawi, "Principal component and multiple regression analysis in modelling of ground-level ozone and factors affecting its concentrations," Environmental Modelling & Software, vol. 20, no. 10, pp. 1263-1271, 2005.
[46] M. O. Akinwande, H. G. Dikko, and A. Samson, "Variance inflation factor: as a condition for the inclusion of suppressor variable (s) in regression analysis," Open journal of statistics, vol. 5, no. 07, p. 754, 2015.
[47] E. Dadfar and F. Shafiei, "Prediction of some thermodynamic properties of sulfonamide drugs using genetic algorithm‐multiple linear regressions," Journal of the Chinese Chemical Society, vol. 67, no. 4, pp. 492-513, 2020.
[48] M. A. Al-Ghouti and L. Al-Atoum, "Virgin and recycled engine oil differentiation: A spectroscopic study," Journal of environmental management, vol. 90, no. 1, pp. 187-195, 2009.
[49] N. E. Huang, "Review of empirical mode decomposition," in Wavelet Applications VIII, 2001, vol. 4391: SPIE, pp. 71-80.
[50] H.-G. Cheong, Y.-S. Kim, and C.-N. Chu, "Machining characteristics of an RC-type generator circuit with an N-channel MOSFET in micro EDM," Procedia CIRP, vol. 68, pp. 631-636, 2018.
[51] H. Akoglu, "User's guide to correlation coefficients," Turkish journal of emergency medicine, vol. 18, no. 3, pp. 91-93, 2018.
[52] J. Cheng, J. Sun, K. Yao, M. Xu, and Y. Cao, "A variable selection method based on mutual information and variance inflation factor," Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, vol. 268, p. 120652, 2022.
[53] H. Zhao, J. Zheng, J. Xu, and W. Deng, "Fault diagnosis method based on principal component analysis and broad learning system," IEEE Access, vol. 7, pp. 99263-99272, 2019.
[54] 黃安華 (2022)。基於RC放電訊號分析之潤滑油品質檢測系統驗證。國立臺灣 科技大學機械工程系碩士論文，台北市。取自https://hdl.handle.net/11296/q38ckh