Visible and Near Infrared Spectral Analysis of the Lubricating Oil Dynamic Viscosity Based on Quantum Genetic-Neural Network Algorithm
LIU Chen-yang1, 2, TANG Xing-jia3, YU Tao3, WANG Tai-sheng1, LU Zhen-wu1, YU Wei-xing3*
1. R&D Center of Precision Instruments and Equipment, Changchun Institute of Optics, Fine Mechanics & Physics, Chinese Academy of Sciences, Changchun 130033, China
2. University of Chinese Academy of Sciences, Beijing 100049, China
3. Key Laboratory of Spectral Imaging Technology, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an 710119, China
Abstract：Dynamic viscosity is one of the most important quality factors of lubricating oil. For the safety of high-speed railway, it is necessary to develop a real-time, fast and non-destructive method to monitor the status of the gearbox. Here we propose a new method that utilizes the quantum genetic-neural network algorithm to quantitatively analyze the visible and near-infrared spectra of lubricant acquired by a micro-spectrometer module. The method not only realizes non-destructive rapid real-time detection of the dynamic viscosity of high-speed railway transmission lubricating oil, but also further improves the prediction accuracy of the lubricating oil dynamic viscosity. Thanks to its excellent performance and small size, the miniature spectrometer has been widely used as a portable and nondestructive device. Here, two kinds of micro-spectral modules with visible/short-wave-infrared and near-infrared waveguide gratings are coupled with optical fibers and obtain a wide spectral range from 330 to 1 700 nm. Here the integrated waveguide and propagating makes the spectrometer compact and small. In experiment, a total of 78 lubricant samples with 13 different viscosity lubricants were prepared for spectral measurement by the micro-spectrometer. The raw spectral data was pre-processed using the Savitzky-Golay convolution smoothing and the first-order differentiation to eliminate the baseline drift and background noise. Next, principal component analysis and Mahalanobis distance algorithm were used to identify the samples outside the concentration boundary, and three out-of-bound samples were excluded. Finally, the BP neural network and the quantum genetic neural network methods were employed for quantitative analyses and the results are compared, respectively. The quantum genetic algorithm is a probabilistic evolutionary algorithm that combines the advantages of quantum computing and genetic algorithm. It uses the form of quantum chromosomes and quantum logic gates for global searching. Therefore, the quantum genetic algorithm can be used to optimize the weight and the threshold of neural network, and the modeling efficiency and accuracy can be improved significantly. In this paper, BP neural network algorithm and quantum genetic neural network algorithm were modeled and simulated respectively. Ten samples were randomly selected from 75 samples as prediction sets, and the remaining 65 were as modeling sets. In the quantum genetic algorithm, the population number was set to 40 and the termination algebra was 200. The optimization results showed that the algorithm could obtain the optimal solution quickly after training of only 81 generations. A comparison of the predicted results showed that the quantum genetic algorithm was much better than the BP neural network, the root mean square error of the prediction was significantly reduced from 0.345 5 to 0.029 4, and the coefficient of determination was increased from 0.850 4 to 0.979 9. This work has developed an effective method for compact, non-destructive, rapid and real-time detection of the dynamic viscosity of the lubricant and would find potential uses for the safety monitoring of high-speed trains.
刘晨阳，唐兴佳，于 涛，王泰升，卢振武，鱼卫星. 量子遗传-神经网络算法的润滑油动力粘度值可见近红外光谱分析[J]. 光谱学与光谱分析, 2020, 40(05): 1634-1639.
LIU Chen-yang, TANG Xing-jia, YU Tao, WANG Tai-sheng, LU Zhen-wu, YU Wei-xing. Visible and Near Infrared Spectral Analysis of the Lubricating Oil Dynamic Viscosity Based on Quantum Genetic-Neural Network Algorithm. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(05): 1634-1639.
[1] Braga J W B, Dos Santos A A, Martins I S. Fuel, 2014, 120：171.
[2] De Paula Pedroza R H, Nic Cio J T N, Dos Santos B S, et al. Analytical Letters, 2013, 46(7): 1145.
[3] JIANG Lu-lu, ZHANG Yu, LIU Fei, et al(蒋璐璐，张 瑜，刘 飞，等). Acta Petrolei Sinica(石油学报), 2011, 27(1): 112.
[4] WANG Han，LI Shui-feng, LIU Xiu-ying(王 晗，李水峰, 刘秀英). Journal of Applied Optics(应用光学), 2008, 29(2): 230.
[5] Camps C, Christen D. LWT-Food Science and Technology, 2009, 42(6): 1125.
[6] Ferreiro-Gonzalez M, Espada-Bellido E, Guillen-Cueto L, et al. Talanta, 2018, 188：288.
[7] He C, Chen L, Yang Z, et al. Bioresource Technology, 2012, 110：314.
[8] CHEN Bin, LIU Ge, ZHANG Xian-ming(陈 彬，刘 阁，张贤明). Infrared and Laser Engineering(红外与激光工程), 2013, 42(12): 3168.
[9] Liu J, Han J, Zhang Y, et al. Spectrochimica Acta Part A, Molecular and Biomolecular Spectroscopy, 2018, 204：33.
[10] Sacko B D, Sanogo S, Konare H, et al. Optics and Photonics Journal, 2018, 8(5): 123.
[11] Ni Y Q, Li M. Measurement, 2016, 88：468.
[12] GONG Rui-kun, ZHOU Guo-qing(龚瑞昆，周国庆). Modern Electronics Technique(现代电子技术), 2018, 41(15): 1004.
[13] ZHANG Li-fang, ZHANG Xi-ping(张立仿，张喜平). Computer Engineering & Science(计算机工程与科学), 2016, 38(1): 1007.
