ISSN 1004-0595
CN 62-1224/O4
ISSN 1004-0595
CN 62-1224/O4
| Citation: |
XIE Peiyuan, FENG Xin, XIA Yanqiu. Multi-Label One-Dimensional Convolutional Neural Network Based on Infrared Spectroscopy for the Identification of Additives in Lubrication Oils[J]. Tribology, 2025, 45(5): 1−12. DOI: 10.16078/j.tribology.2024031
|
Lubricating oil additive is a chemical substance used to improve and enhance the original performance of oil products, endowing oil products with new characteristics and is widely used in various types of lubricating oils. Exploring effective methods for component analysis and substance identification of additives in lubricating oil has practical significance and theoretical value for the identification and evaluation of new oil quality, and the determination of using oil operation and maintenance plans. It has always been a research direction of concern for scholars. Focused on the issue of identifying additives in lubricating oil, polyalphaolefins (PAO40) and Polyol ester (PriEco3000) were mixed as base oil and four common commercial additives (MoDTC, ZDDP, L135 and L57) were blended in different proportions to prepare lubricating oil samples. Fourier transform infrared radiation (FT-IR) was employed to collect mid-infrared spectral information of the samples, which were then subjected to first and second derivative processing. The three spectra were integrated into a Lube oil feature matrix as the input of the model for displaying the feature information of lubricating oil FT-IR spectra to the greatest extent. Different from the traditional single-spectrum and single-label classification task, the identification of additives in lubricating oil essentially reflected the existence of multiple labels in a single FT-IR spectrum. Based on the idea of multi-label classification, a Multi-Label One-Dimensional Convolutional Neural Network (ML-1D-CNN) model was proposing. The model performed supervised feature selection and additive recognition on the input lubricating oil infrared spectra. Deep learning model that was correct and had a certain degree of generalization ability should be able to extract the FT-IR spectral features of each additive, and the effect of feature extraction was an important criterion for judging the correctness of the model. Gradient-weighted Class Activation Mapping (Grad-CAM) was introduced to observe the effect of the models in extracting features from input data. Experimental results revealled that the spectral features extracted by the proposed models corresponding well with the original spectral feature peaks. It was shown that the model could effectively and correctly study the FT-IR spectra of each additive. Whether on the validation set of the training process or on additional test set data, a comparison with three hybrid models PCA+PLS-DA, SPA+SVM and IGA+RF recently mentioned in the literature showed that ML-1D-CNN model performed exceptionally, achieving an recognition accuracy rate of 93.33% to 100% for individual additives and demonstrated strong synchronous recognition capabilities for similar additives. Furthermore, the ML-1D-CNN model maintained a satisfactory recognition rate for additives trained outside the model samples, showing a good generalization ability.
| [1] |
Inoue Y, Tan K W, Hutchinson P A, et al. Contribution of viscosity index improver to fuel economy[J]. Tribology Online, 2019, 14(5): 404–410. doi: 10.2474/trol.14.404.
|
| [2] |
Khalaf H I, Hassan M J M, Hassan O A. Separation & identification of organic compounds in lubricating oil additives using TLC & GC-MS[J]. Journal of Al-Nahrain University Science, 2012, 15(3): 62–68. doi: 10.22401/jnus.15.3.09.
|
| [3] |
Zzeyani S, Mikou M, Naja J, et al. Spectroscopic analysis of synthetic lubricating oil[J]. Tribology International, 2017, 114: 27–32. doi: 10.1016/j.triboint.2017.04.011.
|
| [4] |
Ramopoulou L, Widder L, Brenner J, et al. Atmospheric pressure matrix-assisted laser desorption/ionization mass spectrometry of engine oil additive components[J]. Rapid Communications in Mass Spectrometry: RCM, 2022, 36(9): e9271. doi: 10.1002/rcm.9271.
|
| [5] |
Jamwal R, Amit, Kumari S, et al. Recent trends in the use of FTIR spectroscopy integrated with chemometrics for the detection of edible oil adulteration[J]. Vibrational Spectroscopy, 2021, 113: 103222. doi: 10.1016/j.vibspec.2021.103222.
|
| [6] |
] [夏延秋, 王裕兴, 冯欣, 等. 群智能搜索在基础油性能预测模型中的优化效能[J]. 摩擦学学报, 2023, 43(4): 429–438]. doi: 10.16078/j.tribology. 2021304.
Xia Yanqiu, Wang Yuxing, Feng Xin, et al. Optimization efficiency of swarm intelligence search in base oil performance prediction model[J]. Tribology, 2023, 43(4): 429–438 doi: 10.16078/j.tribology.2021304
|
| [7] |
Feng Xin, Xia Yanqiu, Xie Peiyuan, et al. Classification and spectrum optimization method of grease based on infrared spectrum[J]. Friction, 2024, 12(6): 1154–1164. doi: 10.1007/s40544-023-0786-y.
|
| [8] |
李晓鹤, 冯欣, 夏延秋. 布谷鸟搜索的润滑脂特征红外光谱波段优选技术[J]. 光谱学与光谱分析, 2017, 37(12): 3703–3708]. doi: 10.3964/j.issn.1000-0593(2017)12-3703-06.
Li Xiaohe, Feng Xin, Xia Yanqiu. IR spectra of grease optimization based on cuckoo search[J]. Spectroscopy and Spectral Analysis, 2017, 37(12): 3703–3708 doi: 10.3964/j.issn.1000-0593(2017)12-3703-06
|
| [9] |
Yang Shubo, Moreira J, Li Zukui. Predicting crude oil properties using fourier-transform infrared spectroscopy (FTIR) and data-driven methods[J]. Digital Chemical Engineering, 2022, 3: 100031. doi: 10.1016/j.dche.2022.100031.
|
| [10] |
Liu Qiang, Gong Zhongliang, Li Dapeng, et al. Rapid and low-cost quantification of adulteration content in Camellia oil utilizing UV-vis-NIR spectroscopy combined with feature selection methods[J]. Molecules, 2023, 28(16): 5943. doi: 10.3390/molecules28165943.
|
| [11] |
Meng Xiangru, Yin Chunling, Yuan Libo, et al. Rapid detection of adulteration of olive oil with soybean oil combined with chemometrics by Fourier transform infrared, visible-near-infrared and excitation-emission matrix fluorescence spectroscopy: a comparative study[J]. Food Chemistry, 2023, 405: 134828. doi: 10.1016/j.foodchem.2022.134828.
|
| [12] |
Chai Qinqin, Zeng Jian, Lin Donghong, et al. Improved 1D convolutional neural network adapted to near-infrared spectroscopy for rapid discrimination of Anoectochilus roxburghii and its counterfeits[J]. Journal of Pharmaceutical and Biomedical Analysis, 2021, 199: 114035. doi: 10.1016/j.jpba.2021.114035.
|
| [13] |
Rahimi M, Pourramezan M R, Rohani A. Modeling and classifying the in-operando effects of wear and metal contaminations of lubricating oil on diesel engine: a machine learning approach[J]. Expert Systems with Applications, 2022, 203: 117494. doi: 10.1016/j.eswa.2022.117494.
|
| [14] |
Chimeno-Trinchet C, Murru C, Díaz-García M E, et al. Artificial Intelligence and fourier-transform infrared spectroscopy for evaluating water-mediated degradation of lubricant oils[J]. Talanta, 2020, 219: 121312. doi: 10.1016/j.talanta.2020.121312.
|
| [15] |
夏延秋, 徐大祎, 冯欣, 等. 基于极限学习机和优化算法的润滑油添加剂种类识别与含量预测[J]. 摩擦学学报, 2020, 40(1): 97–106]. doi: 10.16078/j.tribology.2019107.
Xia Yanqiu, Xu Dayi, Feng Xin, et al. Identification and content prediction of lubricating oil additives based on extreme learning machine[J]. Tribology, 2020, 40(1): 97–106 doi: 10.16078/j.tribology.2019107
|
| [16] |
夏延秋, 王宸, 冯欣. GA-BPSO混合优化中红外光谱特征波段筛选的润滑油添加剂种类识别技术[J]. 摩擦学学报, 2022, 42(1): 142–152]. doi: 10.16078/j.tribology.2020164.
Xia Yanqiu, Wang Chen, Feng Xin. GA-BPSO hybrid optimization of middle infrared spectrum feature band selection of lubricating oil additive type identification technology[J]. Tribology, 2022, 42(1): 142–152 doi: 10.16078/j.tribology.2020164
|
| [17] |
Xu Jigang, Liu Shujun, Gao Ming, et al. Classification of lubricating oil types using mid-infrared spectroscopy combined with linear discriminant analysis–support vector machine algorithm[J]. Lubricants, 2023, 11(6): 268. doi: 10.3390/lubricants11060268.
|
| [18] |
关浩坚, 贺石中, 李秋秋, 等. 卷积神经网络在装备磨损颗粒识别中的研究综述[J]. 摩擦学学报, 2022, 42(2): 426–445]. doi: 10.16078/j.tribology.2021025.
Guan Haojian, He Shizhong, Li Qiuqiu, et al. A review of convolutional neural networks in equipment wear particle recognition[J]. Tribology, 2022, 42(2): 426–445 doi: 10.16078/j.tribology.2021025
|
| [19] |
Houran M A, Bukhari S M S, Zafar M H, et al. COA-CNN-LSTM: Coati optimization algorithm-based hybrid deep learning model for PV/wind power forecasting in smart grid applications[J]. Applied Energy, 2023, 349: 121638. doi: 10.1016/j.apenergy.2023.121638.
|
| [20] |
Yektadoust E, Janghorbani A, Talebi A F. XCNN-SC: Explainable CNN for SARS-CoV-2 variants classification and mutation detection[J]. Computers in Biology and Medicine, 2023, 167: 107606. doi: 10.1016/j.compbiomed.2023.107606.
|
| [21] |
Gupta M K, Korkmaz M E, Shibi C S, et al. Tribological characteristics of additively manufactured 316 stainless steel against 100 Cr6 alloy using deep learning[J]. Tribology International, 2023, 188: 108893. doi: 10.1016/j.triboint.2023.108893.
|
| [22] |
Yang Haijun, Li Xianchang, Zhang Shiding, et al. A one-dimensional convolutional neural network based deep learning for high accuracy classification of transformation stages in esophageal squamous cell carcinoma tissue using micro-FTIR[J]. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2023, 289: 122210. doi: 10.1016/j.saa.2022.122210.
|
| [23] |
Shang Hui, Shang Linwei, Wu Jinjin, et al. NIR spectroscopy combined with 1D-convolutional neural network for breast cancerization analysis and diagnosis[J]. Spectrochimica Acta Part A, Molecular and Biomolecular Spectroscopy, 2023, 287(Pt 1): 121990. doi: 10.1016/j.saa.2022.121990.
|
| [24] |
Zhou Kun, Oh S K, Pedrycz W, et al. Design of data feature-driven 1D/2D convolutional neural networks classifier for recycling black plastic wastes through laser spectroscopy[J]. Advanced Engineering Informatics, 2022, 53: 101695. doi: 10.1016/j.aei.2022.101695.
|
| [25] |
Le K H, Pham H H, Nguyen T B, et al. LightX3ECG: a lightweight and eXplainable deep learning system for 3-lead electrocardiogram classification [EB/OL]. 2022: arXiv: 2207.12381. http://arxiv.org/abs/2207.12381.
|
| [26] |
Senjoba L, Ikeda H, Toriya H, et al. Visualization of 1D CNN lithology identification model from rotary percussion drilling vibration signals using explainable artificial intelligence grad-CAM[J]. International Journal of the Society of Materials Engineering for Resources, 2022, 25(2): 224–228. doi: 10.5188/ijsmer.25.224.
|
| [27] |
Song Dezhao, Vold A, Madan K, et al. Multi-label legal document classification: a deep learning-based approach with label-attention and domain-specific pre-training[J]. Information Systems, 2022, 106: 101718. doi: 10.1016/j.is.2021.101718.
|
| [28] |
Pham T, Tao Xiaohui, Zhang Ji, et al. Graph-based multi-label disease prediction model learning from medical data and domain knowledge[J]. Knowledge-Based Systems, 2022, 235: 107662. doi: 10.1016/j.knosys.2021.107662.
|
| [29] |
Meng Yunyun, Yu Lei, Wei Yinsheng. Multi-label radar compound jamming signal recognition using complex-valued CNN with jamming class representation fusion[J]. Remote Sensing, 2023, 15(21): 5180. doi: 10.3390/rs15215180.
|
| [30] |
Lasalvia M, Capozzi V, Perna G. A comparison of PCA-LDA and PLS-DA techniques for classification of vibrational spectra[J]. Applied Sciences, 2022, 12(11): 5345. doi: 10.3390/app12115345.
|
| [31] |
Wei Chenjie, Wang Jifen. A rapid and nondestructive approach for forensic identification of car bumper splinters using attenuated total reflectance Fourier transform infrared spectroscopy and chemometrics[J]. Journal of Forensic Sciences, 2021, 66(2): 583–593. doi: 10.1111/1556-4029.14606.
|
| [32] |
夏延秋, 谢培元, NAY MIN AUNG, 等. 改进遗传算法嵌入经典分类算法实现润滑油添加剂微小量多种类同步识别[J]. 光谱学与光谱分析, 2024, 44(3): 744–750].
Xia Yanqiu, Xie Peiyuan, NAY MIN AUNG, et al. The improved genetic algorithm is embedded into the classical classification algorithm to realize the synchronous identification of small quantity and multi types of lubricating oil additives[J]. Spectroscopy and Spectral Analysis, 2024, 44(3): 744–750
|
| [33] |
高晓光, 马淑芬, 胡刚, 等. 用红外光谱法测定润滑油中MoDTC含量的研究[J]. 润滑与密封, 2022, 47(5): 171–176]. doi: 10.3969/j.issn.0254-0150.2022.05.024.
Gao Xiaoguang, Ma Shufen, Hu Gang, et al. Study on the determination of the content of MoDTC in lubricating oil by infrared spectroscopy[J]. Lubrication Engineering, 2022, 47(5): 171–176 doi: 10.3969/j.issn.0254-0150.2022.05.024
|
| [34] |
Akbari S, Kovač J, Kalin M. Effect of ZDDP concentration on the thermal film formation on steel, hydrogenated non-doped and Si-doped DLC[J]. Applied Surface Science, 2016, 383: 191–199. doi: 10.1016/j.apsusc.2016.04.182.
|
| [35] |
翁诗甫, 徐怡庄. 傅里叶变换红外光谱分析[M]. 3版. 北京: 化学工业出版社, 2016].
Weng Shifu, Xu Yizhuang. Fourier transform infrared spectrum analysis[M]. 3rd ed. Beijing: Chemical Industry Press, 2016
|
Supported by: Beijing Renhe Information Technology Co., Ltd. 
DownLoad: