Near-infrared spectroscopy online detecting for 2,6-dimethylphenol purity based on transfer learning

doi:10.11949/0438-1157.20210791

Abstract

Abstract:

Near-infrared spectroscopy is used to on-line detect the product purity of distillation purification process of 2,6-dimethylphenol (2,6-DMP) monomer separation section. Because the product purity of the 2,6-DMP product tower is relatively high (usually 99.10%—99.95%), the purity value of the samples is concentrated in a small range, the coefficient of variation between samples is small, the discrimination of NIR spectrum is low, and the correlation between NIR spectrum and physical property concentration is small, a reliable model cannot be established. To accurately detect the product purity of the 2,6-DMP product tower, thereby real-time control of the product quality, the migration learning algorithm is introduced to make full use of the similarity of the near-infrared spectroscopy data between the different towers in the 2,6-DMP distillation and purification process. With the help of the near-infrared spectroscopy data of the lower 2,6-DMP purity in other towers, the performance of the near-infrared model of the higher 2,6-DMP purity in the product tower is improved. Finally, the validity of the method is verified by establishing near infrared on-line detection models for the purity of 2,6-DMP in a synthetic material company. The results show that with the help of NIR data of different number and purity range, the accuracy of the purity model after transferring is different. It illustrates that the transfer learning algorithm can not only solve the modeling problem in the case of small spectral discrimination effectively, but also the accuracy of the model is related to the number of spectra and the purity range of product.

Key words: 2,6-dimethylphenol, near-infrared spectroscopy, online detecting, transfer learning, reactive distillation, algorithm

摘要：

使用近红外光谱分析技术，对2,6-二甲酚（2,6-DMP）单体分离工段精馏提纯过程的产品纯度进行在线检测。由于2,6-DMP产品塔的产品纯度较高（通常为99.10%~99.95%），样本的纯度值集中分布在一个较小的范围，样本数据之间的变异系数小，样本之间的区分度低，导致所采集光谱与产品纯度之间缺乏相关性，因而无法建立可靠的近红外模型。为了准确检测2,6-DMP产品塔的产品纯度，从而对产品质量进行实时调控，引入迁移学习算法，充分利用2,6-DMP精馏提纯过程中不同塔之间近红外光谱数据的相似性，借助于其他塔中较低2,6-DMP纯度的近红外光谱数据，改善产品塔中较高2,6-DMP纯度的近红外模型性能。通过对某合成材料公司2,6-DMP精馏提纯过程的产品纯度建立近红外在线检测模型，验证了所提方法的有效性。分析结果表明，借助于不同样本数量以及纯度范围的近红外光谱数据，所建模型精度有所不同，说明迁移学习算法不仅可以有效解决样本区分度低情形下的建模问题，且建模精度与所借助光谱的样本数量以及纯度范围密切相关。

关键词: 2,6-二甲酚, 近红外光谱, 在线检测, 迁移学习, 反应精馏, 算法

CLC Number:

TP 181

Yunfei WU, Xiaoli LUAN, Fei LIU. Near-infrared spectroscopy online detecting for 2,6-dimethylphenol purity based on transfer learning[J]. CIESC Journal, 2022, 73(2): 782-791.

邬云飞, 栾小丽, 刘飞. 基于迁移学习的2，6-二甲酚纯度近红外光谱在线检测[J]. 化工学报, 2022, 73(2): 782-791.

Figures/Tables 12

Fig.1 Process flow diagram

Fig.2 Spectral comparison at different detecting points

Fig.3 Near-infrared spectra before and after data preprocessing

Table 1 2，6-DMP purity distribution at different detecting points

变异

系数/%

Fig.4 Modeling flow diagram of transfer learning algorithm

Fig.5 Prediction effect based on spectral data of 2,6-DMP product tower

Table 2 Domain partition of 2，6-DMP purity at different detecting points

脱苯酚塔检测点/%	邻甲酚粗品塔检测点/%
<79.50	<97.10
79.50~80.00	97.10~97.20
80.00~80.50	97.20~97.30
80.50~81.00	97.30~97.40
81.00~81.50	97.40~97.50
81.50~82.00	97.50~97.60
82.00~82.50	97.60~97.70
82.50~83.00	97.70~97.80
83.00~83.50	97.80~97.90
83.50~84.00	>97.90
>84.00

Fig.6 Different purity domain of dephenolization tower impact on transfer results

Fig.7 Different purity domain of crude o-cresol tower impact on transfer results

Fig.8 Different number of spectra of dephenolization tower impact on transfer results

Fig.9 Different number of spectra of crude o-cresol tower impact on transfer results

Fig.10 Model curves and scatter plots of prediction

References 30

1	Hay A S. Poly(phenylene oxides)s and poly(arylene ether)s derived from 2, 6-diarylphenols[J]. Progress in Polymer Science, 1999, 24(1): 45-80.
2	Kemeleva E A, Vasyunina E A, Sinitsina O I, et al. New promising antioxidants based on 2, 6-dimethylphenol[J]. Russian Journal of Bioorganic Chemistry, 2008, 34(4): 499-509.
3	Prince C, Jia Z. Measurement of detergent concentration using 2,6-dimethylphenol in membrane-protein crystallization[J]. Acta Crystallographica Section D: Biological Crystallography, 2012, 68(12): 1694-1696.
4	陈藕君, 黄国楺. 2,6-二甲基苯酚的填充柱气相色谱分析[J]. 化学世界, 1988, 29(7): 320-322.
	Chen O J, Huang G R. Measurement of 2,6-dimethyl phenol by packed column gas chromatography[J]. Chemical World, 1988, 29(7): 320-322.
5	Richard R, Li Y, Dubreuil B, et al. On-line monitoring of the transesterification reaction between triglycerides and ethanol using near infrared spectroscopy combined with gas chromatography[J]. Bioresource Technology, 2011, 102(12): 6702-6709.
6	Sales R F, Vitale R, de Lima S M, et al. Multivariate statistical process control charts for batch monitoring of transesterification reactions for biodiesel production based on near-infrared spectroscopy[J]. Computers & Chemical Engineering, 2016, 94: 343-353.
7	Silva W K, Chicoma D L, Giudici R. In-situ real-time monitoring of particle size, polymer, and monomer contents in emulsion polymerization of methyl methacrylate by near infrared spectroscopy[J]. Polymer Engineering & Science, 2011, 51(10): 2024-2034.
8	Torraga M G, Giudici R. Stabilizer-free dispersion copolymerization monitoring by in-line NIR spectroscopy[J]. Industrial & Engineering Chemistry Research, 2020, 59(35): 15497-15505.
9	Pasquini C. Near infrared spectroscopy: a mature analytical technique with new perspectives—a review[J]. Analytica Chimica Acta, 2018, 1026: 8-36.
10	Żukowski W, Berkowicz G, Baron J, et al. Selective phenol methylation to 2, 6-dimethylphenol in a fluidized bed of iron-chromium mixed oxide catalyst with o-cresol circulation[J]. Chemistry Central Journal, 2014, 8(1): 51.
11	刘培义, 任玉林, 苟玉慧, 等. 人工神经网络-近红外光谱法用于甲氧苄胺嘧啶粉末药品的非破坏定量分析[J]. 高等学校化学学报, 2000, 21(4): 544-546.
	Liu P Y, Ren Y L, Gou Y H, et al. Nondestructive quantitative analysis of trimethoprim powder pharmaceutical by artificial neural network and near-infrared spectroscopy[J]. Chemical Journal of Chinese Universities, 2000, 21(4): 544-546.
12	瞿海斌, 刘晓宣, 程翼宇. 中药材三七提取液近红外光谱的支持向量机回归校正方法[J]. 高等学校化学学报, 2004, 25(1): 39-43.
	Qu H B, Liu X X, Cheng Y Y. A method for analysis of extracting solution of Panax notoginseng using near-infrared spectroscopy and support vector regression[J]. Chemical Journal of Chinese Universities, 2004, 25(1): 39-43.
13	冯爱明, 方利民, 林敏. 近红外光谱分析中的高斯过程回归方法[J]. 光谱学与光谱分析, 2011, 31(6): 1514-1517.
	Feng A M, Fang L M, Lin M. Gaussian process regression and its application in near-infrared spectroscopy analysis[J]. Spectroscopy and Spectral Analysis, 2011, 31(6): 1514-1517.
14	Chakraborty S. Bayesian multiple response kernel regression model for high dimensional data and its practical applications in near infrared spectroscopy[J]. Computational Statistics & Data Analysis, 2012, 56(9): 2742-2755.
15	Bian X H, Li S J, Fan M R, et al. Spectral quantitative analysis of complex samples based on the extreme learning machine[J]. Analytical Methods, 2016, 8(23): 4674-4679.
16	Wang K Y, Bian X H, Tan X Y, et al. A new ensemble modeling method for multivariate calibration of near infrared spectra[J]. Analytical Methods, 2021, 13(11): 1374-1380.
17	Pan S J, Yang Q. A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10): 1345-1359.
18	周书恒, 杜文莉. 基于迁移学习的裂解炉产率建模[J]. 化工学报, 2014, 65(12): 4921-4928.
	Zhou S H, Du W L. Modeling of ethylene cracking furnace yields based on transfer learning[J]. CIESC Journal, 2014, 65(12): 4921-4928.
19	刘佳, 邵诚, 朱理. 基于迁移学习工况划分的裂解炉收率PSO-LS-SVM建模[J]. 化工学报, 2016, 67(5): 1982-1988.
	Liu J, Shao C, Zhu L. Modeling of cracking furnace yields with PSO-LS-SVM based on operating condition classification by transfer learning[J]. CIESC Journal, 2016, 67(5): 1982-1988.
20	Qureshi A S, Khan A, Zameer A, et al. Wind power prediction using deep neural network based meta regression and transfer learning[J]. Applied Soft Computing, 2017, 58: 742-755.
21	Wang Y F, Wang K, Zhou Z, et al. Modeling of oil near-infrared spectroscopy based on similarity and transfer learning algorithm[J]. Frontiers of Chemical Science and Engineering, 2019, 13(3): 599-607.
22	Wen L, Gao L, Li X Y. A new deep transfer learning based on sparse auto-encoder for fault diagnosis[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2019, 49(1): 136-144.
23	张振良, 刘君强, 黄亮, 等. 基于半监督迁移学习的轴承故障诊断方法[J]. 北京航空航天大学学报, 2019, 45(11): 2291-2300.
	Zhang Z L, Liu J Q, Huang L, et al. A bearing fault diagnosis method based on semi-supervised and transfer learning[J]. Journal of Beijing University of Aeronautics and Astronautics, 2019, 45(11): 2291-2300.
24	毛文涛, 田思雨, 窦智, 等. 一种基于深度迁移学习的滚动轴承早期故障在线检测方法[J]. 自动化学报, 2022, 48(1): 302-314.
	Mao W T, Tian S Y, Dou Z, et al. A new deep transfer learning-based online detection method of rolling bearing early fault[J]. Acta Automatica Sinica, 2022, 48(1): 302-314.
25	Wu H, Zhao J S. Fault detection and diagnosis based on transfer learning for multimode chemical processes[J]. Computers & Chemical Engineering, 2020, 135: 106731.
26	Dai W Y, Yang Q, Xue G R, et al. Boosting for transfer learning[C]// Proceedings of the 24th International Conference on Machine Learning - ICML '07. New York: ACM Press, 2007, 227: 193.
27	Bian X H, Wang K Y, Tan E X, et al. A selective ensemble preprocessing strategy for near-infrared spectral quantitative analysis of complex samples[J]. Chemometrics and Intelligent Laboratory Systems, 2020, 197: 103916.
28	Pardoe D, Stone P. Boosting for regression transfer[C]//Proceedings of the 27th International Conference on Machine Learning. Haifa, Israel, 2010: 863-870.
29	Al-Stouhi S, Reddy C K. Adaptive boosting for transfer learning using dynamic updates[C]//Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Berlin, Heidelberg: Springer, 2011: 60-75.
30	Wold S, Sjöström M, Eriksson L. PLS-regression: a basic tool of chemometrics[J]. Chemometrics and Intelligent Laboratory Systems, 2001, 58(2): 109-130.

[1]	Yue CAO, Chong YU, Zhi LI, Minglei YANG. Industrial data driven transition state detection with multi-mode switching of a hydrocracking unit [J]. CIESC Journal, 2023, 74(9): 3841-3854.
[2]	Chengying ZHU, Zhenlei WANG. Operation optimization of ethylene cracking furnace based on improved deep reinforcement learning algorithm [J]. CIESC Journal, 2023, 74(8): 3429-3437.
[3]	Gang YIN, Yihui LI, Fei HE, Wenqi CAO, Min WANG, Feiya YAN, Yu XIANG, Jian LU, Bin LUO, Runting LU. Early warning method of aluminum reduction cell leakage accident based on KPCA and SVM [J]. CIESC Journal, 2023, 74(8): 3419-3428.
[4]	Xuejin GAO, Yuzhuo YAO, Huayun HAN, Yongsheng QI. Fault monitoring of fermentation process based on attention dynamic convolutional autoencoder [J]. CIESC Journal, 2023, 74(6): 2503-2521.
[5]	Shumin ZHENG, Pengcheng GUO, Jianguo YAN, Shuai WANG, Wenbo LI, Qi ZHOU. Experimental and predictive study on pressure drop of subcooled flow boiling in a mini-channel [J]. CIESC Journal, 2023, 74(4): 1549-1560.
[6]	Xuerong GU, Shuoshi LIU, Siyu YANG. Research on multi-parameter optimization method based on parallel EGO and surrogate-assisted model [J]. CIESC Journal, 2023, 74(3): 1205-1215.
[7]	Sheng’an ZHANG, Guilian LIU. Multi-objective optimization of high-efficiency solar water electrolysis hydrogen production system and its performance [J]. CIESC Journal, 2023, 74(3): 1260-1274.
[8]	Haiou YUAN, Fangjun YE, Shuo ZHANG, Yiqing LUO, Xigang YUAN. Synthesis of heat-integrated distillation sequences with intermediate heat exchangers [J]. CIESC Journal, 2023, 74(2): 796-806.
[9]	Jiahui CHEN, Xinze YANG, Guzhong CHEN, Zhen SONG, Zhiwen QI. A critical discussion on developing molecular property prediction models: density of ionic liquids as example [J]. CIESC Journal, 2023, 74(2): 630-641.
[10]	Yalin WANG, Yuqing PAN, Chenliang LIU. Intermittent process monitoring based on GSA-LSTM dynamic structure feature extraction [J]. CIESC Journal, 2022, 73(9): 3994-4002.
[11]	Xuejin GAO, Kun CHENG, Huayun HAN, Huihui Gao, Yongsheng QI. Fault diagnosis of chillers using central loss conditional generative adversarial network [J]. CIESC Journal, 2022, 73(9): 3950-3962.
[12]	Zhe SUN, Huaqiang JIN, Kang LI, Jiangping GU, Yuejin HUANG, Xi SHEN. Fault diagnosis method of refrigeration and air-conditioning system based on digitized knowledge representation [J]. CIESC Journal, 2022, 73(7): 3131-3144.
[13]	Ling YANG, Guomin CUI, Zhiqiang ZHOU, Yuan XIAO. Fine search strategy applied to mass exchange network synthesis [J]. CIESC Journal, 2022, 73(7): 3145-3155.
[14]	Taoyan ZHAO, Jiangtao CAO, Ping LI, Lin FENG, Yu SHANG. Application of interval type-2 fuzzy immune PID controller to temperature control system for uncatalysed oxidation of cyclohexane [J]. CIESC Journal, 2022, 73(7): 3166-3173.
[15]	Kun WANG, Hongbo SHI, Shuai TAN, Bing SONG, Yang TAO. Local time difference constrained neighborhood preserving embedding algorithm for fault detection [J]. CIESC Journal, 2022, 73(7): 3109-3119.