Soft sensing modeling of metatitanic acid particle size based on machine learning

Lu Ruifang; Liu Chan; Sun Wei; Wu Jianchun; Sun Qiang

doi:10.7513/j.issn.1004-7638.2021.02.007

Volume 42 Issue 2

Apr. 2021

Turn off MathJax

Article Contents

Article Navigation > IRON STEEL VANADIUM TITANIUM > 2021 > 42(2): 36-42

Lu Ruifang, Liu Chan, Sun Wei, Wu Jianchun, Sun Qiang. Soft sensing modeling of metatitanic acid particle size based on machine learning[J]. IRON STEEL VANADIUM TITANIUM, 2021, 42(2): 36-42. doi: 10.7513/j.issn.1004-7638.2021.02.007

Citation:

Lu Ruifang, Liu Chan, Sun Wei, Wu Jianchun, Sun Qiang. Soft sensing modeling of metatitanic acid particle size based on machine learning[J]. IRON STEEL VANADIUM TITANIUM, 2021, 42(2): 36-42. doi: 10.7513/j.issn.1004-7638.2021.02.007

Citation:

PDF( 816 KB)

Soft sensing modeling of metatitanic acid particle size based on machine learning

doi: 10.7513/j.issn.1004-7638.2021.02.007

Lu Ruifang^{1, 2
,},
Liu Chan¹,
Sun Wei³,
Wu Jianchun¹,
Sun Qiang^{3
,
,}

1.
State Key Laboratory of Vanadium and Titanium Resources Comprehensive Utilization, Pangang Group Research Institute Co., Ltd., Panzhihua 617000, Sichuan, China
2.
School of Chemistry and Chemical Engineering, Chongqing University, Chongqing 400030, China
3.
School of Metallurgy, Northeastern University, Shenyang 110006, Liaoning, China

Received Date: 2020-07-21
Publish Date: 2021-04-10

Abstract

Abstract

Taking 3608 data of a titanium dioxide production line by sulfuric acid process as samples, the correlation between the five attribute variables of the industrial titanium sulfate solution and the particle size of metatitanic acid D₅₀ was investigated by Pearson coefficient and statistical p value, and the LOF algorithm was used to clean the outlier data and improve the data quality. On this basis, the regression model algorithm of metatitanic acid particle size control was compiled by Python language based on six models of Ridge, Lasso, KNN, ANN, Random forest and SVR. The regression prediction results of the six algorithms applied to the whole set of data have no significant difference. After the outlier processing, the RMSE and MAE of the data fluctuate around 0.276 and 0.197 respectively, and the model effect is better than that of the model before the outlier processing. Furthermore, through the ensemble learning model of ANN, Random Forest and SVR, the regression prediction effect can be significantly improved, and the RMSE and MAE values decreases to 0.245 and 0.192 respectively.
- TiO₂,
- metatitanic acid,
- particle size,
- soft sensing,
- machine learning

FullText(HTML)

References(10)

References

[1]	Santacesatia E. Kinetics of titanium dioxide precipitation by thermal hydrolysis[J]. Journal of Colloid and Interface Science, 1986, 111(1): 45-53.
[2]	Duncan J F, Richards R G. Solution equilibriums, kinetics and mechanism[J]. N. Z J. Sci., 1976,19(2):179−183.
[3]	Chen Hongyun, Jin Bin, Dong Yingjie, et al. Study on determination of the average particle size of TiO₂ by use of laser particle sizer[J]. Paint & Coating Industry, 2002,32(6):40−42. (陈洪云, 金斌, 董英杰, 等. 激光粒度仪测定钛白粉平均粒径的研究[J]. 涂料工业, 2002,32(6):40−42. doi: 10.3969/j.issn.0253-4312.2002.06.016
[4]	（张立德, 牟季美. 纳米材料与纳米结构[M]. 北京: 科学出版社, 2002.） Zhang Lide, Mou Jimei. Nanometer materials & nanometer structure[M]. Beijing: Science Press, 2002.
[5]	（GB/T 19627—2005. 粒度分析光子相关光谱法[S].） GB/T 19627—2005. Particle size analysis- photon correlation spectroscopy[S].
[6]	Tian Congxue, Hu Hongfei, Du Jianqiao, et al. Determination of the particle size distribution of metatitanic acid by photon correlation spectroscopy[J]. Iron Steel Vanadium Titanium, 2010,31(2):15−19. (田从学, 胡鸿飞, 杜剑桥, 等. 用光子相关光谱法测定偏钛酸粒度分布[J]. 钢铁钒钛, 2010,31(2):15−19. doi: 10.7513/j.issn.1004-7638.2010.02.004
[7]	（何桢. 六西格玛管理[M]. 北京: 中国人民大学出版社, 2014.） He Zhen. Six Sigma management[M]. Beijing: China Renmin University Press, 2014.
[8]	Kadlec P, Grbic R, Gabrys B. Review of adaptation mechanisms for data-driven soft sensors[J]. Computers & Chemical Engineering, 2011,35(1):1−24.
[9]	Kano M, Ogawa M. The state of the art in chemical process control in Japan: Good practice and questionnaire survey[J]. Journal of Process Control, 2010,20(9):969−982. doi: 10.1016/j.jprocont.2010.06.013
[10]	Zhao F, Lu N, Lu J. Quality control of batch processes using natural gradient based model-free optimization[J]. Industrial & Engineering Chemistry Research, 2014,53(44):17419−17428.