Non-Gaussian Information Based JITL Soft Sensor Model

Abstract

Abstract:

Abstract： In order to monitor the non-Gaussian industrial process, a novel non-Gaussian information based JITL soft sensor model was proposed in this paper. First, the non-Gaussian dissimilarity measure selects the most relevant local modeling samples of JITL model. Then, an ICA-PLS regression method was established on the most relevant local samples for quality variable prediction. From the local relevant sample selection to the final regression model construction, the proposed method can efficiently extract the higher-order statistical information and is well suited for the non-Gaussian process quality prediction. Meanwhile, the proposed method can well cope with the changes in process characteristics as well as nonlinearity. The validity of the proposed method was verified on the sulfur recovery unit.

Key words: non-Gaussian dissimilarity measure, just-in-time learning(JITL), quality prediction, sulfur recovery unit

CLC Number:

TP 274

LI Yuan,ZHANG Xinmin. Non-Gaussian Information Based JITL Soft Sensor Model[J]. Journal of Shanghai Jiaotong University, 2015, 49(06): 897-901.

References

［1］Kano M, Fujiwara K. Virtual sensing technology in process industries: Trends and challenges revealed byrecent industrial applications［J］. J Chem Eng Jpn, 2013, 46(1): 117.

［2］Shao X, Wang W, Hou Z, et al. A new regression method based on independent component analysis［J］. Talanta, 2006, 69(3): 676680.

［3］Chen J, Wang X. A new approach to nearinfrared spectral data analysis using independent component analysis［J］. J Chem Inf Comput Sci, 2001, 41(4): 9921001.

［4］Kaneko H, Arakawa M, Funatsu K. Development of a new regression analysis method using independent component analysis［J］. Journal of Chemical Information and Modeling, 2008, 48(3): 534541.

［5］Fujiwara K, Kano M, Hasebe S, et al. Softsensor development using correlationbased justintime modeling［J］. AICHE J, 2009, 55(7): 17541765.

［6］Ge Z, Song Z. A comparative study of justintimelearning based methods for online soft sensor modeling［J］. Chemom Intell Lab Syst, 2010, 104(2): 306317.

［7］Hyvrinen A, Oja E. Independent component analysis: Algorithms and applications［J］. Neural Networks, 2000, 13(4): 411430.

［8］周东华,李钢,李元.数据驱动的过程故障检测与诊断技术［M］.北京：科学出版社, 2011：23113.

［9］Rashid M M, Yu J. A new dissimilarity method integrating multidimensional mutual information and independent component analysis for nongaussian dynamic process monitoring［J］. Chemom Intell Lab Syst, 2012, 115：4458.

［10］Ge Z, Song Z. Nonlinear soft sensor development based on relevance vector machine［J］. Ind Eng Chem Res, 2010, 49(18): 86858693.

［11］Xie L, Zeng J, Gao C. Novel justintime learningbased soft sensor utilizing nongaussian information［J］. Control Systems Technology, IEEE Transactions on, 2014, 22(1): 360368.