Abstract: Identifying factors that exert more influence on system output from data is one of the most challenging tasks in science and engineering. In this work, a sensitivity analysis of the generalized Gaussian process regression (SA-GGPR) model is proposed to identify important factors of the nonlinear counting system. In SA-GGPR, the GGPR model with Poisson likelihood is adopted to describe the nonlinear counting system. The GGPR model with Poisson likelihood inherits the merits of nonparametric kernel learning and Poisson distribution, and can handle complex nonlinear counting systems. Nevertheless, understanding the relationships between model inputs and output in the GGPR model with Poisson likelihood is not readily accessible due to its nonparametric and kernel structure. SA-GGPR addresses this issue by providing a quantitative assessment of how different inputs affect the system output. The application results on a simulated nonlinear counting system and a real steel casting-rolling process have demonstrated that the proposed SA-GGPR method outperforms several state-of-the-art methods in identification accuracy.

非线性计数系统的关键因子辨识方法

[1]Abdi H, 2010. Partial least squares regression and projection on latent structure regression (PLS regression). WIREs Comput Stat, 2(1):97-106. doi: 10.1002/wics.51

[2]Biau G, 2012. Analysis of a random forests model. J Mach Learn Res, 13(1):1063-1095.

[3]Blix K, Camps-Valls G, Jenssen R, 2017. Gaussian process sensitivity analysis for oceanic chlorophyll estimation. IEEE J Sel Top Appl Earth Obs Remote Sens, 10(4):1265-1277. doi: 10.1109/JSTARS.2016.2641583

[4]Bühlmann P, 2012. Bagging, boosting and ensemble methods. In: Gentle JE, Härdle WK, Mori Y (Eds.), Handbook of Computational Statistics. Springer, Berlin, Germany, p.985-1022. doi: 10.1007/978-3-642-21551-3_33

[5]Chan AB, Dong DX, 2011. Generalized Gaussian process models. Proc 24^th IEEE Conf on Computer Vision and Pattern Recognition, p.2681-2688. doi: 10.1109/CVPR.2011.5995688

[6]Coxe S, West SG, Aiken LS, 2009. The analysis of count data: a gentle introduction to Poisson regression and its alternatives. J Pers Assess, 91(2):121-136. doi: 10.1080/00223890802634175

[7]Cutler A, Cutler DR, Stevens JR, 2012. Random forests. In: Zhang C, Ma YQ (Eds.), Ensemble Machine Learning: Methods and Applications. Springer, Boston, USA, p.157-175. doi: 10.1007/978-1-4419-9326-7

[8]Ge ZQ, 2018. Process data analytics via probabilistic latent variable models: a tutorial review. Ind Eng Chem Res, 57(38):12646-12661. doi: 10.1021/acs.iecr.8b02913

[9]Ge ZQ, Song ZH, Ding SX, et al., 2017. Data mining and analytics in the process industry: the role of machine learning. IEEE Access, 5:20590-20616. doi: 10.1109/ACCESS.2017.2756872

[10]Hutchinson MK, Holtman MC, 2005. Analysis of count data using Poisson regression. Res Nurs Health, 28(5):408-418. doi: 10.1002/nur.20093

[11]Kano M, Ogawa M, 2010. The state of the art in chemical process control in Japan: good practice and questionnaire survey. J Process Contr, 20(9):969-982. doi: 10.1016/j.jprocont.2010.06.013

[12]Mohri M, Rostamizadeh A, Talwalkar A, 2018. Foundations of Machine Learning. MIT Press, Cambridge, UK.

[13]Nickisch H, Rasmussen CE, 2008. Approximations for binary Gaussian process classification. J Mach Learn Res, 9:2035-2078.

[14]Rasmussen CE, Williams CKI, 2006. Gaussian Processes for Machine Learning. MIT Press, Cambridge, UK.

[15]Rasmussen CE, Nickisch H, 2010. Gaussian processes for machine learning (GPML) toolbox. J Mach Learn Res, 11:3011-3015.

[16]Shao WM, Tian XM, 2015. Adaptive soft sensor for quality prediction of chemical processes based on selective ensemble of local partial least squares models. Chem Eng Res Des, 95:113-132. doi: 10.1016/j.cherd.2015.01.006

[17]Sugiyama M, 2015. Introduction to Statistical Machine Learning. Morgan Kaufmann Publishers, Waltham, MA, USA.

[18]Talabis M, McPherson R, Miyamoto I, et al., 2014. Information Security Analytics: Finding Security Insights, Patterns, and Anomalies in Big Data. Syngress, Waltham, MA, USA.

[19]Wang ZX, He QP, Wang J, 2015. Comparison of variable selection methods for PLS-based soft sensor modeling. J Process Contr, 26:56-72. doi: 10.1016/j.jprocont.2015.01.003

[20]Wold S, Sjöström M, Eriksson L, 2001. PLS-regression: a basic tool of chemometrics. Chemom Intell Lab Syst, 58(2):109-130. doi: 10.1016/S0169-7439(01)00155-1

[21]Zhang XM, Kano M, Li Y, 2017. Locally weighted kernel partial least squares regression based on sparse nonlinear features for virtual sensing of nonlinear time-varying processes. Comput Chem Eng, 104:164-171. doi: 10.1016/j.compchemeng.2017.04.014

[22]Zhang XM, Kano M, Matsuzaki S, 2019. A comparative study of deep and shallow predictive techniques for hot metal temperature prediction in blast furnace ironmaking. Comput Chem Eng, 130:106575. doi: 10.1016/j.compchemeng.2019.106575

[23]Zhang XM, Kano M, Song ZH, 2020a. Optimal weighting distance-based similarity for locally weighted PLS modeling. Ind Eng Chem Res, 59(25):11552-11558. doi: 10.1021/acs.iecr.9b06847

[24]Zhang XM, Wada T, Fujiwara K, et al., 2020b. Regression and independence based variable importance measure. Comput Chem Eng, 135:106757. doi: 10.1016/j.compchemeng.2020.106757