LI Jun, LI Kai
（School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China）
Abstract： Aiming at the problem of soft sensing modeling for chemical process with strong nonlinearity and complexity, a soft sensing modeling method based on kernel-based orthogonal projections to latent structures (K-OPLS) is proposed. Orthogonal projections to latent structures (O-PLS) is a general linear multi-variable data modeling method. It can eliminate systematic variations from descriptive variables (input) that are orthogonal to response variables (output). In the framework of O-PLS model, K-OPLS method maps descriptive variables to high-dimensional feature space by using “kernel technique” to calculate predictive components and response-orthogonal components in the model. Therefore, the K-OPLS method gives the non-linear relationship between the descriptor and the response variables, which improves the performance of the model and enhances the interpretability of the model to a certain extent. To verify the validity of K-OPLS method, it was applied to soft sensing modeling of component content of debutane tower base butane (C4), the quality index of the key product output for industrial fluidized catalytic cracking unit (FCCU) and H2S and SO2 concentration in sulfur recovery unit (SRU). Compared with support vector machines (SVM), least-squares support-vector machine (LS-SVM), support vector machine with principal component analysis (PCA-SVM), extreme learning machine (ELM), kernel based extreme learning machine (KELM) and kernel based extreme learning machine with principal component analysis(PCA-KELM) methods under the same conditions, the experimental results show that the K-OPLS method has superior modeling accuracy and good model generalization ability.
Key words： kernel method; orthogonal projection to latent structures (K-OPLS); soft sensing; chemical process
CLD number： TP183 doi： 10.3969/j.issn.1674-8042.2020.01.003
References
［1］Fortuna L, Graziani S, Rizzo A, et al. Soft sensors for monitoring and control of industrial processes. Springer Science & Business Media, USA, 2006.
［2］Souza F A A, Araujo R, Mendes J. Review of soft sensor methods for regression applications. Chemometrics and Intelligent Laboratory Systems, 2016, 152: 69-79.
［3］Kadlec P, Grbic R, Gabrys B. Review of adaptation mechanisms for data-driven soft sensors. Computers & Chemical Engineering, 2011, 35(1): 1-24.
［4］Muoz D A, Alvarez H. Phenomenological based soft sensor for online estimation of slurry rheological properties. International Journal of Automation and Computing, 2019, 16(5): 696-706.
［5］Huang Y, Zang H, Cheng X, et al. Data-driven soft sensor for animal cell suspension culture process based on DRVM. Applied Soft Computing, 2019, 77: 34-40.
［6］Wang Z X, He Q P, Wang J. Comparison of variable selection methods for PLS-based soft sensor modeling. Journal of Process Control, 2015, 26: 56-72.
［7］Yuan X, Ye L, Bao L, et al. Nonlinear feature extraction for soft sensor modeling based on weighted probabilistic PCA. Chemometrics and Intelligent Laboratory Systems, 2015, 147: 167-175.
［8］Zhao T, Li P, Cao J. Soft sensor modeling of chemical process based on self-organizing recurrent interval type-2 fuzzy neural network. ISA Transactions, 2019, 84: 237-246.
［9］Duchanoy C A, Moreno-Armendáriz M A, Urbina L, et al. A novel recurrent neural network soft sensor via a differential evolution training algorithm for the tire contact patch. Neurocomputing, 2017, 235: 71-82.
［10］Zhang M, Liu X. A soft sensor based on adaptive fuzzy neural network and support vector regression for industrial melt index prediction. Chemometrics and Intelligent Laboratory Systems, 2013, 126: 83-90.
［11］Canete J F D, Saz-Orozco P D, Baratti R, et al. Soft-sensing estimation of plant effluent concentrations in a biological wastewater treatment plant using an optimal neural network. Expert Systems with Applications, 2016, 63: 8-19.
［12］Liu Y, Hu N, Wang H, et al. Soft chemical analyzer development using adaptive least-squares support vector regression with selective pruning and variable moving window size. Industrial & Engineering Chemistry Research, 2009, 48(12): 5731-574.
［13］Ge Z. Supervised latent factor analysis for process data regression modeling and soft sensor application. IEEE Transactions on Control Systems Technology, 2016, 24(3): 1004-1011.
［14］Fortuna L, Graziani S, Xibilia M G. Soft sensors for product quality monitoring in debutanizer distillation columns. Control Engineering Practice, 2005, 13(4): 499-508.
［15］Zheng W, Liu Y, Gao Z, et al. Just-in-time semi-supervised soft sensor for quality prediction in industrial rubber mixers. Chemometrics and Intelligent Laboratory Systems, 2018, 180: 36-41.
［16］Zhang M, Liu X, Zhang Z. A soft sensor for industrial melt index prediction based on evolutionary extreme learning machine. Chinese Journal of Chemical Engineering, 2016, 24(8): 1013-1019.
［17］Trygg J, Wold S. Orthogonal projections to latent structures (O-PLS). Journal of Chemometrics, 2002, 16(3): 119-128.
［18］Rantalainen M, Bylesj M, Cloarec O, et al. Kernel-based orthogonal projections to latent structures (K-OPLS). Journal of Chemometrics, 2007, 21(7-9): 376-385.
［19］Shi X, Xiong W. Approximate linear dependence criteria with active learning for smart soft sensor design. Chemometrics and Intelligent Laboratory Systems, 2018, 180: 8-95.
［20］Li Q, Xing L, Liu W, et al. Adaptive soft sensor based on a moving window just-in-time learning LS-SVM for distillation processes. IFAC-PapersOnLine, 2015, 48(28): 51-56.
［21］Zhai G, Chen J, Wang S, et al. Material identification of loose particles in sealed electronic devices using PCA and SVM. Neurocomputing, 2015, 148: 222-228.
［22］Geng Z, Dong J, Chen J, et al. A new self-organizing extreme learning machine soft sensor model and its applications in complicated chemical processes. Engineering Applications of Artificial Intelligence, 2017, 62: 38-50.
［23］Lu S, Yu H, Dong H, et al. Single-step prediction method of burning zone temperature based on real-time wavelet filtering and KELM. Engineering Applications of Artificial Intelligence, 2018, 70: 142-148.
［24］Xu D, Chen Y, Chen X, et al. Multi-model soft measurement method of the froth layer thickness based on visual features. Chemometrics and Intelligent Laboratory Systems, 2016, 154: 112-121.
［25］Li X L, Su H Y, Chu J A. Multiple model soft sensor based on affinity propagation,Gaussian process and Bayesian committee machine. Chinese Journal of Chemical Engineering, 2009, 17(1): 95-99.
［26］Ge Z Q, Song Z H. A comparative study of just-in-time-learning based methods for online soft sensor modeling. Chemometrics and Intelligent Laboratory Systems, 2010, 104(2): 306-317.
［27］Trygg J, Wold S. O2-PLS, a two-block (X-Y) latent variable regression (LVR) method with an integral OSC filter. Journal of Chemometrics, 2003, 17(1): 53-64.
［28］Olufemi A A, Armando B C. Dynamic neural networks partial least squares(DNNPLS) identification of multivariable processes. Computers and Chemical Engineering, 2003, 27(2): 43-155.
K-OPLS方法在化工软测量建模中的应用
李 军， 李 恺
（兰州交通大学 自动化与电气工程学院， 甘肃 730070）
摘 要：针对强非线性复杂化工过程的软测量建模问题， 提出了一种基于核隐变量正交投影（K-OPLS）的建模方法。 隐变量正交投影(O-PLS)是一种通用的线性多变量数据建模方法， 它可以消除与响应变量（输出）正交的描述变量（输入）的总体变化。 在O-PLS模型框架下， K-OPLS方法利用“核技巧”将描述变量映射到高维特征空间， 计算模型中的预测成分和响应-正交成分。 因此， K-OPLS方法通过给出描述与响应变量之间的非线性关系， 在一定程度上提高了模型的性能， 增强了模型的可解释性。 为了验证K-OPLS方法的有效性， 将其分别应用于脱丁烷塔基丁烷（C4）组分含量估计、 工业流化催化裂化装置(FCCU)关键产品产量预测、 硫回收装置（SRU）中H2S和SO2浓度预测的软测量建模实例中。 实验结果表明， 在相同条件下， 与支持向量机(SVM)、 最小二乘支持向量机(LSSVM)、 主元分析-支持向量机(PCA-SVM)、 极限学习机(ELM)、 核极限学习机(KELM)和PCA-KELM方法相比较， K-OPLS方法具有更好的建模精度和模型泛化能力。
关键词： 核学习； 隐变量正交投影； 软测量； 化工过程
引用格式： LI Jun, LI Kai. Application in soft sensing modeling of chemical process based on K-OPLS method. Journal of Measurement Science and Instrumentation, 2020, 11（1）： 17-27. ［doi： 10.3969／j.issn.1674-8042.2020.01.003］
[full text view]
