Research and application of interval prediction method for complex processes based on principal component independent analysis and mixed kernel RVM

doi:10.11949/j.issn.0438-1157.20161559

Abstract

Abstract:

In recent years, higher requirements have been put forward to process monitoring and key variable prediction with increasing complexity of chemical processes. Traditional point predictions do not meet these actual needs nor describe uncertainty concern, so that they could not predict variable trending well. An interval prediction method was proposed from principal component independent analysis and mixed kernel RVM. First, kernel principal component analysis (KPCA) and independent element analysis (ICA) were combined to extract principal components from original variables in complex process and to form independent principal components by independent analysis. Second, mixed kernel from Gauss and polynomial kernel functions and RVM were combined to generate a regression prediction model for the independent principal components, and T distribution was used to make interval estimation on predicted values of the model. Third, comprehensive interval evaluation function was constructed to analyze quality of the interval estimation results. Based on prediction interval coverage probability (PICP) and normal mean prediction interval width (NMPIW), accumulative deviation (AD) was introduced to improve rationality of the interval evaluation. The interval prediction analysis on TE simulation process showed that the proposed interval prediction method had better prediction accuracy and interval estimation quality, which could effectively predict trending of key variables in actual production process.

Key words: kernel principal component analysis, independent component analysis, relevance vector machine, prediction model, interval evaluation

摘要：

近年来，随着化工过程日趋复杂，对过程监控及关键变量预测提出了更高的要求。传统意义上的点预测已不能满足化工过程上的实际需求，且点预测无法描述过程上的不确定性问题，因此不能很好地把握预测变量的趋势。由此，提出了一种基于主元独立性分析（principal component independent analysis，PCIA）与混合核相关向量机（RVM）的区间预测方法。首先，结合核主元成分分析（KPCA）和独立元分析（ICA）对复杂过程原始变量进行主元成分提取和独立性分析，形成独立主元；其次，将高斯核函数与多项式核函数相结合形成混合核，与RVM结合对得到的独立主元进行回归建模预测，并运用T分布对预测值进行区间估计；然后，构造区间评价综合函数对区间估计结果进行优劣分析，在分析预测区间覆盖率（PICP）及预测区间宽度（NMPIW）的基础上，引入累积偏差（AD）提高区间评判的合理性。最后，将所提方法应用到TE仿真过程进行区间预测分析，仿真结果表明，提出的区间预测方法对实际生产过程具有较高的预测精度和区间估计质量，可以有效地预测关键变量的趋势。

关键词: 核主元分析, 独立主元分析, 相关向量机, 预测模型, 区间评价

CLC Number:

TP29

XU Yuan, ZHANG Mingqing. Research and application of interval prediction method for complex processes based on principal component independent analysis and mixed kernel RVM[J]. CIESC Journal, 2017, 68(3): 925-931.

徐圆, 张明卿. 基于主元独立性分析与混合核RVM的复杂过程区间预测方法研究及应用[J]. 化工学报, 2017, 68(3): 925-931.

References 30

[1]	FARUK D O. A hybrid neural network and ARIMA model for water quality time series prediction[J]. Engineering Applications of Artificial Intelligence, 2010, 23(4):586-594.
[2]	XIONG T, BAO Y, HU Z, et al. Forecasting interval time series using a fully complex-valued RBF neural network with DPSO and PSO algorithms[J]. Information Sciences, 2015, 305:77-92.
[3]	KHOSRAVI A, MAZLOUMI E, NAHAVANDI S, et al. Prediction intervals to account for uncertainties in travel time prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2011, 12(2):537-547.
[4]	NIX D A, WEIGEMD A S. Estimating the mean and variance of the target probability distribution[C]//IEEE World Congress on IEEE International Conference on Neural Networks. 1994:55-60
[5]	LI P, DIMITRIS N. Bootstrap prediction intervals for linear, nonlinear and nonparametric autoregressions[J]. Journal of Statistical Planning and Inference, 2014, 177:1-27.
[6]	TRUCIOS C, HOTTA L K. Bootstrap prediction in univariate volatility models with leverage effect[J]. Mathematics and Computers in Simulation, 2016, 120:91-103.
[7]	党宏涛, 杜祖良, 任宏文, 等. 基于Bootstrap方法的平台惯导系统标定参数重复性区间预测[J]. 中国惯性技术学报, 2013, 21(3):411-414. DANG H T, DU Z L, REN H W, et al. Repeatability interval prediction for calibrated parameters of INS based on Bootstrap method[J]. Journal of Chinese Inertial Technology, 2013, 21(3):411-414.
[8]	WANG C, NIU M, SONG Y H, et al. Pareto optimal prediction intervals of electricity price[J]. IEEE Transactions on Power Systems, 2016, 32:1.
[9]	李知艺, 丁剑鹰, 吴迪, 等. 电力负荷区间预测的集成极限学习机方法[J]. 华北电力大学学报, 2014, 41(2):78-88. LI Z Y, DING J Y, WU D, et al. An ensemble model of the extreme learning machine for load interval prediction[J]. Journal of North China Electric Power University, 2014, 41(2):78-88.
[10]	WAN C, XU Z, PINSON P, et al. Probabilistic forecasting of wind power generation using extreme learning machine[J]. IEEE Transactions on Power Systems, 2014, 29(29):1033-1044.
[11]	VAPNIK V N. The Nature of Statistical Learning Theory[M]. New York:Springer-Verlag, 1995:52-123.
[12]	SHRIVASTAVA N A, KHOSRAVI A, PANIGRAHI B K. Prediction interval estimation of electricity prices using PSO-tuned support vector machines[J]. IEEE Transactions on Industrial Informatics, 2015, 11(2):322-331.
[13]	ZHAO J H, DONG Z Y, XU Z, et al. A statistical approach for interval forecasting of the electricity price[J]. IEEE Transactions on Power Systems, 2008, 23(2):267-276.
[14]	DE B K, DE B J, SUYKENS J A. Approximate confidence and prediction intervals for least squares support vector regression[J]. IEEE Transactions on Neural Networks, 2010, 22(1):110-120.
[15]	CHENG Q, TEZCAN J, CHENG J. Confidence and prediction intervals for semiparametric mixed-effect least squares support vector machine[J]. Pattern Recognition Letters, 2014, 40(40):88-95.
[16]	KHOSRAVI A, NAHAVANDI S, CREIGHTON D, et al. Lower upper bound estimation method for construction of neural network-based prediction intervals[J]. IEEE Transactions on Neural Networks, 2011, 22(3):337-46.
[17]	HAO Q, SRINIVASAN D, KHOSRAVI A. Uncertainty handling using neural network-based prediction intervals for electrical load forecasting[J]. Energy, 2014, 73(7):916-925.
[18]	ZHANG G, WU Y, WONG K P, et al. An advanced approach for construction of optimal wind power prediction intervals[J]. IEEE Transactions on Power Systems, 2015, 30(5):2706-2715.
[19]	HAO Q, SRINIVASAN D, KHOSRAVI A. Short-Term load and wind power forecasting using neural network-based prediction intervals[J]. IEEE Transactions on Neural Networks & Learning Systems, 2014, 25(2):303-315.
[20]	KAVOUSI-FARD A, KHOSRAVI A, NAHAVANDI S. A New fuzzy-based combined prediction interval for wind power forecasting[J]. IEEE Transactions on Power Systems, 2015, 31(1):1-9.
[21]	WAN C, XU Z, PINSON P, et al. Optimal prediction intervals of wind power generation[J]. IEEE Transactions on Power Systems, 2014, 29(3):1166-1174.
[22]	HOSEN M, KHOSRAVI A, NAHAVANDI S, et al. Prediction interval-based neural network modelling of polystyrene polymerization reactor-a new perspective of data-based modelling[J]. Chemical Engineering Research & Design, 2014, 92(11):2041-2051.
[23]	韩帅, 李树刚. 基于区间预测模型的流感趋势预测[J]. 计算机仿真, 2014, 31(9):237-242. HAN S, LI S G. Influenza trends forecast based on interval prediction model[J]. Computer Simulation, 2014, 31(9):237-242.
[24]	SCHLKOPF B, SMOLA A, MULLER K. Nonlinear component analysis as a kernel eigenvalue problem[J]. Neural Computation, 1998, 10(5):1299-1319.
[25]	李海波, 柴天佑, 岳恒. 浮选工艺指标KPCA-ELM软测量模型及应用[J]. 化工学报, 2012, 63(9):2892-2898. LI H B, CHAI T Y, YUE H. Soft sensor of technical indices based on KPCA-ELM and application for flotation process[J]. CIESC Journal, 2012, 63(9):2892-2898.
[26]	STEFATOS G, HAMZA A B. Dynamic independent component analysis approach for fault detection and diagnosis[J]. Expert Systems with Applications, 2010, 37(12):8606-8617.
[27]	KANO M, HASEBE S, HASHIMOTO I, et al. Evolution of multivariate statistical process control:application of independent component analysis and external analysis[J]. Computers and Chemical Engineering, 2004, 28(6/7):1157-1166.
[28]	MIANJI F A, ZHANG Y. Robust hyperspectral classification using relevance vector machine[J]. IEEE Transactions on Geoscience & Remote Sensing, 2011, 49(6):2100-2112.
[29]	TIPPING M. Sparse Bayesian learning and the relevance vector machine[J]. Journal of Machine Learning Research, 2001, 1(3):211-244.
[30]	杨树仁, 沈洪远. 基于相关向量机的机器学习算法研究与应用[J]. 计算技术与自动化, 2010, 29(1):43-47. YANG S R, SHEN H Y. Research and application of machine learning algorithm based on relevance vector machine[J]. Computing Technology and Automation, 2010, 29(1):43-47.