Enhanced real-time quality prediction model based on feature selected nonlinear calibration techniques

详细信息    查看全文

• 作者：Hyun-Woo Cho (1)
  
  1. Department of Industrial and Management Engineering ; Daegu University ; Kyungsan ; 712-714 ; Republic of Korea
  
• 关键词：Process data ; Monitoring ; Quality prediction ; Feature selection ; Nonlinear method
• 刊名：The International Journal of Advanced Manufacturing Technology
• 出版年：2015
• 出版时间：April 2015
• 年：2015
• 卷：78
• 期：1-4
• 页码：633-640
• 全文大小：804 KB
• 参考文献：1. Zhao, C, Gao, F, Sun, Y (2013) Between-phase calibration modeling and transition analysis for phase-based quality interpretation and prediction. AIChE J 59: pp. 108-119 CrossRef
  2. Qin, SJ, Zheng, Y (2013) Quality-relevant and process-relevant fault monitoring with concurrent projection to latent structures. AIChE J 59: pp. 496-504 CrossRef
  3. Eriksson, L, Trygg, J, Wold, S (2014) A chemometrics toolbox based on projections and latent variables. J Chemometr 28: pp. 332-346 CrossRef
  4. Sharma, S, Goodarzi, M, Ramon, H, Saeys, W (2014) Performance evaluation of preprocessing techniques utilizing expert information in multivariate calibration. Talanta 121: pp. 105-112 CrossRef
  5. Zhaoa, J, Yan, G, Fenga, B, Mao, W, Bai, J (2013) An adaptive support vector regression based on a new sequence of unified orthogonal polynomials. Pattern Recogn 46: pp. 899-913 CrossRef
  6. Bunke, H, Riesen, K (2012) Towards the unification of structural and statistical pattern recognition. Pattern Recogn Lett 33: pp. 811-825 CrossRef
  7. Rosipal, R, Trejo, LJ (2001) Kernel partial least squares regression in reproducing kernel Hilbert space. J Mach Learn Res 2: pp. 97-123
  8. Zhang, Y (2009) Enhanced statistical analysis of nonlinear processes using KPCA, KICA and SVM. Chem Eng Sci 64: pp. 801-811 CrossRef
  9. Singh, KP, Gupta, S, Rai, P (2014) Predicting dissolved oxygen concentration using kernel regression modeling approaches with nonlinear hydro-chemical data. Environ Monit Assess 186: pp. 2749-2765 CrossRef
  10. Galelli, S, Castelletti, A (2013) Tree-based iterative input variable selection for hydrological modeling. Water Resour Res 49: pp. 4295-4310 CrossRef
  11. Leardi, R (2001) Genetic algorithms in chemometrics and chemistry: a review. J Chemom 15: pp. 559-569 CrossRef
  12. Wold, S, Antti, H, Lindgren, F, 脰hman, J (1998) Orthogonal signal correction of nearinfrared spectra. Chemometr Intell Lab Syst 44: pp. 175-185 CrossRef
  13. Ge, Z, Song, Z, Gao, F (2013) Review of recent research on data-based process monitoring. Ind Eng Chem Res 52: pp. 3543-3562
  14. Westerhuis, J, Jong, S, Smilde, AK (2001) Direct orthogonal signal correction. Chemometr Intell Lab Syst 56: pp. 13-25 CrossRef
  15. Yu, J (2013) A support vector clustering-based probabilistic method for unsupervised fault detection and classification of complex chemical processes using unlabeled data. AIChE J 59: pp. 407-419 CrossRef
  16. Yu S, Yu K, Tresp V, Kriegel H, Wu M (2006) Supervised probabilistic principal component analysis. Proceedings of the 12th International Conference on Knowledge Discovery and Data Mining (SIGKDD):464鈥?73
  17. Blommers, MJJ, Lucasius, CB, Kateman, G, Kaptein, R (1992) Conformation analysis of a dinucleotide photodimer with the aid of the genetic algorithm. Biopolymers 32: pp. 45-52 CrossRef
  18. Leardi, R, Gonzalez, AL (1998) Genetic algorithms applied to feature selection in PLS regression: how and when to use them. Chemometr Intell Lab Syst 41: pp. 195-207 CrossRef
  19. Kemsley, EK (2001) A hybrid classification method: discrete canonical variate analysis using a genetic algorithm. Chemometr Intell Lab Syst 55: pp. 39-51 CrossRef
  20. Esteban-D铆ez, I, Gonz谩lez-S谩iz, JM, G贸mez-C谩mara, D, Pizarro Millan, C (2006) Multivariate calibration of near infrared spectra by orthogonal wavelet correction using a genetic algorithm. Anal Chim Acta 555: pp. 84-95 CrossRef
  21. Majak, J, Pohlak, M (2010) Decomposition method for solving optimal material orientation problems. Compos Struct 92: pp. 1839-1845 CrossRef
  22. Deb K, Agrawal S, Pratap A, Meyarivan T (2000) A fast elitist non-dominated sorting genetic algorithm for multi-objective optimization: NSGA-II Lecture Notes in Comp Sci 1917:849鈥?58
  23. Wold, S (1978) Cross-validatory estimation of components in factor and principal components models. Technometrics 20: pp. 397-405 CrossRef
  
• 刊物类别：Engineering
• 刊物主题：Industrial and Production Engineering
  Production and Logistics
  Mechanical Engineering
  Computer-Aided Engineering and Design
  
• 出版者：Springer London
• ISSN：1433-3015

文摘

This paper evaluates multivariate statistical calibration models for predicting final quality values from process variables. The use of a feature selection technique for multivariate calibration is also provided. Instead of using a full set of process variables, some process variables selected can be used. The objective of such feature selection schemes is to eliminate non-informative variables producing better prediction performance. In this work, genetic algorithm is used as an optimization tool. The performance of the proposed calibration model is demonstrated using real process data. The quality of the final products from the plant is not measured in a real-time basis. Due to the time delay related to measuring final quality values, reliable and timely prediction of the quality characteristics is quite important for safe and efficient operation. By adopting a feature selection scheme along with a filtering step, the prediction performance improved because of the exclusion of non-informative features. The nonlinear calibration models with feature selection and a preprocessing step were shown to produce better performance than those without these two steps. In addition, most of the calibration models considered here benefits from the use of a feature selection step in this case study.