Abstract




 
   

IJE TRANSACTIONS A: Basics Vol. 31, No. 4 (April 2018) 372-379    Article in Press

PDF URL: http://www.ije.ir/Vol31/No4/A/24.pdf  
downloaded Downloaded: 0   viewed Viewed: 110

  ONLINE MONITORING FOR INDUSTRIAL PROCESSES QUALITY CONTROL USING TIME VARYING PARAMETER MODEL
 
R. Parvizi Moghadam
 
( Received: November 22, 2017 – Accepted: January 04, 2018 )
 
 

Abstract    A novel data-driven soft sensor is designed for online product quality prediction and control performance modification in industrial units. A combined approach of time variable parameter (TVP) model, dynamic auto regressive exogenous variable (DARX) algorithm, nonlinear correlation analysis and criterion-based elimination method is introduced in this work. The soft sensor performance validation is tested by data set of an industrial SRU. The comparative study indicated the result associated with more robust soft sensor and more appropriate performance index values compared to other methods for SRU soft sensor design in diverse achievements. Due to high prediction accuracy, low complication of the model and also time saving, this technique can be very noticeable in industrial processes control.

 

Keywords    Soft sensor, time varying parameter, SRU, Quality estimation, Identification, Data- based modeling

 

چکیده    یک حسگر نرم داده­محور جدید برای پیش­بینی آنلاین و بهبود عملکرد کنترل کیفیت محصول در واحدهای صنعتی طراحی شده است. رویکرد ترکیبی مدل پارامتری متغیر با زمان، الگوریتم دینامیکی متغیر خارجی خودرگرسیون، آنالیز همبستگی غیرخطی و روش حذفی با معیار ارزیابی عملکرد در این تحقیق معرفی شده است. اعتبار عملکرد حسگر نرم به وسیله بخشی از داده­های صنعتی واحد بازیافت گوگرد ارزیابی شد. نتایج دلالت بر مقاومت بیشتر و شاخص عملکردی مناسب­تر این حسگر در مقایسه با نتایج حاصل از دیگرروش­های به کار گرفته شده برای طراحی حسگر نرم واحد بازیافت گوگرد، در سایر تحقیقات داشت. به واسطه­ی دقت پیش­بینی بالا، عدم پیچیدگی مدل حاصل و صرفه­جویی در زمان، این تکنیک می­تواند در کنترل فرایندهای صنعتی بسیار مورد توجه قرار گیرد.

References    1. Fortuna, L., Graziani, S. and Xibilia, M.G., "Soft sensors for monitoring and control of industrial processe, NewYork, Springer,  (2007). 2. Ramli, N.M., Hussain, M.A., Jan, B.M. and Abdullah, B., "Composition prediction of a debutanizer column using equation based artificial neural network model", Neurocomputing,  Vol. 131, No., (2014), 59-76. 3. Fortuna, L., Graziania, S. and Xibilia, M.G., "Soft sensors for product qualitymonitoring in debutanizer distillation columns", Control Engineering Practice,  Vol. 13, No., (2005), 499-508. 4. Kadlec, P., Gabrys, B. and Strandtb, S., "Data-driven soft sensors in the process industry", Computers and Chemical Engineering,  Vol. 33, No., (2009), 795–814. 5. Pani, A.K., Amin, K.G. and Mohanta, H.K., "Soft sensing of product quality in the debutanizer column with principal component analysis and feed-forward artificial neural network", Alexandria Engineering Journal,  Vol. 55, No., (2016), 1667- 1674. 6. Kano, M., Showchaiya, N., Hasebe, S. and Hashimoto, I., "Hashimoto, inferential control of distillation compositions:  Selection of model and control configuration", Control Engineering Practice,  Vol. 11, No. 8, (2003), 927- 933. 7. Kim, S., Okajimaa, R., Kanob, M. and Hasebe, S., "Development of soft sensor using locally weighted pls with adaptive similarity measure", Chemometrics and Intelligent Laboratory Systems,  Vol. 124, No., (2013), 43- 49. 8. Komulainena, T., Souranderb, M. and Jämsä-Jounela, S.-L., "An online application of dynamic pls to a de-aromatization process", Computers & Chemical Engineering,  Vol. 28, No. 12, (2004). 9. Shao, W., Tian, X., Wang, P., Deng, X. and Chen, S., "Online soft sensor design using local partial least squares models with adaptive process state partition", Chemometrics and Intelligent Laboratory Systems,  Vol. 144, No., (2015), 108- 121. 10. Ge, Z. and Song, Z., "Semi supervised bayesian method for soft sensor modeling with unlabeled data samples", AIChE Journal,  Vol. 57, No. 8, (2011), 2109–2119 11. Wang, Y.-J., Jia, M.-X. and Mao, Z.-Z., "A fast monitoring method for multiple operating batch processes with incomplete modeling data types", Journal of Industrial and Engineering Chemistry,  Vol. 21, No., (2015), 328-337. 12. Zhang, X., Yan, W., Zhao, X. and Shao, H., "Nonlinear real-time process monitoring and fault diagnosis based on principal component analysis and kernel fisher discriminant analysis", Chemical Engineering & Technology,  Vol. 30, No. 9, (2007), 1203–1211. 13. Ma, M.-D., Kob, J.-W., Wang, S.-J., Wud, M.-F., Jangd, S.-S., Shiehe, S.-S. and Wong, D.S.-H., "Development of adaptive soft sensor based on statistical identification of  key variables", Control Engineering Practice,  Vol. 17, No. 9, (2009), 1026- 1034. 14. Chew, C.M., Aroua, M.K. and Hussain, M.A., "A practical hybrid modelling approach for the prediction of potential fouling parameters in ultrafiltration membrane water treatment plant", Journal of Industrial and Engineering Chemistry,  Vol. 45, No., (2017), 145-155. 15. Naeini, M.K. and Bayati, N., "Pattern recognition in control chart using neural network based on a new statistical feature", International Journal of Engineering,  Vol. 30, No. 9, (2017), 1372-1380. 16. Park, S. and Ha, C., "A nonlinear soft sensor based on multivariate smoothing procedure for quality estimation in distillation columns", Computers & Chemical Engineering,  Vol. 24, No. 2-7, (2000), 871- 877. 17. Kadlec, P. and Gabrys, B., "Adaptive local learning soft sensor for inferential control support", in Computational Intelligence for Modelling Control & Automation, Vienna, Austria IEEE. Vol., No. Issue, (2008 of Conference). 18. Radhakrishnan, V.R. and Mohamed, A.R., "Neural networks for the identification and control of blast furnace hot metal quality", Journal of Process Control,  Vol. 10, No. 6, (2000), 509- 524. 19. Liu, Y. and Chen, J., "Integrated soft sensor using just-in-time support vector regression and probabilistic analysis for quality prediction of multi-grade processes", Journal of Process Control,  Vol. 23, No. 6, (2013), 793-804. 20. Jin, H., Chen, X., Yang, J. and Wu, L., "Adaptive soft sensor modeling framework based on just-in-time learning and kernel partial least squares regression for non- linear multiphase batch processes", Computers & Chemical Engineering,  Vol. 71, No., (2014), 77-93. 21. Fujiwara, K., Kano, M., Hasebe, S. and Takinami, A., "Soft-sensor development using correlation-based just-in-time modeling", AIChE Journal,  Vol. 55, No. 7, (2009), 1754-1765. 22. Kadlec, P. and Gabrys, B., "Adaptive online prediction soft sensing without historical data", in Neural Networks (IJCNN), The 2010 International Joint Conference, Barcelona, Spain IEEE. Vol., No. Issue, (2010 of Conference), 1-8. 23. Ge, Z. and Song, Z., "A comparative study of just-in-time-learning based methods for online soft sensor modeling", Chemometrics and Intelligent Laboratory Systems,  Vol. 104, No. 2, (2010). 24. Bosca, S. and Fissore, D., "Design and validation of an innovative soft-sensor for pharmaceuticals freeze-drying monitoring", Chemical Engineering Science,  Vol. 66, No. 21, (2011), 5127- 5136. 25. Khatibisepehr, S., Huang, B. and Khare, S., "Design of inferential sensors in the process industry: A review of bayesian methods", Journal of Process Control,  Vol. 23, No. 10, (2013), 1575- 1596. 26. McIntyre, N., Young, P., Orellana, B., Marshall, M., Reynolds, B. and Wheater, H., "Identification of nonlinearity in rainfall-flow response using data-based mechanistic modeling", WATER RESOURCES RESEARCH,  Vol. 47, No., (2011). 27. Abbasi, M., Soleymani, A.R. and Parssa, J.B., "Operationsimulation of a recycled electrochemical ozone generator using artificial neural network", Chemical Engineering Research and Design,  Vol. 92, No. 11, (2014), 2618–2625. 28. Hosen, M.A., Khosravi, A., Nahavandi, S. and Creighton, D., "Prediction interval-based neural network modeling of polystyrene polymerization reactor—a new perspective of data-based modeling", Chemical Engineering Research and Design,  Vol. 92, No. 11, (2014), 2041–2051. 29. Mitra, K. and Ghivari, M., "Modeling of an industrial wet grinding operation using data-driven techniques. Comput", Computers & Chemical Engineering,  Vol. 30, No. 3, (2006), 508-520. 30. Bidar, B., Sadeghi, J., Shahraki, F. and Khalilipour, M.M., "Data-driven soft sensor approach for online quality prediction using state dependent parameter models", Chemometrics and Intelligent Laboratory Systems,  Vol. 162, No., (2017), 130–141. 31. Taylor, C.J., Pedregal, D.J., Young, P. and Tych, W., "Environmental time series analysis and forecasting with the captain toolbox", Environmental Modelling & Software,  Vol. 22, No., (2007), 797-814. 32. Young, P.C., "Recursive estimation and time-series analysis", Seconded ed, New York, Springer,  (2011). 33. Young, P.C., MCKENNA, P. and BRUUN, J., "Identification of non-linear stochastic systems by state dependent parameter estimation", International Journal of Control,  Vol. 74, No., (2001), 1837-1857. 34. Pedregal, D.J., Taylor, C.J. and Young, P.C., "System identification, time series analysis and forecasting: The captain toolbox handbook, Faculty of Science and Technology, Lancaster Environment Centrer, Lancaster University, United Kingdom,  (2007). 35. Sadeghi, J., "Modelling and control of non-linear systems using state-dependent parameter (sdp) models and proportional-integral-plus (pip)control method", Lancaster University, Centre for Research on Environmental System and Statistics, United Kingdom, PhD,  (2006), 36. Young, P.C., Data-based mechanistic modeling: Natural philosophy revisited?, in System identification, environmental modelling, and control system design. 2011, Springer. 321-340. 37. Young, P.C., kenna, P.M. and Bruun, J., "Identification of nonlinear stochastic systems by state dependent parameter estimation", International Journal of Control,  Vol. 74, No. 18, (2001), 1837-1857. 38. Snipes, M. and Taylor, D.C., "Model selection and akaike information criteria: An example from wine ratings and prices", Wine Economics and Policy,  Vol. 3, No. 1, (2014), 3-9. 39. Dziak, J., Li, R. and Collins, L., Critical review and comparison of variable selection procedures for linear regression (technical report). 2005, Methodology Center, Penn State University. 40. Lees, M.J., "Data-based mechanistic modeling and forecasting of hydrological systems", Journal of Hydroinformatics,  Vol. 2, No. 1, (2000), 15-34. 41. Fortuna, L., Rizzo, A., Sinatra, M. and Xibilia, M.G., "Soft analyzers for a sulfur recovery unit", Control Engineering Practice,  Vol. 11, No. 12, (2003), 1491-1500. 42. Shao, W., Tian, X. and Wang, P., "Local partial least squares based online soft sensing method for multi-output processes with adaptive process states division", Chinese Journal of Chemical Engineering,  Vol. 22, No. 7, (2014), 828- 836. 43. Graziani, S., Napoli, G. and Xibilia, M.G., "Soft sensor design for a sulfur recovery unit using a clustering based approach", in Measurement Technology Conference, Victoria, BC, Canada  IEEE Vol., No. Issue, (2008 of Conference). 44. Bella, A.D., Fortuna, L., Graziani, S., Napoli, G. and Xibilia, M.G., "Soft sensor design for a sulfur recovery unit using genetic algorithms", in, Alcala de Henares, Spain IEEE. Vol., No. Issue, (2007 of Conference). 45. Xiong, W., Li, Y., Zhao, Y. and Huang, B., "Adaptive soft sensor based on time differencegaussian process regression with local time-delayreconstruction", Chemical Engineering Research and Design,  Vol. 117, No., (2017), 670-680.


Download PDF 



International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir