Data-driven online modelling for a UGI gasification process using modified lazy learning with a relevance vector machine

• Autorzy: Liu Shida , Ji Honghai , Hou Zhongsheng , Zuo Jiashuo , Fan Lingling

Identyfikatory

DOI

10.34768/amcs-2021-0022

• Języki publikacji: EN

Abstrakty

EN

A modified lazy learning algorithm combined with a relevance vector machine (MLL-RVM) is presented to address a data-driven modelling problem for a gasification process inside a united gas improvement (UGI) gasifier. During the UGI gasification process, the measured online temperature of the produced crude gas is a crucial aspect. However, the gasification process complexities, especially severe changes in the temperature versus infrequent manipulation of the gasifier and the unknown noise in collected data, pose difficulties in dynamics process descriptions via conventional first principles. In the MLL-RVM, a novel weighted neighbour selection method is adopted based on the proposed dynamic cost functions. Moreover, the RVM is utilized in the implementation and design of the proposed online local modelling owing to its short test time and sparseness. Furthermore, the leave-one-out cross-validation technique is used for local model validation, by which the modelling performance is further improved. The MLL-RVM is applied to a series of real data collected from a pragmatic UGI gasifier, and its effectiveness is verified.

Słowa kluczowe

EN

data-driven modelling; UGI gasification process; relevance vector machine; modified lazy learning

PL

modelowanie oparte na danych; proces gazyfikacji; maszyna wektorów istotnych

• Wydawca: Oficyna Wydawnicza Uniwersytetu Zielonogórskiego
• Czasopismo: International Journal of Applied Mathematics and Computer Science
• Rocznik: 2021
• Tom: Vol. 31, no. 2
• Strony: 321--335
• Opis fizyczny: Bibliogr. 45 poz., rys., tab., wykr.

Twórcy

autor

Liu Shida

• School of Electrical and Control Engineering, North China University of Technology, 5 Jinyuanzhuang Road, Shijingshan District, Beijing, 100093, China

autor

Ji Honghai

• School of Electrical and Control Engineering, North China University of Technology, 5 Jinyuanzhuang Road, Shijingshan District, Beijing, 100093, China

autor

Hou Zhongsheng

• School of Automation, Qingdao University, 308 Ningxia Road, Laoshan District, Qingdao, 266071, China

autor

Zuo Jiashuo

• Robot Control Laboratory, School of Electronic Engineering, Yanshan University, No. 438, West Section of Hebei Street, Baitaling Street, Haigang District, Qingdao, 066004, China

autor

Fan Lingling

• School of Automation, Beijing Information Science and Technology University, Qinghe Xiaoying Dong 12 Road, Haidian District, Beijing, 100092, China

Bibliografia

• [1] Aha, D.W. (1997). Lazy Learning, Kluwer Academic Publisher, Dordrecht.
• [2] Aha, D.W., Kibler, D. and Albert, M.K. (1991). Instance-based learning algorithms, Machine Learning 6(1): 37–66.
• [3] Altafini, C.R., Wander, P.R. and Barreto, R.M. (2003). Prediction of the working parameters of a wood waste gasifier through an equilibrium model, Energy Conversion and Management 44(17): 2763–2777.
• [4] Atkeson, C.G., Moore, A.W. and Schaal, S. (1997). Locally weighted learning, in D.A. Kidwell (Ed.), Lazy Learning, Springer, Dordrecht, pp. 11–73.
• [5] Babu, B. and Sheth, P.N. (2006). Modeling and simulation of reduction zone of downdraft biomass gasifier: Effect of char reactivity factor, Energy Conversion and Management 47(15–16): 2602–2611.
• [6] Bontempi, G., Birattari, M. and Bersini, H. (1999). Lazy learning for local modelling and control design, International Journal of Control 72(7–8): 643–658.
• [7] Chavan, P., Sharma, T., Mall, B., Rajurkar, B., Tambe, S., Sharma, B. and Kulkarni, B. (2012). Development of data-driven models for fluidized-bed coal gasification process, Fuel 93: 44–51.
• [8] Chen, S., Gunn, S.R. and Harris, C.J. (2001). The relevance vector machine technique for channel equalization application, IEEE Transactions on Neural Networks 12(6): 1529–1532.
• [9] Cheng, C. and Chiu, M.-S. (2004a). A new data-based methodology for nonlinear process modeling, Chemical Engineering Science 59(13): 2801–2810.
• [10] Cheng, C. and Chiu, M.-S. (2004b). A new data-based methodology for nonlinear process modeling, Chemical Engineering Science 59(13): 2801–2810.
• [11] Corella, J. and Sanz, A. (2005). Modeling circulating fluidized bed biomass gasifiers. A pseudo-rigorous model for stationary state, Fuel Processing Technology 86(9): 1021–1053.
• [12] Demir, B. and Erturk, S. (2007). Hyperspectral image classification using relevance vector machines, IEEE Geoscience and Remote Sensing Letters 4(4): 586–590.
• [13] Fiaschi, D. and Michelini, M. (2001). A two-phase one-dimensional biomass gasification kinetics model, Biomass and Bioenergy 21(2): 121–132.
• [14] Garcia, E.K., Feldman, S., Gupta, M.R. and Srivastava, S. (2010). Completely lazy learning, IEEE Transactions on Knowledge and Data Engineering 22(9): 1274–1285.
• [15] Gordillo, E. and Belghit, A. (2011). A two phase model of high temperature steam-only gasification of biomass char in bubbling fluidized bed reactors using nuclear heat, International Journal of Hydrogen Energy 36(1): 374–381.
• [16] Han, P., Li, D.-Z. and Wang, Z. (2008). A study on the biomass gasification process model based on least squares SVM, Energy Conservation Technology 1(147): 3–7.
• [17] Hou, Z.-S. and Wang, Z. (2013). From model-based control to data-driven control: Survey, classification and perspective, Information Sciences 235: 3–35.
• [18] Hou, Z.-S. and Xu, J.-X. (2009). On data-driven control theory: The state of the art and perspective, Acta Automatica Sinica 35(6): 650–667.
• [19] Huang, C.-E., Li, D. and Xue, Y. (2013). Active disturbance rejection control for the ALSTOM gasifier benchmark problem, Control Engineering Practice 21(4): 556–564.
• [20] Kalita, P., Clifford, M., Jiamjiroch, K., Kalita, K., Mahanta, P. and Saha, U. (2013). Characterization and analysis of thermal response of rice husk for gasification applications, Journal of Renewable and Sustainable Energy 5(1): 013119.
• [21] Liu, S., Sun, J., Ji, H. and Hou, Z. (2020). Model free adaptive control for the temperature adjustment of UGI coal gasification processes in synthetic ammonia industry, IEEE 9th Data Driven Control and Learning Systems Conference (DDCLS), Guangxi, China, pp. 1–6.
• [22] Mondal, P., Dang, G. and Garg, M. (2011). Syngas production through gasification and cleanup for downstream applications: Recent developments, Fuel Processing Technology 92(8): 1395–1410.
• [23] Nelles, O. and Isermann, R. (1996). Basis function networks for interpolation of local linear models, Proceedings of the 35th IEEE Conference on Decision and Control, Kobe, Japan, pp. 470–475.
• [24] Nougués, J., Pan, Y., Velo, E. and Puigjaner, L. (2000). Identification of a pilot scale fluidised-bed coal gasification unit by using neural networks, Applied Thermal Engineering 20(15–16): 1561–1575.
• [25] Papole, G., Focke, W.W. and Manyala, N. (2012). Characterization of medium-temperature Sasol–Lurgi gasifier coal tar pitch, Fuel 98: 243–248.
• [26] Petersen, I. and Werther, J. (2005). Experimental investigation and modeling of gasification of sewage sludge in the circulating fluidized bed, Chemical Engineering and Processing: Process Intensification 44(7): 717–736.
• [27] Puig-Arnavat, M., Hern´andez, J.A., Bruno, J.C. and Coronas, A. (2013). Artificial neural network models for biomass gasification in fluidized bed gasifiers, Biomass and Bioenergy 49: 279–289.
• [28] Raman, P., Walawender, W.P., Fan, L. and Chang, C.-C. (1981). Mathematical model for the fluid-bed gasification of biomass materials: Application to feedlot manure, Industrial & Engineering Chemistry Process Design and Development 20(4): 686–692.
• [29] Ren, Y.-Q., Xu, S.-S. and Gao, S.-W. (2004). Development status and tendency of coal gasification technology with dry coal feed in china, Electric Power 37(6): 49–52.
• [30] Ruggiero, M. and Manfrida, G. (1999). An equilibrium model for biomass gasification processes, Renewable Energy 16(1–4): 1106–1109.
• [31] Sadaka, S.S., Ghaly, A. and Sabbah, M. (2002). Two phase biomass, air-steam gasification model for fluidized bed reactors. Part I: Model development, Biomass and Bioenergy 22(6): 439–462.
• [32] Shabbir, Z., Tay, D.H. and Ng, D.K. (2012). A hybrid optimisation model for the synthesis of sustainable gasification-based integrated biorefinery, Chemical Engineering Research and Design 90(10): 1568–1581.
• [33] Simani, S., Farsoni, S. and Castaldi, P. (2018). Data-driven techniques for the fault diagnosis of a wind turbine benchmark, International Journal of Applied Mathematics and Computer Science 28(2): 247–268, DOI: 10.2478/amcs-2018-0018.
• [34] Simone, M., Barontini, F., Nicolella, C. and Tognotti, L. (2013). Assessment of syngas composition variability in a pilot-scale downdraft biomass gasifier by an extended equilibrium model, Bioresource Technology 140: 43–52.
• [35] Srinivas, T., Gupta, A. and Reddy, B. (2009). Thermodynamic equilibrium model and exergy analysis of a biomass gasifier, Journal of Energy Resources Technology 131(3): 98–107.
• [36] Sun, B., Liu, Y., Chen, X., Zhou, Q. and Su, M. (2011). Dynamic modeling and simulation of shell gasifier in IGCC, Fuel Processing Technology 92(8): 1418–1425.
• [37] Taieb, S.B., Sorjamaa, A. and Bontempi, G. (2010). Multiple-output modeling for multi-step-ahead time series forecasting, Neurocomputing 73(10–12): 1950–1957.
• [38] Tipping, M.E. (2001). Sparse Bayesian learning and the relevance vector machine, Journal of Machine Learning Research 1(Jun): 211–244.
• [39] Tipping, M.E. and Faul, A.C. (2003). Fast marginal likelihood maximisation for sparse Bayesian models, Proceedings of the 9th International Workshop on Artificial Intelligence and Statistics, Key West, USA, pp. 1–14.
• [40] Wei, L., Yang, Y., Nishikawa, R.M., Wernick, M.N. and Edwards, A. (2005). Relevance vector machine for automatic detection of clustered microcalcifications, IEEE Transactions on Medical Imaging 24(10): 1278–1285.
• [41] Wei, Q. and Liu, D. (2013). Adaptive dynamic programming for optimal tracking control of unknown nonlinear systems with application to coal gasification, IEEE Transactions on Automation Science and Engineering 11(4): 1020–1036.
• [42] Wei, Q. and Liu, D. (2014). Data-driven neuro-optimal temperature control of water–gas shift reaction using stable iterative adaptive dynamic programming, IEEE Transactions on Industrial Electronics 61(11): 6399–6408.
• [43] Yu, G.W., Wang, Y.M. and Xu, Y.Y. (2013). Modeling analysis of Shell, Texaco gasification technology’s effects on water gas shift for Fischer–Tropsch process, Advanced Materials Research 608–609: 1446–1453.
• [44] Zanoli, S., Astolfi, G. and Barboni, L. (2012). Application of a new dataset selection procedure for the prediction of the syngas composition of a gasification plant, IFAC Proceedings Volumes 45(15): 868–873.
• [45] Zhao, D., Liu, J., Wu, R., Cheng, D. and Tang, X. (2019). An active exploration method for data efficient reinforcement learning, International Journal of Applied Mathematics and Computer Science 29(2): 351–362, DOI: 10.2478/amcs-2019-0026.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).