Intelligent computationally efficient modelling of multi-input multi-output non-linear dynamical process plants: An industrial steam generator case study

Abstract

Most of the process plants have intrinsic non-linear, time-varying, non-minimum phase and coupling characteristics that result in a highly time-consuming and tedious task to derive complicated non-linear dynamic equations governing on such types of processes. On the other hand, even though such equations can be analytically extracted, they have not worked out in most cases yet. To find a simple fix that can address these hurdles associated with analytical modelling, two types of non-analytical models, namely, simulator and predictor, are proposed based on a computationally efficient technique so-called locally linear neuro-fuzzy modelling. That is, a simulator model as well as a specially structured long-term predictor model that is built based on a sequential arrangement of single-stage predictor models is presented for multi-input multi-output non-linear dynamical process plants and feasibly applied to a real water-tube steam generator for the first time. An adaptive evolving algorithm named linear model tree contributes to estimate the parameters of neuro-fuzzy simulator and predictor models. Furthermore, an order selection method based on Lipschitz theory, whose merit is being totally independent from developing any model prior to commencing tedious modelling trials, is also proposed for the first time by defining a modified Lipschitz index to remedy the order determination problem within the very first steps of black-box non-linear system identification. The blend of such a fully modelling-independent order selection algorithm and a unique type of computationally inexpensive non-linear neuro-fuzzy model lessens the overall computational burden of modelling procedure that represents a great concern in a black-box system identification approach. The recorded data from a real water-tube steam generator operating at Abbot Power plant unit of Champaign, IL, were exploited to carry out experimental modelling in order to reveal the pros and cons of the presented models.

Keywords

Water-tube steam generator non-linear process identification locally linear neuro-fuzzy network locally linear model tree model-based predictive control fault diagnosis

Get full access to this article

View all access options for this article.

References

Ashoori

Moshiri

Khaki-Sedigh

. Optimal control of a non-linear fed-batch fermentation process using model predictive approach. J Process Contr 2009; 19: 1162–1173.

Nozari

Simani

Shoorehdeli

. Model-based robust fault detection and isolation of an industrial gas turbine prototype using soft computing techniques. Neurocomputing 2012; 91: 29–47.

McDonald

Kwatney

Spare

. A non-linear model for reheat boiler-turbine-generator systems, parts I and II. In: Proceedings of 12th Joint Automatic Control Conference, St. Louis, MO, 11–13 August 1971, pp.219–236.

Åström

Bell

. Simple drum-boiler models. In: IFAC international symposium on power systems modelling and control applications, Brussels, Belgium, 5–8 September 1988.

Chawdry

Hogg

. Identification of boiler models. IEE Proc: D 1989; 136: 261–271.

Rivas Perez

Herranz

Llanes

Cartaya

. Modelo Matemático Dinámico de Generadores de Vapor. Ingeniería Electrónica, Automática y Comunicaciones 1994; 3: 45–54.

Pellegrinetti

Bentsman

. Non-linear control oriented boiler modeling – a benchmark problem for controller design. IEEE T Contr Syst T 1996; 4: 57–64.

Hogg

. Dynamic non-linear modeling of power plant by physical principles and neural networks. Int J Elec Power 2000; 22: 67–78.

Gilman

. Boiler control systems engineering. Research Triangle Park, NC: The Instrumentation, Systems and Automation Society, 2005.

10.

Rizvi

Al-Duwaish

. Modelling of a nonlinear multivariable boiler plant using Hammerstein model: a nonparametric approach. In: Proceedings of 29th IASTED Conference on Modelling, Identification and Control, Innsbruck, Austria. 15– February 2010, pp. 102–108.

11.

Magdi

. Linear identification of a steam generation plant. In: Proceedings of the 2011 World Congress on Engineering, London, UK, 6–8 July 2011, pp. 2457–2465.

12.

Betchine

Lamamra

. Steam generator modeling using thermofluid Matlab-Simulink library. Int J Eng Res Tech 2013; 2(7): 2329–2334.

13.

Havlena

Findejs

. Application of model predictive control to advanced combustion control. Control Eng Pract 2005; 13: 671–680.

14.

Ghaffari

Chaibakhsh

Shahhoseini

. Neuro-fuzzy modeling of heat recovery steam generator. Int J Mach Learn Comput 2012; 2: 604–608.

15.

Rubashkin

Khesin

. Dynamic models for fossil power plant training simulators. In: Proceeding of American power conference, Chicago, IL, US, 13–15 April 1993, pp.871–875.

16.

Parlos

Rais

. Non-linear control of U-tube steam generators via H_∞ control. Control Eng Pract 2000; 8: 921–936.

17.

Mohammadzaheri

Ley

. Intelligent modeling of MIMO non-linear dynamic process plants for predictive control purposes. In: Proceedings of the 17th world congress: the international federation of automatic control, Seoul, South Korea, 6–11 July 2008, pp.12401–12406.

18.

Fábio

Helon

VHA

André

. Multivariable non-linear boiler power plant identification through neural networks and particle swarm optimization approaches. In: 9th IEEE/IAS conference on industry applications, Sao Paulo, Brazil, 8–10 November 2010, pp.1–6. New York: IEEE.

19.

Heping

. Use of neural networks for modelling the steam generator of a nuclear power plant. Ele Com Eng 1994; 2: 734–738.

20.

Rusinowski

Stanek

. Neural modelling of steam boilers. Energ Convers Manage 2007; 48: 2802–2809.

21.

Rusinowski

Stanek

. Hybrid model of steam boiler. Energy 2010; 35: 1107–1113.

22.

Sainleza

Heyen

. Recurrent neural network prediction of steam production in a Kraft recovery boiler. Comput Aided Chem Eng 2011; 29: 1784–1788.

23.

Nozari

Banadaki

Mokhtare

. Intelligent non-linear modelling of an industrial winding process using recurrent local linear neuro-fuzzy networks. J Zhejiang Univ: Sc C 2012; 13: 403–412.

24.

Benazzouz

Benammar

Adjerid

. Fault detection and isolation based on neural networks case study: steam turbine. Energ Power Eng 2011; 3: 513–516.

25.

Ismail Alnaimi

Al-Kayiem

. Artificial intelligent system for steam boiler diagnosis based on superheater monitoring. J Appl Sci 2011; 11: 1566–1572.

26.

Razavi-Far

Davilu

Palade

. Model-based fault detection and isolation of a steam generator using neuro-fuzzy networks. Neurocomputing 2009; 72: 2939–2951.

27.

Banadaki

Nozari

Kakahaji

. Non-linear simulator model identification of a walking beam furnace using recurrent local linear neuro-fuzzy network. Int J Control Autom 2011; 4: 123–134.

28.

Gao

Ovaska

. Power prediction using an optimal neuro-fuzzy predictor. In: IEEE conference on instrumentation and measurement technology, Ottawa, ON, Canada, 19–21 May 1997, vol. 2, pp.1225–1230. New York: IEEE.

29.

Ghaffari

Chaibakhsh

Lucas

. Soft computing approach for modeling power plant with a once-through boiler. Eng Appl Artif Intel 2007; 20: 809–819.

30.

Liu

Guan

. Neuro-fuzzy generalized predictive control of boiler steam temperature. J Contr Theor Appl 2007; 5: 83–88.

31.

Jamali

Jazayeri-Rad

. Application of adaptive local linear model tree for non-linear identification of heat recovery steam generator system based on experimental data. In: UKSim 4th European symposium on computer modeling and simulation, Pisa, 17–19 November 2010, pp.16–20. New York: IEEE.

32.

Shen

Lee

. Offset-free fuzzy model predictive control of a boiler–turbine system based on genetic algorithm. Simul Model Pract Th 2012; 26: 77–95.

33.

Cheng

Bai

. Research on water level control system of steam generator based on fuzzy generalized predictive control. J Comput Inform Syst 2012; 8(20): 8257–8265.

34.

Hossu

Fagarasan

Hossu

. Evolved fuzzy control system for a steam generator. Int J Comput Commun 2010; 5(2): 179–192.

35.

Nelles

Isermann

. Basis function networks for interpolation of local linear models. In: Proceedings of IEEE conference on decision and control, Kobe, Japan, 11–13 December 1996, pp.470–475. New York: IEEE.

36.

Nelles

. Nonlinear system identification: from classical approaches to neural networks and fuzzy models. Berlin: Springer Press, 2001.

37.

Billings

Voon

WSF

. Piecewise linear identification of non-linear systems. Int J Control 1987; 46: 215–235.

38.

Billings

Voon

WSF

. Correlation based model validity test for non-linear models. Int J Control 1986; 44: 235–244.

39.

Makaremi

Fatehi

Araabi

. Lipschitz numbers: a medium for delay estimation. In: Proceedings of the 17th world congress: the international federation of automatic control, Seoul, South Korea, 6–11 July 2008, pp.7468–7473.

40.

Database for the Identification of Systems (DaISy). http://homes.esat.kuleuven.be/∼smc/daisy/