Softsensor for estimation of steam quality in riser tubes of boilers

Abstract

Steam fraction in riser tubes of boilers is a critical process variable which impacts the life of the tubes and could lead to tube rupture, long boiler down time, and expensive repairs. Unfortunately this parameter is difficult to measure by hardware sensors. This article presents a new neural network softsensor for estimation and monitoring steam mass and volume fractions in riser tubes. First, conventional data were collected from a target industrial boiler. The data are then used to develop a detailed nonlinear simulation model for the two phase flow in the riser tubes and risers and downcomers water circulation. The model output is verified against the collected field data. Next, the boiler nonlinear model is used to generate data covering a wide rage of operating conditions for training and testing the neural network. The input of the neural network includes the heating power, the steam flow rate, the water feed rate, the drum level, and the drum pressure. The neural networks predict the mass steam quality and the steam volume fractions. The softsensor achieves a root mean square error on the test data less than 1.5%. The predicted steam quality is then compared with the critical limits to guide the operators for safe and healthy operation of the boilers. The developed softsensor for estimation of the steam quality has simple structure and can be implemented easily at the operator stations or the application servers.

Keywords

Boiler dynamic modeling boiler operation boiler safety softsensing neural networks nonlinear state estimation boiler steam fraction boiler steam quality

Get full access to this article

View all access options for this article.

References

Astrom

Eklund

. A simplified non-linear model of a drum boiler-turbine unit. Int J Control 1972; 16: 145–169.

Unbehauen

Kocaarslan

. Experimental modelling and adaptive power control of a 750 MV once-through boiler. Proceedings of the preprints IFAC 11th world congress on automatic control, 13–17 August 1990, vol. 11, Tallinn, Estonia32–37.

Kwatny

Berg

. Drum level regulation at all loads. Proceedings of the IFAC 12th world congress, 19–23 July 1993, vol. 3, Sydney, Australia405–408.

Astrom

Bell

. Drum – boiler dynamics. Automatica 2000; 36: 363–378.

Flynn

O’Malley

. A drum boiler model for long term power system dynamic simulation. IEEE Trans Power Syst 1999; 14: 209–217.

Dong

Tingkuan

. HGSSP-A computer program for simulation of once-through boiler start-up behavior. Heat Transfer Eng 2001; 22(5): 50–60.

Kim

Choi

. A model on water level dynamics in natural circulation drum-type boilers. Int Commun Heat Mass Transfer 2005; 32: 786–796.

Wolf AL and Neill TE. Thermal shock. Application Engineering/Technical Services, Heating and Cooling Technology, 2006, pp.1–6.

Kudryavtsev

Burmistrova

Maminov

. Fatigue testing of boiler steels under an asymmetric stress range. J Strength Mater 1970; 2(2): 183–186. translated from Problemy Prochnosti (2): 77–80).

10.

Kruger

Rode

Franke

. Optimal control for fast boiler start-up based on a non-linear model and considering the thermal stress on thick-walled components. Proceedings of the IEEE international conference on control applications, 5–7 September 2001, Mexico City, Mexico570–576.

11.

Kruger

Franke

Rode

. Optimization of boiler start-up using a nonlinear boiler model and hard constraints. Energy 2004; 29: 2239–2251.

12.

Emara-Shabaik

Habib

Al-Zaharna

. Prediction of risers’ tubes temperature in water tube boilers. Appl Math Modell 2009; 33: 1323–1336.

13.

Habib

Al-Zaharnah

Ayinde

. Influence of boiler swing rate on dynamics of thermal and flow characteristics in water circulation boilers. Comput Therm Sci 2011; 3(6): 483–500.

14.

Wallace

Clarke

. The application of Kalman filtering estimation techniques in power station control systems. IEEE Trans Autom Control 1983; 28: 416–427.

15.

Song

Marchand

. Modelling and state estimation of power station boilers. Part I: modelling. Int J Electr Power Syst Res 1990a; 18: 175–189.

16.

Song

Marchand

. Modelling and state estimation of power station boilers. Part II: application. Int J Electr Power Syst Res 1990b; 18: 191–203.

17.

Hogg

. Dynamic nonlinear modelling of power plant by physical principles and neural networks. Electr Power Energy Syst 2000; 22: 67–78.

18.

Julier

Uhlmann

. Unscented filtering and nonlinear estimation. Proc IEEE 2004; 92: 401–422.

19.

Rathamarit

. State estimation of a boiler model using the unscented Kalman filter. IET Gener Transm Distrib 2008; 2(6): 917–931.

20.

Keeler

Ferguson

. Commercial applications of soft sensors: the virtual online analyzer and the software CEM. Proceedings of IFAC conference, 30 June–5 July 1996, San Francisco, CA.

21.

Martin

. Consider soft sensors. Chem Eng Prog 1997; 7: 66–70.

22.

Wang

Luo

Shao

. Designing a soft sensor for distillation column with the fuzzy distributed radial basis function neural network. Proceedings of IEEE 35th conference on decision and control, 11–13 December 1996, Kobe1714–1719.

23.

Traver

Atkinson

. Neural network-based diesel engine emissions prediction using in-cylinder combustion pressure. Proceedings of the international spring fuels and lubricants meeting and exposition,, 3–6 May 1999, Dearborn, MI.

24.

Elshafei

Habib

Al-Dajani

. Prediction of boilers emissions using polynomial networks. IEEE electrical and computer engineering Canadian conference, 7–10 May 2006, Ottawa, ON823–827.

25.

Elshafei

Habib

Al-Dajani

. Influence of combustion parameters on NOx production in an industrial boiler. J Comput Fluid 2008; 37(1): 12–23.

26.

Shakil

Elshafei

Habib

. Soft sensor for NOx emission using dynamic neural network. J Comput Electr Eng 2009; 35(4): 527–608.

27.

Ilamathi

Selladurai

Balamurugan

. Predictive modelling and optimization of power plant nitrogen oxides emission. IAES Int J Artif Intell 2012; 1(1): 11–18.

28.

Hosseini

Bashirnezhad

Moghiman

. Experimental comparison of combustion characteristic and pollutant emission of gas oil and biodiesel. World Academy Sci Eng Technol 2010; 72: 304–307.

29.

Shuangchen

. Simulation on SO₂ and NO _X emission from coal–fired power plants in North-Eastern North America. Energy Power Eng 2010; 2: 190–195.

30.

Haykin

. Neural networks and learning machines, 3rd edn. New York: Prentice Hall, 2009.

31.

Hornik

Stinchcombe

White

. Multilayer feed-forward network are universal approximators. Neural Networks 1989; 2: 359–366.

32.

Hagan

Menhaj

. Training feedforward networks with the Marquardt algorithm. IEEE Trans Neural Networks 1994; 5: 989–993.

33.

Saudi ARAMCO. Determination of maximum boiler swing rate. Project Report, Saudi ARAMCO project no. 2277, Mechanical Engineering Department, Saudi ARAMCO, May 2007–December 2009. Dhahran: Saudi ARAMCO.