Advertisement

The parameter identification method of steam turbine nonlinear servo system based on artificial neural network

  • Jin-Long Liao
  • Feng Yin
  • Zhi-Hao Luo
  • Bo Chen
  • De-Ren Sheng
  • Zi-Tao Yu
Technical Paper
  • 132 Downloads

Abstract

The servo system in steam turbine digital electric-hydraulic control system (DEH) is affected by nonlinear factors when it is working. To accurately simulate dynamic characteristics of the DEH, a new nonlinear servo system is proposed, which has limit, dead zone and correction coefficient caused by unknown factors. The model parameters are divided into linear parameters and nonlinear parameters to be identified, respectively. Neural networks are used to identify linear parameters. The nonlinear parameters should be identified according to flow characteristic curve. To verify the validity of the proposed model and parameter identification method, the actual data of primary frequency control from a 1000 MW Ultra Supercritical Unit is adopted. Meanwhile, the linear model with no nonlinear factors is used for comparison. Where the fitting degree of valve opening is 98.445% and power is 96.986%, the output of nonlinear model coincides with actual output well. Where the relative error of stable result is 5% of valve opening and 1.58% of power, the error of linear model is larger. The simulation results of the proposed method show that the nonlinear factors of high-power units cannot be ignored and the nonlinear model of servo system is more accurate.

Keywords

Steam turbine Nonlinear servo system Parameter identification Artificial neural network 

Abbreviations

ANN

Artificial neural network

BP

Back propagation

DEH

Digital electric-hydraulic control system

GA

Genetic algorithm

NN

Neural network

PFC

Primary frequency control

PSO

Particle swarm optimization

RBF

Radial basis function

UHV

Ultra-high voltage

UHVTT

Ultra-high voltage transmission technology

List of symbols

d1

Artificial neural network

d2

Back propagation

ft

Digital electric-hydraulic control system

fz

Genetic algorithm

l1

Neural network

k2

Primary frequency control

l1

Particle swarm optimization

l2

Radial basis function

n

Ultra-high voltage

s

Ultra-high voltage transmission technology

T

Primary frequency control

Ty

Particle swarm optimization

Tc

Radial basis function

x

Ultra-high voltage

xmin

Ultra-high voltage transmission technology

xmax

Ultra-high voltage transmission technology

x*

Ultra-high voltage transmission technology

Greek symbols

τ

Time constant of delay rate(s)

γ

Parameter vector

Subscripts

α

Output number of neural network

β

Input number of neural network

Notes

Acknowledgements

This research was supported by the Electric Power Research Institute of State Grid Corporation of China in Zhejiang province.

References

  1. 1.
    Fu ZG, Jin T, Zhou LJ, Ge ZH, Zheng L, Yang YP (2009) Research and application of the reversed modeling method and partial least-square regression modeling for the complex thermal system. Proc CSEE 29(2):25–29 (in chinese) Google Scholar
  2. 2.
    Wang ZQ, Zhu SZ, Lou HX, Sheng SD, Zhang LY (2003) PLPF based modeling and parameter identifying of large steam turbine in time domain. Proc CSEE 23:128–133 (in chinese) Google Scholar
  3. 3.
    Zhu Y, Jiang WL, Kong XD, Zheng Z (2015) Study on nonlinear dynamics characteristics of electrohydraulic servo system. Nonlinear Dyn 80:723–737CrossRefGoogle Scholar
  4. 4.
    Guan C, Pan S (2008) Adaptive sliding mode control of electro-hydraulic system with nonlinear unknown parameters. Control Eng Prac 16:1275–1284CrossRefGoogle Scholar
  5. 5.
    Li W, Zheng ZJ, Sheng DR, Cheng JH, Ren HR (2008) Recursive least square method based parameter identification of steam turbine digital electric-hydraulic governing system. J Zhejiang Univ (Eng Sci) 42:1761–1764Google Scholar
  6. 6.
    Hiyama T, Suzuki N, Karino H, Kwang Yun L, Andou H (1999) Artificial neural network based modeling of governor-turbine system. In: IEEE Power Engineering Society. Winter Meeting (Cat. No. 99CH36233) 1:129–133Google Scholar
  7. 7.
    Rashtchi V, Rahimpour E, Rezapour EM (2006) Using a genetic algorithm for parameter identification of transformer R-L-C-M model. Electr Eng 88:417–422CrossRefGoogle Scholar
  8. 8.
    Rahimpour E, Rashtchi V, Pesaran M (2007) Parameter identification of deep-bar induction motors using genetic algorithm. Electr Eng 89:547–552CrossRefGoogle Scholar
  9. 9.
    Li Q, Chen W, Wang Y, Liu S (2011) Parameter identification for PEM fuel-cell mechanism model based on effective informed adaptive particle swarm optimization. IEEE Trans Industr Electron 58:2410–2419CrossRefGoogle Scholar
  10. 10.
    Liu W, Liu L, Chung IY, Cartes DA (2011) Real-time particle swarm optimization based parameter identification applied to permanent magnet synchronous machine. Appl Soft Comp 11:2556–2564CrossRefGoogle Scholar
  11. 11.
    Johnson W, Gupta NK (2015) Instrumental variables algorithm for modal parameter identification in flutter testing. AIAA J 16:800–806CrossRefzbMATHGoogle Scholar
  12. 12.
    Tóth R, Laurain V, Gilson M, Garnier H (2012) Instrumental variable scheme for closed-loop LPV model identification ☆. Automatica 48:2314–2320MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    Janot A, Vandanjon PO, Gautier M (2013) Identification of physical parameters and instrumental variables validation with two-stage least squares estimator. IEEE Trans Control Syst Technol 21:1386–1393CrossRefGoogle Scholar
  14. 14.
    Zahid T, Li W (2016) A comparative study based on the least square parameter identification method for state of charge estimation of a LiFePO4 battery pack using three model-based algorithms for electric vehicles. Energies 9:720CrossRefGoogle Scholar
  15. 15.
    Yang T, Feng Y, Yang T, Ren Y, Tang L, Li Y, (2012) Parameter identification of steam turbine speed governor system. In: 2012 Asia-Pacific Power and Energy Engineering Conference. pp. 1–8Google Scholar
  16. 16.
    Karayaka HB, Keyhani A, Agrawal BL, Selin DA, Heydt GT (2000) Identification of armature, field, and saturated parameters of a large steam turbine-generator from operating data. IEEE Trans Energy Convers 15:181–187CrossRefGoogle Scholar
  17. 17.
    Levin AU, Narendra KS (1996) Control of nonlinear dynamical systems using neural networks. II. Observability, identification, and control. Trans Neur Netw 7:30–42CrossRefGoogle Scholar
  18. 18.
    Mashor MY (2005) Performance comparison between HMLP, MLP and RBF networks with application to on-line system identification. In Cybernetics and Intelligent Systems, 2004 IEEE Conference on 2005. vol. 1 pp. 643–648Google Scholar

Copyright information

© The Brazilian Society of Mechanical Sciences and Engineering 2018

Authors and Affiliations

  • Jin-Long Liao
    • 1
  • Feng Yin
    • 2
  • Zhi-Hao Luo
    • 2
  • Bo Chen
    • 2
  • De-Ren Sheng
    • 1
  • Zi-Tao Yu
    • 1
  1. 1.Institute of Thermal Science and Power SystemsZhejiang UniversityHangzhouChina
  2. 2.Electric Power Research Institute of State Grid Zhejiang Electric Power CompanyHangzhouChina

Personalised recommendations