ArticlesNo Access

A GRAY-BOX NEURAL NETWORK-BASED MODEL IDENTIFICATION AND FAULT ESTIMATION SCHEME FOR NONLINEAR DYNAMIC SYSTEMS

ZHAOHUI CEN

Department of Electronic and Information Engineering, Huazhong University of Science and Technology, Wuhan, China

Search for more papers by this author

JIAOLONG WEI

Department of Electronic and Information Engineering, Huazhong University of Science and Technology, Wuhan, China

Corresponding author.

Search for more papers by this author

, and

RUI JIANG

Smart Transport Research Center, Civil Engineering and Built Environment School, Science and Engineering Faculty, Queensland University of Technology, Queensland, Australia

Search for more papers by this author

https://doi.org/10.1142/S0129065713500251Cited by:24 (Source: Crossref)

Abstract

A novel gray-box neural network model (GBNNM), including multi-layer perception (MLP) neural network (NN) and integrators, is proposed for a model identification and fault estimation (MIFE) scheme. With the GBNNM, both the nonlinearity and dynamics of a class of nonlinear dynamic systems can be approximated. Unlike previous NN-based model identification methods, the GBNNM directly inherits system dynamics and separately models system nonlinearities. This model corresponds well with the object system and is easy to build. The GBNNM is embedded online as a normal model reference to obtain the quantitative residual between the object system output and the GBNNM output. This residual can accurately indicate the fault offset value, so it is suitable for differing fault severities. To further estimate the fault parameters (FPs), an improved extended state observer (ESO) using the same NNs (IESONN) from the GBNNM is proposed to avoid requiring the knowledge of ESO nonlinearity. Then, the proposed MIFE scheme is applied for reaction wheels (RW) in a satellite attitude control system (SACS). The scheme using the GBNNM is compared with other NNs in the same fault scenario, and several partial loss of effect (LOE) faults with different severities are considered to validate the effectiveness of the FP estimation and its superiority.

Keywords:

References

L.-W. Ho and G. G. Yen, Int. J. Neural Syst. 12(6), 497 (2002), DOI: 10.1142/S0129065702001333. Link, Google Scholar
I. Morgan and H. Liu, IEEE Trans. Ind. Electron. 56(5), 1774 (2009), DOI: 10.1109/TIE.2008.2011306. Web of Science, Google Scholar
X. Jiang and H. Adeli, Int. J. Numer. Methods Eng. 71(5), 606 (2007), DOI: 10.1002/nme.1964. Web of Science, Google Scholar
X. Jiang, S. Mahadevan and H. Adeli, Struct. Control. Health Monit. 14(2), 333 (2007), DOI: 10.1002/stc.161. Web of Science, Google Scholar
B.-H. Choet al., Comput.-Aided Civ. Infrastruct. Eng. 27(3), 218 (2012), DOI: 10.1111/j.1467-8667.2011.00740.x. Web of Science, Google Scholar
G. C. Marano, G. Quaranta and G. Monti, Comput.-Aided Civ. Infrastruct. Eng. 26(2), 92 (2011), DOI: 10.1111/j.1467-8667.2010.00659.x. Web of Science, Google Scholar
U. R. Acharyaet al., Int. J. Neural Syst. 23(3), 1350009 (2013), DOI: 10.1142/S0129065713500093. Link, Web of Science, Google Scholar
R. J. Martiset al., Int. J. Neural Syst. 1350014 (2013), DOI: 10.1142/S0129065713500147. Medline, Web of Science, Google Scholar
Y. Yi, L. Guo and H. Wang, IEEE Trans. Neural Netw. 20(3), 420 (2009). Medline, Web of Science, Google Scholar
M. Chow, G. Bilbro and S. O. Yee, Int. J. Neural Syst. 91(2), 91 (1991). Web of Science, Google Scholar
E. D. Wandekokemet al., Integr. Comput. Aided Eng. 18(1), 61 (2011). Web of Science, Google Scholar
A. Alvanchi, S. Lee and S. AbouRizk, Comput.-Aided Civ. Infrastruct. Eng. 26(2), 77 (2011), DOI: 10.1111/j.1467-8667.2010.00650.x. Web of Science, Google Scholar
F. Ahmadkhanlou and H. Adeli, Eng. Appl. Artif. Intell. 18(1), 65 (2005), DOI: 10.1016/j.engappai.2004.08.025. Web of Science, Google Scholar
H. Adeli and H. S. Park, Comput. Struct. 57(3), 383 (1995), DOI: 10.1016/0045-7949(95)00048-L. Web of Science, Google Scholar
H. Adeli and H. S. Park, Neural Netw. 8(5), 769 (1995), DOI: 10.1016/0893-6080(95)00026-V. Web of Science, Google Scholar
H. S. Park and H. Adeli, Comput. Struct. 57(3), 391 (1995), DOI: 10.1016/0045-7949(95)00047-K. Web of Science, Google Scholar
H. S. Park and H. Adeli, J. Struct. Eng. 123(7), 880 (1997), DOI: 10.1061/(ASCE)0733-9445(1997)123:7(880). Web of Science, Google Scholar
H. Adeli and A. Karim, J. Constr. Eng. Manage. 123(4), 450 (1997), DOI: 10.1061/(ASCE)0733-9364(1997)123:4(450). Web of Science, Google Scholar
A. B. Senouci and H. Adeli, J. Constr. Eng. Manage. 127(1), 28 (2001), DOI: 10.1061/(ASCE)0733-9364(2001)127:1(28). Web of Science, Google Scholar
H. Adeli and H. Kim, Commun. Numer. Methods Eng. 17(11), 771 (2001), DOI: 10.1002/cnm.448. Web of Science, Google Scholar
A. Tashakori and H. Adeli, J. Constr. Steel Res. 58(12), 1545 (2002), DOI: 10.1016/S0143-974X(01)00105-5. Web of Science, Google Scholar
D.-Y. Lin, Comput.-Aided Civ. Infra- struct. Eng. 26(8), 581 (2011), DOI: 10.1111/j.1467-8667.2010.00705.x. Web of Science, Google Scholar
A. Khashman, Int. J. Neural Syst. 18(5), 453 (2008), DOI: 10.1142/S0129065708001713. Link, Web of Science, Google Scholar
N. Wanget al., Int. J. Neural Syst. 20(5), 389 (2010), DOI: 10.1142/S0129065710002486. Link, Web of Science, Google Scholar
S. Wu and T. W. S. Chow, IEEE Trans. Ind. Electron. 51(1), 183 (2004), DOI: 10.1109/TIE.2003.821897. Web of Science, Google Scholar
H. Su and K. T. Chong, IEEE Trans. Ind. Electron. 54(1), 241 (2007), DOI: 10.1109/TIE.2006.888786. Web of Science, Google Scholar
R. J. Patton, C. J. Lopez-Toribio and F. J. Uppal, Appl. Math. Comput. 9, 471 (1999). Web of Science, Google Scholar
G. Puscasu and B. Codres, Int. J. Neural Syst. 21(4), 319 (2011), DOI: 10.1142/S0129065711002869. Link, Web of Science, Google Scholar
K. S. Narendra and K. Parthasarathy, IEEE Trans. Neural Netw. 1(1), 4 (1990), DOI: 10.1109/72.80202. Medline, Google Scholar
G. Puscasuet al., Int. J. Neural Syst. 19(2), 115 (2009), DOI: 10.1142/S0129065709001884. Link, Web of Science, Google Scholar
X.-D. Li, J. K. L. Ho and T. W. S. Chow, IEEE Trans. Circuits Syst. II 52(10), 656 (2005). Google Scholar
S. Freitag, W. Graf and M. Kaliske, Integr. Comput. Aided Eng. 18(3), 265 (2011). Web of Science, Google Scholar
A. Yazdizadeh and K. Khorasani, Nonlinear system identification using embedded dynamic neural networks, Proc. Int. Joint Conf. Neural Networks (IJCNN) (1998) pp. 378–383. Google Scholar
F. Abdollahi, H. A. Talebi and R. V. Patel, IEEE/ASME Trans. Mechatron. 11(4), 488 (2006), DOI: 10.1109/TMECH.2006.878527. Web of Science, Google Scholar
X. Jiang and H. Adeli, Comput.-Aided Civ. Infrastruct. Eng. 20(5), 316 (2005), DOI: 10.1111/j.1467-8667.2005.00399.x. Web of Science, Google Scholar
H. Adeli and X. Jiang, J. Struct. Eng. 132(1), 102 (2006), DOI: 10.1061/(ASCE)0733-9445(2006)132:1(102). Web of Science, Google Scholar
D. Theodoridis, Y. Boutalis and M. Christodoulou, Int. J. Neural Syst. 22(2), (2012), DOI: 10.1142/S0129065712500049. Medline, Web of Science, Google Scholar
E. B. Kosmatopouloset al., IEEE Trans. Neural Netw. 6(2), 422 (1995), DOI: 10.1109/72.363477. Medline, Web of Science, Google Scholar
J. A. Ruz-Hernandez, E. N. Sanchez and D. A. Suarez, Hybrid Intelligent Systems (Springer, 2007) pp. 329–356. Google Scholar
X. Jiang and H. Adeli, J. Transp. Eng. 131(10), 771 (2005), DOI: 10.1061/(ASCE)0733-947X(2005)131:10(771). Web of Science, Google Scholar
Y. H. Kim, F. L. Lewis and C. T. Abdallah, Nonlinear observer design using dynamic recurrent neural networks, 35th IEEE Conf. Decision and Control, CDC (1996) pp. 949–954. Google Scholar
H. A. Talebi, K. Khorasani and S. Tafazoli, IEEE Trans. Neural Netw. 20(1), 45 (2009), DOI: 10.1109/TNN.2008.2004373. Medline, Web of Science, Google Scholar
E. Sobhani-Tehrani and K. Khorasani , Fault Diagnosis of Nonlinear Systems Using a Hybrid Approach ( Springer Verlag , 2009 ) . Google Scholar
E. Sobhani-Tehrani, H. A. Talebi and K. Khorasani, A nonlinear hybrid fault detection, isolation and estimation using bank of neural parameter estimators, Proc. of the 17th IFAC World Congress (2008) pp. 7251–7258. Google Scholar
X. Hong and S. Chen, IEEE Trans. Neural Netw. 22(5), 818 (2011). Medline, Web of Science, Google Scholar
X. Hong and S. Chen, Neurocomputing 82, 216 (2012), DOI: 10.1016/j.neucom.2011.11.016. Web of Science, Google Scholar
Z. Q. Li, L. Ma and K. Khorasani, Fault diagnosis of an actuator in the attitude control subsystem of a satellite using neural networks, Proc. Int. Joint Conf. Neural Networks (IJCNN) (2007) pp. 2658–2663. Google Scholar
N. Tudoroiu and K. Khorasani, IEEE Trans. Aerosp. Electron. Syst. 43(4), 1334 (2007). Web of Science, Google Scholar
Z. Cen, J. Wei and R. Jiang, Fault diagnosis based on grey-box neural network identification model, Proc. Int. Conf. Control Automation and Systems (ICCAS) (2010) pp. 249–254. Google Scholar
Z. Cen, J. Wei and R. Jiang, A Grey-Box Neural Network based identification model for nonlinear dynamic systems, Proc. of the Fourth Int. Workshop on Advanced Computational Intelligence (IWACI) (2011) pp. 300–307. Google Scholar
Z. Cenet al., Diagnosis for actuator partial LOE Fault in Dynamic System with nonlinear actuator, Proc. of The 29th Chinese Control Conference (CCC) (2010) pp. 3993–3999. Google Scholar
D. P. Mandic and J. Chambers , Recurrent Neural Networks for Prediction: Learning Algorithms, Architectures and Stability ( John Wiley & Sons, Inc , 2001 ) . Google Scholar
J. Sjöberget al., Automatica 31(12), 1691 (1995). Web of Science, Google Scholar
H. Demuth and M. Beale , Neural network toolbox for use with MATLAB ( The Math Works , 1993 ) . Google Scholar
Z. Cenet al., J. Astronaut. 32(6), 1318 (2011). Google Scholar
H. Liao, Studies on the attitude determination and control system of an earth-oriented three-axis stabilized satellite, Ph. D. monogram dissertation, Department of Aerospace Engineering, Northwestern Polytechnical University, Xian, China (2000) . Google Scholar
X. Wang and M. Ni, Aerospace Contr. Appl. 34(4), 33 (2008). Google Scholar
Z. Liet al., J. Shandong University (Eng. Sci.) 35(3), 88 (2005). Google Scholar