Abstract




 
   

IJE TRANSACTIONS A: Basics Vol. 28, No. 10 (October 2015) 1423-1429   

downloaded Downloaded: 129   viewed Viewed: 2051

  VERIFICATION OF AN EVOLUTIONARY-BASED WAVELET NEURAL NETWORK MODEL FOR NONLINEAR FUNCTION APPROXIMATION
 
S. M. A. Hashemi, H. Haji Kazemi and A. Karamodin
 
( Received: April 12, 2015 – Accepted: October 16, 2015 )
 
 

Abstract    Nonlinear function approximation is one of the most important tasks in system analysis and identification. Several models have been presented to achieve an accurate approximation on nonlinear mathematics functions. However, the majority of the models are specific to certain problems and systems. In this paper, an evolutionary-based wavelet neural network model is proposed for structure definition and optimization of nonlinear systems. The proposed model involves structure identification and also a parameter tuning phase to be adapted for modeling of an arbitrary system. The proposed structure and the learning algorithm are validated by comparing with some other most commonly used alternatives. The simulation shows the performance and adaptability of the proposed model in approximating multivariate nonlinear mathematics functions.

 

Keywords    Wavelet neural network, Evolutionary learning algorithm, Nonlinear function approximation.

 

چکیده    تقریب توابع غیر خطی یکی از موارد مهم در تشخیص و آنالیز سیستم ها می باشد. مدلهای مختلفی به منظور تقریب دقیق توابع غیر خطی ریاضی ارائه شده است، هر چند که عمده این مدلها، برای مسائل و سیستم های خاص تعریف شده اند. در این مقاله یک شبکه عصبی-موجکی تکاملی به منظور تعیین ساختار و بهینه سازی سیستم های غیر خطی پیشنهاد شده است. مدل پیشنهاد شده از یک مکانیزم شناسایی ساختار و تنظیم پارامترهای ساختار برای مدلسازی توابع و سیستم های غیرخطی دلخواه استفاده می نماید. ساختار پیشنهادی و الگوریتم آموزشی به کار گرفته شده برای آن از طریق مقایسه با سایر روشهای معمول و متداول راستی آزمایی و اعتبارسنجی می شود. شبیه سازی های انجام شده، نمایانگر کارایی و توانایی مدل پیشنهادی در تقریب توابع چندمتغیره غیرخطی ریاضی می باشد.

References   

 

1.     Abiyev, R.H. and Kaynak, O., "Fuzzy wavelet neural networks for identification and control of dynamic plants a novel structure and a comparative study", Industrial Electronics, IEEE Transactions on,  Vol. 55, No. 8, (2008), 3133-3140.

2.     Tzeng, S.T., "Design of fuzzy wavelet neural networks using the ga approach for function approximation and system identification", Fuzzy sets and systems,  Vol. 161, No. 19, (2010), 2585-2596.

3.     Sedighizadeh, M. and Kashani, M.F., "A tribe particle swarm optimization for parameter identification of proton exchange membrane fuel cell (technical note)", International Journal of Engineering-Transactions A: Basics,  Vol. 28, No. 1, (2014), 16-24.

4.     Talatahari, S. and Rahbari, N.M., "Enriched imperialist competitive algorithm for system identification of magneto-rheological dampers", Mechanical Systems and Signal Processing,  Vol. 62, No., (2015), 506-516.

5.     Tavakolpour-Saleh, A., Nasib, S., Sepasyan, A. and Hashemi, S., "Parametric and nonparametric system identification of an experimental turbojet engine", Aerospace Science and Technology,  Vol. 43, No., (2015), 21-29.

6.     Deng, J., "Dynamic neural networks with hybrid structures for nonlinear system identification", Engineering Applications of Artificial Intelligence,  Vol. 26, No. 1, (2013), 281-292.

7.     Khoa, T., Phuong, L., Binh, P. and Lien, N., "Application of wavelet and neural network to long-term load forecasting", in Power System Technology, 2004. PowerCon 2004. 2004 International Conference on, IEEE. Vol. 1, No. Issue, (2004), 840-844.

8.     Zhang, Q. and Benveniste, A., "Wavelet networks", Neural Networks, IEEE Transactions on,  Vol. 3, No. 6, (1992), 889-898.

9.     Lapedes, A. and Farber, R., Nonlinear signal processing using neural networks: Prediction and system modelling. Los Alamos Nat. Lab Tech. Rep, LA-UR-872662. (1987).

10.   Goharriz, M. and Marandi, S., "Assessment of lateral displacements using neuro-fuzzy group method of data handling systems", International Journal of Engineering-Transactions B: Applications,  Vol. 28, No. 5, (2015), 677-685.

11.   Rakideh, M., Dardel, M. and Pashaei, M., "Crack detection of timoshenko beams using vibration behavior and neural network",  International Journal of Engineering, Transactions C: Aspects,  Vol. 26, No. 12, (2013), 1433-1444.

12.   Khalid, M., Yusof, R., Joshani, M., Selamat, H. and Joshani, M., "Nonlinear identification of a magnetorheological damper based on dynamic neural networks", ComputerAided Civil and Infrastructure Engineering,  Vol. 29, No. 3, (2014), 221-233.

13.   SadeghpourHajia, M., Mirbagherib, S., Javidc, A., Khezria, M. and Najafpour, G., "A wavelet support vector machine combination model for daily suspended sediment forecasting" International Journal of Engineering, Transactions C: Aspects Vol.27, No.6 (2014), 855-864

14.   Kim, H. and Adeli, H., "Wavelet-hybrid feedback linear mean squared algorithm for robust control of cable-stayed bridges", Journal of Bridge Engineering,  Vol. 10, No. 2, (2005), 116-123.

15.   Wang, N. and Adeli, H., "Self-constructing wavelet neural network algorithm for nonlinear control of large structures", Engineering Applications of Artificial Intelligence,  Vol. 41, No., (2015), 249-258.

16.   Ganjefar, S. and Tofighi, M., "Single-hidden-layer fuzzy recurrent wavelet neural network: Applications to function approximation and system identification", Information Sciences,  Vol. 294, No., (2015), 269-285.

17.   Miranian, A. and Abdollahzade, M., "Developing a local least-squares support vector machines-based neuro-fuzzy model for nonlinear and chaotic time series prediction", Neural Networks and Learning Systems, IEEE Transactions on,  Vol. 24, No. 2, (2013), 207-218.

18.   Razjouyan, J., Gharibzadeh, S., Fallah, A., Khayat, O., Ghergherehchi, M., Afarideh, H. and Moghaddasi, M., "A neuro-fuzzy based model for accurate estimation of the lyapunov exponents of an unknown dynamical system", International Journal of Bifurcation and Chaos,  Vol. 22, No. 03, (2012),143-150.

19.   Khayat, O., "Structural parameter tuning of the first-order derivative of an adaptive neuro-fuzzy system for chaotic function modeling", Journal of Intelligent & Fuzzy Systems,  Vol. 27, No. 1, (2014), 235-245.





International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir