Ortalama farksal gelişim algoritması ile bilineer sistem kimliklendirme

Year 2018, Volume: 20 Issue: 2, 546 - 560, 01.12.2018

Burhanettin Durmuş

https://doi.org/10.25092/baunfbed.489724

Abstract

Bu çalışmada, bilineer sistem kimliklendirme problemi için ortalama farksal gelişim (average differential evolution-ADE) algoritması önerilmiştir.  Doğrusal olmayan sisteme ait parametrelerin ADE tabanlı bilineer model üzerinden kestirimi gerçekleştirilmiştir. Bilinmeyen sistem çıkışı ile bilineer model çıkışı arasındaki Ortalama Karesel Hata (Mean Square Error, MSE) performans ölçütü olarak kullanılmıştır.  Önerilen algoritmanın performansı, hem farklı sezgisel algoritmaların kullanıldığı benzetim çalışmaları ile hem de literatürde rapor edilmiş diğer metotlar ile karşılaştırılmıştır.  Karşılaştırmalı sonuçlarda, ADE tabanlı modelleme ile hata değerlerinin azaldığı ve hesaplanan parametre değerlerinin doğruluk oranının arttığı görülmüştür.  Hızlı bir yakınsama ile global çözüme ulaşma kabiliyetine sahip olan ADE algoritması, parametre kestirimi uygulamaları için etkin bir araç olarak kullanılabilir.

Keywords

Bilineer sistem, sistem kimliklendirme, sezgisel algoritmalar

Bilinear system identification with average differential evolution algorithm

Abstract

In this paper, average differential evolution (ADE) algorithm is proposed for bilinear system identification problem.  The parameters of the nonlinear system were estimated using ADE based bilinear model.  The mean square error (MSE) between the unknown system output and the bilinear model output is used as the performance criterion.  The performance of the proposed algorithm is compared with both the simulation studies using different heuristic algorithms and other methods reported in the literature.  The comparative results show that the ADE based modeling reduces the error values and increases the accuracy of the calculated parameter values.  The ADE algorithm, which has global convergence capability with fast convergence, can be used as an effective tool for parameter estimation applications.

Keywords

Bilinear system, system identification, meta-heuristic algorithms

References

• Chinarro, D., System engineering applied to fuenmayor karst aquifer and collins glacier, Springer International Publishing, Switzerland, (2014).
• Lin, J., Chen, C., Parameter estimation of chaotic systems by an oppositional seeker optimization algorithm, Nonlinear Dynamics, 76(1), 509-517, (2014).
• Zhang, R.D., Lu, R.Q., Xue, A.K., Gao, F.R., Predictive functional control for linear systems under partial actuator faults and application on an injection molding batch process, Industrial & Engineering Chemistry Research, 53(2), 723-731, (2014).
• Dai, C., Chen, W., Zhu, Y., Seeker optimization algorithm for digital IIR filter design, IEEE Transactions on Industrial Electronics, 57(5), 1710-1718, (2010).
• Mostajabi, T., Poshtan, J., Mostajabi, Z., IIR model identification via evolutionary algorithms, Artificial Intelligence Review, 39, 1-15, (2013).
• Luitel, B., Venayagamoorthy, G.K., Particle swarm optimization with quantum infusion for system identification, Engineering Applications of Artificial Intelligence, 23(5), 635-649, (2010).
• Kumar, M., Kumar, T.K., Aggarwal, A., Adaptive infinite impulse response system identification using modified-interior search algorithm with Levy flight, ISA Transactions, 67, 266-279, (2017).
• Durmuş, B., Gün, A., Parameter identification using particle swarm optimization, Proceedings , 6th International Advanced Technologies Symposium, 188-192, Elazığ, (2011).
• Mathews, V.J., Sicuranza, G.L., Polynomial signal processing, Wiley, New York, (2000).
• Greblicki, W., Nonlinearity estimation in hammerstein systems based on ordered observations, IEEE Transactions on Signal Processing, 44(5), 1224-1233, (1996).
• Kristinsson, K., Dumont, G.A., System identification and control using genetic algorithm, IEEE Transactions on Systems, Man, and Cybernetics, 22(5), 1033-1046, (1992).
• Kuo, S.M., Wu, H.T., Nonlinear adaptive bilinear filters for active noise control systems, IEEE Transactions on Circuits and Systems, 52(3), 617-624, (2005).
• Kalouptsidis, N., Koukoulas, P., Mathews, V.J., Blind identification of bilinear systems, IEEE Transactions on Signal Processing, 51, 484-499, (2003).
• Wang, Z., Gu, H., Parameter identification of bilinear system based on genetic algorithm, Lecture Notes in Computer Science, 4688, 83-91, (2007).
• Modares, H., Alfi, A., Sistani, M.N., Parameter estimation of bilinear systems based on an adaptive particle swarm optimization, Engineering Applications of Artificial Intelligence, 23, 1105-1111, (2010).
• Kawaria, N., Patidar, R., George, N.V., Parameter estimation of MIMO bilinear systems using a Levy shuffled frog leaping algorithm, Soft Computing, 21, 3849-3858, (2017).
• Durmuş, B., Optimal components selection for active filter design with average differential evolution algorithm, International Journal of Electronics and Communications, 94, 293-302, (2018).
• Geem, Z.W., Kim, J.H., Loganathan, G.V., A new heuristic optimization algorithm: harmony search, Simulation, 76(2), 60-68, (2001).
• Rashedi, E., Nezamabadi-pour, H., Saryazdi, S., GSA: A gravitational search algorithm, Information Sciences, 179(13), 2232-2248, (2009).
• Kaveh, A., Talatahari, S., A novel heuristic optimization method: charged system search, Acta Mechanica, 213(3-4), 267-289, (2010).
• Lee, S.H., Kong, J.S., Seo, J.H., 1997. Observers for bilinear systems with unknown inputs and application to superheater temperature control, Control Engineering Practice, 5(4), 493-506, (1997).
• Özer, Ş., Zorlu, H., Identification of bilinear systems using differential evolution algorithm, Sadhana, 36(3), 281-292, (2011).
• Mete, S., Özer, Ş., Zorlu, H., System identification using Hammerstein model optimized with differential evolution algorithm, International Journal of Electronics and Communications, 70, 1667-1675, (2016).