Development of Artificial Neural Network Model in Predicting Performance of the Smart Wind Turbine Blade

E.E. Supeni; J.A. Epaarachchi; M.M. Islam; K.T. Lau

doi:10.15282/jmes.6.2014.1.0071

Authors

E.E. Supeni Department of Mechanical Engineering, Faculty of Engineering, Universiti Putra Malaysia, Malaysia
J.A. Epaarachchi Centre Excellence in Engineered Fibre Composites, University of Southern Queensland, Australia
M.M. Islam Centre Excellence in Engineered Fibre Composites, University of Southern Queensland, Australia
K.T. Lau Department of Mechanical Engineering, Hong Kong Polytechnic University HongKong, China

DOI:

https://doi.org/10.15282/jmes.6.2014.1.0071

Keywords:

Artificial neural network; back-propagation; multiple back-propagation; non-linear autoregressive exogenous model.

Abstract

This paper demonstrates the applicability of artificial neural networks (ANNs) that use multiple bck-propagation networks (MBP) and a non-linear autoregressive exogenous model (NARX) for predicting the deflection of a smart wind turbine blade specimen. A neural network model has been developed to perform the deflection with respect to the number of wires required as the output parameter, and parameters such as load, current, time taken and deflection as the input parameters. The network has been trained with experimental data obtained from experimental work. The various stages involved in the development of a genetic algorithm based neural network model are addressed in detail in this paper.

References

Abaqus. (2012). Abaqus/cae release note 6.12.

Aeyzarq Muhammad Hadzreel, M. R., & Siti Rabiatull Aisha, I. (2013). Effect of reinforcement alignment on the properties of polymer matrix composite. Journal of Mechanical Engineering and Sciences, 4, 548-554.

Gayan, C. K., Jayantha, A. E., Hao, W., & Lau, K. T. (2013). Prediction of obsolete fbg sensor using ann for efficient and robust operation of shm systems. Key Engineering Materials, 558, 546-553.

Howard, D., & Mark, B. (2000). Neural network toolbox for computation, visualization and programming-user's guide The MathWorks, I. (Ed.) pp. 323.

Khan, M. A. R., Rahman, M. M., Kadirgama, K., & Bakar, R. A. (2012). Artificial neural network model for material removal rate of ti-15-3 in electrical discharge machining. Energy Education Science and Technology Part A: Energy Science and Research, 29(2), 1025-1038.

Khan, M. A. R., Rahman, M. M., Kadirgama, K., Maleque, M. A., & Bakar, R. A. (2011). Artificial intelligence model to predict surface roughness of ti-15-3 alloy in edm process. World Academy of Science, Engineering and Technology, 74, 198-202.

M. Khairul Zaimy, A. G., Zafiah, A., Rus, M., Ab Latif, N., & Nurulsaidatulsyida, S. (2013). Mechanical and thermal properties of waste bio-polymer compound by hot compression molding technique. Journal of Mechanical Engineering and Sciences, 5, 582-591.

Noel, L., & Bernardete, R. (2001). Hybrid learning multi neural architecture. IEEE International Joint Conference on Neural Networks, 4, 2788-2793.

Noel, L., & Bernardete, R. (2003). An efficient gradient-based learning algorithm applied to neural networks with selective actuation neurons. Neural Parallel and Scientific Computations, 11, 253-272.

Nolet, S. C. (2011). Composite wind blade engineering and manufacturing. Indepedent activities period mini-course. from http://web.mit.edu/windenergy/windweek/ Presentations/Nolet_Blades.pdf.

Peter, J. S., & Richard, J. C. (2012). Wind turbine blade design: Review. Energies, 5, 3425-3449

Rahman, M. M., Mohyaldeen, H. M., Noor, M. M., Kadirgama, K., & Bakar, R. A. (2011). Linear static response of suspension arm based on artificial neural network technique Advanced Materials Research, 213, 419-426.

Sapuan, S. M., & Iqbal, M. M. (2010). Composite materials technology : Neural network applications: CRC Press Taylor and Francis Group.

Sorensen, B. F., Jørgensen, E., Christian, P. D., & Jensen, F. M. (2004). Improved design of large wind turbine blade of fibre composites based onstudies of scale effects (phase 1) Risø-R-1390 (En) Denmark.

Srihari, P. V., Govindarajulu, K., & Ramachandra, K. (2010). A method to improve reliability of gearbox fault detection with artificial neural networks. International Journal of Automotive and Mechanical Engineering, 2, 221-230.

Supeni, E. E., Epaarachchi, J. A., Islam, M. M., & Lau, K. T. (2012a). Design and analysis of a smart composite beam for small wind turbine blade construction. Paper presented at the The Southern Region Engineering Conference (SREC) USQ, Toowoomba, Australia.

Supeni, E. E., Epaarachchi, J. A., Islam, M. M., & Lau, K. T. (2012b). Development of smart wind turbine blades. Paper presented at the The 8th Asian-Australasian Conference on Composite Materials (AACM-8), (KLCC),Kuala Lumpur, Malaysia.