A cuckoo search based neural network to predict fatigue life in rotor blade composites

Khaled Ziane; Adrian Ilinca; Abdullah Khan; Soraya Zebirate

doi:10.15282/jmes.14.1.2020.18.0503

Authors

Khaled Ziane Wind Energy Research Laboratory (WERL), Université du Québec à Rimouski, 300, allée des Ursulines, Rimouski, G5L 3A1, CANADA.
Adrian Ilinca Wind Energy Research Laboratory (WERL), Université du Québec à Rimouski, 300, allée des Ursulines, Rimouski, G5L 3A1, CANADA.
Abdullah Khan Institute of Business and Management Science, University of Agricultural Peshawar, PAKISTAN.
Soraya Zebirate Laboratoire d’Ingénierie en Sécurité Industrielle et Développement Durable LISIDD, IMSI, Université d’Oran 2 Mohamed Ben Ahmed, ALGERIA.

DOI:

https://doi.org/10.15282/jmes.14.1.2020.18.0503

Keywords:

Wind turbine blades, composite materials, fiber orientation, fatigue life prediction, cuckoo search, neural network

Abstract

In modern wind turbine blades industry, fiber-reinforced composites are mostly used for their good mechanical characteristics: high stiffness, low density and long fatigue life. Wind turbine blades are constructed in different structural elements from a variety of composite laminates, often including Unidirectional (UD) material in spars and multiple forms of Multidirectional (MD) in skins and webs. The purpose of this paper is to identify materials that have appropriate fiber orientations to improve fatigue life. By using Cuckoo Search-based Neural Network (CSNN), we have developed a model to predict fatigue life under tension-tension charges for five composite materials, with different fiber stacking sequences embedded in three types of resin matrices (epoxy, polyester and vinylester), which are all appropriate for the design of wind turbine blades. In the CSNN approach used in this work, the cost function was assessed using the Mean Square Error (MSE) computed as the squared difference between the predicted values and the target values for a number of training set samples, obtained from an experimental fatigue database. The results illustrate that the CSNN can provide accurate fatigue life prediction for different MD/UD composite laminates, under different angles of fiber orientation.

References

Attaf B. Designing composite wind turbine blades from cradle to cradle. In Recent advances in composite materials for wind turbine blades; Attaf, B., Ed.; The world academic publishing, Hong Kong. 2013;2-24.

Nijssen RPL. Fatigue life prediction and strength degradation of wind turbine rotor blade composites. PhD Thesis. Delft University the Netherlands, Delft. 2006.

Mishnaevsky Jr L, Branner K, Petersen HN, Beauson J, McGugan M, F. Sørensen B. Materials for wind turbine blades: An overview. Materials. 2017;10:1-24.

Beauson J, Madsen B, Toncelli C, Brøndsted P, Bech JI. Recycling of shredded composites from wind turbine blades in new thermoset polymer composites. Compos. Part A. 2016;90:390-99.

Mandell JF, Samborsky DD, Miller DA. Effects of resin and reinforcement variations on fatigue resistance of wind turbine blades. In Advances in wind turbine blade and design. Brondsted P, Nijssen RPL, Eds., Woodhead Publishing Limited, UK. 2013;210-50.

Al-Assadi M, El Kadi H, Deiab IM. Using artificial neural networks to predict the fatigue life of different composite materials including the stress ratio effect. Appl. Compos. Mater. 2011;18:297-309.

Yang XS, Deb S. Cuckoo search via Lévy flights. World Congress on Nature & Biologically Inspired Computing. India. 2009.

Yang XS. Nature-Inspired Metaheuristic Algorithms Second Edition. Luniver Press, UK, 2010.

Nawi NM, Khan A, Rehman MZ. A new back-propagation neural network optimized with cuckoo search algorithm. International Conference on Computational Science and Its Applications. Ho Chi Minh, 2013.

SNL/MSU/DOE Composite Material Fatigue Database. Mechanical properties of composite materials for wind turbine blades. Montana State University-Bozeman, Version 25.0, Available online: http://energy.sandia.gov/ (accessed on 20 October 2016).

Ziane K, Zebirate S, Zaitri A. Particle swarm optimization-based neural network for predicting fatigue strength in composite laminates of wind turbine blades. Composites: Mechanics, Computations, Applications: An International Journal. 2015;6:321-38.

Ziane K, Zebirate S, Zaitri A. Fatigue strength prediction in composite materials of wind turbine blades under dry–wet conditions: An artificial neural network approach. Wind Engineering. 2016;40:189-98.

Al-Assadi M, El-Kadi H, Deiab IM. Predicting the fatigue life of different composite materials using artificial neural networks. Appl. Compos. Mater. 2010;17:1-14.

Mathur S, Gope P, Sharma J. Prediction of fatigue lives of composites material by artificial neural network. In Proceedings of the SEM 2007 Annual Conference and Exposition, Springfield, Massachusetts, USA. 2007; Paper No. 260.

Jiménez AA, Gómez Muñoz CQ, García Márquez FP. Machine learning for wind turbine blades maintenance management. Energies. 2017;11:1-16.

Liu X, Liu Z, Liang Z, Zhu S, Correia JAFO, De Jesus AMP. PSO-BP Neural Network-Based Strain Prediction of Wind Turbine Blades. Materials. 2019;12:225-34.

Mandell JF, Samborsky DD, Miller DA. Analysis of SNL/MSU/DOE Fatigue Database Trends for Wind Turbine Blade Materials, 2010-2015. Research Report No. SAND SAND2016-1441, Sandia National Laboratories. 2016.

Samborsky DD, Agastra P, Mandell JF. Fatigue trends for wind blade infusion resins and fabrics. Proc. 51st AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference, Florida. 2010.

Agastra P, Samborsky DD, Mandell JF. Fatigue resistance of fiberglass laminates at thick material transitions. Proc. 50th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference, California. 2009.

Mandell JF, Samborsky DD, Agastra P, Sears AT, Wilson T.J. Analysis of SNL/MSU/DOE Fatigue Database Trends for Wind Turbine Blade Materials. Research Report No. SAND2010-7052, Sandia National Laboratories. 2010.

Ziane K. Analyse, évaluation et réduction des risques d’un parc éolien. PhD Dissertation, Université d’Oran 2 Mohamed Ben Ahmed, Oran. 2017.

Svozil D, KvasniEka V, Pospichal J. Introduction to multi-layer feedforward neural networks. Chemometrics and Intelligent Laboratory Systems. 1997;39:43-62.

Rath AK, Das HC, Parhi DR, Kumar PB. Application of artificial neural network for control and navigation of humanoid robot. Journal of Mechanical Engineering and Sciences. 2018;12:3529-38.

Hanief M, Wani MF. Artificial neural network and regression-based models for prediction of surface roughness during turning of red brass (C23000). Journal of Mechanical Engineering and Sciences. 2016;10:1835-45.

Mohanty JR, Verma BB, Parhi DRK, Ray PK. Application of artificial neural network for predicting fatigue crack propagation life of aluminum alloys. Archives of Computational Materials Science and Surface Engineering. 2009;1:133-38.

Al-Assaf Y, El-Kadi H. Fatigue life prediction of unidirectional glass fiber/epoxy composite laminae using neural networks. Compos. Struct. 2001;53:65-71.

Vassilopoulos AP, Georgopoulos EF, Dionysopoulos V. Artificial neural networks in spectrum fatigue life prediction of composite materials. International Journal of Fatigue. 2007;29:20-29.

Nawi NM, Khan A, Rehman MZ. A New Cuckoo Search Based Levenberg-Marquardt (CSLM) Algorithm. International Conference on Computational Science and Its Applications, Ho Chi Minh. 2013.

Jafari S, Bozorg-Haddad O, Chu X. Cuckoo Optimization Algorithm. In Advanced Optimization by Nature-Inspired Algorithms; Bozorg-Haddad, O., Ed.; Springer: Singapore. 2018;39-49.

Ding J, He X, Jiang B, Wu Y. Parameter identification for area-specific resistance of direct methanol fuel cell using cuckoo search algorithm. In Bio-Inspired Computing - Theories and Applications. Gong M, Linqiang P, Tao S, Tang K, Zhang X, Eds.; Springer: Heidelberg, Germany. 2015;107-12.

Yi J, Xu W, Chen Y. Novel back propagation optimization by cuckoo search algorithm. The Scientific World Journal. 2014;1-8.