Cover
Vol. 25 No. 1 (2025)

Published: September 9, 2025

Pages: 7-14

Original Article

Adaptive Neuro-Fuzzy Inference System Model for Predicting the Tensile and Bending Properties of Carbon Fiber-Epoxy Composite

Azhar D. Habeeb 1
1 Department of Mechanical Engineering, College of Engineering, University of Basrah, Basrah, Iraq
History
  • Received: December 27, 2023
  • Revised: June 24, 2024
  • Accepted: October 7, 2024
  • Available Online: August 16, 2025
DOI

https://doi.org/10.33971/bjes.25.1.2

Abstract

The aim of this work is to experimentally study the influence of fiber prestress and curing temperature on the tensile and flexural properties of carbon fiber-epoxy composite. Adaptive Neuro-Fuzzy Inference System model was used to predict the effect of fiber prestress and curing temperature on the tensile strength, tensile modulus, flexural strength and flexural modulus of carbon fiber-epoxy composite. It was found that, the best membership functions for predicting the tensile strength, tensile modulus and flexural modulus are Gaussian membership functions with 4 number of membership function, and for predicting the flexural strength are generalized bell membership functions with 4 number of membership functions. From the comparison between the experimental and predicted results of carbon fiber-epoxy composite properties, it is found that the prediction results of this model show a good agreement with experimental results.

Keywords

References

  1. S. Krishnamurthy, “Prestressed Advanced Fiber Reinforced Composites”, Ph.D. thesis, Cranfield University, 2006. http://hdl.handle.net/1826/1039
  2. H. S. Kim, D. G. Lee, “Avoidance of Fabricational Thermal Residual Stresses in Co-Cure Bonded MetalComposite Hybrid Structures”, Journal of Adhesion Science and Technology, Vol. 20, Issue 9, pp. 959-979, 2006. https://doi.org/10.1163/156856106777657805
  3. S. Motahhari, “A Study of the Influences of Fiber Prestressing on the Mechanical Properties of Polymer Matrix Composites”, Ph.D. thesis, Queen's University, Kingston, Ontario, Canada, 1998.
  4. O. A. Abdullah, “Effect of Fiber Prestress and Curing Temperature on the Tensile and Flexural Properties of Carbon Fiber-Epoxy Composite”, Ph.D. thesis, University of Basrah, 2016.
  5. A. A. Al-Jeebory, A. I. Al-Mosawi, “Mechanical Properties of Araldite Matrix Composites Reinforced with Hybrid Carbon-Kevlar Fibers”, Al-Qadisiya Journal for Engineering Sciences, Vol. 3, Issue 1, pp. 44-50, 2010.
  6. J. Zhao, J. Cameron, “Polypropylene Matrix Composites Reinforced with Pre-Stressed Glass Fibers”, Polymer Composites, Vol. 19, Issue 3, pp. 218-224, 1998.
  7. M. A. Jarrah, Y. Al-Assaf, H. E. Kadi, “Neuro-Fuzzy Modeling of Fatigue Life Prediction of Unidirectional Glass Fiber/Epoxy Composite Laminates”, Journal of Composite Materials, Vol. 36, Issue 6, pp. 685-700, 2002.
  8. N. Vallalperumal, B. Vidivelli, “Anfis Based Modelling of CFRP Confined Concrete Columns Under Axial Compression”, Asian Journal of Civil Engineering (BHRC), Vol. 17, Issue 6, pp. 803-815, 2016.
  9. A. D. Habeeb, “Adaptive Neuro-Fuzzy Inference System Model for Predicting the Mechanical Properties of Carbon Fiber-Epoxy Composite”, M.Sc. thesis, University of Basrah, 2017.
  10. Sika Kimia Sdn Bhd, SikaWrap®-300 C Product Data Sheet, Edited by Lot 689 Nilai Industrial Estate, Malaysia, 2010.
  11. Sika Gulf B.S.C., Sikadur®-330 Product Data Sheet, Edited by Bldg. 925, Kingdom of Bahrain, 2006.
  12. ASTM D 3039. Standard Test Method for Tensile Properties of Polymer Matrix Composite Materials. Annual Book of ASTM Standards. Current edition published July 2000.
  13. I. O. Bachi, N. Abdulr azzaq, Z. He, “Neuro Fuzzy Model for Predicting the Dynamic Characteristics of Beams”, Acta Mechanica Solida Sinica, Vol. 27, Issue 1, pp. 85-96, 2014. https://doi.org/10.1016/S0894-9166(14)60019-7
  14. J. S. R. Jang, C. Tsai, E. Mizutani, Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence, Simon & Schuster/A Viacom Company, 3rd Edition, United States of America, 1997.