Bearing Response Prediction in Hydrothermal Aged Carbon Fiber Reinforced Epoxy Composite Joints Using Machine Learning Techniques

Document Type : Special Issue: Mechanics of Advanced Fiber Reinforced Composite Structures

Authors

1 Department of Mechanical Engineering, Chandigarh University, Mohali, Punjab, 140301, India

2 Faculty of Geoengineering, Mining and Geology, Wroclaw University of Science and Technology, Na Grobli 15, 50-421 Wroclaw, Poland

3 Department of Electronics and Communication Engineering, Chandigarh University, Mohali, Punjab, 140301, India

Abstract

The work focuses on predicting the bearing response in hydrothermal-aged carbon fiber-reinforced epoxy composite (CFREC) joints through the utilization of machine learning techniques. CFREC are extensively employed in aerospace and other high-performance applications, and their long-term structural integrity is of paramount importance. The hydrothermal aging process can significantly affect the mechanical behavior of such composites, particularly in joint configurations. In this research, an innovative support vector regression approach is present that leverages machine learning algorithms to forecast the bearing response of CFREC joints after undergoing hydrothermal aging. The study encompasses the development of predictive models using a comprehensive dataset of experimental observations. The machine learning technique, support vector regression is trained and evaluated to assess their accuracy and reliability in predicting bearing response. The results show that the overall percent reduction in bearing response, after 30 days of pristine composite bolted joints at 0 Nm bolt torque shows reductions of 23.22 % at 65°C, respectively. Conversely, under the same conditions, MWCNTs added composite bolted joints exhibit only a 9.2% reduction. The predictive models find the value of 0.0081 RSME and 0.8 R2 respectively through support vector regression confirming that the predicted values lie in between the upper and lower bond.

Keywords

Main Subjects

References

[1]    Palaniappan, S.K., Singh, M.K., Rangappa, S.M. and Siengchin, S., 2023. Eco-friendly Biocomposites: A Step Towards Achieving Sustainable Development Goals. Composites,  7(12), pp. 7373. 
[2]    Kumar, M, Saini, J.S. and Bhunia, H., 2020. Performance of mechanical joints prepared from carbon-fiber-reinforced polymer nanocomposites under accelerated environmental aging. Journal of Materials Engineering and Performance 29, pp. 7511-7525.
[3]    Kumar, M., Saini, J.S., Bhunia, H. and Chowdhury, S.R., 2021. The behavior of mechanical joints prepared from EB-cured CFRP nanocomposites subjected to hygrothermal aging under bolt preloads. Applied Composite Materials, 28, pp.271-296.
[4]    Dhiman, N., Saini, J.S. and Kumar, M., 2023. Hygrothermal effect on strength of thermally cured glass epoxy nanocomposite made joints. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 237(23), pp. 5692-5707.
[5]    De'Nève, B. and Shanahan, M.E.R., 1993. Water absorption by an epoxy resin and its effect on the mechanical properties and infra-red spectra. Polymer, 34(24), pp. 5099-5105.
[6]    Zheng, Q. and Morgan, R.J., 1993. Synergistic thermal-moisture damage mechanisms of epoxies and their carbon fiber composites. Journal of Composite Materials, 27(15), pp. 1465-1478.
[7]    Ray, B.C., 2006. Temperature effect during humid ageing on interfaces of glass and carbon fibers reinforced epoxy composites. Journal of colloid and interface science, 298(1), pp. 111-117.
[8]    Suyambulingam, I., Rangappa, S.M. and Siengchin, S., 2023. Advanced Materials and Technologies for Engineering Applications. Applied Science and Engineering Progress, 16(3), pp. 6760-6760.
[9]    Tian, W. and Hodgkin, J., 2010. Long‐term aging in a commercial aerospace composite sample: Chemical and physical changes. Journal of Applied Polymer Science, 115(5), pp. 2981-2985.
[10]    Dao, B., Hodgkin, J.H., Krstina, J., Mardel, J. and Tian, W., 2007. Accelerated ageing versus realistic ageing in aerospace composite materials. IV. Hot/wet ageing effects in a low temperature cure epoxy composite. Journal of applied polymer science, 106(6), pp. 4264-4276.
[11]    Dao, B., Hodgkin, J., Krstina, J., Mardel, J. and Tian, W., 2010. Accelerated aging versus realistic aging in aerospace composite materials. V. The effects of hot/wet aging in a structural epoxy composite. Journal of applied polymer science, 115(2), pp. 901-910.
[12]    Alessi, S., Pitarresi, G. and Spadaro, G., 2014. Effect of hydrothermal ageing on the thermal and delamination fracture behaviour of CFRP composites. Composites Part B: Engineering, 67, pp. 145-153.
[13]    Hong, B., Xian, G. and Wang, Z., 2018. Durability study of pultruded carbon fiber reinforced polymer plates subjected to water immersion. Advances in Structural Engineering, 21(4), pp. 571-579.
[14]    Yin, B.B. and Liew, K.M., 2021. Machine learning and materials informatics approaches for evaluating the interfacial properties of fiber-reinforced composites. Composite Structures, 273, pp. 114328.
[15]    Naser, M.Z., Thai, S. and Thai, H.T., 2021. Evaluating structural response of concrete-filled steel tubular columns through machine learning. Journal of Building Engineering, 34, pp. 101888.
[16]    Chaabene, W.B., Flah, M. and Nehdi, M.L., 2020. Machine learning prediction of mechanical properties of concrete: Critical review. Construction and Building Materials, 260, pp. 119889.
[17]    Ford, E., Maneparambil, K., Rajan, S. and Neithalath, N., 2021. Machine learning-based accelerated property prediction of two-phase materials using microstructural descriptors and finite element analysis. Computational Materials Science, 191, pp. 110328.
[18]    Sacco, C., Radwan, A.B., Anderson, A., Harik, R. and Gregory, E., 2020. Machine learning in composites manufacturing: A case study of Automated Fiber Placement inspection. Composite Structures, 250, pp. 112514.
[19]    Machello, C., Bazli, M., Rajabipour, A., Rad, H.M., Arashpour, M. and Hadigheh, A., 2023. Using machine learning to predict the long-term performance of fibre-reinforced polymer structures: A state-of-the-art review. Construction and Building Materials, 408, pp. 133692.
[20]    Alhusban, M., Alhusban, M. and Alkhawaldeh, A.A., 2023. The Efficiency of Using Machine Learning Techniques in Fiber-Reinforced-Polymer Applications in StructuralEngineering. Sustainability, 16(1), pp. 11.
[21]    Kumar, M., Saini, J.S. and Bhunia, H., 2023. Radiation Curing of Fiber Reinforced Polymer Composite Based Mechanical Joints. In Applications of High Energy Radiations: Synthesis and Processing of Polymeric Materials (pp. 107-148). Singapore: Springer Nature Singapore.
[22]    Chauhan, S., Singh, M. and Kumar Aggarwal, A., 2021. An effective health indicator for bearing using corrected conditional entropy through diversity-driven multi-parent evolutionary algorithm. Structural Health Monitoring, 20(5), pp. 2525-2539.
[23]    Kumar, A. and Kumar, R., 2017. Time-frequency analysis and support vector machine in automatic detection of defect from vibration signal of centrifugal pump. Measurement, 108, pp. 119-133.
[24]    Kumar, M., Saini, J.S., Bhunia, H. and Chowdhury, S.R., 2021. Aging of bolted joints prepared from electron‐beam‐cured multiwalled carbon nanotube‐based nanocomposites with variable torques. Polymer Composites, 42(8), pp. 4082-4104.
[25]    Kumar, M., Saini, J.S. and Bhunia, H., 2021. Investigations on MWCNT embedded carbon/epoxy composite joints subjected to hygrothermal aging under bolt preloads. Fibers and Polymers, 22(7), pp.1957-1975.
Mechanics of Advanced Composite Structures
Volume 12, Issue 2 - Serial Number 25
Special Issue on Mechanics of Advanced Fiber-Reinforced Composite Structures: Celebrating the 50th Anniversary of Semnan University, Handled by the Esteemed Journal Editor, Prof. Dr. Mavinkere Rangappa Sanjay - In Progress
August 2025
Pages 329-338

Files

Cited by

Share

How to cite

Statistics