Predicting fatigue life of automotive adhesive bonded joints: a data-driven approach using combined experimental and numerical datasets

Abstract

The majority of vehicle structural failures originate from joint areas. Cyclic loading is one of the primary factors in joint failures, making the fatigue performance of joints a critical consideration in vehicle structure design. The use of traditional fatigue analysis methods is constrained by the absence of adhesive life data and the wide variety of joint geometries. Therefore, there is a pressing need for an accurate fatigue life estimation method for the joints in the automotive industry. In this work, we proposed a data-driven approach embedding physical knowledge-guided parameters based on experimental data and finite element analysis (FEA) results. Different machine learning (ML) algorithms are adopted to investigate the fatigue life of three typical adhesive joints, namely lap shear, coach peel and KSII joints. After the feature engineering and tuned process of the ML models, the preferable model using the Gaussian process regression algorithm is established, fed with eight input parameters, namely thicknesses of the substrates, line forces and bending moments of the adhesive bonded joints obtained from FEA. The proposed method is validated with the test data set and part-level physical tests with complex loading states for an unbiased evaluation. It demonstrates that for life prediction of adhesive joints, the data-driven solutions can constitute an improvement over conventional solutions.

Keywords

Fatigue life / Adhesive bonded joints / Finite element analysis (FEA) / Machine learning (ML)

References

[1] da Silva LFM, Öchsner A, Adams RD. da Silva LFM, Öchsner A, Adams RD. Introduction to adhesive bonding technology. Handbook of adhesion technology, 2018, Cham: Springer 1-7.

[2] Schijve J (2009) Fatigue of joints. In: fatigue of structures and materials. Springer, Dordrecht, pp 499–533

[3] Wit FM, Poulis JA. Rowe J. Joining technologies for automotive components. Advanced materials in automotive engineering, 2012, Sawston: Woodhead Publishing 315-329.

[4] Satheeshkumar V, Narayanan RG, Gunasekera JS (2023) Sustainable manufacturing. In: sustainable manufacturing processes. Elsevier, Amsterdam, pp 53–112

[5] Abdel Wahab MM. Fatigue in adhesively bonded joints: a review. ISRN Mater Sci, 2012, 2012: 1-25.

[6] Da Costa Mattos HS, Monteiro AH, Palazzetti R. Failure analysis of adhesively bonded joints in composite materials. Mater Des, 2012, 33: 242-247.

[7] Beber VC, Schneider B. Fatigue of structural adhesives under stress concentrations: notch effect on fatigue strength, crack initiation and damage evolution. Int J Fatigue, 2020, 140: 105824.

[8] Donough MJ, Gunnion AJ, Orifici AC, et al. Plasticity induced crack closure in adhesively bonded joints under fatigue loading. Int J Fatigue, 2015, 70: 440-450.

[9] Sonsino C. Course of SN-curves especially in the high-cycle fatigue regime with regard to component design and safety. Int J Fatigue, 2007, 29: 2246-2258.

[10] He X. A review of finite element analysis of adhesively bonded joints. Int J Adhes Adhes, 2011, 31: 248-264.

[11] Nolting A, Underhill P, DuQuesnay D, et al. Fatigue behavior of adhesively bonded aluminium double strap joints. J Astm Int, 2008.

[12] Gao ZZ, Yue ZF. Fatigue failure of polyethylene methacrylate in adhesive assembly under unsymmetrical bending. Theoret Appl Fract Mech, 2007, 48: 89-96.

[13] Romanko J, Liechti KM, Knauss WG. Mittal KL. Life prediction methodology for adhesively bonded joints. Adhesive joints: formation, characteristics, and testing, 1984, Boston: Springer 567-586.

[14] Kumar S, Pandey PC. Fatigue life prediction of adhesively bonded single lap joints. Int J Adhes Adhes, 2011, 31: 43-47.

[15] Shenoy V, Ashcroft IA, Critchlow GW, et al. Unified methodology for the prediction of the fatigue behaviour of adhesively bonded joints. Int J Fatigue, 2010, 32: 1278-1288.

[16] Khoramishad H, Crocombe AD, Katnam KB, et al. Predicting fatigue damage in adhesively bonded joints using a cohesive zone model. Int J Fatigue, 2010, 32: 1146-1158.

[17] Abdel Wahab MM, Ashcroft IA, Crocombe AD, et al. Finite element prediction of fatigue crack propagation lifetime in composite bonded joints. Compos A Appl Sci Manuf, 2004, 35: 213-222.

[18] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521: 436-444.

[19] Butler KT, Davies DW, Cartwright H, et al. Machine learning for molecular and materials science. Nature, 2018, 559: 547-555.

[20] Bhadeshia HKDH. Neural networks and information in materials science. Stat Anal Data Min, 2009, 1: 296-305.

[21] Gan L, Wu H, Zhong Z. Fatigue life prediction considering mean stress effect based on random forests and kernel extreme learning machine. Int J Fatigue, 2022, 158: 106761.

[22] Liang T, Yin A, Pan M, et al. Gaussian process flow and physical model fusion driven fatigue evaluation model using Kalman filter. Int J Fatigue, 2022, 165: 107182.

[23] Karolczuk A, Skibicki D, Pejkowski L. Gaussian process for machine learning-based fatigue life prediction model under multiaxial stress–strain conditions. Materials, 2022, 15: 7797.

[24] Farid M. Data-driven method for real-time prediction and uncertainty quantification of fatigue failure under stochastic loading using artificial neural networks and Gaussian process regression. Int J Fatigue, 2022, 155: 106415.

[25] Lyathakula KR, Yuan FG. A probabilistic fatigue life prediction for adhesively bonded joints via ANNs-based hybrid model. Int J Fatigue, 2021, 151: 106352.

[26] Chen Q, Guo H, Avery K, et al. Fatigue performance and life estimation of automotive adhesive joints using a fracture mechanics approach. Eng Fract Mech, 2017, 172: 73-89.

[27] Prastyo PH, Ardiyanto I, Hidayat R (2020) A review of feature selection techniques in sentiment analysis using filter, wrapper, or hybrid methods. In: 2020 6th international conference on science and technology, Yogyakarta, Indonesia, 2020, pp 1−6. https://doi.org/10.1109/ICST50505.2020.9732885

[28] Mangalathu S, Hwang SH, Jeon JS. Failure mode and effects analysis of RC members based on machine-learning-based Shapley additive explanations (SHAP) approach. Eng Struct, 2020, 219: 110927.

[29] Hastie T, Tibshirani R, Friedman J. The elements of statistical learning, 2009, New York: Springer.

[30] Breiman L. Random forests. Mach Learn, 2001, 45: 5-32.

[31] Tognan A, Laurenti L, Salvati E. Contour method with uncertainty quantification: a robust and optimized framework via Gaussian process regression. Exp Mech, 2022, 62: 1305-1317.

Funding

National Natural Science Foundation(52205377)

Key Technologies Research and Development Program http://dx.doi.org/10.13039/501100012165(2022YFB4601804)

Key Basic Research Project of Suzhou(SJC2022029)

Key Basic Research Project of Suzhou (SJC2022031)