Developing an atmospheric aging evaluation model of acrylic coatings: A semi-supervised machine learning algorithm

Abstract

To study the atmospheric aging of acrylic coatings, a two-year aging exposure experiment was conducted in 13 representative climatic environments in China. An atmospheric aging evaluation model of acrylic coatings was developed based on aging data including 11 environmental factors from 567 cities. A hybrid method of random forest and Spearman correlation analysis was used to reduce the redundancy and multicollinearity of the data set by dimensionality reduction. A semi-supervised collaborative trained regression model was developed with the environmental factors as input and the low-frequency impedance modulus values of the electrochemical impedance spectra of acrylic coatings in 3.5wt% NaCl solution as output. The model improves accuracy compared to supervised learning algorithms model (support vector machines model). The model provides a new method for the rapid evaluation of the aging performance of acrylic coatings, and may also serve as a reference to evaluate the aging performance of other organic coatings.

References

[1] LiXG, ZhangDW, LiuZY, LiZ, DuCW, DongCF. Materials science: Share corrosion data. Nature, 2015, 527(7579): 441

[2] WangL, GaoJ, LiXG, HuJW. Effect of photo-radiation on anti-corrosion and protection performance of acrylic polyurethane coating. J. Univ. Sci. Technol. Beijing, 2008, 30(2): 152

[3] GuermaziN, ElleuchK, AyediHF. The effect of time and aging temperature on structural and mechanical properties of pipeline coating. Mater. Des., 2009, 30(6): 2006

[4] PereraDY. Effect of thermal and hygroscopic history on physical ageing of organic coatings. Prog. Org. Coat., 2002, 44(1): 55

[5] StartsevVO, LebedevMP, KhrulevKA, MolokovMV, FrolovAS, NizinaTA. Effect of outdoor exposure on the moisture diffusion and mechanical properties of epoxy polymers. Polym. Test., 2018, 65: 281

[6] GengS, GaoJ, LiXG, ZhaoQL. Aging behaviors of acrylic polyurethane coatings during UV irradiation. J. Univ. Sci. Technol. Beijing, 2009, 31(6): 752

[7] M.D. Yu, C.Q. Fan, F. Ge, Q.Y. Lu, X. Wang, and Z.Y. Cui, Anticorrosion behavior of organic offshore coating systems in UV, salt spray and low temperature alternation simulated Arctic offshore environment, Mater. Today Commun., 28(2021), art. No. 102545.

[8] K.Y. Che, P. Lyu, F. Wan, and M.L. Ma, Investigations on aging behavior and mechanism of polyurea coating in marine atmosphere, Materials, 12(2019), No. 21, art. No. 3636.

[9] GaoJ, LiC, LvZ, WangR, WuDQ, LiXG. Correlation between the surface aging of acrylic polyurethane coatings and environmental factors. Prog. Org. Coat., 2019, 132: 362

[10] da SilvaTC, MallarinoS, TouzainS, Margarit-MattosICP. DMA, EIS and thermal fatigue of organic coatings. Electrochim. Acta, 2019, 318: 989

[11] GacPL, ChoqueuseD, MelotD, MelveB, MeniconiL. Life time prediction of polymer used as thermal insulation in offshore oil production conditions: Ageing on real structure and reliability of prediction. Polym. Test., 2014, 34: 168

[12] LvYD, HuangYJ, YangJL, et al. . Outdoor and accelerated laboratory weathering of polypropylene: A comparison and correlation study. Polym. Degrad. Stab., 2015, 112: 145

[13] D.Q. Wu, D.W. Zhang, S.P. Liu, et al., Prediction of polycarbonate degradation in natural atmospheric environment of China based on BP-ANN model with screened environmental factors, Chem. Eng. J., 399(2020), art. No. 125878.

[14] W. Sai, G.B. Chai, and N. Srikanth, Fatigue life prediction of GLARE composites using regression tree ensemble-based machine learning model, Adv. Theory Simul., 3(2020), No. 6, art. No. 2000048.

[15] KuangJG, LongZL. Prediction model for corrosion rate of low-alloy steels under atmospheric conditions using machine learning algorithms. Int. J. Miner. Metall. Mater., 2024, 31(2): 337

[16] WuMW, YongW, FuCQ, MaCM, LiuRP. Machine learning-assisted efficient design of Cu-based shape memory alloy with specific phase transition temperature. Int. J. Miner. Metall. Mater., 2024, 31(4): 773

[17] YangXJ, YangJK, YangY, et al. . Data-mining and atmospheric corrosion resistance evaluation of Sn- and Sb-additional low alloy steel based on big data technology. Int. J. Miner. Metall. Mater., 2022, 29(4): 825

[18] Z.B. Pei, D.W. Zhang, Y.J. Zhi, et al., Towards understanding and prediction of atmospheric corrosion of an Fe/Cu corrosion sensor via machine learning, Corros. Sci., 170(2020), art. No. 108697.

[19] Y.P. Diao, L.C. Yan, and K.W. Gao, Improvement of the machine learning-based corrosion rate prediction model through the optimization of input features, Mater. Des., 198(2021), art. No. 109326.

[20] Y.J. Zhi, Z.H. Jin, L. Lu, et al., Improving atmospheric corrosion prediction through key environmental factor identification by random forest-based model, Corros. Sci., 178(2021), art. No. 109084.

[21] A. Roy, M.F.N. Taufique, H. Khakurel, R. Devanathan, D.D. Johnson, and G. Balasubramanian, Machine-learning-guided descriptor selection for predicting corrosion resistance in multi-principal element alloys, NPJ Mater. Degrad., 6(2022), art. No. 9.

[22] van EngelenJE, HoosHH. A survey on semi-supervised learning. Mach. Learn., 2020, 109(2): 373

[23] ZhouZH, LiM. Semisupervised regression with cotraining-style algorithms. IEEE Trans. Knowl. Data Eng., 2007, 19(11): 1479

[24] MaL, WangXL. Semi-supervised regression based on support vector machine co-training. Comput. Eng. Appl., 2011, 47(3): 177

[25] BreimanL. Random forests. Mach. Learn., 2001, 45(1): 5

[26] XiaoCW, YeJQ, EstevesRM, RongCM. Using Spearman’s correlation coefficients for exploratory data analysis on big dataset. Concurr. Comput. Pract. Exp., 2016, 28(14): 3866

[27] LiuJW, LiuY, LuoXL. Semi-supervised learning methods. Chin. J. Comput., 2015, 38(8): 1592

[28] ZhouZH. Machine Learning, 2016BeijingTsinghua University Publishing House Co., ltd225

[29] DingSF, QiBJ, TanHY. An overview on theory and algorithm of support vector machines. J. Univ. Electron. Sci. Technol. China, 2011, 40(1): 2

[30] J.K. Wang, L.W. Ma, X. Guo, et al., Two birds with one stone: Nanocontainers with synergetic inhibition and corrosion sensing abilities towards intelligent self-healing and self-reporting coating, Chem. Eng. J., 433(2022), art. No. 134515.

[31] XuYX, YanCW, DingJ, GaoYM, CaoCN. UV photo-degradation of coatings. J. Chin. Soc. Corros. Prot., 2004, 24(3): 168

[32] YangXF, LiJ, CrollSG, TallmanDE, BierwagenGP. Degradation of low gloss polyurethane aircraft coatings under UV and prohesion alternating exposures. Polym. Degrad. Stab., 2003, 80(1): 51

[33] FeldmanD. Polymer weathering: Photo-oxidation. J. Polym. Environ., 2002, 10(4): 163

[34] QinHL, ZhangSM, LiuHJ, XieSB, YangMS, ShenDY. Photo-oxidative degradation of polypropylene/montmoril-lonite nanocomposites. Polymer, 2005, 46(9): 3149

[35] JohnsonBW, McIntyreR. Analysis of test methods for UV durability predictions of polymer coatings. Prog. Org. Coat., 1996, 27(1–4): 95

[36] ZhangK, HaoL, DuM, MiJ, WangJN, MengJP. A review on thermal stability and high temperature induced ageing mechanisms of solar absorber coatings. Renewable Sustainable Energy Rev., 2017, 67: 1282

[37] LacombreCV, BouvetG, TrinhD, MallarinoS, TouzainS. Effect of pigment and temperature onto swelling and water uptake during organic coating ageing. Prog. Org. Coat., 2018, 124: 249

[38] P. Sivakumar, S.M. Du, M. Selter, I. Ballard, J. Daye, and J. Cho, Long-term thermal aging of parylene conformal coating under high humidity and its effects on tin whisker mitigation, Polym. Degrad. Stab., 191(2021), art. No. 109667.

[39] TaylorSR, MoongkhamklangP. The delineation of local water interaction with epoxy coatings using fluorescence microscopy. Prog. Org. Coat., 2005, 54(3): 205

[40] GuoYJ, YanH, XiaoF. Accelerated thermal-oxygen aging test for epoxy resin. J. Tsinghua Univ. (Sci. Tech.), 2000, 40(7): 1

[41] ZhangSY, LiSJ, LuoXW, ZhouWF. Mechanism of the significant improvement in corrosion protection by lowering water sorption of the coating. Corros. Sci., 2000, 42(12): 2037