پیش‌بینی عمق کربناته شدن بتن و بررسی عوامل تأثیرگذار از طریق مدل‌‌های یادگیری ماشین و بهینه‌سازی

منصوری, شعیب; رهایی, علیرضا; راشدی, سیدهادی; مقدس نژاد, فریدون

doi:10.22060/ceej.2024.22980.8086

دانشگاه صنعتی امیرکبیر

تعداد نشریات	7
تعداد شماره‌ها	405
تعداد مقالات	5,425
تعداد مشاهده مقاله	5,552,205
تعداد دریافت فایل اصل مقاله	5,029,463

	پیش‌بینی عمق کربناته شدن بتن و بررسی عوامل تأثیرگذار از طریق مدل‌‌های یادگیری ماشین و بهینه‌سازی
نشریه مهندسی عمران امیرکبیر
مقاله 5، دوره 56، شماره 12، 1403، صفحه 1583-1604 اصل مقاله (1.14 M)
نوع مقاله: مقاله پژوهشی
شناسه دیجیتال (DOI): 10.22060/ceej.2024.22980.8086
نویسندگان
شعیب منصوری؛ علیرضا رهایی؛ سیدهادی راشدی؛ فریدون مقدس نژاد^*
دانشکده مهندسی عمران و محیط زیست، دانشگاه صنعتی امیرکببر، تهران، ایران
چکیده
پیش‌بینی دقیق عمق کربناته شدن بتن برای محافظت در برابر پیامدهای زیان‌بار مانند ترک‌‌خوردگی و خوردگی بسیار مهم است. با این وجود، به دلیل پیچیدگی‌های فرآیند و انبوه متغیرهای موجود، تشخیص پارامترهایی که بیشترین اهمیت را در مدل‌سازی عمق کربناته بتن دارند، چالش‌ بزرگی محسوب می‌‌شود. این مطالعه به توسعه یک روش انتخاب ویژگی هایبرید (ترکیبی) به نام MOEA/D-ANN می‌‌پردازد. هدف این روش شناسایی مهم‌‌ترین متغیرهایی است که به دستیابی بالاترین دقت پیش بینی کمک می کنند. این روش پیشنهادی الگوریتم تکاملی بهینه‌‌سازی چند هدفه مبتنی بر جداسازی را با شبکه‌های عصبی مصنوعی ترکیب می‌کند تا با استفاده از قدرت روش‌های بهینه‌سازی و یادگیری ماشین، مشکل انتخاب ویژگی را به طور موثر حل کند. برای ارزیابی عملکرد روش معرفی شده از الگوریتم (RReliefF) که یک الگوریتم رتبه بندی ویژگی است ، نیز بهره گرفته شده است. از روش ANN برای پیش‌بینی عمق کربناته بتن و از روش‌‌های ترکیبیMOEA/D-ANN و RReliefFبرای یافتن متغیرهای‌‌ تأثیرگذار استفاده شده است. نتایج بدست آمده نشان داده اند که مدل ایجاد شده با استفاده از رویکرد MOEA/D-ANN، با ترکیب متغیرهای تعیین‌شده توسط آن، درصد خطا را کاهش و دقت را افزایش داد. در این مدل به مقدار قابل‌‌توجه ضریب تعیین R² = 0.99 می‌‌رسد، که بر دقت خوب آن در پیش بینی عمق کربناته بتن و تأیید انتخاب دقیق متغیرهای تأثیرگذار تأکید می‌‌کند. همچنین نتایج نشان داده که با افزایش نسبت آب به سیمان به میزان 10 درصد، عمق کربناته شدن بتن به میزان 15 درصد افزایش می‌یابد.
کلیدواژه‌ها
عمق کربناته شدن؛ پیش‌‌بینی؛ یادگیری ماشین؛ شبکه عصبی مصنوعی؛ MOEA/D؛ بهینه‌‌سازی
موضوعات
یادگیری ماشین؛ بهینه سازی؛ تعمیر و تقویت روسازی؛ تکنولوژی بتن؛ تکنولوژی بتن
عنوان مقاله [English]
Predicting Concrete Carbonation Depth and Investigating the Influencing Factors through Machine Learning Approaches and Optimization
نویسندگان [English]
Shoaib Mansouri؛ Alireza Rahai؛ Seyed Hadi Rashedi؛ Fereidoon Moghadas Nejad
Civil and Environmental Engineering Department, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran
چکیده [English]
Accurate prediction of concrete carbonation depth is crucial for mitigating detrimental effects such as cracking and corrosion. However, due to the complexity of the process and the multitude of variables involved, identifying the most significant parameters for modeling carbonation depth poses a considerable challenge. This paper introduces a hybrid feature selection method known as MOEA/D-ANN. The primary aim of this method is to identify the most critical variables that contribute to achieving the highest prediction accuracy. The proposed approach combines a multi-objective evolutionary optimization algorithm based on decomposition with artificial neural networks to effectively address the feature selection problem using the strengths of optimization and machine learning techniques. To evaluate the performance of the introduced method, the conventional feature ranking algorithm RReliefF was also employed. ANN was used for predicting carbonation depth, while the combined methods of MOEA/D-ANN and RReliefF were utilized to identify influential variables. The results indicate that the model developed using the MOEA/D-ANN approach significantly reduced the error rate and increased accuracy by combining the selected variables. This model achieves a notable coefficient of determination (R² = 0.99), highlighting its excellent accuracy in predicting concrete carbonation depth and confirming the precise selection of influential variables. Additionally, the results demonstrate that an increase in the water-to-cement ratio by 10% leads to a 15% increase in carbonation depth.
کلیدواژه‌ها [English]
Carbonation Depth, Prediction, Machine Learning, Artificial Neural Network, MOEA/D, Optimization

مراجع
[1] H. Naseri, H. Jahanbakhsh, K. Khezri, A.A. Shirzadi Javid, Toward sustainability in optimizing the fly ash concrete mixture ingredients by introducing a new prediction algorithm, Environment, development and sustainability, 24(2) (2022) 2767-2803. [2] S.O. Ekolu, Model for natural carbonation prediction (NCP): Practical application worldwide to real life functioning concrete structures, Engineering Structures, 224 (2020) 111126. [3] W.Z. Taffese, E. Sistonen, Machine learning for durability and service-life assessment of reinforced concrete structures: Recent advances and future directions, Automation in Construction, 77 (2017) 1-14. [4] Y. Kellouche, B. Boukhatem, M. Ghrici, A. Tagnit-Hamou, Exploring the major factors affecting fly-ash concrete carbonation using artificial neural network, Neural Computing and Applications, 31 (2019) 969-988. [5] H. Xu, Z.Q. Chen, S.B. Li, W. Huang, D. Ma, Carbonation test study on low calcium fly ash concrete, Applied Mechanics and Materials, 34 (2010) 327-331. [6] A. Rahai, S.H. Rashedi, Evaluation of ductility of bearing concrete wall systems with regard to their boundary element, Amirkabir Journal of Civil Engineering, 49(1) (2017) 13-22. [7] S.H. Rashedi, A. Rahai, P. Tehrani, Seismic performance evaluation of RC bearing wall structures, Computers and Concrete, 30(2) (2022) 113-126. [8] I. Nunez, M.L. Nehdi, Machine learning prediction of carbonation depth in recycled aggregate concrete incorporating SCMs, Construction and Building Materials, 287 (2021) 123027. [9] I.D. Uwanuakwa, Deep learning modelling and generalisation of carbonation depth in fly ash blended concrete, Arabian Journal for Science and Engineering, 46(5) (2021) 4731-4746. [10] P. Akpinar, I.D. Uwanuakwa, Intelligent prediction of concrete carbonation depth using neural networks, Bulletin of the Transilvania University of Brasov. Series III: Mathematics and Computer Science, (2016) 99-108. [11] H. Lee, H.-S. Lee, P. Suraneni, Evaluation of carbonation progress using AIJ model, FEM analysis, and machine learning algorithms, Construction and Building Materials, 259 (2020) 119703. [12] W.Z. Taffese, E. Sistonen, J. Puttonen, CaPrM: Carbonation prediction model for reinforced concrete using machine learning methods, Construction and Building Materials, 100 (2015) 70-82. [13] R. Biswas, E. Li, N. Zhang, S. Kumar, B. Rai, J. Zhou, Development of hybrid models using metaheuristic optimization techniques to predict the carbonation depth of fly ash concrete, Construction and Building Materials, 346 (2022) 128483. [14] C. Lu, R. Liu, Predicting carbonation depth of prestressed concrete under different stress states using artificial neural network, Advances in Artificial Neural Systems, (2009). [15] W.Z. Taffese, F. Al-Neshawy, E. Sistonen, M. Ferreira, Optimized neural network based carbonation prediction model, in: International Symposium Non-Destructive Testing in Civil Engineering (NDT-CE). Berlin, Germany, 2015, pp. 1074-1083. [16] E.F. Felix, E. Possan, R. Carrazedo, Analysis of training parameters in the ANN learning process to mapping the concrete carbonation depth, Journal of building pathology and rehabilitation, 4(1) (2019) 16. [17] P. Akpinar, I. Uwanuakwa, Investigation of the parameters influencing progress of concrete carbonation depth by using artificial neural networks, Materiales de Construcción, 70(337) (2020) e209-e209. [18] E.F. Felix, R. Carrazedo, E. Possan, Carbonation model for fly ash concrete based on artificial neural network: Development and parametric analysis, Construction and Building Materials, 266 (2021) 121050. [19] M. Ehsani, M. Ostovari, S. Mansouri, H. Naseri, H. Jahanbakhsh, F.M. Nejad, Machine learning for predicting concrete carbonation depth: A comparative analysis and a novel feature selection, Construction and Building Materials, 417 (2024) 135331. [20] P.C. Deka, A primer on machine learning applications in civil engineering, CRC Press, 2019. [21] K. Meshram, Machine Learning Applications in Civil Engineering, Elsevier, 2023. [22] V. Plevris, A. Ahmad, N.D. Lagaros, Artificial Intelligence and Machine Learning Techniques for Civil Engineering, IGI Global, 2023. [23] M. Ehsani, H. Naseri, R. Saeedi Nezhad, M. Etebari Ghasbeh, F. Moghadas Nejad, Compressive strength prediction of ordinary concrete, fly ash concrete, and slag concrete by novel techniques and presenting their optimal mixtures, Amirkabir Journal of Civil Engineering, 53(10) (2021) 4105-4124. [24] N. Roshan, M. Ghale Navi, A. Khosravi, Prediction of concrete compressive strength using machine learning regression algorithms, in: The 12th National Congress of Civil Engineering, Tehran, Iran, 2020, in Persian. [25] N. Shirzad, M. Taheri, A. Ashrafian, Development of a tree model to predict the depth of carbonation in concrete containing fly ash, in: 7th International Conference on Civil Engineering, Architecture and Urban Planning, Tehran, Iran, 2022, in Persian. [26] H. Hosseinzadeh, A. Hosni, S. Arman, A. Safipour, (2022). Prediction of compressive strength of concrete based on group machine learning, in: 20th Concrete Day Conference and 14th National Concrete Conference, Tehran, Iran, 2022, in Persian. [27] V.Q. Tran, H.V.T. Mai, Q.T. To, M.H. Nguyen, Machine learning approach in investigating carbonation depth of concrete containing Fly ash, Structural Concrete, 24(2) (2023) 2145-2169. [28] I.D. Uwanuakwa, P. Akpınar, Enhancing the reliability and accuracy of machine learning models for predicting carbonation progress in fly ash‐concrete: A multifaceted approach, Structural Concrete, (2024). [29] H. Ji, H. Ye, Machine learning prediction of corrosion rate of steel in carbonated cementitious mortars, Cement and Concrete Composites, 143 (2023) 105256. [30] R. Kazemi, A hybrid artificial intelligence approach for modeling the carbonation depth of sustainable concrete containing fly ash, Scientific Reports, 14(1) (2024) 11948. [31] D. Wang, Q. Tan, Y. Wang, G. Liu, Z. Lu, C. Zhu, B. Sun, Carbonation depth prediction and parameter influential analysis of recycled concrete buildings, Journal of CO2 Utilization, 85 (2024) 102877. [32] C.D. Atiş, Accelerated carbonation and testing of concrete made with fly ash, Construction and Building Materials, 17(3) (2003) 147-152. [33] B. Das, S. Pandey, Influence of fineness of fly ash on the carbonation and electrical conductivity of concrete, Journal of materials in civil engineering, 23(9) (2011) 1365-1368. [34] P. Van den Heede, N. De Belie, A service life based global warming potential for high-volume fly ash concrete exposed to carbonation, Construction and Building Materials, 55 (2014) 183-193. [35] C.H. Huang, G.L. Geng, Y.S. Lu, G. Bao, Z.R. Lin, Carbonation depth research of concrete with low-volume fly ash, Applied Mechanics and Materials, 155 (2012) 984-988. [36] L. Jiang, Z. Liu, Y. Ye, Durability of concrete incorporating large volumes of low-quality fly ash, Cement and concrete research, 34(8) (2004) 1467-1469. [37] J. Khunthongkeaw, S. Tangtermsirikul, T. Leelawat, A study on carbonation depth prediction for fly ash concrete, Construction and building materials, 20(9) (2006) 744-753. [38] S. Lammertijn, N. De Belie, Porosity, gas permeability, carbonation and their interaction in high-volume fly ash concrete, Magazine of Concrete Research, 60(7) (2008) 535-545. [39] P. Nath, Durability of conrete using fly ash as a partial replacement of cement, Curtin University, 2010. [40] P. Nath, P. Sarker, Effect of fly ash on the durability properties of high strength concrete, Procedia Engineering, 14 (2011) 1149-1156. [41] P. Sulapha, S. Wong, T. Wee, S. Swaddiwudhipong, Carbonation of concrete containing mineral admixtures, Journal of materials in civil engineering, 15(2) (2003) 134-143. [42] M.K. Rao, D. Kumar, Durability assessment of concrete with class-F fly ash by chloride ion permeability, International Journal of Recent Technology and Engineering, 8 (2019) 8831-8836. [43] E. Roziere, A. Loukili, F. Cussigh, A performance based approach for durability of concrete exposed to carbonation, Construction and Building Materials, 23(1) (2009) 190-199. [44] K. Sisomphon, L. Franke, Carbonation rates of concretes containing high volume of pozzolanic materials, Cement and Concrete Research, 37(12) (2007) 1647-1653. [45] A. Younsi, P. Turcry, E. Rozière, A. Aît-Mokhtar, A. Loukili, Performance-based design and carbonation of concrete with high fly ash content, Cement and Concrete Composites, 33(10) (2011) 993-1000. [46] P. Zhang, Q. Li, Effect of fly ash on durability of high performance concrete composites, Research Journal of Applied Sciences, Engineering and Technology, 6(1) (2013) 7-12. [47] A. Behnood, V. Behnood, M.M. Gharehveran, K.E. Alyamac, Prediction of the compressive strength of normal and high-performance concretes using M5P model tree algorithm, Construction and Building Materials, 142 (2017) 199-207. [48] S. Ghavami, H. Naseri, H. Jahanbakhsh, F.M. Nejad, The impacts of nano-SiO2 and silica fume on cement kiln dust treated soil as a sustainable cement-free stabilizer, Construction and Building Materials, 285 (2021) 122918. [49] S. Ghafari, M. Ehsani, F.M. Nejad, Prediction of low-temperature fracture resistance curves of unmodified and crumb rubber modified hot mix asphalt mixtures using a machine learning approach, Construction and Building Materials, 314 (2022) 125332. [50] A.A. Shirzadi Javid, H. Naseri, M.A. Etebari Ghasbeh, Estimating the optimal mixture design of concrete pavements using a numerical method and meta-heuristic algorithms, Iranian Journal of Science and Technology, Transactions of Civil Engineering, 45(2) (2021) 913-927. [51] S. Ranjbar, F.M. Nejad, H. Zakeri, A.H. Gandomi, Computational intelligence for modeling of asphalt pavement surface distress, in: New Materials in Civil Engineering, Elsevier, 2020, pp. 79-116. [52] S. Haykin, Neural networks: a comprehensive foundation, Prentice Hall PTR, 1998. [53] I.N. Da Silva, D. Hernane Spatti, R. Andrade Flauzino, L.H.B. Liboni, S.F. dos Reis Alves, I.N. da Silva, D. Hernane Spatti, R. Andrade Flauzino, L.H.B. Liboni, S.F. dos Reis Alves, Artificial neural network architectures and training processes, Springer, 2017. [54] M. Robnik-Šikonja, I. Kononenko, Theoretical and empirical analysis of ReliefF and RReliefF, Machine learning, 53 (2003) 23-69. [55] M.V. Selvi, S. Mishra, Input features selection using rrelieff algorithm for electricity demand forecasting, in: 2020 IEEE First International Conference on Smart Technologies for Power, Energy and Control (STPEC), IEEE, 2020, pp. 1-6. [56] S. Ghafari, S. Ranjbar, M. Ehsani, F.M. Nejad, P. Paul, Sustainable crumb rubber modified asphalt mixtures based on low-temperature crack propagation characteristics using the response surface methodology, Theoretical and Applied Fracture Mechanics, 123 (2023) 103718. [57] A. Askari, P. Hajikarimi, M. Ehsani, F. Moghadas Nejad, Prediction of rutting deterioration in flexible pavements using artificial neural network and genetic algorithm, Amirkabir Journal of Civil Engineering, 54(9) (2022) 3581-3602. [58] M. Ehsani, F. Moghadas Nejad, P. Hajikarimi, Developing an optimized faulting prediction model in Jointed Plain Concrete Pavement using artificial neural networks and random forest methods, International journal of pavement engineering, 24(2) (2023) 2057975. [59] M. Ehsani, P. Hamidian, P. Hajikarimi, F.M. Nejad, Optimized prediction models for faulting failure of Jointed Plain concrete pavement using the metaheuristic optimization algorithms, Construction and Building Materials, 364 (2023) 129948. [60] Q. Zhang, H. Li, MOEA/D: A multiobjective evolutionary algorithm based on decomposition, IEEE Transactions on evolutionary computation, 11(6) (2007) 712-731. [61] Z. Chen, J. Lin, K. Sagoe-Crentsil, W. Duan, Development of hybrid machine learning-based carbonation models with weighting function, Construction and Building Materials, 321 (2022) 126359. [62] K. Liu, M.S. Alam, J. Zhu, J. Zheng, L. Chi, Prediction of carbonation depth for recycled aggregate concrete using ANN hybridized with swarm intelligence algorithms, Construction and Building Materials, 301 (2021) 124382. [63] M. Zhang, L. Jiao, W. Ma, J. Ma, M. Gong, Multi-objective evolutionary fuzzy clustering for image segmentation with MOEA/D, Applied Soft Computing, 48 (2016) 621-637. [64] J. Zhang, G. Ma, Y. Huang, F. Aslani, B. Nener, Modelling uniaxial compressive strength of lightweight self-compacting concrete using random forest regression, Construction and Building Materials, 210 (2019) 713-719. [65] M.R. Kaloop, D. Kumar, P. Samui, J.W. Hu, D. Kim, Compressive strength prediction of high-performance concrete using gradient tree boosting machine, Construction and Building Materials, 264 (2020) 120198.
آمار تعداد مشاهده مقاله: 1,348 تعداد دریافت فایل اصل مقاله: 499

سامانه مدیریت نشریات علمی. طراحی و پیاده سازی از سیناوب

پیوندهای مفید

آمار

پیش‌بینی عمق کربناته شدن بتن و بررسی عوامل تأثیرگذار از طریق مدل‌‌های یادگیری ماشین و بهینه‌سازی