机器学习在混凝土抗压强度预测的应用研究
1. 中国计量大学, 信息工程学院, 浙江杭州 310018
2. 中才邦业(杭州)智能技术有限公司, 浙江杭州 310000
| 摘 要： | 混凝土抗压强度是影响建筑质量的主要因素之一，也是混凝土设计的关键参数，对其进行预测具有必要性。然而，早期采用经验公式预测混凝土抗压强度大多数是针对特定的混凝土，无法普遍推广，而其他预测方法例如：物理检测法、有限元分析法等步骤繁琐，适用条件苛刻也无法形成普适性的预测模型。近年来，基于机器学习的混凝土抗压强度预测模型成为国内外研究热点。本文首先通过比较各种机器学习方法，包括回归模型、支持向量回归机模型、树模型、神经网络和集成学习等在混凝土抗压强度方面的应用，得出支持向量回归机模型与集成学习在抗压强度的预测上具有更高的有效性。最后，文章讨论了目前所广泛采用的混凝土抗压强度预测方法的不足之处，并给出了基于机器学习的混凝土抗压强度预测模型未来的研究方向。 |
| 关 键 词： | 混凝土抗压强度; 机器学习; 集成学习; 过拟合 |
| DOI： | 10.57237/j.se.2023.05.003 |
View:
Downloads:
收稿日期: 2023-09-08
接受日期: 2023-10-26
在线出版日期: 2023-10-28
A Study on the Application of Machine Learning for Predicting Concrete Compressive Strength
1. School of Information Engineering, China Jiliang University, Hangzhou 310018, China
2. SINOMA Bonyear (Hangzhou) Intelligent Technology Co. Ltd., Hangzhou 310000, China
| Abstract: | The compressive strength of concrete is one of the main factors affecting the quality of construction, and it is also a key parameter for concrete design, so it is necessary to predict it. However, most of the early empirical formulas for predicting the compressive strength of concrete are for specific concretes, which can not be universally promoted, while other prediction methods such as physical testing method, finite element analysis method, etc. are cumbersome in terms of steps, and can not be formed into a generalized prediction model under the harsh conditions of applicability. In recent years, the concrete compressive strength prediction model based on machine learning has become a hot research topic at home and abroad. In this paper, firstly, by comparing the application of various machine learning methods, including regression model, support vector regression machine model, tree model, neural network and integrated learning in concrete compressive strength, it is concluded that the support vector regression machine model and integrated learning have higher effectiveness in the prediction of compressive strength. Finally, the article discusses the shortcomings of the widely used concrete compressive strength prediction methods and gives the future research direction of machine learning based concrete compressive strength prediction model. |
| Keywords: | Concrete Compressive Strength; Machine Learning; Ensemble Learning; Overfitting |
参考文献
| [1] | Bloem D L, Delevante O L. Building code requirements for reinforced concrete [J]. ACI Journal, 1970, 1(1970): 77. |
| [2] | Neville A M. Properties of concrete [M]. London: Longman, 1995. |
| [3] | 肖建庄, 李佳彬, 孙振平. 回弹法检测再生混凝土抗压强度研究 [J]. 四川建筑科学研究, 2004, 30(4): 51-54. |
| [4] | Yoon H, Kim Y J, Kim H S, et al. Evaluation of early-age concrete compressive strength with ultrasonic sensors [J]. Sensors, 2017, 17(8): 1817. |
| [5] | Popovics S. New formulas for the prediction of the effect of porosity on concrete strength [C] // Journal Proceedings. 1985, 82(2): 136-146. |
| [6] | Young B A, Hall A, Pilon L, et al. Can the compressive strength of concrete be estimated from knowledge of the mixture proportions? New insights from statistical analysis and machine learning methods [J]. Cement and Concrete Research, 2019, 115: 379-388. |
| [7] | DeRousseau M A, Kasprzyk J R, Srubar Iii W V. Computational design optimization of concrete mixtures: A review [J]. Cement and Concrete Research, 2018, 109: 42-53. |
| [8] | Biernacki J J, Bullard J W, Sant G, et al. Cements in the 21st century: challenges, perspectives, and opportunities [J]. Journal of the American Ceramic Society, 2017, 100(7): 2746-2773. |
| [9] | Seber G A F, Lee A J. Linear regression analysis [M]. John Wiley & Sons, 2003. |
| [10] | 朱伟, 石超峰, 李楠. 基于遗传算法优化支持向量机的再生混凝土抗压强度预测模型 [J]. 中外公路, 2014, 34(1): 311-314. |
| [11] | Zhang D, Sun F, Liu T. Prediction of compressive strength of geopolymer concrete based on support vector machine and modified cuckoo algorithm [J]. Advances in Materials Science and Engineering, 2021, 2021: 1-14. |
| [12] | Wu X, Zhu F, Zhou M, et al. Intelligent Design of Construction Materials: A Comparative Study of AI Approaches for Predicting the Strength of Concrete with Blast Furnace Slag [J]. Materials, 2022, 15(13): 4582. |
| [13] | Shah S A R, Azab M, Seif ElDin H M, et al. Predicting Compressive Strength of Blast Furnace Slag and Fly Ash Based Sustainable Concrete Using Machine Learning Techniques: An Application of Advanced Decision-Making Approaches [J]. Buildings, 2022, 12(7): 914. |
| [14] | 吴贤国, 刘鹏程, 陈虹宇, 等. 基于随机森林的高性能混凝土抗压强度预测 [J]. 混凝土, 2022. |
| [15] | Haykin S. Neural networks: a comprehensive foundation [M]. Prentice Hall PTR, 1998. |
| [16] | Dietterich T G. Ensemble methods in machine learning [C] // Multiple Classifier Systems: First International Workshop, MCS 2000 Cagliari, Italy, June 21–23, 2000 Proceedings 1. Springer Berlin Heidelberg, 2000: 1-15. |
| [17] | Zhou Z H, Zhou Z H. Ensemble learning [M]. Springer Singapore, 2021. |
| [18] | Gazder U, Al-Amoudi O S B, Khan S M S, et al. Predicting compressive strength of bended cement concrete with ANNs [J]. Computers and Concrete, An International Journal, 2017, 20(6): 627-634. |
| [19] | Chou J S, Pham A D. Enhanced artificial intelligence for ensemble approach to predicting high performance concrete compressive strength [J]. Construction and Building Materials, 2013, 49: 554-563. |
| [20] | Chore H S, Shelke N L. Prediction of compressive strength of concrete using multiple regression model [J]. Structural engineering and mechanics: An international journal, 2013, 45(6): 837-851. |
| [21] | Saha P, Prasad M L V, RathishKumar P. Predicting strength of SCC using artificial neural network and multivariable regression analysis [J]. Comput. Concr, 2017, 20(1): 31-38. |
| [22] | Nguyen H, Vu T, Vo T P, et al. Efficient machine learning models for prediction of concrete strengths [J]. Construction and Building Materials, 2021, 266: 120950. |
| [23] | Huang Y, Zhang J, Ann F T, et al. Intelligent mixture design of steel fibre reinforced concrete using a support vector regression and firefly algorithm based multi-objective optimization model [J]. Construction and Building Materials, 2020, 260: 120457. |
| [24] | Nguyen-Sy T, Wakim J, To Q D, et al. Predicting the compressive strength of concrete from its compositions and age using the extreme gradient boosting method [J]. Construction and Building Materials, 2020, 260: 119757. |
| [25] | Yan K, Xu H, Shen G, et al. Prediction of splitting tensile strength from cylinder compressive strength of concrete by support vector machine [J]. Advances in Materials Science and Engineering, 2013, 2013. |
| [26] | Garg A, Aggarwal P, Aggarwal Y, et al. Machine learning models for predicting the compressive strength of concrete containing nano silica [J]. Comput. Concr, 2022, 30(1): 33-42. |
| [27] | Zhang M, Li M, Shen Y, et al. Multiple mechanical properties prediction of hydraulic concrete in the form of combined damming by experimental data mining [J]. Construction and Building Materials, 2019, 207: 661-671. |
| [28] | Zhang J, Li D, Wang Y. Toward intelligent construction: Prediction of mechanical properties of manufactured-sand concrete using tree-based models [J]. Journal of Cleaner Production, 2020, 258: 120665. |
| [29] | Erdal H I. Two-level and hybrid ensembles of decision trees for high performance concrete compressive strength prediction [J]. Engineering Applications of Artificial Intelligence, 2013, 26(7): 1689-1697. |
| [30] | Ouyang N, Song Y, Li Y, et al. Predicting concrete’s strength by machine learning: Balance between accuracy and complexity of algorithms [J]. ACI Materials Journal, 2020, 117(6). |
| [31] | Marani A, Nehdi M L. Machine learning prediction of compressive strength for phase change materials integrated cementitious composites [J]. Construction and Building Materials, 2020, 265: 120286. |
| [32] | Huang J, Sabri M M S, Ulrikh D V, et al. Predicting the compressive strength of the cement-fly ash–slag ternary concrete using the firefly algorithm (fa) and random forest (rf) hybrid machine-learning method [J]. Materials, 2022, 15(12): 4193. |
| [33] | Pham A D, Ngo N T, Nguyen Q T, et al. Hybrid machine learning for predicting strength of sustainable concrete [J]. Soft Computing, 2020, 24(19): 14965-14980. |
| [34] | Yeh I C. Modeling of strength of high-performance concrete using artificial neural networks [J]. Cement and Concrete research, 1998, 28(12): 1797-1808. |
| [35] | Trtnik G, Kavčič F, Turk G. Prediction of concrete strength using ultrasonic pulse velocity and artificial neural networks [J]. Ultrasonics, 2009, 49(1): 53-60. |
| [36] | Uysal M, Tanyildizi H. Predicting the core compressive strength of self-compacting concrete (SCC) mixtures with mineral additives using artificial neural network [J]. Construction and Building Materials, 2011, 25(11): 4105-4111. |
| [37] | Prasad B K R, Eskandari H, Reddy B V V. Prediction of compressive strength of SCC and HPC with high volume fly ash using ANN [J]. Construction and Building Materials, 2009, 23(1): 117-128. |
| [38] | Koo C, Jin R, Li B, et al. Case-based reasoning approach to estimating the strength of sustainable concrete [J]. Computers and Concrete, 2017, 20 (6): 645-654. |
| [39] | Özcan F, Atiş C D, Karahan O, et al. Comparison of artificial neural network and fuzzy logic models for prediction of long-term compressive strength of silica fume concrete [J]. Advances in Engineering Software, 2009, 40(9): 856-863. |
| [40] | Qu D, Cai X, Chang W. Evaluating the effects of steel fibers on mechanical properties of ultra-high performance concrete using artificial neural networks [J]. Applied Sciences, 2018, 8(7): 1120. |
| [41] | 吴顺川, 王艳超, 张化进. 基于 Stacking 集成算法的岩石单轴抗压强度预测方法研究 [J]. 矿业研究与开发, 2022. |
| [42] | Schapire R. E. The Strength of Weak Learnability [M]. Kluwer Academic Publishers, 1990. |
| [43] | Liu G, Sun B. Concrete compressive strength prediction using an explainable boosting machine model [J]. Case Studies in Construction Materials, 2023, 18: e01845. |
| [44] | Li Q, Song Z. Prediction of compressive strength of rice husk ash concrete based on stacking ensemble learning model [J]. Journal of Cleaner Production, 2023, 382: 135279. |
