Predicting compressive strength of AAC blocks through machine learning advancements
DOI: https://doi.org/10.20528/cjcrl.2024.02.003
View Counter: Abstract | 220 times | ‒ Full Article | 83 times |
Full Text:
PDFAbstract
Determining the strength properties of Autoclaved Aerated Concrete (AAC) through conventional compression experiments is both time-consuming and costly. Using sophisticated Machine Learning (ML) algorithms to forecast concrete compressive strength can expedite time-consuming experimental procedures and reduce expenses. In this study, four ML models were proposed, including Random Forest (RF), Support Vector Regression (SVR), Linear Regression (LR), and Stochastic Gradient Descent (SGD). These models were developed to forecast the compressive strength of AAC blocks based on a dataset of 525 cubic samples. By comparing the results using different evaluation indices, the study analyzed each input variable’s relative importance and impact on the output. The findings revealed that the SVR model had the least error and is thus the most suitable for concrete compressive strength estimation. This approach results in cost savings on both specimens and laboratory tests. Out of the seven input factors, which encompass the proportions of water, cement, sand, lime, fly ash, aluminum powder, and gypsum, the proportions of cement and water content were pinpointed as the most crucial characteristics. In contrast, aluminum powder and gypsum displayed less prominent significance.
Keywords
References
Albuthbahak OM, Hiswa AA (2019). Prediction of concrete compressive strength using supervised machine learning models through ultrasonic pulse velocity and mix parameters. Revista Romana de Materiale, 49(2), 232–243.
Aydın Y, Cakiroglu C, Bekdaş G, Işıkdağ Ü, Kim S, Hong J, Geem ZW (2023). Neural network predictive models for alkali-activated concrete carbon emission using metaheuristic optimization algorithms. Sustainability, 16(1), 142.
Behnood A, Golafshani EM (2020). Machine learning study of the mechanical properties of concretes containing waste foundry sand. Construction and Building Materials, 243, 118152.
Cakiroglu C, Islam K, Bekdaş G, Kim S, Geem ZW (2022). Interpretable machine learning algorithms to predict the axial capacity of FRP-reinforced concrete columns. Materials, 15(8), 2742.
Cheng MY, Chou JS, Roy AF, Wu YW (2012). High-performance concrete compressive strength prediction using time-weighted evolutionary fuzzy support vector machines inference model. Automation in Construction, 28, 106–115.
Cohen T, Freytsis M, Ostdiek B (2018). Machine learning to do more with less. Journal of High Energy Physics, 2018(2), 1-28.
de Prado-Gil J, Palencia C, Jagadesh P, Martínez-García R (2022). A study on the prediction of compressive strength of self-compacting recycled aggregate concrete utilizing novel computational approaches. Materials, 15(15), 5232.
Deshpande N, Londhe S, Kulkarni S (2014). Modeling compressive strength of recycled aggregate concrete by artificial neural network, model tree and non-linear regression. International Journal of Sustainable Built Environment, 3(2), 187–198.
DIN 771-4: 2011-07 (2011). Festlegungen für mauersteine–teil 4: Porenbetonsteine. DIN Deutsches Institut für Normung e, V., Berlin, Germany.
DIN 772-1: 2016-05 (2016). Methods of test for masonry units–part 1: Determination of compressive strength. DIN Deutsches Institut für Normung e, V., Berlin, Germany.
Domingo ER (2008). An introduction to autoclaved aerated concrete including design requirements using strength design. Technical report, Kansas State University, Kansas, USA.
Dudukalov E, Munister V, Zolkin A, Losev A, Knishov A (2021). The use of artificial intelligence and information technology for measurements in mechanical engineering and in process automation systems in industry 4.0. In: Journal of Physics: Conference Series, Vol. 1889. IOP Publishing, p. 052011.
El-Mir A, El-Zahab S, Sbartaï ZM, Homsi F, Saliba J, El-Hassan H (2023). Machine learning prediction of concrete compressive strength using rebound hammer test. Journal of Building Engineering, 64, 105538.
Erdal HI (2013). Two-level and hybrid ensembles of decision trees for high performance concrete compressive strength prediction. Engineering Applications of Artificial Intelligence, 26(7), 1689–1697.
Fan Z, Chiong R, Hu Z, Lin Y (2020). A fuzzy weighted relative error support vector machine for reverse prediction of concrete components. Computers & Structures, 230, 106171.
Faridmehr I, Nehdi ML, Huseien GF, Baghban MH, Sam ARM, Algaifi HA (2021). Experimental and informational modeling study of sustainable self-compacting geopolymer concrete. Sustainability, 13(13), 7444.
Géron A (2017). Hands-on machine learning with scikit-learn and tensorflow: concepts, tools, and techniques to build intelligent systems. O'Reilly Media, Sebastopol, CA, 54–56.
Güçlüer K, Özbeyaz A, Göymen S, Günaydın O (2021). A comparative investigation using machine learning methods for concrete compressive strength estimation. Materials Today Communications, 27, 102278.
Hadzima-Nyarko M, Nyarko EK, Ademovic N, Miličević I, Šipoš TK (2019). Modelling the influence of waste rubber on compressive strength of concrete by artificial neural networks. Materials, 12(4), 561.
Hamad AJ (2014). Materials, production, properties and application of aerated lightweight concrete. International Journal of Materials Science and Engineering, 2(2), 152–157.
Harirchian E, Hosseini SEA, Jadhav K, Kumari V, Rasulzade S, Işık E, Wasif M, Lahmer T (2021). A review on application of soft computing techniques for the rapid visual safety evaluation and damage classification of existing buildings. Journal of Building Engineering, 102536.
Harirchian E, Kumari V, Jadhav K, Das RR, Rasulzade S, Lahmer T (2020). A machine learning framework for assessing seismic hazard safety of reinforced concrete buildings. Applied Sciences, 10(20), 7153.
Islam MM, Hossain MB, Akhtar MN, Moni MA, Hasan KF (2022). CNN based on transfer learning models using data augmentation and transformation for detection of concrete crack. Algorithms, 15(8), 287.
Jiang Y, Li H, Zhou Y (2022). Compressive strength prediction of fly ash concrete using machine learning techniques. Buildings, 12(5), 690.
Kalpana M, Mohith S (2020). Study on autoclaved aerated concrete. Materials Today: Proceedings, 22, 894–896.
Kavita M, Tarjani C (2016). Comparison on auto aerated concrete to normal concrete. Recent Advances in Civil Engineering for Global Sustainability, 90–94.
Korotcov A, Tkachenko V, Russo DP, Ekins S (2017). Comparison of deep learning with multiple machine learning methods and metrics using diverse drug discovery data sets. Molecular Pharmaceutics, 14(12), 4462-4475.
Krivenko P (2020). Compressive Strength of Concrete. John Wiley & Sons, Inc., Toronto, Canada.
Liu T, Cakiroglu C, Islam K, Wang Z, Nehdi ML (2024). Explainable machine learning model for predicting punching shear strength of FRC flat slabs. Engineering Structures, 301, 117276.
Mehmannavaz T, Ismail M, Radin Sumadi S, Rafique Bhutta MA, Samadi M, Sajjadi SM (2014). Binary effect of fly ash and palm oil fuel ash on heat of hydration aerated concrete. The Scientific World Journal, 2014.
Muhammad W, Brahme AP, Ibragimova O, Kang J, Inal K (2021). A machine learning framework to predict local strain distribution and the evolution of plastic anisotropy & fracture in additively manufactured alloys. International Journal of Plasticity, 136, 102867.
Mylvaganam N, Elakneswaran Y (2023). A systematic review and assessment of concrete strength prediction models. Case Studies in Construction Materials, e01830.
Narayanan N, Ramamurthy K (2000). Structure and properties of aerated concrete: a review. Cement and Concrete Composites, 22(5), 321–329.
Ni HG, Wang JZ (2000). Prediction of compressive strength of concrete by neural networks. Cement and Concrete Research, 30(8), 1245–1250.
Qu X, Zhao X (2017). Previous and present investigations on the components, microstructure and main properties of autoclaved aerated concrete–a review. Construction and Building Materials, 135, 505–516.
Rafiza AR, Fazlizan A, Thongtha A, Asim N, Noorashikin MS (2022). The physical and mechanical properties of autoclaved aerated concrete (AAC) with recycled AAC as a partial replacement for sand. Buildings, 12(1), 60.
Ramamurthy K, Nambiar EK, Ranjani GIS (2009). A classification of studies on properties of foam concrete. Cement and Concrete Composites, 31(6), 388–396.
Różycka A, Kotwica L (2022). Waste originating from the cleaning of flue gases from the combustion of industrial wastes as a lime partial replacement in autoclaved aerated concrete. Materials, 15(7), 2576.
Schober G (2011). Porosity in Autoclaved Aerated Concrete (AAC): A review on pore structure, types of porosity, measurement methods and effects of porosity on properties. Proceedings of the 5th International Conference on Autoclaved Aerated Concrete, Bydgoscsz, Poland, 351–359.
Shah HA, Yuan Q, Akmal U, Shah SA, Salmi A, Awad YA, Shah LA, Iftikhar Y, Javed MH, Khan MI (2022). Application of machine learning techniques for predicting compressive, splitting tensile, and flexural strengths of concrete with metakaolin. Materials, 15(15), 5435.
Tosee SVR, Faridmehr I, Bedon C, Sadowski L, Aalimahmoody N, Nikoo M, Nowobilski T (2021). Metaheuristic prediction of the compressive strength of environmentally friendly concrete modified with eggshell powder using the hybrid ANN-SFL optimization algorithm. Materials, 14(20), 6172.
Wongkeo W, Thongsanitgarn P, Pimraksa K, Chaipanich A (2012). Compressive strength, flexural strength and thermal conductivity of autoclaved concrete block made using bottom ash as cement replacement materials. Materials & Design, 35, 434–439.
Yang Q, Du S (2015). Prediction of concrete cubic compressive strength using ANN based size effect model. Computers, Materials & Continua, 47(3).
Refbacks
- There are currently no refbacks.