داده‌کاوی خصوصیات مکانیکی‌ بتن‌‌های حاوی رس‌های کلسینه شده به عنوان مواد جایگزین در بتن

نوع مقاله : مقاله پژوهشی

نویسندگان

دانشگاه تربیت دبیر شهید رجایی

10.22124/jcr.2022.16268.1436

چکیده

بتن به دلیل خواص عالی، هزینه کم و در دسترس بودن گسترده، پرمصرف‌ترین محصول ساختمانی در جهان است. با توجه به افزایش جمعیت جهان، میزان تولید سیمان به عنوان یکی از مواد اصلی مورد استفاده در بتن افزایش یافته است. تولید سیمان باعث انتشار گاز دی اکسید کربن شده که باعث افزایش آلودگی محیط زیست می‌شود. یکی از روش‌ها موجود برای جلوگیری از افزایش آلودگی، استفاده از مواد جایگزین به جای سیمان است. از مهمترین مواد جایگزین که در سالیان اخیر مورد استفاه قرار گرفته، می‌توان به سیمان LC3 اشاره کرد. این نوع سیمان با کاهش مقدار کلینکر سیمان، نیاز به سوخت‌های فسیلی را کاهش داده که در نتیجه انتشار دی اکسید کربن کاهش می‌یابد. علاوه بر آن، یکی از خواص مکانیکی مهم بتن، مقاومت فشاری آن بوده که تخمین مقدار آن با توجه به زیاد بودن پارامترهای موجود پیچیده است. در نتیجه از روش‌های آزمایشگاه که پرهزینه است، استفاده می‌شود که دارای خطا می باشد. در این مقاله از روش‌های که برمبنای درخت تصمیم توسعه می‌یابند استفاده شده است و عملکرد آن‌ها با استفاده از الگوریتم ژنتیک بهبود یافته است. دو روش LightGBM و XGBoost با دقت‌های برابر 0/958 در پیش‌بینی مقاومت فشاری بتن، عملکرد بهتری نسبت به روش‌های درخت تصمیم و جنگل تصادفی با دقت‌های 0/91 و 0/932 نشان داده‌اند. همچنین میزان عملکرد پارامترهای ورودی در پیش‌بینی مقاومت فشاری ارائه شده و یک مجموعه داده جدید مورد تست قرار می‌گیرد که صحت سنجی روش‌های ارائه شده بررسی شود.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Data Mining Mechanical properties of concretes containing calcined clays as supplementary cementitious materials in concrete

نویسندگان [English]

  • Ali Hosein Ghanemi
  • Amir Tarighat
Shahid Rajaee Teacher Training University
چکیده [English]

Concrete due to its excellent properties, low cost, and wide availability is the most used construction product in the world. As the world population grows, cement production has increased as one of the main materials used in concrete. Cement production emits carbon dioxide which increases environmental pollution. One of the ways to prevent pollution is to use Supplementary cementing materials instead of cement. One of the most important alternative materials used in recent years is LC3 cement. This type of cement reduces the amount of clinker in cement, decreases our need for fossil fuels, and therefore reduces the emission of carbon dioxide. Moreover, one of the most important mechanical properties of concrete is its compressive strength, which its estimation is complex since the number of existing parameters is high. Hence, costly laboratory methods are used which consist of high error. In this paper, machine learning models that work based on decision tree model are used which their performance have been improved by genetic algorithm. LightGBM and XGBoost models got a prediction score of 0.958 in the prediction of the compressive strength of concrete and perform better than decision tree and random forest models with 0.91 and 0.932 prediction scores. Also, the feature importance of each model has been presented and a new data set has been used to evaluate the validation of models.

کلیدواژه‌ها [English]

  • Concrete
  • Machine Learning and Data Mining
  • LC3 cement
  • Supplementary cement materials
  • Boosting algorithm

مراجع

[1]          K. Scrivener, Options for the future of cement, Indian Concr. J. Vol. 88 (2014) 11–21.
[2]         A. K. Scrivener, A. Dekeukelaere, L.G. F. Avet, Financial Attractiveness of LC3, (2019).
[3]         A. Jain, A. Fandango, A. Kapoor, TensorFlow Machine Learning Projects: Build 13 Real-World Projects with Advanced Numerical Computations Using the Python Ecosystem, Packt Publishing, 2018.
[4]         K. Scrivener, F. Martirena, S. Bishnoi, S. Maity, Calcined clay limestone cements (LC3), Cem. Concr. Res. 114 (2018) 49–56. https://doi.org/10.1016/j.cemconres.2017.08.017.
[5]         D. Zhou, R. Wang, M. Tyrer, H. Wong, C. Cheeseman, Sustainable infrastructure development through use of calcined excavated waste clay as a supplementary cementitious material, J. Clean. Prod. 168 (2017) 1180–1192. https://doi.org/10.1016/j.jclepro.2017.09.098.
[6]         A.C. Emmanuel, P. Haldar, S. Maity, S. Bishnoi, Second pilot production of limestone calcined clay cement in India: The experience, Indian Concr. J. 90 (2016) 57–63.
[7]         S. Bishnoi, S. Maity, A. Mallik, S. Joseph, S. Krishnan, Pilot scale manufacture of limestone calcined clay cement : The Indian experience, Indian Concr. J. 88 (2014) 22–28.
[8]         S.M. Gupta, Support Vector Machines based Modelling of Concrete Strength, World Acad. Sci. Eng. Technol. 36 (2007) 305–311.
[9]         S. Lai, M. Serra, Concrete strength prediction by means of neural network, Constr. Build. Mater. 11 (1997) 93–98. https://doi.org/10.1016/S0950-0618(97)00007-X.
[10]      M. Sarıdemir, Prediction of compressive strength of concretes containing metakaolin and silica fume by artificial neural networks, Adv. Eng. Softw. 40 (2009) 350–355. https://doi.org/10.1016/j.advengsoft.2008.05.002.
[11]      A. Chahal, P. Gulia, Machine learning and deep learning, Int. J. Innov. Technol. Explor. Eng. 8 (2019) 4910–4914. https://doi.org/10.35940/ijitee.L3550.1081219.
[12]      C. Deepa, K. SathiyaKumari, V.P. Sudha, Prediction of the Compressive Strength of High Performance Concrete Mix using Tree Based Modeling, Int. J. Comput. Appl. 6 (2010) 18–24. https://doi.org/10.5120/1076-1406.
[13]      S. Dutta, P. Samui, D. Kim, Comparison of machine learning techniques to predict compressive strength of concrete, Comput. Concr. 21 (2018) 463–470. https://doi.org/10.12989/cac.2018.21.4.463.
[14]      J.-S. Chou, C.-K. Chiu, M. Farfoura, I. Al-Taharwa, Optimizing the Prediction Accuracy of Concrete Compressive Strength Based on a Comparison of Data-Mining Techniques, J. Comput. Civ. Eng. 25 (2011) 242–253. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000088.
[15]      S. Iii, Machine Learning Methods for Predicting the Field Compressive Strength of Concrete, (2019).
[16]      L. Yang, A. Shami, On hyperparameter optimization of machine learning algorithms: Theory and practice, Neurocomputing. 415 (2020) 295–316. https://doi.org/10.1016/j.neucom.2020.07.061.
[17]      L.O. Ettu, C.A. Ajoku, K.C. Nwachukwu, C.T.G. Awodiji, U.G. Eziefula, Strength variation of OPC-rice husk ash composites with percentage rice husk ash, Int. J. Appl. Sci. Eng. Res. 2 (2013) 420–424. https://doi.org/10.6088/ijaser/020400004.
[18]      E. Opoku Amankwah, Influence of Calcined Clay Pozzolana on Strength Characteristics of Portland Cement Concrete, Int. J. Mater. Sci. Appl. 3 (2014) 410. https://doi.org/10.11648/j.ijmsa.20140306.30.
[19]      R.M. Ferreira, J.P. Castro-Gomes, P. Costa, R. Malheiro, Effect of metakaolin on the chloride ingress properties of concrete, KSCE J. Civ. Eng. 20 (2016) 1375–1384. https://doi.org/10.1007/s12205-015-0131-8.
[20]      G. Kaplan, H. Yaprak, S. Memiş, A. Alnkaa, Artificial neural network estimation of the effect of varying curing conditions and cement type on hardened concrete properties, Buildings. 9 (2019). https://doi.org/10.3390/buildings9010010.
[21]      D.. Vu, P. Stroeven, V.. Bui, Strength and durability aspects of calcined kaolin-blended Portland cement mortar and concrete, Cem. Concr. Compos. 23 (2001) 471–478. https://doi.org/10.1016/S0958-9465(00)00091-3.
[22]      R.-S. Lin, X.-Y. Wang, H.-S. Lee, H.-K. Cho, Hydration and Microstructure of Cement Pastes with Calcined Hwangtoh Clay, Materials (Basel). 12 (2019) 458. https://doi.org/10.3390/ma12030458.
[23]      M.F. Nuruddin, S.U. Khan, N. Shafiq, Effect of Calcined Kaolin on the Mechanical Properties of High-Strength Concrete as Cement Replacing Material, Appl. Mech. Mater. 567 (2014) 375–380. https://doi.org/10.4028/www.scientific.net/AMM.567.375.
[24]      L. Vizcaíno, M. Antoni, A. Alujas, F. Martirena, K. Scrivener, Industrial Manufacture of a Low-Clinker Blended Cement Using Low-Grade Calcined Clays and Limestone as SCM: The Cuban Experience, in: RILEM Bookseries, 2015: pp. 347–358. https://doi.org/10.1007/978-94-017-9939-3_43.
[25]      I.-C. Yeh, Modeling slump of concrete with fly ash and superplasticizer, Comput. Concr. 5 (2008) 559–572. https://doi.org/10.12989/cac.2008.5.6.559.
[26]      A. SAAND, M.A. KEERIO, D. khan BANGWAR, EFFECT OF METAKAOLIN DEVELOPED FROM LOCAL NATURAL MATERIAL SOORH ON WORKABILITY, COMPRESSIVE STRENGTH, ULTRASONIC PULSE VELOCITY AND DRYING SHRINKAGE OF CONCRETE, Archit. Civ. Eng. Environ. 10 (2017) 115–122. https://doi.org/10.21307/acee-2017-025.
[27]      H.A. Razak, H.S. Wong, Strength estimation model for high-strength concrete incorporating metakaolin and silica fume, Cem. Concr. Res. 35 (2005) 688–695. https://doi.org/10.1016/j.cemconres.2004.05.040.
[28]      K. Shui, K. Yuan, T. Sun, Q. Li, W. Zeng, Calcined Clays for Sustainable Concrete, Springer Netherlands, Dordrecht, 2015. https://doi.org/10.1007/978-94-017-9939-3.
[29]      K. Mermerdaş, M. Gesoǧlu, E. Güneyisi, T. Özturan, Strength development of concretes incorporated with metakaolin and different types of calcined kaolins, Constr. Build. Mater. 37 (2012) 766–774. https://doi.org/10.1016/j.conbuildmat.2012.07.077.
[30]      R.R. Raj, E.B.P. Pillai, Shear Strength of High Performance Concrete Containing High Reactivity Metakaolin under Direct Shearing, Int. J. Environ. Sci. Technol. (2008).
[31]      S.A. Zareei, F. Ameri, F. Dorostkar, M. Ahmadi, Rice husk ash as a partial replacement of cement in high strength concrete containing micro silica: Evaluating durability and mechanical properties, Case Stud. Constr. Mater. 7 (2017) 73–81. https://doi.org/10.1016/j.cscm.2017.05.001.
[32]      A.F. Karen Scrivener, Ruben Snellings, Xuerun Li, Cement Chemistry and Sustainable Cementitious Materials course, (n.d.). https://www.edx.org/course/cement-chemistry-and-sustainable-cementitious-mate.
[33]      American Society for Testing and Materials, ASTM C 150 : Standard Specification for Portland Cement, Annu. B. ASTM Stand. 04.01 (2001) 149–155.
[34]      M. Bediako, J.T. Kevern, J.S. Ankrah, Strength and durability of cement-based materials incorporated with low grade kaolinitic calcined clay, Sustain. Constr. Mater. Technol. 2016-Augus (2016).
[35]      I.-C.C. Yeh, Modeling of strength of high-performance concrete using artificial neural networks, Cem. Concr. Res. 28 (1998) 1797–1808. https://doi.org/10.1016/S0008-8846(98)00165-3.
[36]      D. Zhou, Developing Supplementary Cementitious Materials From Waste London Clay, (2016) 236. https://spiral.imperial.ac.uk/handle/10044/1/44528.
[37]      M. Sullivan, M. Chorzepa, H. Hamid, S. Durham, S. Kim, Sustainable Materials for Transportation Infrastructures: Comparison of Three Commercially-Available Metakaolin Products in Binary Cementitious Systems, Infrastructures. 3 (2018) 17. https://doi.org/10.3390/infrastructures3030017.
[38]      K. Ganesan, K. Rajagopal, K. Thangavel, Rice husk ash blended cement: Assessment of optimal level of replacement for strength and permeability properties of concrete, Constr. Build. Mater. 22 (2008) 1675–1683. https://doi.org/10.1016/j.conbuildmat.2007.06.011.
[39]      I.-C. Yeh, L.-C. Lien, Knowledge discovery of concrete material using Genetic Operation Trees, Expert Syst. Appl. 36 (2009) 5807–5812. https://doi.org/10.1016/j.eswa.2008.07.004.
[40]      H.I. Erdal, O. Karakurt, E. Namli, High performance concrete compressive strength forecasting using ensemble models based on discrete wavelet transform, Eng. Appl. Artif. Intell. 26 (2013) 1246–1254. https://doi.org/10.1016/j.engappai.2012.10.014.
[41]      D.-C. Feng, Z.-T. Liu, X.-D. Wang, Y. Chen, J.-Q. Chang, D.-F. Wei, Z.-M. Jiang, Machine learning-based compressive strength prediction for concrete: An adaptive boosting approach, Constr. Build. Mater. 230 (2020) 117000. https://doi.org/10.1016/j.conbuildmat.2019.117000.
[42]      S. Zhang, C. Zhang, Q. Yang, Data preparation for data mining, Appl. Artif. Intell. 17 (2003) 375–381. https://doi.org/10.1080/713827180.
[43]      J.F. Martirena Hernandez, A. Favier, K. Scrivener, Calcined Clays for Sustainable Concrete, Springer Netherlands, Dordrecht, 2018. https://doi.org/10.1007/978-94-024-1207-9.
[44]      E. Al Daoud, Comparison between XGBoost , LightGBM and CatBoost Using a Home Credit Dataset, 13 (2019) 6–10. https://doi.org/10.5281/zenodo.3607805.
[45]      Y. Freund, R.E. Schapire, A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting, J. Comput. Syst. Sci. 55 (1997) 119–139. https://doi.org/10.1006/jcss.1997.1504.
[46]      V. Chandwani, V. Agrawal, R. Nagar, Modeling slump of ready mix concrete using genetic algorithms assisted training of Artificial Neural Networks, Expert Syst. Appl. 42 (2015) 885–893. https://doi.org/10.1016/j.eswa.2014.08.048.

فایل ها

هم رسانی

ارجاع به این مقاله

آمار