مصالح و سازه های بتنی

مصالح و سازه های بتنی

پیش‌بینی خواص بتن خودتراکم با استفاده از مدل‌های تلفیقی بر پایه الگوریتم‌های فرا‌ ابتکاری

نوع مقاله : مقاله پژوهشی

نویسندگان
هادی پوریان 1
اشکان خدابنده لو 2
پیمان حمیدی 3
فدرا اشرف زاده 3
1 دانشجوی دکتری، گروه مهندسی عمران، واحد ارومیه، دانشگاه آزاد اسلامی، ارومیه، ایران
2 دانشیار، گروه مهندسی عمران، واحد ارومیه، دانشگاه آزاد اسلامی، ارومیه، ایران
3 استادیار، گروه مهندسی عمران، واحد ارومیه، دانشگاه آزاد اسلامی، ارومیه، ایران
10.30478/jcsm.2025.441113.1360
چکیده
بتن یکی از اساسی‌ترین و پرمصرف‌ترین مصالح در صنعت ساخت و ساز می‌باشد. توسعه و نوآوری در این زمینه به معرفی بتن خودتراکم منجر شده‌ که خود پیشرفت‌های عظیمی را به دنبال داشته‌است. طرح مخلوط بتن خودتراکم از مسائل بسیار با اهمیت بوده و لازم است تا مقادیر مصالح مصرفی در این بتن با دقت زیادی تعیین شود. از طرفی انجام آزمایش مقاومت فشاری بتن در سنین مقرر باعث، صرف هزینه زیاد، تولید پسماند بتن و آسیب به محیط زیست می‌شود. طی سالیان گذشته استفاده از روش‌های نوین هوش مصنوعی که توانایی یادگیری و مدل‌سازی مسائل پیچیده را دارند در حوزه تکنولوژی بتن افزایش یافته‌است. بنابراین تحقیق حاضر از روش‌های یادگیری ماشین مختلف، از جمله ماشین بردار پشتیبانی (SVM)، رگرسیون اسپلاین چند متغیره تطبیقی (MARS) و مدل درخت (Mp5-MT) برای پیش‌بینی رفتارهای رئولوژی به همراه مقاومت فشاری بتن خودتراکم استفاده می‌کند. بدین منظور چهار پارامتر قطر جریان اسلامپ، نسبت جعبه (L)، مدت زمان قیف (V) و مقاومت فشاری 28 روزه بتن از مراجع موثق جمع‌آوری شده‌است. مقدار بایندر، درصد مواد جایگزین سیمان (SCMs)، نسبت آب به بایندر، مقدار مصالح ریز و مصالح خشک و مقدار سوپرپلاستیسایزر به عنوان متغیرهای ورودی انتخاب شدند. با توجه به اینکه روش MARS دارای درون‌پارامترهایی (Hyperparameter) بوده که مقدار آنها بر دقت مدل بسیار تاثیرگذار است، در این تحقیق از تکنیک بهینه‌سازی الگوریتم جستجوی گرانش (Gravitational Search Algorithm, GSA) برای تعیین آنها استفاده شده‌است. نتایج این تحقیق نشان داد که مدل MARS ترکیب شده با تکنیک بهینه‌سازی الگوریتم جستجوی گرانش می‌تواند دقت پیش‌بینی متغیرهای مد نظر را به ترتیب تا 35/1، 1/11، 3/2 و 07/1 درصد نسبت به مدل MARS افزایش دهد. همچنین مدل Mp5-MT توانایی بیشتری در پیش‌بینی نتایج در مقایسه با مدل MARS-GSA از خود نشان داد که به عنوان مدل منتخب برای پیش‌بینی رفتارهای رئولوژیکی و مقاومت فشاری بتن خودتراکم معرفی می‌گردد.
کلیدواژه‌ها
بتن خودتراکم
ویژگی‌های رئولوژی
استحکام فشاری
یادگیری ماشین
الگوریتم بهینه‌سازی فرا‌ابتکاری

موضوعات

عنوان مقاله English

Predicting properties of self-compacting concrete using integrated models based on metaheuristic algorithms

نویسندگان English

Hadi pouryan 1
Ashkan KhodaBandehLou 2
Peyman Hamidi 3
Fedra ashrafzadeh 3
1 Ph.D. Student, Department of Civil Engineering, Urmia Branch, Islamic Azad University, Urmia, Iran
2 Associate Professor, Department of Civil Engineering, Urmia Branch, Islamic Azad University, Urmia, Iran
3 Assistant Professor, Department of Civil Engineering, Urmia Branch, Islamic Azad University, Urmia, Iran
چکیده English

Concrete is one of the most fundamental and widely used materials in the construction industry. Development and innovation in this field have led to the introduction of self-compacting concrete (SCC), which has brought considerable technological developments. The mix design of SCC is one of the substantial issues, so the number of materials used in this concrete must be measured precisely. On the other hand, testing the compressive strength of concrete at certain ages causes high costs, concrete waste, and environmental damage. Modern artificial intelligence techniques that are capable of learning and modeling sophisticated problems have been increasingly used in concrete technology over the past years. Therefore, this study adopts various machine learning methods, including support vector machine (SVM), Multivariate Adaptive Regression Splines (MARS), and model tree (Mp5-MT) to predict the rheological behaviors and compressive strength of SCC. For this purpose, four parameters of slump flow’s diameter, L-box ratio (L), funnel duration (V), and 28-day compressive strength of concrete were collected through authenticate resources. Input variables included Binder amount, Supplementary Cementitious Materials (SCMs), water binder ratio, amount of fine and dry materials, and Superplasticizers. As the MARS technique comprises some hyperparameters whose values highly affect the model accuracy, the optimization technique of the Gravitational Search Algorithm (GSA) has been used in this study to determine these values. The results of this study showed that the MARS model integrated with the optimization GSA technique can enhance the anticipation accuracy by up to 1.35%. 11.1%, 2.3%, and 1.07% rather than the MARS model. Also, the Mp5-MT model outperformed the MARS-GSA model in predicting results, so this is proposed as the selected model for predicting rheological behaviors and compressive strength of SCC.

کلیدواژه‌ها English

Self-Compacting Concrete
Rheological Properties
Compressive Strength
Machine Learning
Metaheuristic Optimization Algorithm
  1. Taheri Amiri, M. J., Ashrafian, A., Berenjian, J. (2019). Prediction of Compressive Strength of Self-Compacting Concrete Containing Fly Ash Using Multivariate Adaptive Regression Splines (MARS). Concrete Research, 12(2): 113-125. doi: 10.22124/jcr.2020.5966.1139
  2. Siddique, R. (2011). Properties of self-compacting concrete containing class F fly ash. Materials & Design, 32(3), 1501-1507.
  3. Sonebi, M., & Cevik, A. (2009). Genetic programming based formulation for fresh and hardened properties of self-compacting concrete containing pulverised fuel ash. Construction and Building Materials, 23(7), 2614-2622.
  4. Dey, S., Kumar, V. P., Goud, K. R., & Basha, S. K. J. (2021). State of art review on self compacting concrete using mineral admixtures. Journal of Building Pathology and Rehabilitation, 6(1), 18.
  5. Emadi, M., Madani, S. H. (2017). Modeling Compressive Strength of Roller Compacted Concrete Pavement Using Artificial Neural Network, ANFIS and Support Vector Machine. Journal of Transportation Infrastructure Engineering, 3(3): 55-78. doi: 10.22075/jtie.2017.1823.1176
  6. Huseien, G. F., & Shah, K. W. (2020). Durability and life cycle evaluation of self-compacting concrete containing fly ash as GBFS replacement with alkali activation. Construction and Building Materials, 235, 117458.
  7. Witten I.H, Frank E. (2005). Data mining: practical machine learning tools and techniques with Java implementations, Morgan Kaufmann: San Francisco.
  8. Yeh, I. C. (2007). Modeling slump flow of concrete using second-order regressions and artificial neural networks. Cement and concrete composites, 29(6), 474-480.
  9. Kina, C., Turk, K., Atalay, E., Donmez, I., & Tanyildizi, H. (2021). Comparison of extreme learning machine and deep learning model in the estimation of the fresh properties of hybrid fiber-reinforced SCC. Neural Computing and Applications, 33, 11641-11659.
  10. Pham, A. D., Hoang, N. D., & Nguyen, Q. T. (2016). Predicting compressive strength of high-performance concrete using metaheuristic-optimized least squares support vector regression. Journal of Computing in Civil Engineering, 30(3), 06015002.
  11. Belalia Douma, O., Boukhatem, B., Ghrici, M., & Tagnit-Hamou, A. (2017). Prediction of properties of self-compacting concrete containing fly ash using artificial neural network. Neural Computing and Applications, 28, 707-718.
  12. Ghanizadeh, A. R., Karimi Goghari, M., & Tavana Amlashi, A. (2018). Modeling of compressive strength of roller-compacted concrete containing reclaimed asphalt pavement using response surface methodology (RSM). Concrete Research, 11(2), 67-79.
  13. Fathi, M., Rostami, S., & Khorami, M. S. (2018). P‌r‌e‌d‌i‌c‌t‌i‌o‌n o‌f c‌o‌m‌p‌r‌e‌s‌s‌i‌v‌e s‌t‌r‌e‌n‌g‌t‌h c‌o‌n‌c‌r‌e‌t‌e b‌y a‌r‌t‌i‌f‌i‌c‌i‌a‌l n‌e‌u‌r‌a‌l n‌e‌t‌w‌o‌r‌k‌s, f‌u‌z‌z‌y l‌o‌g‌i‌c a‌n‌d m‌u‌l‌t‌i‌p‌l‌e r‌e‌g‌r‌e‌s‌s‌i‌o‌n. Sharif Journal of Civil Engineering, 34(3.2), 83-92.
  14. Taheri Amiri, M. J., Ashrafian, A., Haghighi, F. R., & Javaheri Barforooshi, M. (2019). Prediction of the compressive strength of self-compacting concrete containing rice husk ash using data driven models. Modares Civil Engineering journal, 19(1), 209-221.
  15. Taheri Amiri, M. J., Ashrafian, A., & Berenjian, J. (2019). Prediction of Compressive Strength of Self-Compacting Concrete Containing Fly Ash Using Multivariate Adaptive Regression Splines (MARS). Concrete Research, 12(2), 113-125. doi: 10.22124/jcr.2020.5966.1139
  16. Golewski, G. L., & Szostak, B. (2022). Strength and microstructure of composites with cement matrixes modified by fly ash and active seeds of CSH phase. Structural Engineering and Mechanics, An Int'l Journal, 82(4), 543-556.
  17. Behnood, A., Behnood, V., Gharehveran, M. M., & Alyamac, K. E. (2017). Prediction of the compressive strength of normal and high-performance concretes using M5P model tree algorithm. Construction and Building Materials, 142, 199-207.
  18. Ehsani, M., Naseri, H., Saeedi Nezhad, R., Etebari Ghasbeh, M., & Moghadas Nejad, F. (2021). 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), 4105-4124. doi: 10.22060/ceej.2020.17649.6631
  19. Sadowski, Ł., Piechówka-Mielnik, M., Widziszowski, T., Gardynik, A., & Mackiewicz, S. (2019). Hybrid ultrasonic-neural prediction of the compressive strength of environmentally friendly concrete screeds with high volume of waste quartz mineral dust. Journal of cleaner production, 212, 727-740.
  20. Sun, L., Koopialipoor, M., Jahed Armaghani, D., Tarinejad, R., & Tahir, M. M. (2021). Applying a meta-heuristic algorithm to predict and optimize compressive strength of concrete samples. Engineering with Computers, 37, 1133-1145.
  21. Asteris, P. G., Ashrafian, A., & Rezaie-Balf, M. (2019). Prediction of the compressive strength of self-compacting concrete using surrogate models.  Concr, 24(2), 137-150.
  22. DeRousseau, M. A., Laftchiev, E., Kasprzyk, J. R., Rajagopalan, B., & Srubar III, W. V. (2019). A comparison of machine learning methods for predicting the compressive strength of field-placed concrete. Construction and Building Materials, 228, 116661.
  23. Golafshani, E. M., Behnood, A., & Arashpour, M. (2020). Predicting the compressive strength of normal and High-Performance Concretes using ANN and ANFIS hybridized with Grey Wolf Optimizer. Construction and Building Materials, 232(1): 117266-75.
  24. Sattar, A. A., Elhakeem, M., Rezaie-Balf, M., Gharabaghi, B., & Bonakdari, H. (2019). Artificial intelligence models for prediction of the aeration efficiency of the stepped weir. Flow Measurement and Instrumentation, 65, 78-89.
  25. Jaradat, O. Z., Gadri, K., Tayeh, B. A., & Guettalaa, A. (2021). Influence of sisal fibres and rubber latex on the engineering properties of sand concrete. Structural Engineering and Mechanics, 80(1), 47.
  26. Rashedi, E., Nezamabadi-Pour, H., & Saryazdi, S. (2009). GSA: a gravitational search algorithm. Information sciences, 179(13), 2232-2248.
  27. Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine learning, 20, 273-297.
  28. Najafzadeh, M., Rezaie Balf, M., & Rashedi, E. (2016). Prediction of maximum scour depth around piers with debris accumulation using EPR, MT, and GEP models. Journal of Hydroinformatics, 18(5), 867-884.
  29. Deka, P. C. (2014). Support vector machine applications in the field of hydrology: a review. Applied soft computing, 19, 372-386.
  30. Naqi, A., & Jang, J. G. (2019). Recent progress in green cement technology utilizing low-carbon emission fuels and raw materials: A review. Sustainability, 11(2), 537.
  31. Gettu, Miraki, H., Shariatmadari, N., Ghadir, P., Jahandari, S., Tao, Z., & Siddique, R. (2022). Clayey soil stabilization using alkali-activated volcanic ash and slag. Journal of Rock Mechanics and Geotechnical Engineering, 14(2), 576-591.
  32. Patel, Souza, M. T., Ferreira, I. M., de Moraes, E. G., Senff, L., & de Oliveira, A. P. N. (2020). 3D printed concrete for large-scale buildings: An overview of rheology, printing parameters, chemical admixtures, reinforcements, and economic and environmental prospects. Journal of Building Engineering, 32, 101833.
  33. Felekoğlu, B., Türkel, S., & Baradan, B. (2007). Effect of water/cement ratio on the fresh and hardened properties of self-compacting concrete. Building and environment, 42(4), 1795-1802.
  34. Şahmaran, M., Yaman, İ. Ö., & Tokyay, M. (2009). Transport and mechanical properties of self consolidating concrete with high volume fly ash. Cement and concrete composites, 31(2), 99-106.
  35. Güneyisi, E., & Gesoğlu, M. (2008). Properties of self-compacting mortars with binary and ternary cementitious blends of fly ash and metakaolin. Materials and Structures, 41, 1519-1531.
  36. Mahalingam, B., & Nagamani, K. (2011). Effect of processed fly ash on fresh and hardened properties of self compacting concrete. Int J Earth Sci Eng, 4(5), 930-940.
  37. Siddique, R., Aggarwal, P., & Aggarwal, Y. (2012). Influence of water/powder ratio on strength properties of self-compacting concrete containing coal fly ash and bottom ash. Construction and Building Materials, 29, 73-81.
  38. Uysal, M., Yilmaz, K., & Ipek, M. (2012). The effect of mineral admixtures on mechanical properties, chloride ion permeability and impermeability of self-compacting concrete. Construction and Building Materials, 27(1), 263-270.
  39. Siddique, R., Aggarwal, P., & Aggarwal, Y. (2012). Influence of water/powder ratio on strength properties of self-compacting concrete containing coal fly ash and bottom ash. Construction and Building Materials, 29, 73-81.
  40. Muthupriya, P., Sri, P. N., Ramanathan, M. P., & Venkatasubramani, R. (2012). Strength and workability character of self compacting concrete with GGBFS, FA and SF. Int J Emerg Trends Eng Dev, 2(2), 424-434.
  41. Madandoust, R., & Mousavi, S. Y. (2012). Fresh and hardened properties of self-compacting concrete containing metakaolin. Construction and building materials, 35, 752-760.
  42. Dhiyaneshwaran, S., Ramanathan, P., Baskar, I., & Venkatasubramani, R. (2013). Study on durability characteristics of self-compacting concrete with fly ash. Jordan journal of civil engineering, 7(3), 342-353.
  43. Bingöl, A. F., & Tohumcu, İ. (2013). Effects of different curing regimes on the compressive strength properties of self compacting concrete incorporating fly ash and silica fume. Materials & Design, 51, 12-18.
  44. Ranjbar, M. (2017). Durability characteristics of self-compacting concrete incorporating pumice and metakaolin, Mater. Civ. Eng., 29(11), 89-94.
  45. Krishnapal, P., Yadav, R. K., & Rajeev, C. (2013). Strength characteristics of self compacting concrete containing fly ash. Res J Eng Sci ISSN, 2278, 9472.
  46. Nepomuceno, M. C., Pereira-de-Oliveira, L. A., & Lopes, S. M. R. (2014). Methodology for the mix design of self-compacting concrete using different mineral additions in binary blends of powders. Construction and Building Materials, 64, 82-94.
  47. Vivek, S. S., & Dhinakaran, G. (2017). Fresh and hardened properties of binary blend high strength self compacting concrete. Engineering science and technology, an international journal, 20(3), 1173-1179.
  48. Tang, W. C., Wang, Z., Liu, Y., & Cui, H. Z. (2018). Influence of red mud on fresh and hardened properties of self-compacting concrete. Construction and Building Materials, 178, 288-300.
  49. Gholhaki, M., Hajforoush, M., & Kazemi, M. (2018). An investigation on the fresh and hardened properties of self-compacting concrete incorporating magnetic water with various pozzolanic materials. Construction and Building Materials, 158, 173-180.
  50. De Belie, N., Soutsos, M., & Gruyaert, E. (2018). Properties of fresh and hardened concrete containing supplementary cementitious materials(Vol. 25). Cham, Switzerland: Springer.
  51. Hani, N., Nawawy, O., Ragab, K. S., & Kohail, M. (2018). The effect of different water/binder ratio and nano-silica dosage on the fresh and hardened properties of self-compacting concrete. Construction and Building Materials, 165, 504-513.
  52. Nuruzzaman, M. D., Casimiro, J. O. C., & Sarker, P. K. (2020). Fresh and hardened properties of high strength self-compacting concrete using by-product ferronickel slag fine aggregate. Journal of Building Engineering, 32, 101686.

  • تاریخ دریافت 12 بهمن 1402
  • تاریخ بازنگری 12 دی 1403
  • تاریخ پذیرش 16 دی 1403