پیش‌بینی مقاومت فشاری بتن خودتراکم حاوی فیلر‌های مختلف با کمک شبکه‌های عصبی مصنوعی

نوع مقاله : مقاله پژوهشی

نویسندگان

دانشکده فنی مهندسی، دانشگاه مازندران، بابلسر، ایران

چکیده

بتن‌های خودمتراکم با خواص رئولوژی و مکانیکی مناسب، از بتن‌های جدید محسوب می‌شوند که در اواخر قرن 20 و اوایل قرن 21 مورد توجه محققین و صاحبان صنایع قرار گرفت. دقت در بتن‌‌ریزی، تراکم بتن و همچنین ظاهر بتن به عنوان یک متریال اکسپوز همواره از دغدغه‌های طراحان و مجریان پروژه‌های عمرانی محسوب می‌شود. بتن‌های خودمتراکم با خاصیت تراکم وزنی همواره می‌تواند از گزینه‌های پیش روی طراحان باشد. تنوع در مواد مورد استفاده در بتن‌های خودمتراکم از جمله مواد بازیافتی، با خاصیت پوزولانی و پر کنندگی در جهت رسیدن به اهداف رئولوژی و مکانیکی، از چالش‌هایی است که طراحان با آن روبرو هستند. همچنین دقت در تعیین نسبت‌های اختلاط و نتایج حاصل از آن بسیار زمان بر و پرهزینه می‌باشد. علوم کامپیوتر با بهره‌گیری از محاسبات نرم و شبکه‌های عصبی الهام گرفته از ساختار بیولوژیکی مغز انسان، سعی در افزایش سرعت، دقت و همچنین کاهش هزینه به جهت جلوگیری از آزمایشات مخرب می‌پردازد. در این پژوهش با کمک دو شبکه ANN و LSTM با بهره‌گیری از 320 نمونه بتن خودمتراکم با پراکندگی و جامعیت مصالح رایج مورد استفاده در آن توسط محققیق مختلف، سعی در پیش‌بینی مقاومت فشاری 28 روزه بتن خودتراکم، بررسی عملکرد و افزایش دقت توسط 6 الگوریتم آموزشی مختلف شده است. در مجموع حدودا 200 تکرار آموزش بر روی 320 نمونه بتن خودتراکم با 14 ویژگی انجام شد، که با مقایسه بهترین نتایج حاصل از الگوریتم‌های آموزشی، بهترین عملکرد با ریشه میانگین مربعات خطای 4/97 و ضریب همبستگی 0/9484 در آزمایش، برای شبکه ANN با الگوریتم آموزشی Beyesian Regularization گزارش شد، که نشان دهنده‌ی دقت بالای آن شبکه می‌باشد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Prediction of compressive strength of self-compacting concrete containing different fillers with the help of Artificial Neural Networks

نویسندگان [English]

  • Seyyed Moein Masrori Saadat
  • Ehsan Jahani
civil engineering department, , university of Mazandaran
چکیده [English]

Self-compacting concretes with suitable rheological and mechanical properties, are among the new concretes that were considered by researchers and industrialists in the late 20th and early 21st centuries. Accuracy in pouring concrete, concrete density and also the appearance of concrete as an exposed material is always a concern of designers and executors of construction projects. Self-compacting concrete with weight compression properties can always be one of the options available to designers. The variety of materials used in self-compacting concrete, including recycled materials, with pozzolanic properties and fillers to achieve rheological and mechanical goals, is one of the challenges that designers face. Also, accurate determination of mixing ratios and their results are very time-consuming and costly. Using soft computing and neural networks inspired by the biological structure of the human brain, computer science seeks to increase speed, accuracy, and cost reduction to prevent malicious experiments. In this study, with the help of ANN and LSTM networks, using 320 samples of self-compacting concrete with dispersion and comprehensiveness of common materials used in it by various researchers, tried to predict the 28-day compressive strength of self-compacting concrete, evaluate performance and increase accuracy by 6 The training algorithm is different. In total, about 200 repetitions of training were performed on 320 samples of self-compacting concrete with 14 characteristics, which by comparing the best results obtained from training algorithms, best performance with root mean square error of 4.97 and correlation coefficient of 0.9484 in the test, for the network. ANN was reported with the Beyesian Regularization training algorithm, which indicates the high accuracy of that network.

کلیدواژه‌ها [English]

  • Self-compacting concrete
  • Compressive strength prediction
  • ANN neural network
  • LSTM neural network

مراجع

 [1] H. Okamura, M. Ouchi, Self-compacting concrete–Journal of Advanced Concrete Technology, vol. 1.(2003).
[2] EFNARC, Guidelines for Self-Compacting Concrete, European Federation for Specialist Construction Chemicals and Concrete Systems, Norfolk, UK. English ed., February, (2002).
[3] M.F. Granata, Pumice powder as filler of self-compacting concrete. Construction and Building Materials, 96 (2015) 581-590.
[4] F.A. Mustapha, A. Sulaiman, R.N. Mohamed, S.A. Umara, The effect of fly ash and silica fume on self-compacting high-performance concrete. Materials Today: Proceedings, 39 (2021) 965-969.
[5] F. Pirmohammadi Alishah, The Effect of Zeolite on Different Mechanical Properties and Permeability of Self-Compacting Concrete. Computational Engineering and Physical Modeling, 3(1) (2020) 53-68.
[6] J. Seelapureddy, J. Bommisetty, M.V. Seshagiri Rao, Effect of metakaolin and micro silica on strength characteristics of standard grades of self-compacting concrete. Materials Today: Proceedings, 45 (2021) 884-890.
[7] E.M. Raisi, J.V. Amiri, M.R. Davoodi, Mechanical performance of self-compacting concrete incorporating rice husk ash. Construction and Building Materials, 177 (2018) 148-157.
[8] A.A.A. Al-Oran, N.A. Safiee, N.A. Mohd Nasir, Fresh and hardened properties of self-compacting concrete using metakaolin and GGBS as cement replacement. European Journal of Environmental and Civil Engineering, (2019) 1-14.
[9] J. Xiao, Z. Ma, T. Sui, A. Akbarnezhad, Z. Duan, Mechanical properties of concrete mixed with recycled powder produced from construction and demolition waste. Journal of Cleaner Production, 188 (2018) 720-731.
[10] A. Majumdar, A. Mitra, D. Banerjee, P.K. Majumdar, Soft computing applications in fabrics and clothing: a comprehensive review. Research Journal of Textile and Apparel, (2010).
[11] S. Selvaraj, S. Sivaraman, Prediction model for optimized self-compacting concrete with fly ash using response surface method based on fuzzy classification. Neural Computing and Applications, 31(5) (2019) 1365-1373.
[12] A. Iqtidar, N. Bahadurkhan, S. Kashif-ur-Rehman, M. Faisal Javed, F. Aslam, R. Alyousef, H. Alabduljabbar, A. Mosavi, Prediction of compressive strength of rice husk ash concrete through different machine learning processes. Crystals, 11(4) (2021) 352.
[13] M. Serraye, S. Kenai, B. Boukhatem, Prediction of compressive strength of self-compacting concrete (SCC) with silica fume using neural networks models. Civil Engineering Journal, 7(1) (2021) 118-139.
[14] S. Hochreiter, J. Schmidhuber, Long short-term memory. Neural computation, 9(8) (1997) 1735-1780.
[15]F.A. Gers, J. Schmidhuber, Recurrent nets that time and count. in Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium. (2000).
[16] S.M. Davoodnabi, M. Safehian, The effect of using mineral additives (silica fume, zeolite, slag, limestone powder) on the compressive strength and surface electrical resistance of self-compacting concrete considering the fixed paste volume.3rd International Conference on Applied Researches in structural engineering and construction management, (2019) (in Persian).
[17] M.S. Abasifar, M.R. Pirmohammadi, S.M. Mirhoseini, SH. Pirmohammadi, The effect of replacing limestone powder with recycled travertine stone powder on compressive strength and volume water absorption in self-compacting concretes. 11th National Conference on concrete, Tehran, (2019) (in Persian).
[18] E. Varjavand, M. Sobhaninia, The effect of rice husk ash and sugarcane pulp on the compressive strength of self-compacting concrete. 3rd Conference on Engineering Sciences, Kish Island, (2019) (in Persian).
[19] M. Khanzadi, M.R. Nabizadeh, S.R. Bagheri, V. Ghalenoei, Investigation of the effect of zeolite and mesbar on the performance of self-compacting concrete. First National Concrete Industry Conference, Kerman, (2012) (in Persian).
[20] A. Khani, M. Tadion, M.E. Komaki, S.M. Sajad Atar, Investigation and evaluation of K factor in self-compacting concretes containing zeolite and smelting furnace slag. 9th National Conference on concrete, Tehran, (2017) (in Persian).
[21] P. Ghoddousi, A.A. Shirzad Javid, S.H. Hoseini Rostami, B. Mehri, Rheology study of self-compacting concretes containing mineral additives. 5th National Conference on Self-Consolidating concrete and 1st National Conference on Repair and Maintenance of concrete structures, Tehran, (2017) (in Persian).
[22] P. Razmara, S. Saidijam, J. Afiati, Self-compacting concrete: Green concrete technology with an attitude towards the environment. The 4th International Conference on Environmental planning and Management, Tehran, (2017) (in Persian).
[23] M.S. Hoseini, H. Varastepour, Investigation of the effects of water to cement ratio on the properties of self-compacting concrete and its optimization with VMA and lime powder. 4th International Conference on Advanced Technology in Civil engineering, Architecture and Urban planning, Tehran, (2017) (in Persian).
[24] M.H. Khazali, A.R. Nikkhah, D. Rahimi, Investigation of the effect of zeolite, microsilica, slag and lime powder on the mechanical properties of self-compacting concrete. 9th National Conference on concrete, Tehran, (2017) (in Persian).
[25] P.S. Pourhosein, Investigation of physical properties of self-compacting concrete containing different ratios of water to cement. International conference on the new horizons in the basic and technical sciences and engineering, Tehran, (2017) (in Persian).
[26] E. Nassirnia, S. Rahimi, S.Y. Mousavi, The effect of pozzolan pumice on the properties of fresh and hardened self-compacting concrete. A Thesis Presented for the Degree of Master of science In Civil Engineering-Structure. Allameh Mohaddes Nouri University, Nour, iran, (2016) (in Persian).
[27] A. Meshkini, F. Pirmohammadi alishah, Properties of lightweight self-compacting concrete containing pumice as a cement substitute. 3rd International conference on science and engineering, Istanbul, Turkey, (2016) (in Persian).
[28] A.A. Hassan, M.K. Ismail, J. Mayo, Mechanical properties of self-consolidating concrete containing lightweight recycled aggregate in different mixture compositions. Journal of Building Engineering, 4 (2015) 113-126.
[29] H. Nouripahlevanlou, J. Berenjian, M. Hoseinalibeygi, O. Lotfi Omran, S. Jalilian, Laboratory study of engineering properties and stability of self-compacting concrete containing methacoline pozzolan. 7th National concrete Conference of iran, Tehran, (2015) (in Persian).
[30] A. Eftekhari, V. Naderi, A. Foroughi Asl, Impact of microsilica on the mechanical properties and permeability of self-compacting concrete. 9th National concrete Conference of iran, Tehran, (2015) (in Persian).
[31] H. Varastepour, J. Morovati, S.V. Aghebatkhah, Investigation of the effects of VMA and limestone powder composition on the properties of fresh and hardened self-compacting concrete. International conference on science and engineering, Dubai, UAE, (2015) (in Persian).
[32] J. Berenjian, H. Nouri pahlevanloo, The effect of rice husk ash pozzolan replacement on the mechanical properties of self-compacting concrete. 2nd International congress on structure, architecture & urban development, Tabriz, (2014) (in Persian).
[33] M. Ghasemi, J. Berenjian, H. Azari Jafari, N.R. Forouhar, The effect of natural zeolite and Taftan pumice replacement on the characteristics of fresh and hardened self-compacting concrete. 5th National concrete Conference of iran, Tehran, (2013) (in Persian).
[34] H. Aslani, Z. Khazemi, A. Aslani, Self-compacting concrete mixing scheme without the use of viscosity modifiers. National Conference on Applied Civil Engineering and New Achievements, Karaj, (2014) (in Persian).
[35] M.S. Sargazi Moghdam, M.H. Mirabi Moghadam, S. Rahat Dehmardeh, Influence of superplasticizer rate on rheological, mechanical and porosity properties of self-compacting concrete. 2nd National conference on material and new structures, Esfahan, (2014) (in Persian).
[36] T. Khazaeni, M. Miri, N. Sarani, Investigation of durability and mechanical properties of self-compacting concrete containing metakaolin and pumice. 5th National concrete Conference of iran, Tehran, (2013) (in Persian).
[37] R. Madandoust, S.Y. Mousavi, Fresh and hardened properties of self-compacting concrete containing metakaolin. Construction and building materials, 35 (2012) 752-760.
[38] M.M. Ranjbar, R. Madandoust, F. Ghane, S. Esapour, M. Karimi, Evaluation of engineering properties of potent self-compacting concrete containing pozzolans. 4th National concrete Conference of iran, Tehran, (2012) (in Persian).
[39] A. Sadrmomtazi, M.A. Ahmadi Rad, H. Rostami Atigh, Evaluation of flexural compressive strength and modulus of elasticity of SCC self-compacting concrete containing rice paddy husk ash. National congress of self-compacting concrete(NCSCC), Kerman, (2011) (in Persian).
[40] O. Farshadfar, K. Behfarnia, D. Mostofinejad, Investigation of the effect of pozzolan types on mechanical properties of fiber self-compacting concrete. 6th National Congress of Civil Engineering, Semnan, (2011) (in Persian).
[41] A. Askari, M.R. Sohrabi, Y. Rahmani, M. Mehravaran, The effect of nanosilica on the mechanical properties of self-compacting concrete containing fly ash. 6th National Congress of Civil Engineering, Semnan, (2011) (in Persian).
[42] E. Güneyisi, M. Gesoglu, E. Özbay, Evaluating and forecasting the initial and final setting times of self-compacting concretes containing mineral admixtures by neural network. Materials and structures, 42(4) (2009) 469-484.
[43] L. Smith, R. German, M. Smith, A neural network approach for solution of the inverse problem for selection of powder metallurgy materials. Journal of Materials processing technology, 120(1-3) (2002) 419-425.
[44] S. Lek, M. Delacoste, Ph. Baran, L. Lauga, S. Aulagnier,  Application of neural networks to modelling nonlinear relationships in ecology. Ecological modelling, 90(1) (1996) 39-52.
نشریه مهندسی عمران امیرکبیر
دوره 54، شماره 10
دی 1401
صفحه 3835-3856

فایل ها

هم رسانی

ارجاع به این مقاله

آمار