پیش‎بینی مقاومت فشاری بتن خودتراکم توسط شبکه عصبی مصنوعی المان همراه با دو مجموعه متفاوت از پارامترهای ورودی

نوع مقاله : علمی - پژوهشی

نویسندگان

1 موسسه اموزش عالی طبری بابل

2 رئیس موسسه آموزش عالی طبری بابل-هیات علمی و استادیار دانشکده نوشیروانی بابل

چکیده

در سال‎های اخیر، شبکه‎های عصبی مصنوعی از یک رویکرد نظری به یک فن‎آوری با قابلیت استفاده گسترده همراه با برنامه‎های کاربردی موفق برای مسائل گوناگون تبدیل شده‎اند. در حقیقت، شبکه‌های عصبی مصنوعی یک ابزار محاسباتی قدرتمندی هستند که راه‎ حل‌های مناسبی را برای حل مسائلی ارائه می‌دهند که با استفاده از روش‌‎های مرسوم و سنتی دشوار هستند. امروزه این شبکه‏ها که از سیستم عصبی زیستی الهام گرفته‎ شده‎اند، به طور گسترده برای حل یک سطح وسیعی از مسائل پیچیده در مهندسی عمران نیز مورد استفاده قرار می‌گیرند. هدف از مطالعه حاضر، ارزیابی عملکرد شبکه‎های عصبی مصنوعی المان با در نظر گرفتن پارامترهای ورودی مختلف در پیش‎بینی مقاومت فشاری بتن خودتراکم می‎باشد. ازین‌رو، یک‌بار 8 پارامتر تاثیرگذار و بار دیگر جهت نزدیک ‌‌شدن هرچه بیشتر شرایط پیش‎بینی به شرایط آزمایشگاهی، 140پارامتر به عنوان ورودی وارد شبکه‎های عصبی المان شدند. طبق نتایج حاصله، شبکه‎ها‎ی عصبی المان به عنوان ابزار قابل اعتمادی با صرفه‎جویی در زمان و هزینه دارای قدرت بالایی در پیش‎بینی مشخصه‎های مورد نظر می‎باشند. به علاوه، در پیش‌بینی هر دو مقاومت فشاری 7 و 28 روزه، شبکه‎های ساخته شده با تعداد 140پارامتر به ترتیب به میزان 74/54 و 70/44 درصد بهبود در خطای تست نسبت به شبکه‌ها با 8 پارامتر دارند که این اثرگذاری مستقیم پارامترهای موثر در نظر گرفته شده به عنوان ورودی را بر میزان خطای شبکه در پیش‎بینی خواص مدنظر نشان می‎دهد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Predicting the compressive strength of self-compacting concrete using Elman artificial neural network with two different sets of input parameters

نویسندگان [English]

  • Atefeh Gholamzadeh Chitgar 1
  • Javad Berenjian 2
1 Tabari Institute of Higher Education, Babol
2 Assistant Professor and Head of the Tabari Institute of Higher Education
چکیده [English]

In recent years, artificial neural networks converted from a theoretical approach to the widely-used technology with successful applications to different problems. In fact, artificial neural networks are a powerful tool that give appropriate solutions to problems which are difficult to solve through conventional techniques. Nowadays, these networks, which are inspired by the biological nervous system, are also extensively used to solve a wide range of complex problems in civil engineering. The purpose of the current study is a performance evaluation of the Elman artificial neural networks with various input parameters in order to predict the compressive strength of Self Compacting Concrete (SCC). Therefore, once, 8 effective parameters and next, in order to simulate a real experimental conditions, 140 parameters were entered as inputs in the Elman neural networks. According to the results, Elman neural networks, as a reliable tool, have high strength for predicting the desired properties along with saving time and cost. In addition, in both 7 and 28-day compressive strength, the constructed networks with 140 input parameters compared to ones with 8, have 74.54 and 70.44 percent improvement respectively regarding their test errors. The effective inputs straightly affect the networks errors in the prediction of the desired properties.

کلیدواژه‌ها [English]

  • Self Compacting Concrete
  • Prediction
  • Compressive Strength
  • Neural Network
  • Input
[1] Bartos, P.J.M., Gibbs, J.C., Zhu, W. (2001). Uniformity of in Situ Properties of Self- Compacting Concrete in Full Scale Structural Elements. Cement and Concrete Composites, 23(1), 57-64.
[2] Okamura, H., Ouchi, M. (2003). Self-compacting concrete. Journal of Advanced Concrete Technology, 1(1), 5-15.
[3] Dehwah HAF. (2012). Mechanical properties of self-compacting concrete incorporating quarry dust powder, silica fume or fly ash. Construction and Building Materials, 26, 547-551.
[4] Kasperkiewicz, J., Racz, J., dubrawski, A. (1995). HPC Strength Prediction Using Artificial Neural Network. Journal of Computing in Civil Engineering, 9(4), 279-284.
[5] Oztas, A., Pala, M., Ozbay, E., Kanca, E., Caglar, N., Bhatti, M.A. (2006). Predicting the compressive strength and slump of high strength concrete using neural network. Construction and Building Materials, 20(9), 769–775.
[6] Demir, F. (2008). Prediction of elastic modulus of normal and high strength concrete by artificial neural networks. Construction and Building Materials, 22(7), 1428–1435.
[7] Barbuta, M., Diaconescu, R.M., Harja, M. (2012). Using Neural Networks for Prediction of Properties of Polymer Concrete with Fly Ash. Journal of Materials in Civil Engineering, 24(5), 523-528.
[8] Sonebi, M., Grünewald, S., Cevik, A., Walraven, J. (2016). Modelling fresh properties of self-compacting concrete using Neural network technique. Computers and Concrete, 18(4), 903-920.
[9] Raghu Prasad, B.K., Eskandari, H., Venkatarama Reddy, B.V. (2009) .Prediction of compressive strength of SCC and HPC with high volume fly ash using ANN. Construction and Building Materials, 23(1), 117-128.
[10]Malagavelli, V., Manalel, P.A. (2014). Modeling of Compressive Strength of Admixture-based Self Compacting Concrete using Fuzzy Logic and Artificial Neural Networks. Asian Journal of Applied Sciences, 7, 536-551.
[11]Abd, M., Elaty, A. (2014). Compressive strength prediction of Portland cement concrete with age using a new model. HBRC Journal, 10(2), 145-155.
[12] Neville, A.M., Brooks, J.J. (2010). Concrete Technology. The Second Edition. Pennsylvania: Trans-Atlantic Publications, 1-464.
[13] Minin, A. (2006). The Neural-Network Analysis Data Filters. 1-12.
[14] Hassoun, M.H. (1995). Fundamentals of Artificial Neural Networks. Cambridge: A Bradford Book, 1-511.
[15] McCulloch, W.S., Pitts, W.H. (1943). A logical calculus of the ideas immanent in neural nets. Bulletin of Mathematical Biology, 5, 115-133.
[16] Rosenblatt, F. (1962). Principles of Neurodynamics: Perceptron and the Theory of Brain Mechanism. Washington: Spartan Books, 1-616.
[17] Hubick, K. T. (1992). Artificial neural networks in Australia. Canberra: Department of Industry, Technology and Commerce, 1-132.
[18] Elman, J.L. (1990). Finding structure in time, Cognitive Science, 14, 179-211.
[19] Suzuki, K. (2011). Artificial Neural Networks: Methodological Advances and Biomedical Applications. Rijeka: InTech, 1-362.
[20] Tang, Z.H., Li, R. (2011). An Improved Neural Network Model and Its Applications. Journal of Information & Computational Science, 10, 1881–1888.
[21] Douglas, R.P. (2004). Properties of Self-Consolidating Concrete Containing Type F Fly Ash. Msc Thesis. Northwestern University, Evanston, Illinois.
[22] Turk, K., Karatas, M. (2011). Abrasion Resistance and Mechanical Preperties of Self-Compacting Concrete with Different Dosage of Fly Ash/Silica Fume. Indian Journal of Engineering & Materials Sciences, 18, 49-60.
[23] Abdul Hameed, M. (2005). A study of mix design and durability of Self Compacting Concrete. Msc Thesis. King Fahd University of Petroleum & Minerals, Saudi Arabia.
[24] Kumar, R., Madan, S.K, Devgan, N.P., Roshan, L. (2013). An Experimental Study on Performance of Self Compacting Concrete Contaning Lime Stone Quarry Fines and Fly Ash. Asian Journal of Civil Engineering (BHRC), 15(3), 421-433.
[25] Corinaldesi, V., Moriconi, G. (2011). Characterization of self-compacting concretes prepared with different fibers and mineral additions. Cement & Concrete Composites, 33(5), 596-601.
[26] Venkateswara Rao, S., Seshagiri Rao, M.V., Rathish Kumar, P. (2010). Effect of Size of Aggregate and Fines on Standard and High Strength Self Compacting Concrete. Journal of Applied Sciences Research, (5), 433-442.
[27] Beigi, M., Berenjian, J., Lotfi Omran, O., Sadeghi Nik, A., Nikbin, I. (2013). An experimental survey on combined effects of fibers and nanosilica on the mechanical, rheological, and durability properties of self-compacting concrete. Materials and Design, 50, 1019–1029.
[28] Guneyisi, E., Gesoglu, M., Ozbay, E. (2010). Strength and drying shrinkage properties of self-compacting concretes incorporating multi-system blended mineral admixtures. Construction and Building Materials, 24(10), 1878–1887.
[29] Hossain, K.M.A., Lachemi, M., Sammour, M., Sonebi, M. (2013). Strength and fracture energy characteristics of self-consolidating concrete incorporating polyvinyl alcohol, steel and hybrid fibers. Construction and Building Materials, 45, 20–29.
[30] Sahmaran, M., Yurtseven, A., Ozgur Yaman, I. (2005). Workability of hybrid fiber reinforced self-compacting concrete. Building and Environment, 40(12), 1672–1677.
[31] Aydin, A.C. (2007). Self compactability of high volume hybrid fiber reinforced concrete. Construction and Building Materials, 21(6), 1149–1154.
[32] Patel, A., Bhuva, P., George, E., Bhatt, D. (2011). Compressive Strength and Modulus of Elasticity of Self-Compacting Concrete. In: National Conference on Recent Trends in Engineering & Technology, India.
[33] Masters, T. (1993). Practical neural network recipes in C++. San Diego, California: Academic Press publication, 1-493.
[34] Kanellopoulas, I., Wilkinson, G.G. (1997). Strategies and best practice for neural network image classification. International Journal of Remote Sensing, 18(4), 711–725.
[35] Govindaraju, R.S. (2000). ASCE Task Committee on Application of Artificial Neural Networks in Hydrology. Journal of Hydrologic Engineering, 5(2), 115- 123.
[36] Ripley, B.D. (1993). Statistical aspects of neural networks: Networks and chaos-statistical and probabilistic aspects. London: Chapman & Hall, 40–123.
[37] Wang, C.A. (1994). Theory of generalization in learning machines with neural application. PhD Thesis. Pennsylvania University, USA.
[38] Sarıdemir, M., Topcu, I.B., Ozcan, F., Severcan, M.H. (2009). Prediction of long-term effects of GGBFS on compressive strength of concrete by artificial neural networks and fuzzy logic. Construction and Building Materials, 23, 1279–1286.
[39] Smith, M. (1993). Neural networks for statistical modelling. New York: Van Nostrand Reinhold, 1-235.
[40] MATLAB Software, Neural Network Toolbox: mapminmax, R2013b, Version: (8.2.0.701), august 13 (2013).