ترکیب مدل‌های شبکه عصبی برای پیش‌بینی مقاومت چسبندگی میلگردهای پلیمری با الیاف شیشه به بتن

نوع مقاله : علمی - پژوهشی

نویسندگان

1 استادیار، دانشکده مهندسی علوم آب، گروه سازه های آبی، دانشگاه شهید چمران، اهواز، ایران.

2 دانشجوی دکتری، گروه عمران- مدیریت ساخت، دانشکده عمران، معماری و هنر، واحد علوم و تحقیقات، دانشگاه آزاد اسلامی، تهران، ایران.

چکیده

استفاده از مصالح FRP و سایر مصالح کامپوزیتی به عنوان میلگرد یا ورق، یکی از گزینه‌های مناسب فنی و اقتصادی در ساخت، بهسازی و مقاوم‌سازی سازه‌هایی نظیر سازه‌های بتنی است. یکی از مهمترین مسائلی که باید در مورد استفاده از چنین مصالحی مدنظر قرار گیرد، مقاومت چسبندگی آنها به بتن سازه‌ای است. در این مقاله، تأثیر ترکیب مدل‌های پیش‌بینی گروهی با مد‌‌ل‌های تخمین منفرد بر روی بهتر شدن نتایج مدل‌های منفرد برآورد مقاومت چسبندگی میلگردهای FRP با الیاف شیشه به بتن مورد بررسی قرار می‌گیرد. برای رسیدن به این هدف ابتدا از شبکه‌های عصبی با ورودی‌های نتایج پیش‌بینی دو مدل منفرد قبلأ ارائه شده برای برآورد مقاومت چسبندگی GFRP به منظور بهبود نتیجه بهترین مدل از میان دو مدل مذکور استفاده می‌شود. سپس با درنظرگیری خروجی-های پیش‌بینی مدل شبکه عصبی اول و بهترین مدل منفرد از بین دو مدل فوق‌الذکر به عنوان ورودی، دوباره از شبکه‌های عصبی برای ارائه یک مدل بهتر از مدل ANN اول استفاده می‌شود. نتایج انتهایی نشان از کاهش خطای پیش‌بینی مدل ANN ترکیب شده از روش-های منفرد و گروهی نسبت به مدل‌های منفرد قبلأ ارائه شده، مدل میانگین وزن‌دار نتایج خروجی پیش‌بینی شده‌ دو مدل منفرد مذکور و مدل ANN ترکیبی آن دو مدل منفرد می‌دهند.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Combining Neural Network Models to Prediction the Bond Strength of Glass FRP to Concrete

نویسندگان [English]

  • Ahmad Fathi 1
  • Farshad Peyman 2
1 Assistant Professor, Water Sciences Engineering Faculty, Department of Hydraulic Structures, Shahid Chamran University, Ahvaz, Iran.
2 Ph.D. Student, Department of Civil Engineering – Construction Management and Engineering , Faculty of Civil , Architecture and Art, Science and Research Branch, Islamic Azad University, Tehran, Iran.
چکیده [English]

The use of FRP and other composite materials as bar or sheets is one of the most technically and economically viable options in the construction, refurbishment, and reinforcement of structures such as concrete structures. One of the most important issues to consider when using such materials is their bond strength to structural concrete. In this paper, the effect of combining ensemble prediction models with single estimation models on improving the results of single models is estimated to estimate the bond strength of GFRP bars to concrete. To this end, neural networks with predictive results inputs are first used to estimate the bond strength of GFRP to improve the best model result from the two previous models- Be. Then, by considering the prediction outputs of the first neural network model and the best single model above mentioned as input, the neural networks are again used to present a better model than the first ANN model. The final results show the reduction of the prediction error of the ANN model combined with single and ensemble methods compared to the single models previously presented, the weighted average output model of the two single models above and the ANN model. The combination of the two models usefulness a single.

کلیدواژه‌ها [English]

  • Bond strength of GFRP bar
  • Structural concrete
  • Artificial neural networks
  • Combination of ensemble and single models
  • MATLAB software
[1] Zandi, Y. (2009). Advanced Concrete Technology. 2nd Edition. Tabriz: Forouzesh Publisher, 577-596 (In Persian).
[2] Golafshani, E.M., Rahai, A. and Sebt, M.H. (2015). Artificial neural network and genetic programming for predicting the bond strength of GFRP bars in concrete. Materials and Structures, 48, pp 1581-1602.
[3] Coelho, M.R.F., Sena-Cruz, J.M., Neves, L.A.C., Pereira, M., Cortez, P. and Miranda, T. (2016). Using data mining algorithms to predict the bond strength of NSM FRP systems in concrete. Construction and Building Materials, 126, 484-495.
[4] Naderpour, H., Nourmohammadi, E. and Fakharian, P. (2017). Prediction of punching shear capacity of RC slabs using support vector machine. Concrete Research, 10 (2), 95-107 (In Persian).
[5] Bazli, M., Ashrafi, H. and Oskouei, A.V. (2017). Experiments and probabilistic models of bond strength between GFRP
bar and different types of concrete under aggressive environments. Construction and Building Materials, 148, 429-443.
[6] Kaboutari, M., Ghiami, A., Sadrsadat, E. and Ghorbani, B. (2017). Prediction of Bond Strength Between Concrete and FRP Using Data Laboratory. 5th International Congress on Civil Engineering, Architecture and Urban Development. Tehran: Shahid Beheshti University, 1-9 (In Persian).
[7] Yan, F., Lin, Z., Wang, X., Azarmi, F. and Sobolev, K. (2017). Evaluation and prediction of bond strength of GFRP-bar reinforced concrete using artificial neural network optimized with genetic algorithm. Composite Structures, 161, 441-452.
[8] Naderpour, H. and Fakharian, P. (2018). Predicting the torsional strength of reinforced concrete beams strengthened with FRP sheets in terms of artificial neural networks. Journal of Structural and Construction Engineering, 5 (1), 20-35 (In Persian).
[9] Bolandi, H., Banzhaf, W., Lajnef, N., Barri, K. and Alavi, A.H. (2019). An intelligent model for the prediction of bond strength of FRP bars in concrete: A soft computing approach. Technologies, 7 (2), 42;1-16.
[10] Naderpour, H., Nagai, K., Fakharian, P. and Haji, M. (2019). Innovative models for prediction of compressive strength of FRP-confined circular reinforced concrete columns using soft computing methods. Composite Structures, 215, 69-84.
[11] Naderpour, H. and Mirrashid, M. (2019). A neuro-fuzzy model for punching shear prediction of slab-column connections reinforced with FRP. Journal of Soft Computing in Civil Engineering, 3 (1), 16-26.
[12] Chou, J.S. and Pham, A.D. (2013). Enhanced artificial intelligence for ensemble approach to predicting high performance concrete compressive strength. Construction and Building Materials, 49, 554-563.
[13] Chou, J.S., Tsai, C.F., Pham, A.D. and Lu, Y.H. (2014). Machine learning in concrete strength simulations: Multi-nation data analytics. Construction and Building Materials, 73, 771-780.
[14] Aydogmus, H.Y., Erdal, H.I., Karakurt, O., Namli, E., Turkan, Y.S. and Erdal, H. (2015). A comparative assessment of bagging ensemble models for modeling concrete slump flow. Computers and Concrete, 16 (5), 741–757.
[15] Naderpour, H., Rafiean, A.H. and Fakharian, P. (2018). Compressive strength prediction of environmentally friendly concrete using artificial neural networks. Journal of Building Engineering, 16, 213-219.
[16] Ling, H., Qian, C., Kang, W., Liang, C. and Chen, H. (2019). Combination of Support Vector Machine and K-Fold cross validation to predict compressive strength of concrete in marine environment. Construction and Building Materials, 206, 355-363.
[17] Zhang, M., Li, M., Shen, Y., Ren, Q. and Zhang, J. (2019). Multiple mechanical properties prediction of hydraulic concrete in the form of combined damming by experimental data mining. Construction and Building Materials, 207, 661-671.
[18] Naderpour, H., Rezazadeh Eidgahee, D., Fakharian, P., Rafiean, A.H. and Kalantari, S.M. (2019). A new proposed approach for moment capacity estimation of ferrocement members using Group Method of Data Handling. Engineering Science and Technology, an International Journal, In press, doi.org/10.1016/j.jestch.2019.05.013.
[19] Shahmansouri, A.A., Akbarzadeh Bengar, H. and Jahani, E. (2019). Predicting compressive strength and electrical resistivity of eco-friendly concrete containing natural zeolite via GEP algorithm. Construction and Building Materials, 229, Number Article: 116883.
[20] Kia, S.M. (2012). Neural Networks in the MATLAB. 2nd  Edition. Tehran: Kian Rayaneh Sabz Publisher, 81-239 (In Persian).
[21] Golafshani, E.M. and Ashour, A. (2016). A feasibility study of BBP for predicting shear capacity of FRP reinforced concrete beams without stirrups. Advances in Engineering Software, 97, 29-39.