پیش‌بینی پارامترهای چسبندگی الیاف فولادی هوک شکل و بتن با استفاده از شبکه‌های عصبی مصنوعی
محورهای موضوعی : آنالیز سازه - زلزله
1 - عضو هیات علمی دانشگاه ازاد اسلامی
کلید واژه: الیاف فولادی, شبکه عصبی مصنوعی, نیروی بیرون‌کشیدگی, مدل المان محدود. ,
چکیده مقاله :
با توجه به اهمیت بکارگیری الیاف فولادی در تقویت بتن، در تحقیق حاضر با استفاده از شبکه‌های عصبی مصنوعی به پیش‌بینی رفتار بیرون کشیدگی الیاف فولادی هوک شکل از بتن پرداخته شده است. به دلیل محدودیت داده‌های جامع آزمایشگاهی، از داده‌های به دست آمده از تحلیل المان محدود به عنوان ورودی شبکه عصبی استفاده شده است. به منظور شبیه‌سازی بیرون کشیدگی الیاف از روش المان محدود سه‌بعدی و نرم‌افزار آباکوس استفاده می‌شود. در مدل المان محدود، اندرکنش بین الیاف و بتن با استفاده از مفهوم ناحیه انتقالی سطح مشترک شبیه‌سازی شده است که پارامترهای آن با استفاده از روش المان محدود معکوس و استفاده از نتایج تست تجربی بیرون‌کشیدگی انجام پذیرفته بر روی یک نمونه الیاف به دست آمده است. پس از صحت‌سنجی نتایج مدل عددی با نتایج تجربی، نتایج به ازای پارامترهای مؤثر الیاف استخراج شده و بر اساس آنها مدل‌سازی با استفاده از شبکه‌های عصبی صورت گرفته است. پیش‌بینی نیروی بیرون‌کشیدگی توسط شبکه‌های عصبی مصنوعی چندلایه و الگوریتم آموزش انتشار به عقب، با تکنیک بهینه‌سازی مارکورادت-لونبرگ انجام شده است. نتایج نشان می‌دهد که مدل شبکه عصبی ارائه شده در این تحقیق، به دلیل توانایی استفاده از متغیرهای بیشتر در مدل‌سازی و نتایج دقیق‌تر، روشی مؤثر برای پیش‌بینی نیروی بیرون‌کشیدگی الیاف از بتن است.
As steel fibers are important reinforcement materials in concrete, in this study, the behavior of hook-shaped steel fibers from concrete is predicted through the use of artificial neural networks. In the absence of comprehensive laboratory data, data obtained from finite element analysis was used for modeling. The simulations are carried out using ABAQUS software's finite element method in 3D. Using the concept of the transition zone of the interface, whose parameters were obtained by inverse finite element analysis and experimental tests conducted on a sample of fibers, this model has been developed to simulate the interaction between fibers and concrete. On the basis of the results of the numerical model validated against the experimental results, the effective parameters of the fibers were extracted, and a neural network was then constructed based on the results. A multilayer forward perceptron artificial neural network and back-propagation training algorithm are used to predict pull-out force, with Marquardt-Lonberg optimization applied. The results demonstrate that the neural network model presented in this research is an effective method for predicting the pull-out force of fibers from concrete, in part because it allows the use of more variables in modeling, as well as delivering more accurate results.
[1] Zhang P, Wang C, Gao Z, Wang F. A review on fracture properties of steel fiber reinforced concrete. Journal of Building Engineering. 2023; 32: 105-125.
[2] Vahidi Pashaki P, Pouya M, Maleki VA. High-speed cryogenic machining of the carbon nanotube reinforced nanocomposites: Finite element analysis and simulation. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science. 2018; 232(11): 1927-36.
[3] Esmaeili J, Andalibi K, Gencel O, Maleki FK, Maleki VA. Pull-out and bond-slip performance of steel fibers with various ends shapes embedded in polymer-modified concrete. Construction and Building Materials. 2021; 271: 123-140.
[4] Zheng X, Zhang C, Gao S, Wang F. Predicting the bond strength between steel wire and mortar based on interfacial porosity and shrinkage. Journal of Building Engineering. 2023; 36: 106-118.
[5] Li M, Sun J, Li L, Meng L, Wang S, Wei J. Effect of nanosilica on fiber pullout behavior and mechanical properties of strain hardening ultra-high performance concrete. Construction and Building Materials. 2023; 367: 130-155.
[6] Jiang K, Wang X, Ding L, Chen Z, Liu J, Wu Z. Experimental study on pullout behaviour of basalt fiber-reinforced polymers minibar embedded in ultra-high performance seawater sea-sand concrete. Journal of Building Engineering. 2023; 63: 106-123.
[7] Esmaeili J, Khoshkanabi SP, Andalibi K, Kasaei J. An innovative method for improving the cyclic performance of concrete beams retrofitted with prefabricated basalt-textile-reinforced ultra-high performance concrete. Structures. 2023; 63: 32-46.
[8] Esmaeili J, Andalibi K, Gencel O. Mechanical characteristics of experimental multi-scale steel fiber reinforced polymer concrete and optimization by Taguchi methods. Construction and Building Materials. 2021; 31: 69-76.
[9] Deng Y, Zhang Z, Shi C, Wu Z, Zhang C. Steel Fiber–Matrix Interfacial Bond in Ultra-High Performance Concrete: A Review. Engineering. 2022; 96: 65-79.
[10] Baghad A, El Mabrouk K, Vaudreuil S, Nouneh K. Effects of high operating temperatures and holding times on thermomechanical and mechanical properties of autoclaved epoxy/carbon composite laminates. Polymer Composites. 2022; 43(2): 862-73.
[11] Pi Z, Xiao H, Du J, Li C, Cai W, Liu M. Effect of the water/cement ratio on the improvement of pullout behaviors using nano-SiO2 modified steel fiber and the micro mechanism. Construction and Building Materials. 2022; 338: 127-139.
[12] Thiagarajan K, Umamaheswari N. Time-dependent behavior of pre-coated crimped, 4-Dimensional and 5-Dimensional steel fiber pull-out in normal and rubber concrete. Construction and Building Materials. 2022; 359: 129-146.
[13] Zhang C, Zhang G, Shi X, Wang X. Effects of carbon nanotubes on the interlaminar shear strength and fracture toughness of carbon fiber composite laminates: a review. Journal of Materials Science. 2022; 57(4): 2388-410.
[14] Yoo D-Y, Kim S. Comparative pullout behavior of half-hooked and commercial steel fibers embedded in UHPC under static and impact loads. Cement and Concrete Composites. 2019; 97: 89-106.
[15] Benedetty CA, Krahl PA, Almeida LC, Trautwein LM, Siqueira GH, de Andrade Silva F. Interfacial mechanics of steel fibers in a High-Strength Fiber-Reinforced Self Compacting Concrete. Construction and Building Materials. 2021; 301: 124-144.
[16] Dehghani A, Aslani F. Effect of 3D, 4D, and 5D hooked-end type and loading rate on the pull-out performance of shape memory alloy fibres embedded in cementitious composites. Construction and Building Materials. 2021; 273: 121-132.
[17] Di Maida P. Analytical Approach for Modelling the Pull-Out Mechanism of Recycled Synthetic Fibres in Fibre-Reinforced Concrete (FRC). Engineered Materials for Sustainable Structures. 2022; 134: 35-49.
[18] Chaabene WB, Flah M, Nehdi ML. Machine learning prediction of mechanical properties of concrete: Critical review. Construction and Building Materials. 2020; 260: 116-130.
[19] Asteris PG, Mokos VG. Concrete compressive strength using artificial neural networks. Neural Computing and Applications. 2020; 32(15): 11807-26.
[20] Fakeh M, Jawdhari A, Fam A. Calibration of ABAQUS Concrete Damage Plasticity (CDP) Model for UHPC Material. International Interactive Symposium on Ultra-High Performance Concrete; 2023: Iowa State University Digital Press.
[21] Saleh M, AlHamaydeh M, Zakaria M. Finite element analysis of reinforced concrete deep beams with square web openings using damage plasticity model. Engineering Structures. 2023; 278: 115-126.
[22] Xue L, Ren X, Ballarini R. Damage-plasticity modeling of shear failure in reinforced concrete structures. Engineering Fracture Mechanics. 2023; 290: 109-136.
[23] Kmiecik Pa, Kamiński M. Modelling of reinforced concrete structures and composite structures with concrete strength degradation taken into consideration. Archives of civil and mechanical engineering. 2011; 11(3): 623-636.
[24] Jiang J, Hu G, Li X, Xu X, Zheng P, Stringer J. Analysis and prediction of printable bridge length in fused deposition modelling based on back propagation neural network. Virtual and physical prototyping. 2019; 14(3): 253-266.
