مدل‌سازی رفتار جانبی دیوارهای گهواره‌ای بتنی با استفاده از شبکه عصبی چند هدفه

نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه مهندسی عمران، دانشکده فنی و مهندسی، دانشگاه مازندران، بابلسر، ایران

2 انستیتوی مشترک دانشگاه میشیگان و دانشگاه شانگهای جیائوتونگ، دانشگاه شانگهای جیائوتونگ، شانگهای، چین

چکیده

دیوارهای گهواره‌ای بتنی به دلیل هزینه‌های خرابی و تعمیر کمتر، یک جایگزین مناسب برای دیوارهای برشی بتنی معمولی هستند. شناخت رفتار دقیق عناصر سازه‌ای به طور کلی با انجام آزمایشات جامع، که پرهزینه و زمان‌بر است، حاصل می‌شود. با توجه به مطالعات پیشین و روند پژوهش در زمینه دیوارهای گهواره‌ای، ضرورت ارائه یک مدل جامع به منظور طراحی دیده می‌شود. ارائه یک مدل تئوری جهت پیش‌بینی رفتار دیوارهای گهواره‌ای بتنی، که پارامترهای متنوعی را شامل شود، امری دشوار می‌باشد و محاسبه همزمان اثر آن پارامترها نیازمند یک مدل جامع است. ارائه چنین مدلی از طریق روش‌های کلاسیک یا عددی، به دلیل پیچیدگی مسئله یا دشواری‌های مدل‌سازی، نیازمند صرف زمان زیاد و محاسبات پیچیده است. اما حل این مسئله به وسیله روش‌های محاسبات نرم امکان ساده‌سازی و تسریع این محاسبات را فراهم می‌سازد. از این رو، این پژوهش با هدف ارائه یک مدل شبکه عصبی چند هدفه برای پیش‌بینی رفتار جانبی دیوارهای گهواره‌ای بتنی انجام شده است. برای ایجاد داده‌های مورد نیاز جهت مدل‌سازی، از نتایج آزمایشگاهی استفاده شد و تمام پارامترهای موثر بر ظرفیت باربری جانبی دیوارهای گهواره‌ای بتنی استخراج شد تا از آنها به عنوان پارامترهای ورودی استفاده شود. سرانجام، منحنی‌های بار جانبی-تغییر مکان و تار خنثی-تغییر مکان به عنوان پارامترهای خروجی پیش‌بینی شدند. علاوه بر این، دقت روابط موجود ارائه شده در آیین‌نامه‌های بتن بین‌المللی و توسعه یافته توسط محققان در پیش‌بینی مقاومت خمشی دیوارهای گهواره‌ای بتنی با استفاده از نتایج آزمایشات انجام شده بر روی این دیوارها بررسی شد. این پژوهش نشان می‌دهد که مدل شبکه عصبی چند هدفه با دقت قابل قبولی رفتار جانبی دیوارهای گهواره‌ای بتنی را پیش‌بینی می‌کند. این مدل قادر است سختی اولیه، سختی ثانویه، مقاومت بیشینه و ظرفیت دورانی را به درستی پیش‌بینی کند. مطابق با نتایج، روابط آیین‌نامه‌های طراحی بتن ایالات متحده (ACI 318-14)، نیوزیلند (NZS 3101) و استرالیا (AS 3600) مقاومت خمشی دیوارهای گهواره‌ای بتنی را در محدوده 0.59 تا 0.99 مقادیر واقعی پیش‌بینی می‌کنند. همچنین، آیین‌نامه طراحی بتن کانادا (CSA-A23.3) پیش‌بینی بسیار محافظه کارانه‌ای از مقاومت خمشی دیوارها ارائه می‌دهد. با وجود این، مدل شبکه عصبی چند هدفه پیش‌بینی‌های بسیار دقیقی را در مقایسه با آیین‌نامه‌های بررسی شده و عبارات موجود نشان داد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Modeling the Lateral Behavior of Concrete Rocking Walls Using Multi-Objective Neural Network

نویسندگان [English]

  • Amir Ali Shahmansouri 1
  • Habib Akbarzadeh Bengar 1
  • Abouzar Jafari 2
1 Department of Civil Engineering, Faculty of Engineering and Technology, University of Mazandaran, Babolsar, Iran
2 University of Michigan and Shanghai Jiao Tong University Joint Institute, Shanghai Jiao Tong University, China
چکیده [English]

Concrete rocking walls (CRWs) are an appropriate alternative for common concrete shear walls due to lower repair and downtime costs. Knowing the exact behavior of structural elements is generally achieved by conducting comprehensive experiments, which are costly and time-consuming. According to previous studies and research trends in the field of rocking walls, it is necessary to provide a comprehensive model for design purposes. It is difficult to provide a theoretical model for predicting the behavior of concrete rocking walls, which includes a variety of parameters, and simultaneous calculation of the effect of those parameters requires a comprehensive model. Providing such a model through classical or numerical methods, due to the complexity of the problem or modeling difficulties, requires much time and complex calculations. However, solving this problem by soft computing methods makes it possible to simplify and speed up these calculations. Therefore, this paper aims to develop a multi-objective neural network (MNN) model to predict the lateral behavior of CRWs. To generate the required data for modeling, experimental results were employed, and all the parameters affecting the lateral bearing capacity of CRWs were extracted to use them as input parameters. Finally, the lateral force-displacement and neutral axis-displacement curves were predicted as the output parameters. Besides, the accuracy of the existing equations presented in international concrete codes and developed by researchers in predicting the flexural strength of CRWs was investigated using the results of experiments performed on these walls. This study shows that the MNN model predicts the lateral behavior of CRWs with acceptable accuracy. This model is able to correctly predict initial stiffness, secondary stiffness, maximum strength, and rotational capacity. According to the results, the terms of the concrete design codes of the United States (ACI 318-14), New Zealand (NZS 3101), and Australia (AS 3600) predict the flexural strength of CRWs in the range of 0.59 to 0.99 actual values. Also, Canada's concrete design code (CSA-A23.3-04) provides a highly unconservative prediction of the walls' flexural strength. Nevertheless, the MNN model showed more accurate predictions in comparison with the investigated codes and existing expressions.

کلیدواژه‌ها [English]

  • Concrete Rocking Walls
  • Multi-Objective Neural Network
  • post-tensioning
  • Lateral Behavior Estimation
[1] Kurama Y, Sause R, Pessiki S, Lu L-W (1999). Lateral load behavior and seismic design of unbonded post-tensioned precast concrete walls. Structural Journal 96 (4):622-632.
[2] Priestley MN, Sritharan S, Conley JR, Pampanin S (1999). Preliminary results and conclusions from the PRESSS five-story precast concrete test building. PCI Journal 44 (6):42-67.
[3] Kurama YC, Sause R, Pessiki S, Lu L-W (2002). Seismic response evaluation of unbonded post-tensioned precast walls. Structural Journal 99 (5):641-651.
[4] Perez FJ, Sause R, Pessiki S (2007). Analytical and experimental lateral load behavior of unbonded posttensioned precast concrete walls. Journal of Structural Engineering 133 (11):1531-1540.
[5] ACI Innovation Task Group 5 (2007) Acceptance criteria for special unbonded post-tensioned precast structural walls based on validation testing. ACI ITG-5.1-07, American Concrete Institute.
[6] ACI Innovation Task Group 5 (2009) Requirements for Design of a Special Unbonded Post-tensioned Precast Shear Wall Satisfying ACI ITG-5.1 (ACI ITG-5.2-09) and Commentary: An ACI Standard. American Concrete Institute.
[7] Hassani B, Jafari A (2012). An investigation on the seismic performance of reinforced concrete panel structures. Asian Journal of Civil Engineering (Building and Housing) 13 (2):181-193.
[8] Zandi Y, Sadeghi M, Jafari A, Keyhani A (2013). Effect of height on the seismic behavior of reinforced concrete bearing wall structural systems with high ductility. Middle East Journal of Scientific Research 14 (10):1345-1353.
[9] Jafari A, Ghasemi MR, Akbarzadeh Bengar H, Hassani B (2016). Modeling of dynamic behavior and estimation of damage incurred by self-centering rocking walls. Journal of Rehabilitation in Civil Engineering 4 (2):93-108.
[10] Azadi Kakavand MR, Khanmohammadi M (2018). Seismic Fragility assessment of local and global failures in low-rise non-ductile existing RC buildings: Empirical shear-axial modelling vs. ASCE/SEI 41 approach. Computational Engineering and Physical Modeling 1 (1):38-57.
[11] Jafari A, Dugnani R (2018). Estimation of Load-Induced Damage and Repair Cost in Post-Tensioned Concrete Rocking Walls. Journal of Shanghai Jiaotong University (Science) 23 (1):122-131.
[12] Jafari A, Ghasemi MR, Bengar HA, Hassani B (2018). A novel method for quantifying damage to cast‐in‐place self‐centering concrete stepping walls. Structural Concrete 19 (6):1713-1726.
[13] Jafari A, Ghasemi MR, Bengar HA, Hassani B (2018). Seismic performance and damage incurred by monolithic concrete self-centering rocking walls under the effect of axial stress ratio. Bulletin of Earthquake Engineering 16 (2):831-858.
[14] Ghoddusi M, Bakhshi H, Khosravi H (2019). Evaluation of seismic behavior of steel shear wall by time history analysis. Computational Engineering and Physical Modeling 2 (1):32-52.
[15] Henry R (2011) Self-centering precast concrete walls for buildings in regions with low to high seismicity. ResearchSpace@ Auckland,
[16] Wight GD (2006) Seismic performance of a post-tensioned concrete masonry wall system. ResearchSpace@ Auckland,
[17] ElGawady M, Booker AJ, Dawood HM (2010). Seismic behavior of posttensioned concrete-filled fiber tubes. Journal of Composites for Construction 14 (5):616-628.
[18] ElGawady MA, Sha’lan A (2011). Seismic behavior of self-centering precast segmental bridge bents. Journal of Bridge Engineering 16 (3):328-339.
[19] Mattock AH, Yamazaki J, Kattula BT Comparative study of prestressed concrete beams, with and without bond. In: Journal Proceedings, 1971. vol 2. pp 116-125.
[20] Hassanli R (2019) Experimental Investigation of Unbonded Post-tensioned Masonry Walls. In:  Behavior of Unbounded Post-tensioned Masonry Walls. Springer, pp 163-194.
[21] Building Seismic Safety Council (2009) NEHRP Recommended Provisions for New Buildings and Other Structures, Part I (Provisions) and Part II (Commentary). FEMA P-750/2009 ed. Washington, DC.
[22] Aaleti S, Sritharan S (2009). A simplified analysis method for characterizing unbonded post-tensioned precast wall systems. Engineering Structures 31 (12):2966-2975.
[23] Hassanli R, ElGawady MA, Mills JE (2016). Force–displacement behavior of unbonded post-tensioned concrete walls. Engineering Structures 106:495-505.
[24] ACI 318 (2019) Building Code Requirements for Structural Concrete and Commentary (ACI 318-19), ACI Committee 318. American Concrete Institute, Farmington Hills, MI.
[25] NZS 3101 (2006) The design of concrete structures. Standards New Zealand, New Zealand.
[26] AS3600 (2009) Australian standard: concrete structures. Standards Australia International, Sydney, Australia.
[27] Canadian Standards Association (2004) CAN CSA A23. 3-04 Design of concrete structures. CSA, Rexdale, Ontario.
[28] Torkian H, Keshavarz Z (2018). Determining the drift in reinforced concrete building using ANFIS soft computing modeling. Computational Engineering and Physical Modeling 1 (1):1-11.
[29] Shahmansouri AA, Bengar HA, Jahani E (2019). Predicting compressive strength and electrical resistivity of eco-friendly concrete containing natural zeolite via GEP algorithm. Construction and Building Materials 229:116883.
[30] Naderpour H, Nagai K, Fakharian P, 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.
[31] Shahmansouri AA, Akbarzadeh Bengar H, Ghanbari S (2020). Experimental investigation and predictive modeling of compressive strength of pozzolanic geopolymer concrete using gene expression programming. Journal of Concrete Structures and Materials 5 (1):92-117.
[32] Kanchidurai S, Krishnan P, Baskar K (2020). Compressive Strength Estimation of Mesh Embedded Masonry Prism Using Empirical and Neural Network Models. Journal of Soft Computing in Civil Engineering 4 (4):24-35.
[33] Shahmansouri AA, Bengar HA, Ghanbari S (2020). Compressive strength prediction of eco-efficient GGBS-based geopolymer concrete using GEP method. Journal of Building Engineering 31:101326.
[34] Hwang S-H, Mangalathu S, Shin J, Jeon J-S (2021). Machine learning-based approaches for seismic demand and collapse of ductile reinforced concrete building frames. Journal of Building Engineering 34:101905.
[35] Naderpour H, Rafiean AH, Fakharian P (2018). Compressive strength prediction of environmentally friendly concrete using artificial neural networks. Journal of Building Engineering 16:213-219.
[36] Mangalathu S, Heo G, Jeon J-S (2018). Artificial neural network based multi-dimensional fragility development of skewed concrete bridge classes. Engineering Structures 162:166-176.
[37] Shahmansouri AA, Yazdani M, Ghanbari S, Bengar HA, Jafari A, Ghatte HF (2020). Artificial neural network model to predict the compressive strength of eco-friendly geopolymer concrete incorporating silica fume and natural zeolite. Journal of Cleaner Production 279:123697.
[38] Abbaszadeh MA, Sharbatdar M (2020). Modeling of Confined Circular Concrete Columns Wrapped by Fiber Reinforced Polymer Using Artificial Neural Network. Journal of Soft Computing in Civil Engineering 4 (4):61-78.
[39] Nematzadeh M, Shahmansouri AA, Zabihi R (2021). Innovative models for predicting post-fire bond behavior of steel rebar embedded in steel fiber reinforced rubberized concrete using soft computing methods. Structures.
[40] Naderpour H, Fakharian P, Rafiean AH, Yourtchi E (2016). Estimation of the shear strength capacity of masonry walls improved with Fiber Reinforced Mortars (FRM) using ANN-GMDH approach. Journal of Concrete Structures and Materials 1 (2):47-59.
[41] Naderpour H, Fakharian P (2016). A synthesis of peak picking method and wavelet packet transform for structural modal identification. KSCE Journal of Civil Engineering 20 (7):2859-2867.
[42] Naderpour H, 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.
[43] Azadi Kakavand MR, Allahvirdizadeh R (2019). Enhanced empirical models for predicting the drift capacity of less ductile RC columns with flexural, shear, or axial failure modes. Frontiers of Structural and Civil Engineering 13 (5):1251-1270.
[44] Jafari A, Johnson S (2019). The inherent power efficiency of continuous tunable stiffness mechanisms. Mechanism and Machine Theory 135:208-224.
[45] Abdulla NA (2020). Using the artificial neural network to predict the axial strength and strain of concrete-filled plastic tube. Journal of Soft Computing in Civil Engineering 4 (2):63-86.
[46] Bengar HA, Shahmansouri AA, Sabet NAZ, Kabirifar K, Tam VW (2020). Impact of elevated temperatures on the structural performance of recycled rubber concrete: Experimental and mathematical modeling. Construction and Building Materials 255:119374.
[47] Azadi Kakavand MR, Taciroglu E (2020). An enhanced damage plasticity model for predicting the cyclic behavior of plain concrete under multiaxial loading conditions. Frontiers of Structural and Civil Engineering 14 (6):1531-1544.
[48] Bengar HA, Shahmansouri AA (2020). A new anchorage system for CFRP strips in externally strengthened RC continuous beams. Journal of Building Engineering 30:101230.
[49] Naderpour H, Eidgahee DR, Fakharian P, Rafiean AH, Kalantari SM (2020). A new proposed approach for moment capacity estimation of ferrocement members using Group Method of Data Handling. Engineering Science and Technology, an International Journal 23 (2):382-391.
[50] Azadi Kakavand MR, Sezen H, Taciroglu E (2021). Data-Driven Models for Predicting the Shear Strength of Rectangular and Circular Reinforced Concrete Columns. Journal of Structural Engineering 147 (1):04020301.
[51] Shahmansouri AA, Bengar HA, AzariJafari H (2021). Life cycle assessment of eco-friendly concrete mixtures incorporating natural zeolite in sulfate-aggressive environment. Construction and Building Materials 268:121136.
[52] Feng D-C, Cetiner B, Azadi Kakavand MR, Taciroglu E (2021). Data-Driven Approach to Predict the Plastic Hinge Length of Reinforced Concrete Columns and Its Application. Journal of Structural Engineering 147 (2):04020332.
[53] Shahmansouri AA, Nematzadeh M, Behnood A (2021). Mechanical properties of GGBFS-based geopolymer concrete incorporating natural zeolite and silica fume with an optimum design using response surface method. Journal of Building Engineering 36:102138.
[54] Chatterjee S, Sarkar S, Hore S, Dey N, Ashour AS, Shi F, Le D-N (2017). Structural failure classification for reinforced concrete buildings using trained neural network based multi-objective genetic algorithm. Structural Engineering and Mechanics 63 (4):429-438.
[55] Moradi MJ, Hariri-Ardebili MA (2019). Developing a library of shear walls database and the neural network based predictive meta-model. Applied Sciences 9 (12):2562.
[56] Khaleghi M, Salimi J, Farhangi V, Moradi MJ, Karakouzian M (2021). Application of Artificial Neural Network to Predict Load Bearing Capacity and Stiffness of Perforated Masonry Walls. CivilEng 2 (1):48-67.