طراحی بهینه سازه های فضاکار با در نظر گرفتن سختی اتصالات با استفاده از مدل جایگزینی مبتنی بر یادگیری ماشین

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشکده مهندسی عمران، دانشگاه علم و صنعت ایران، تهران، ایران

2 دانشکده مهندسی عمران، دانشگاه علم و صنعت ایران، تهران، ایران.

چکیده

در این پژوهش، طراحی بهینه سازه‌های فضاکار با در نظر گرفتن سختی واقعی اتصالات به کمک یک مدل جایگزینی مبتنی بر الگوریتم یادگیری ماشین صورت گرفته است. سازه‌های فضاکار به عنوان یکی از مهم‌ترین انواع سازه‌های سبک و مقاوم، اغلب دارای اتصالاتی با رفتار نیمه‌صلب هستند که در طراحی‌های متداول به صورت ایده‌آل صلب یا مفصلی در نظر گرفته می‌شوند. این فرض غیرواقعی می‌تواند منجر به افزایش وزن سازه یا افزایش هزینه‌های اجرایی شود. بنابراین، لحاظ کردن سختی واقعی اتصالات در طراحی بهینه می‌تواند به کاهش وزن کلی سازه و افزایش کارایی آن منجر شود. از آنجا که محاسبه دقیق وزن سازه شامل هزینه‌های مرتبط با اتصالات نیز ضروری است و حدود ۱۵ تا ۴۵ درصد از وزن کل سازه را تشکیل می‌دهد، در این پژوهش وزن اتصالات نیز در تابع هدف لحاظ شده است. به منظور کاهش هزینه‌های محاسباتی، از یک مدل جایگزینی مبتنی بر الگوریتم یادگیری ماشین استفاده شده است. همچنین، به منظور افزایش دقت و کارایی مدل جایگزینی، از یک روش یادگیری فعال برای انتخاب هوشمندانه داده‌های آموزشی استفاده شده است. نتایج حاصل نشان می‌دهد که روش پیشنهادی با تعداد تحلیل‌های کمتری نسبت به الگوریتم فراابتکاری قادر به یافتن جواب بهینه است. طبق نتایج مشاهده شد که سازه‌های فضاکار ۸۰۰ عضوی و ۱۰۱۶ عضوی دارای اتصالات نیمه‌صلب به ترتیب 4.25 و 14.48 درصد وزن کمتری نسبت به سازه‌های دارای اتصالات مفصلی و صلب دارند.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Optimal Design of Space Structures Considering Connection Stiffness Using a Machine Learning Based Surrogate Model

نویسندگان [English]

  • Majid Ilchi Ghazaan 1
  • Mostafa Sharifi 2
  • Sevim Rahimbaksh Khiabani 2
1 School of Civil Engineering, Iran University of Science and Technology, Tehran, Iran
2 School of Civil Engineering, Iran University of Science and Technology, Tehran, Iran.
چکیده [English]

In this research, the optimal design of space structures considering the actual stiffness of connections is performed using a surrogate model based on a machine learning algorithm. Space structures, as one of the most important types of lightweight and robust structural systems, often have semi-rigid connections whose behavior is conventionally idealized as either rigid or pinned. This unrealistic assumption can lead to an increase in structural weight or construction costs. Therefore, incorporating the actual stiffness of connections into the optimal design process can result in reduced overall structural weight and improved efficiency. Since accurately calculating the total structural weight including the weight and costs associated with connections, which account for approximately 15 to 45 percent of the total weight is essential, connection weight has also been included in the objective function. To reduce computational costs, a surrogate model based on a machine learning algorithm is employed. Moreover, to enhance the accuracy and efficiency of the surrogate model, an active learning method is used for the intelligent selection of training data. The results indicate that the proposed method is capable of finding optimal solutions with fewer analyses compared to metaheuristic algorithms. According to the results, 800-member and 1016-member space structures with semi-rigid connections have 4.25% and 14.48% less weight, respectively, compared to structures with pinned and rigid connections.

کلیدواژه‌ها [English]

  • Space Structures
  • Connection Stiffness
  • Optimization
  • Surrogate Models
  • Active Learning

مراجع

[1] Stelmack TW, Marley MJ, Gerstle KH. Analysis and tests of flexibly connected steel frames. Journal of Structural Engineering. 1986 Jul; 112(7): 1573-1588. doi: 10.1061/(ASCE)0733-9445(1986)112:7(1573)
[2] Shin MK, Park KJ, Park GJ. Optimization of structures with nonlinear behavior using equivalent loads. Computer Methods in Applied Mechanics and Engineering. 2007 Jan 1; 196(4-6): 1154-1167. doi: 10.1016/j.cma.2006.09.001
[3] Kaveh A, Zolghadr A. Democratic PSO for truss layout and size optimization with frequency constraints. Computers & Structures. 2014 Jan 1; 130: 10-21. doi: 10.1016/j.compstruc.2013.09.002
[4] Toğan V, Daloğlu AT. Optimization of 3d trusses with adaptive approach in genetic algorithms. Engineering Structures. 2006 Jun 1; 28(7): 1019-1027. doi: 10.1016/j.engstruct.2005.11.007
[5] Dorigo M, Stützle T. The ant colony optimization metaheuristic: Algorithms, applications, and advances. Handbook of metaheuristics. 2003 Jan 31: 250-285. doi: 10.1007/0-306-48056-5_9
[6] Kaveh A, Ghazaan MI. Enhanced whale optimization algorithm for sizing optimization of skeletal structures. Mechanics Based design of structures and Machines. 2017 Jul 3; 45(3): 345-362. doi: 10.1080/15397734.2016.1213639 
[7] Diwekar UM, Gebreslassie BH. Efficient ant colony optimization (EACO) algorithm for deterministic optimization. International Journal of Swarm Intelligence and Evolutionary Computation. 2016 Mar. doi: 10.4172/2090-4908.1000131
[8] Miguel LF, Miguel LF. Shape and size optimization of truss structures considering dynamic constraints through modern metaheuristic algorithms. Expert Systems with Applications. 2012 Aug 1; 39(10): 9458-9467. doi: 10.1016/j.eswa.2012.02.113 
[9] Lee KS, Geem ZW. A new structural optimization method based on the harmony search algorithm. Computers & structures. 2004 Apr 1; 82(9-10): 781-798. doi: 10.1016/j.compstruc.2004.01.002 
[10] Maheri MR, Narimani MM. An enhanced harmony search algorithm for optimum design of side sway steel frames. Computers & Structures. 2014 May 1; 136: 78-89. doi: 10.1016/j.compstruc.2014.02.001 
[11] Ho-Huu V, Vo-Duy T, Luu-Van T, Le-Anh L, Nguyen-Thoi T. Optimal design of truss structures with frequency constraints using improved differential evolution algorithm based on an adaptive mutation scheme. Automation in Construction. 2016 Aug 1; 68: 81-94. doi: 10.1016/j.autcon.2016.05.004 
[12] Degertekin SO. Improved harmony search algorithms for sizing optimization of truss structures. Computers & Structures. 2012 Feb 1; 92: 229-241. doi: 10.1016/j.compstruc.2011.10.022 
[13] Pham HA. Truss optimization with frequency constraints using enhanced differential evolution based on adaptive directional mutation and nearest neighbor comparison. Advances in Engineering Software. 2016 Dec 1; 102: 142-154. doi: 10.1016/j.advengsoft.2016.10.004 
[14] Hosseini P, Hatami N, Hoseini Vaez SR. Reliability-Based Optimum Design of Dome Truss Structures through Enhanced Vibration Particle System. Journal of Rehabilitation in Civil Engineering. 2023 Aug 1; 11(3): 47-67. doi: 10.22075/jrce.2022.26341.1615 
[15] Paknahd M, Hosseini P, Kaveh A, Hakim SJ. A Self-Adaptive Enhanced Vibrating Particle System Algorithm for Structural Optimization: Application to Iscso Benchmark Problems. Int. J. Optim. Civil Eng. 2025; 15(1): 111-130. 
[16] Haji Mazdarani MJ, Hoseini Vaez SR, Hosseini P, Fathali MA. Reliability-based layout optimization of concentrically braced in 3D steel frames. In Structures. 2023 Jan 1; 47, 1094-1112. doi: 10.1016/j.istruc.2022.11.130 
[17] Hosseini P, Kaveh A, Fathali MA, Hoseini Vaez SR. A two-loop RBDO approach for steel frame structures using EVPS, GWO, and Monte Carlo simulation. Mechanics of Advanced Materials and Structures. 2025 Feb 16; 32(4): 605-624. doi: 10.1080/15376494.2024.2352800 
[18] Hajela P, Berke L. Neural networks in structural analysis and design: an overview. Computing Systems in Engineering. 1992 Jan 1; 3(1-4): 525-538. doi: 10.1016/0956-0521(92)90138-9 
[19] Salajegheh E, Gholizadeh S. Optimum design of structures by an improved genetic algorithm using neural networks. Advances in Engineering Software. 2005 Nov 1; 36(11-12): 757-767. doi: 10.1016/j.advengsoft.2005.03.022 
[20] Kaveh A. Applications of artificial neural networks and machine learning in civil engineering. Cham, Switzerland: Springer; 2024 Jul 29. doi: 10.1007/978-3-031-66051-1 
[21] Naderpour H, Hoseini Vaez SR, Malekshahi N. Predicting the behavior of concrete dams using artificial neural networks (case study of Dez dam). Civil Infrastructure Researches. 2021 Feb 19; 6(2): 123-132. doi: 10.22091/cer.2021.6898.1242 [In Persian]
[22] Monforton GR. Matrix analysis of frames with semi-rigid connections. 
[23] Lu M, Ye J. Guided genetic algorithm for dome optimization against instability with discrete variables. Journal of Constructional Steel Research. 2017 Dec 1; 139: 149-156. doi: 10.1016/j.jcsr.2017.09.019 
[24] Seifi H, Xie YM, O’Donnell J, Williams N. Design and fabrication of structural connections using bi-directional evolutionary structural optimization and additive manufacturing. Applied Mechanics and Materials. 2016 Sep 18; 846: 571-576. doi: 10.4028/www.scientific.net/AMM.846.571 
[25] Truong VH, Kim SE. A robust method for optimization of semi-rigid steel frames subject to seismic loading. Journal of Constructional Steel Research. 2018 Jun 1; 145: 184-195. doi: 10.1016/j.jcsr.2018.02.025 
[26] Chen T, Guestrin C. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. 2016 Aug 13; 785-794. doi: 10.1145/2939672.2939785 
[27] Kaveh A, Ghazaan MI. Meta-heuristic algorithms for optimal design of real-size structures. Switzerland: Springer International Publishing; 2018 Apr 10. doi: 10.1007/978-3-319-78780-0 
[28] Mohammadi-Balani A, Nayeri MD, Azar A, Taghizadeh-Yazdi M. Golden eagle optimizer: A nature-inspired metaheuristic algorithm. Computers & Industrial Engineering. 2021 Feb 1; 152: 107050. doi: 10.1016/j.cie.2020.107050 
ارسال نظر در مورد این مقاله
CAPTCHA Image
پژوهش های زیرساخت های عمرانی

مقالات آماده انتشار، پذیرفته شده
انتشار آنلاین از تاریخ 25 مرداد 1404

فایل ها

هم رسانی

ارجاع به این مقاله

آمار