نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی کارشناسی ارشد معماری، دانشکده معماری و شهرسازی، دانشگاه فردوسی مشهد، مشهد، ایران.

2 استادیار، دانشکده معماری و شهرسازی، دانشگاه فردوسی مشهد، مشهد، ایران.

چکیده

امروزه با توجه به گستردگی متغیرهای تاثیرگذار بر طراحی معماری، از کامپیوتر به عنوان ابزاری در تعامل با فرایند طراحی جهت یافتن راه‌حل‌های بهینه و با کارایی بالا استفاده ‌می‌گردد. با توجه به محدودیت‌های موجود در استفاده از این روش‌ها برای طراحان و مطرح بودن طراحی نظام فضایی پلان به عنوان یکی از پرسابقه‌ترین پرچالش‌ترین مسائل طراحی از نظر تعداد پارامترهای تاثیرگذار، در این تحقیق پس از بررسی انتشاراتی که در آن‌ها طراحی نظام فضایی معماری با استفاده از الگوریتم‌های بهینه‌سازی‌ انجام شده‌‌است به شیوه تحلیل محتوای متن و مقایسه دو الگوریتم ژنتیک و بهینه‌سازی انبوه ذرات به عنوان نمایندگان دو گروه از الگوریتم‌های تکاملی در یک مساله‌ی مبنا، الگوریتم بهینه‌سازی انبوه ذرات به دلیل همگرایی سریع تر و کیفیت بالاتر انتخاب گردید. پس از معرفی و بررسی امکانات، محدودیت‌ها و نحوه‌ی کاربرد آن در طراحی نظام فضایی پلان، پیاده‌سازی راهکارعملیاتی آن برای بهینه‌سازی نظام فضایی شامل 1- تعیین اهداف مساله، معیارها و محدودیت‌ها، 2- عددی‌­سازی و کمی­‌کردن معیارها و محدودیت‌ها و 3- تعیین تابع برازندگی و پیاده‌سازی آن در پلتفرم برنامه‌نویسی NET. و به زبان #C همراه با محیط گرافیکی به‌عنوان رابط کاربری جهت تسلط و درک بیشتر کاربران از فرآیند انجام گردید.

تازه های تحقیق

  • پس از مقایسه دو الگوریتم ژنتیک و بهینه‌سازی انبوه ذرات به عنوان نمایندگان دو گروه از الگوریتم‌های تکاملی در یک مساله‌ی مبنا در حوزه نظام فضایی، الگوریتم بهینه‌سازی انبوه ذرات به دلیل همگرایی سریع تر و کیفیت بالاتر انتخاب گردید.
  • پیاده‌سازی راهکارعملیاتی برای بهینه‌سازی نظام فضایی در 3 مرحله 1- تعیین اهداف مساله، معیارها و محدودیت‌ها، 2- عددی‌سازی و کمی‌کردن معیارها و محدودیت‌ها و 3- تعیین تابع برازندگی و پیاده‌سازی انجام گردید.
  • اهداف مساله بهینه‌سازی نظام فضایی در سه حوزه کلی معیارها و محدودیت‌های اولیه، طراح و مخاطبین بررسی گردید و مدل نهایی‌­شده بر اساس الگوریتم بهینه‌سازی انبوه ذرات در پلتفرم برنامه‌نویسی NET. همراه با یک محیط گرافیکی به عنوان رابط کاربری جهت تسلط و درک بیشتر از فرآیند پیاده‎‌سازی شد.

کلیدواژه‌ها

عنوان مقاله [English]

Optimization of planning layout in architecture based on particle swarm optimization algorithm

نویسندگان [English]

  • Maryam Sadeghian 1
  • Akram Hosseini 2

1 M.A of Architecture, Faculty of Architecture and Urbanism, Ferdowsi University of Mashhad, Mashhad, Iran.

2 Assistant Professor, Faculty of Architecture and Urbanism, Ferdowsi University of Mashhad, Mashhad, Iran.

چکیده [English]

Extended Abstract
Objective and Background: Today, due to the wide range of variables affecting architectural design, the computer is used as a tool in interaction with the design process to find optimal and high-performance solutions. Due to the limitations in the use of these methods for designers and the design of the Space Planning as one of the longest challenging design issues in terms of the number of effective parameters, the present study is necessary. Space Planning Design Improving quality in the design and construction of architectural works is a common concern among developing countries; A step that can lead to the promotion of contemporary Iranian architecture. One of the characteristics of the quality of design and construction in the architecture of these countries is the tendencies that seek to improve the quality of architecture by using new technologies.
Methods: The issue of planning architectural spaces as one of the most widely used and at the same time the most complex issues of architectural design has been one of the most challenging issues in recent research. The use of new and technology-dependent methods in design, especially with emphasis on the use of evolutionary algorithms as a solution has been considered in recent research.
The study of the application and how to use these algorithms as a solution for optimization is the main question of this research.
-In research on the application of optimization algorithms in space Planning design, what algorithms have been used as basic or complementary algorithms and what is the rate of use of Swarm Intelligence Algorithms and especially particle swarm optimization algorithm?
- What are the possibilities and limitations in designing an architectural spatial Planning  using genetic algorithm in comparison with the particle swarm optimization algorithm as the main representatives of the two groups of evolutionary algorithms?
- What is the implementation process and application of particle swarm optimization algorithm in the design of architectural space Planning ?
In order to answer the research questions, 35 researches that have been done in the field of using optimization algorithms in designing the architectural spatial Planning have been collected and then by textual content analysis all the variables based on which the architectural plan optimization has been done Extracted and compiled. In the same way, the basic algorithm and if there is a complementary algorithm used was extracted.
Based on the study of specialized sources regarding the evolutionary optimization algorithm from the available bibliographic resources as well as the study of planning requirements and planning of architectural space and how to use genetic algorithm and swarm particle optimization algorithm in designing the architectural space Planning were compiled and explained. The speed and quality of these two algorithms in response to the designed base problem, according to the capability and nature of the software needed to implement the algorithm, the possibilities and limitations of the method in designing architectural plans in an analytical manner and after explaining the objectives of the problem and numerical benchmarks, implementation of software based on particle swarm optimization algorithm using Microsoft Visual Studio programming software and .NET programming platform in C #, with WinodowsForm graphical user interface as a user interface, to further master the understanding of And the obtained results were performed.
Findings: In this research, while introducing optimization algorithms including three categories of Deterministic algorithms, heuristic and metaheuristic, the features of metaheuristic algorithms are introduced, then the application of optimization algorithms in architecture is explained. The background of the application of evolutionary optimization algorithms and swarm particle optimization in the architectural plan design valley is also examined. After comparing the performance of genetic algorithm and particle swarm optimization algorithm in space Planning optimization, the structure of particle swarm optimization algorithm is introduced and the application of this algorithm in plan design is studied and explained. Based on this, it is shown that the application of the algorithm in the design of the plan can be classified into three stages:
In the first stage, determining the goals, criteria and constraints affecting the architectural space system 1. Primary Criteria and constraints 2. Designers Criteria and constraints 3. Contacts (client and users) Criteria and constraints are examined. In the numerization stage, the criteria of land boundary, list of spaces, allowable aspect ratios of spaces, permissible dimensions of spaces, achieving total area, interference of spaces, adjacency of spaces, daylighting of spaces, verification of list of spaces are reduced. Then, in two steps, the algorithm is determined based on the particle swarm optimization algorithm and the implementation platform of the algorithm is determined.
Conclusion: The difficulty of working with programming languages, the need for software skills and the complexity of software due to being designed to answer problems in various scientific fields, make it uncommon to use them as a designer help in controlling the parameters defined by the designer. In this study, the performance of two genetic algorithms and particle swarm optimization as representatives of the two main groups of evolutionary algorithms in a base problem were compared and it was shown that the particle swarm optimization algorithm converges faster and has a higher quality to optimize the plan with Pays attention to the parameters affecting the design of the plan.
Implementation of an operational solution to optimize the spatial Planning of the plan with emphasis on the parameters affecting the formation in the design of architectural plans in a three-step process using this algorithm was proposed. Objectives of the problem are examined in three related areas and the process of numerization and implementation of the final model based on the particle swarm optimization algorithm in the .NET programming platform along with a graphical interface as a user interface for architects to better understand and understand the implementation process. Became; In addition to achieving optimal plans, provide an introduction to future research in this field; Because of the special nature of the field of architecture, the software required to implement the algorithm, visual and operational efficiency are not sufficient and need to be developed and customized for wider application in various fields of design.

کلیدواژه‌ها [English]

  • optimization
  • Space Planning Design
  • Architecture Plan
  • Particle Swarm Optimization Algorithm
گلابچی، م.، اندجی گرمارودی، ع. و باستانی، ح. (1390). معماری دیجیتال: کاربرد فناوری‌های CAD/CAM/CAE در معماری (نسخه چاپ دوم). دانشگاه تهران.
مهدوی‌نژاد، م. ج. (1393). چالش فناوری ‌شکوفایی در‌معماری ‌معاصر کشورهای ‌در ‌حال ‌توسعه. فصل‌نامه علمی پژوهشی نقش جهان، 4(2)، 43-53.
مهدوی نژاد، م. و رفالیان، غ. (1393). معماری الگوریتمی: داده نگاری و روش های پیشرفته برنامه دهی مقداری در فرآیند طراحی معماری معاصر. نشر دانشگاه آزاد اسلامی واحد علوم و تحقیقات.
مردمی، ک.، سهیلی فرد، م. و آقا عزیزی، م. (1394). همسازی سازه و معماری در راستای جانمایی بهینه تکیه گاه ها به روش الگوریتم ژنتیک (نمونه موردی: پوشانه های با فرم آزاد، طراحی شده بر اساس هندسه گره ایرانی). فصلنامه علـمی- پژوهـشی نقش جهان، (2)5، 65-75.
Baghel, M., Agrawal, S., & Silakari, S. (2012). Survey of Metaheuristic Algorithms for Combinatorial Optimization. International Journal of Computer Applications, 58(19), 21 - 31.
Bahrehmand, A., Batard, T., Marques, R., Evans, A., & Blat, J. (2017). Optimizing layout using spatial quality metrics and user preferences. Graphical Models, 93, 25–38.
Banerjee, A., Quiroz, J. C., & Louis, S. J. (2008). A model of creative design using collaborative interactive genetic algorithm. Design Computing and Cognition, 8, 397-416.
Bausys, R., & Pankrašovaite, I. (2005, January). Optimization of architectural layout by the improved genetic algorithm. Civil Engineering and Management, 11(1), 13-21.
Bentley, P. J. (1998). The revolution of evolution in design: from coffee tables. Recent Advances in Soft Computing, (pp. 172–182).
Beyer, K., Goldstein, J., Ramakrishnan, R., & Shaft, U. (1999). When is “Nearest Neighbor” Meaningful? In Proc. 7th Int. Conf. on Database Theory, (pp. 217–235).
Blum, C., & Roli, A. (2003). Metaheuristics in Combinatorial Optimization: Overview. ACM Computing Surveys, Vol. 35, No. 3, 268–308.
Caldas, L., & Norford, L. K. (1999). A Genetic Algorithm Tool for Design Optimization. ACADIA, 99.
Caldas, L., & Norford, L. K. (2002). A design optimization tool based on a genetic algorithm. Automation in Construction 11, 173–184.
Calixto, V., & Celani, G. (2015). A literature review for space planning optimization using an evolutionary algorithm approach: 1992-2014. XIX Congresso da Sociedade Ibero-americana de Gráfica Digital 2015, (pp. 662-671).
Chiu, C.-C., Cheng, Y.-T., & Chang, C.-W. (2012). Comparison of particle swarm optimization and genetic algorithm for the path loss reduction in an urban area. Applied Science and Engineering, 5(4), 371 - 380.
Cichocka, J. M., Migalska, A., Browne, W. N., & Rodriguez, E. (2017). SILVEREYE– the implementation of Particle Swarm Optimization algorithm in a design optimization tool. CAAD Futures 2017, CCIS 724 (pp. 151–169). Springer Nature Singapore Pte Ltd.
Conceição António, C. A., Monteiro, J. B., & Afonso, C. F. (2014, December 5). Optimal topology of urban buildings for maximization of annual solar irradiation availability using a genetic algorithm. Applied Thermal Engineering, 73(1), 424-437.
Cubukcuoglu, C., Chatzikonstantinou, I., Ekici, B., & Sariyildiz , S. (2016). Multi-objective optimization through differential evolution for restaurant design. 2016 IEEE Congress on Evolutionary Computation (CEC) (pp. 2288 - 2295). Vancouver, BC, Canada: IEEE.
Cuevas, E., Barocio, E., Emilio, E., & Arturo, C. (2019). Introduction to Metaheuristics Methods. In Metaheuristics Algorithms in Power Systems (pp. 1 - 8). Springer Nature Switzerland AG 2019.
Datta, S., Roy, S., & Davim, J. (2019). Optimization Techniques: An Overview. In Optimization in Industry (pp. 1 - 13). Springer Nature Switzerland AG 2019.
Dino, I. G., & Üçoluk, G. (2017). Multiobjective Design Optimization of Building Space Layout, Energy, and Daylighting Performance. Journal of Computing in Civil Engineering, 31(5).
Dorigo, M., & Stützle, T. (2019). Ant Colony Optimization: Overview and Recent Advances. International Series in Operations Research & Management Science, 311 - 351.
Doulgerakis, A. (2007). Genetic programming + unfolding embryology in automated layout planning. Msc thesis, Bartlett School of Graduate Studies.
Du, T., Turrin, M., Jansen, S., & van den Dobbelsteen, A. (2018). A Review on Automatic Generation of Architectural Space Layouts with Energy Performance Optimization. 4thInternational Conference On Building Energy, Environmen, (pp. 856 - 861).
Dutta, K., & Sarthak, S. (2011). Architectural space planning. Artificial Intelligence Review December 2011, 311-321.
Elezkurtaj, T., & Franck, G. (1999, September 15-17). Genetic algorithms in support of creative. Architectural Computing from Turing to 2000, 645–651.
Fasoulaki, E. (2007). Genetic Algorithms in Architecture: A Necessity or a Trend? Generative Art Conference. Milan, Italy.
Finucane, E. L., Derix, C., & Coates, P. S. (2006). Evolving urban structures using computer optimization techniques. Generative Art.
Flack, R. W. (2011). Evolution of Architectural Floor Plans. European Conference on the Applications of Evolutionary Computation (pp. 313-322). Applications of Evolutionary Computation.
Gen, M., & Lin, L. (2009). Evolutionary Techniques for Automation. Springer Handbook of Automation, 487-502.
Gero, J. S., & Kazakov, V. A. (1997). Learning and re-using information in space layout planning problems using genetic engineering. Artificial Intelligence in Engineering, 12(3), 163–176.
Hansen, J. M., Raut, S., & Swami, S. (2010). Retail Shelf Allocation: A Comparative Analysis of Heuristic and Meta-Heuristic Approaches. Journal of Retailing 86 (1, 2010), 94–105.
Homayouni, H. (2007). A genetic algorithm approach to space layout planning. MSc thesis; University of Washington.
Homayouni, H. (2007). A Survey of Computational Approaches to Space Layout Planning (1965-2000). Computational Approaches to Space Layout Planning, 1 - 18.
Inoue, M., & Takagi, H. (2008). Layout Algorithm for an EC-based Room. IEEE Conference on Soft Computing in Industrial Applications (pp. 165–170). Muroran, Japan: IEEE.
Jagielski, R., & Gero, J. S. (1997). A genetic programming approach to the space. CAAD Futures, 875–884.
Jo, J. H., & Gero, J.S. (1998). Space layout planning using an evolutionary approach. Artificial Intelligence in Engineering, 12(3), 149-162.
Juneja, M., & Nagar, S. (2016). Particle swarm optimization algorithm and its parameters: A review. 2016 International Conference on Control, Computing, Communication and Materials (ICCCCM). 2016 IEEE.
Karlen, M. (2009). Space Planning Basics. Wiley, London 240.
Knecht, K., & Koenig, R. (2010). Generating floor plan layouts with k-d trees and evolutionary algorithms. GA2010 - 13th Generative Art Conference (pp. 238–253). Politecnico di Milano University, Italy: Domus Argenia Publisher.
Kumar, A., Dutta, K., Gupta, A., Badyal, S., & Rohan, D. (2017). Assisting an architect with alternative automated space layout designs using order crossover Genetic Algorithm in AutoCAD. 2017 International Conference on Advances in Mechanical Industrial, Automation and Management Systems (AMIAMS). 2017 IEEE.
Lawson B. (1980), How Designers Think, The Design Process Demystified. London: Architectural Press.
Li, L. (2012). The optimization of architectural shape based on Genetic Algorithm, Frontiers of Architectural Research. 392 - 399.
Li, Y., Chen, Y., Zhao, M., & Zha, X. (2018). Optimization of Planning Layout of Urban Building Based on Improved Logit and PSO Algorithms. Hindawi, Complexity, Volume 2018.
Liggett, R. S. (2000, March). Automated facilities layout: past, present and future. Automation in Construction, 9(2), 197-215.
Liu, J., Abbass, H. A., & Tan, K. C. (2019). Evolutionary Computation. In Evolutionary Computation and Complex Networks (pp. 1-23). Springer Nature Switzerland AG 2019.
Makris, D., Ioannis, H., Georges, M., & Dimitri, P. (2006). MultiCAD - MOGA: A system for conceptual style design of buildings. International Conference on Computer Graphics and Artificial Intelligence: Conference Proceedings of the 9th, (pp. 73-84).
Michalek, J. J., & Papalambros, P. Y. (2002). Interactive design optimization of architectural layouts. Engineering Optimization, 34(5), 485–501.
Nagy, D., Lau, D., Locke, J., Stoddart, J., Villaggi, L., Wang, R., . . . Benjamin, D. (2017). project Discover: An application of generative design for architectural space planning. Autodesk Research.
Nandanwar, M. K., Zadagaonkar, A. S., & Shukla, A. (2016, Jan - Feb). Path Planning through PSO Algorithm in Complex Environments. International Journal of Computer Science Trends and Technology (IJCST), 4(1).
Nisztuk, M., & Paweł, M. B. (2018). stability of contemporary tools for the computational design of architectural objects: Review, features evaluation and reflection. international Journal of Architectural Computing2018, Vol. 16(1), 58 –84.
Papadaki, I. N., & Chassiakos, A. P. (2016). Multi-objective construction site layout planning using genetic algorithms. Creative Construction Conference 2016, CCC 2016. 164, pp. 20 – 27. Procedia Engineering.
Papapavlou, A., & Turner, A. (2009). Structural evolution: A genetic algorithm method to generate structurally optimal Delaunay triangulated space frames for dynamic loads. 27th eCAADe Conference. Istanbul.
Poblete, B., & de la, C. I. (2011). Algoritmos genéticos como estrategia de diseño en arquitectura. Ph.D. thesis: Universitat Politècnica de Catalunya.
Rahbar, M., Mahdavinejad, M., Bemanian, M., Davaie Markazi , A. H., & Hovestadt, L. (2019). Generating Synthetic Space Allocation Probability Layouts Based on Trained Conditional-GANs. Applied Artificial Intelligence.
RazaviAlavi, S., & AbouRizk, S. (2017). Site Layout and Construction Plan Optimization Using an Integrated Genetic Algorithm Simulation Framework. Journal of Computing in Civil Engineering, 31(4), 04017011-1 - 04017011-10.
Rodrigues, E., Gaspa, A. R., & Gomes, A. (2013). Evolutionary strategy enhanced with a local search technique for the space allocation problem in architecture Part 1: Methodology. Computer-Aided Design.
Rosenman, M. A. (1997). The generation of form using an evolutionary. Evolutionary algorithms in engineering applications, 69–85.
Schnier, T., & Gero, J. S. (1996). Learning Genetic Representations as Alternative to Hand-Coded Shape Grammars. Artificial Intelligence in Design ’96, 39–57.
Shi, Y., & Eberhart, R. C. (1998). A modified particle swarm optimizer. 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360). Anchorage, AK, USA, USA: IEEE.
Soddu, C. (2005). Visionary Variations of Milano.
Sönmez, N. O. (2015). Architectural Layout Evolution Through Similarity-Based Evaluation. international journal of architectural computing, 13(3+4), 271 – 279.
Sowmya, B., & Mp, S. R. (2013, August). Minimization of Floor planning Area and Wire Length Interconnection Using Particle Swarm Optimization. International Journal of Emerging Technology and Advanced Engineering, 3(8), 321-330.
Su, Z., & Yan, W. (2015, November). A fast genetic algorithm for solving architectural design optimization problems. Artificial intelligence for engineering design analysis and manufacturing, 29(4), 457- 469.
Talbourdet, F., Michel, P., Andrieux, F., & Millet, J.-R. A knowledge-aid approach for designing high-performance buildings. Building Simulation, 6(4), 337–350.
Thakur, M. K., Kumari, M., & Das, M. (2010). Architectural layout planning using genetic algorithms. 3rd International Conference on Computer Science and Information Technology 2010. 4, pp. 5–11. IEEE.
Virirakis, L. (2003). GENETICA: A computer language that supports general formal expression with evolving data structures. Transactions on Evolutionary Computation, 7(5), 456–481.
Wang, B., & Malkawi, A. (2015). Genetic algorithm based building form optimization study for natural ventilation potential. 14th Conference of International Building Performance Simulation Association, (pp. 640 – 647). Hyderabad, India.
Wang, W., Rivard, H., & Zmeureanu, R. (2006, o). Floor shape optimization for green building design. Advanced Engineering Informatics, 20(4), 363-378.
Wetter, M., & Wright, J. (2004). A comparison of deterministic and probabilistic optimization algorithms for nonsmooth simulation-based optimization. Building and Environment, 39(8), 989-999.
Wong, S. S., & Chan, K. C. (2009, September). EvoArch: An evolutionary algorithm for architectural layout design. Computer-Aided Design, 41(9), 649-667.
Yang, X.-S., & Karamanoglu, M. (2013). 1 - Swarm Intelligence and Bio-Inspired Computation: An Overview. Swarm Intelligence and Bio-Inspired Computation-Theory and Applications, 3-23.
Zhang, X., & Shiu, Y. Y. (2015, May). A directional mutation operator for differential evolution algorithms. Applied Soft Computing, 30, 529-548.