基于模型预测控制的多钢筋并行排布智能深化设计方法

doi:10.19678/j.issn.1000-3428.0067854

摘要/Abstract

摘要：

传统钢筋深化设计的大量排布工作是基于手动或半自动化的方式完成的, 时间及人工成本较高。目前基于单根钢筋的智能设计方法存在3个问题: 同向钢筋没有共享机制, 无法利用相似信息, 造成大量重复性计算; 钢筋之间不具备协同机制, 无法保证钢筋前后左右间距的一致性; 优化策略基于局部信息进行智能体轨迹规划, 难以应对复杂和特殊的钢筋排布场景。为解决上述问题, 提出基于模型预测控制(MPC)的多钢筋并行排布智能设计方法, 以提高钢筋的排布效率及质量。MPC是一种可以兼顾全局信息和局部信息的寻优策略, 通过滚动优化和最优解首元素的应用, 提高钢筋应对复杂环境的能力, 实现钢筋智能避障和长度优化。多钢筋并行排布策略采用领航跟随者模式实现信息共享和行为协同, 利用同向钢筋的相似信息, 可减少重复性工作并保证钢筋间距一致。为提高优化效率和质量, 结合群体智能的优点进一步改进差分进化算法, 并将其作为MPC的求解器。实验结果表明, 通过与单钢筋排布方法在不同障碍物情形下的对比, 提出的多钢筋并行排布方法能够有效提高钢筋排布的质量、优化效率和应对复杂障碍物场景, 并以预制混凝土楼梯构件设计为示例, 验证了所提方法的可行性和有效性。

关键词: 智能建造, 深化设计, 智能优化设计, 钢筋排布, 模型预测控制, 进化算法

Abstract:

A significant portion of the layout work in traditional rebar deepening relies on manual or semi-automated methods, incurring high time and labor costs. The current intelligent design method based on a single rebar faces three primary issues: first, there is no sharing mechanism for same-direction rebars, preventing the use of similar information and resulting in numerous repetitive calculations; second, there is no synergistic mechanism between rebars, failing to ensure the consistency of front-back and left-right spacing; and third, the optimization strategy relies on local information for planning the intelligent body trajectory, making it difficult to handle complex and special rebar placement scenarios. To address these problems, an intelligent design method based on Model Predictive Control (MPC) is proposed for a parallel layout of multiple rebars to enhance the efficiency and quality of the rebar layout. MPC is an optimization strategy that considers both global and local information. Hence, it improves the ability of rebars to navigate complex environments through rolling optimization and optimal solution head elements to realize intelligent obstacle avoidance and length optimization of steel bars. The multiple rebar parallel layout strategy employs the leader-follower model for information sharing and behavioral collaboration, leveraging similar information about rebars in the same direction to reduce repetitive work and ensure consistent rebar spacing. To further improve the optimization efficiency and quality, the differential evolutionary algorithm is enhanced by incorporating the benefits of group intelligence and is used as a solver for MPC. By comparing this method with the single rebar layout method in various obstacle scenarios, experimental results demonstrate that the proposed multiple rebar parallel layout method effectively improves the rebar layout quality, optimizes efficiency, and handles complex obstacle scenarios. The feasibility and effectiveness of this method are validated using the design of prefabricated concrete staircase components as an example.

Key words: smart construction, detailed design, intelligent optimal design, rebar layout, Model Predictive Control(MPC), evolutionary algorithm

齐宏拓, 伍洲, 周绪红, 李盛, 许成然, 郑晓磊, 刘界鹏, 廖耘竹. 基于模型预测控制的多钢筋并行排布智能深化设计方法[J]. 计算机工程, 2024, 50(9): 333-343.

QI Hongtuo, WU Zhou, ZHOU Xuhong, LI Sheng, XU Chengran, ZHENG Xiaolei, LIU Jiepeng, LIAO Yunzhu. Intelligent Detailed Design Method of Parallel Layouts of Multiple Rebars Based on Model Predictive Control[J]. Computer Engineering, 2024, 50(9): 333-343.

https://www.ecice06.com/CN/Y2024/V50/I9/333

图/表 20

图1 分步优化示意图

Fig.1 Schematic diagram of decomposition optimization

图2 MPC算法示意图

Fig.2 Schematic diagram of MPC algorithm

图3 x轴方向框架梁示意图

Fig.3 Schematic diagram of frame beam in x axis direction

图4 梁和柱截面钢筋间距示意图

Fig.4 Schematic diagram of steel bar spacing between beam and column section

图5 层级划分及分类

Fig.5 Level division and classification

图6 多钢筋并行策略

Fig.6 Parallel strategy of multiple rebars

图7 行为组合策略

Fig.7 Behavioral combination strategy

图8 多钢筋并行排布流程

Fig.8 Procedure of multi-rebar parallel layout

图9 钢筋混凝土梁的尺寸和边界信息

Fig.9 Dimensions and boundary information of reinforced concrete beams

图10 Z轴障碍物场景下钢筋排布轨迹

Fig.10 Rebar layout trajectory for the Z axis obstacle scenario

图11 X轴和Z轴障碍物场景下钢筋排布轨迹

Fig.11 Rebar layout trajectory for the X, Z axis obstacle scenario

图12 不同策略下钢筋排布轨迹

Fig.12 Rebar layout trajectory for different strategies

图13 特殊障碍物场景

Fig.13 Special obstacle scenarios

图14 特殊障碍物场景下钢筋排布轨迹

Fig.14 Rebar layout trajectory for special obstacle scenarios

图15 预制混凝土楼梯示意图

Fig.15 Schematic diagram of prefabricated concrete stair

图16 预制楼梯中的钢筋与预埋件布置示意图

Fig.16 Schematic diagram of rebars and embedded parts layout in the prefabricated stair

图17 预制楼梯上下部钢筋并行排布结果

Fig.17 Results of parallel arrangement of rebars at the upper and lower parts of prefabricated stairs

参考文献 29

1	TABESH A R, STAUB-FRENCH S. Case study of constructability reasoning in MEP coordination[C]//Proceedings of Construction Research Congress. Honolulu, USA: American Society of Civil Engineers, 2005: 1-10.
2	STAUB-FRENCH S, KHANZODE A. 3D and 4D modeling for design and construction coordination: issues and lessons learned. Electronic Journal of Information Technology in Construction, 2007, 12, 381- 407.
3	MANGAL M, CHENG J C P, WANG Q. Automated clash resolution of steel rebar in RC beam-column joints using BIM and GA[C]//Proceedings of International Symposium on Automation and Robotics in Construction and Mining. Honolulu, USA: American Society of Civil Engineers, 2017: 37-43.
4	李佐军, 刘世斌, 都书巍, 等. BIM技术在钢筋工程方面的应用. 建筑技术开发, 2019, 46 (20): 99- 100. URL
	LI Z J, LIU S B, DU S W, et al. Application of BIM technology in reinforcement engineering. Building Technology Development, 2019, 46 (20): 99- 100. URL
5	AZHAR S, BROWN J. BIM for sustainability analyses. International Journal of Construction Education and Research, 2009, 5 (4): 276- 292. doi: 10.1080/15578770903355657
6	LI M K, LIU Y H, WONG B C L, et al. Automated structural design optimization of steel reinforcement using graph neural network and exploratory genetic algorithms. Automation in Construction, 2023, 146, 104677. doi: 10.1016/j.autcon.2022.104677
7	LIU P K, QI H T, LIU J P, et al. Automated clash resolution for reinforcement steel design in precast concrete wall panels via generative adversarial network and reinforcement learning. Advanced Engineering Informatics, 2023, 58, 102131. doi: 10.1016/j.aei.2023.102131
8	LECUN Y, BENGIO Y, HINTON G. Deep learning. Nature, 2015, 521 (7553): 436- 444. doi: 10.1038/nature14539
9	SCHMIDHUBER J. Deep learning in neural networks: an overview. Neural Networks, 2015, 61, 85- 117. doi: 10.1016/j.neunet.2014.09.003
10	PARK M G, JEON J H, LEE M C. Obstacle avoidance for mobile robots using artificial potential field approach with simulated annealing[C]//Proceedings of IEEE International Symposium on Industrial Electronics Proceedings. Washington D. C., USA: IEEE Press, 2001: 1257-1266.
11	YANG L, QI J, XIAO J. A literature review of USA 3d path planning[C]//Proceedings of the 11th World Congress on Intelligent Control and Automation. Shenyang, China: [s. n. ], 2015: 458-466
12	WHITLEY D. An overview of evolutionary algorithms: practical issues and common pitfalls. Information and Software Technology, 2001, 43 (14): 817- 831. doi: 10.1016/S0950-5849(01)00188-4
13	BÄCK T, SCHWEFEL H P. An overview of evolutionary algorithms for parameter optimization. Evolutionary Computation, 1993, 1 (1): 1- 23. doi: 10.1162/evco.1993.1.1.1
14	LIU J P, LIU P K, FENG L, et al. Automated clash resolution for reinforcement steel design in concrete frames via Q-learning and building information modeling. Automation in Construction, 2020, 112, 103062. doi: 10.1016/j.autcon.2019.103062
15	CLIFTON J, LABER E. Q-learning: theory and applications. Annual Review of Statistics and Its Application, 2020, 7, 279- 301. doi: 10.1146/annurev-statistics-031219-041220
16	LIU J P, XU C R, WU Z, et al. Intelligent rebar layout in RC building frames using artificial potential field. Automation in Construction, 2020, 114, 103172. doi: 10.1016/j.autcon.2020.103172
17	LIU J P, LI S, XU C R, et al. Automatic and optimal rebar layout in reinforced concrete structure by decomposed optimization algorithms. Automation in Construction, 2021, 126, 103655. doi: 10.1016/j.autcon.2021.103655
18	CAMACHO E F, BORDONS C. Model predictive control[M]. London, UK: Springer, 2007.
19	GARCÍA C E, PRETT D M, MORARI M. Model predictive control: theory and practice-a survey. Automatica, 1989, 25 (3): 335- 348. doi: 10.1016/0005-1098(89)90002-2
20	CAMPONOGARA E, JIA D, KROGH B H, et al. Distributed model predictive control. IEEE Control Systems, 2002, 22 (1): 44- 52. doi: 10.1109/37.980246
21	CHEN Y Q, WANG Z M. Formation control: a review and a new consideration[C]//Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. Washington D. C., USA: IEEE Press, 2005: 453-464.
22	伍锡如, 邢梦媛. 分数阶多机器人的领航-跟随型环形编队控制. 控制理论与应用, 2021, 38 (1): 103- 109. URL
	WU X R, XING M Y. Annular formation control of the leader-follower multi-robot based on fractional order. Control Theory & Applications, 2021, 38 (1): 103- 109. URL
23	GARRIDO S, MORENO L, GÓMEZ J V, et al. General path planning methodology for leader-follower robot formations. International Journal of Advanced Robotic Systems, 2013, 10 (1): 64. doi: 10.5772/53999
24	程适, 王锐, 伍国华, 等. 群体智能优化算法. 郑州大学学报(工学版), 2018, 39 (6): 1- 2. URL
	CHENG S, WANG R, WU G H, et al. Swarm intelligence optimization algorithms. Journal of Zhengzhou University (Engineering Science), 2018, 39 (6): 1- 2. URL
25	MARTÍNEZ-MUÑOZ D, GARCÍA J, MARTÍ J V, et al. Discrete swarm intelligence optimization algorithms applied to steel—concrete composite bridges. Engineering Structures, 2022, 266, 114607. doi: 10.1016/j.engstruct.2022.114607
26	ZUO Z Q, YANG X, ZHANG Z C, et al. Lane-associated MPC path planning for autonomous vehicles[C]//Proceedings of 2019 Chinese Control Conference. Washington D. C., USA: IEEE Press, 2019: 6627-6632.
27	ROBERGE V, TARBOUCHI M, LABONTE G. Comparison of parallel genetic algorithm and particle swarm optimization for real-time UAV path planning. IEEE Transactions on Industrial Informatics, 2013, 9 (1): 132- 141. doi: 10.1109/TII.2012.2198665
28	STORN R, PRICE K. Differential evolution: a simple and efficient heuristic for global optimization over continuous spaces. Journal of Global Optimization, 1997, 11 (4): 341- 359. doi: 10.1023/A:1008202821328
29	刘波, 王凌, 金以慧. 差分进化算法研究进展. 控制与决策, 2007, 22 (7): 721- 729. URL
	LIU B, WANG L, JIN Y H. Advances in differential evolution. Control and Decision, 2007, 22 (7): 721- 729. URL

[1]	郑锦灿, 邵立珍, 雷雪梅. 基于改进MOEA/D的模糊柔性作业车间调度算法[J]. 计算机工程, 2024, 50(6): 336-345.
[2]	万昊楠, 吴飞, 尹玲. 基于自适应无人机数量的节时部署优化算法[J]. 计算机工程, 2024, 50(10): 302-312.
[3]	蔡倩倩, 史旭华. 自适应迁移的分解多目标多任务进化算法[J]. 计算机工程, 2023, 49(7): 55-64.
[4]	褚跃跃, 闫飞, 李浦. 含扰动迭代学习补偿的城市交通信号预测控制方法[J]. 计算机工程, 2023, 49(7): 305-312.
[5]	郑丽萍, 赵玉娟, 费选. 基于改进MOEA/D的车联网通信资源分配算法[J]. 计算机工程, 2023, 49(5): 191-197.
[6]	伍洲, 杨寒石, 邬俊俊, 张海军, 宋晴. 进化迁移优化算法综述[J]. 计算机工程, 2023, 49(1): 1-14.
[7]	邱鸿辉, 刘海林, 陈磊. 基于协方差矩阵调整的多目标多任务优化算法[J]. 计算机工程, 2022, 48(8): 306-312.
[8]	生龙, 袁丽娜, 武南南, 姬少培. 基于GSA与DE优化混合核ELM的网络异常检测模型[J]. 计算机工程, 2022, 48(6): 146-153.
[9]	于成龙, 付国霞, 孙超利, 张国晨. 全局与局部模型交替辅助的差分进化算法[J]. 计算机工程, 2022, 48(3): 115-123.
[10]	谢艺蓉, 马永杰. 基于进化ResNet的交通标志识别[J]. 计算机工程, 2022, 48(10): 262-269.
[11]	倪水平, 戚海涛, 李慧芳. 基于多种群遗传与思维进化的混合算法[J]. 计算机工程, 2021, 47(12): 62-70.
[12]	王烁, 谷正气, 韩征彤, 马晓骙. 基于改进离散差分进化算法的桁架优化[J]. 计算机工程, 2021, 47(1): 275-283.
[13]	尚迪雅, 孙华, 洪振厚, 曾庆亮. 基于无梯度进化的神经架构搜索算法研究综述[J]. 计算机工程, 2020, 46(9): 16-26.
[14]	施元昊, 张健铭, 徐正蓺, 滕国伟. 多运动模式下的累积误差修正行人航位推算算法[J]. 计算机工程, 2020, 46(12): 305-312.
[15]	李明, 胡江平. 异构传感器网络中基于差分进化的调度算法[J]. 计算机工程, 2019, 45(9): 70-75.

选择文件类型/文献管理软件名称

选择包含的内容