Recent progress on data-driven concrete material-structure integrated design

被引：0
|
作者：
Hu Z. [1 ]
Liu J. [1 ]
Zhao Y. [2 ]
Zhao H. [3 ]
Qi J. [4 ]
Wang Y. [5 ]
Han F. [5 ]
Jin M. [1 ]
机构：
[1] School of Materials Science and Engineering, Southeast University, Nanjing
[2] School of Architecture and Engineering, Zhejiang University, Hangzhou
[3] School of Civil Engineering and Transportation, Hohai University, Nanjing
[4] School of Civil Engineering, Southeast University, Nanjing
[5] Jiangsu Research Institute of Building Science Co., Ltd, Nanjing
来源：
Jianzhu Jiegou Xuebao/Journal of Building Structures | 2024年 / 45卷 / 08期
关键词：
crack resistance; data-driven; durability; high performance; material-structure integrated design;
D O I：
10.14006/j.jzjgxb.2023.0755
中图分类号：
学科分类号：
摘要：
Material-structure integrated design is to consider the material performance in structural design and to originate the material design from the requirements of the structure, forming a multi-scale design from materials to structures, which is a research focus in concrete constructions in recent years. The design of concrete materials and structures based on data and artificial intelligence algorithms subverts the traditional paradigm of relying on experience and requiring repeated trials, improving effeiciency in material design and structural innovation. This study reviewed the current research on the intelligent design of concrete materials and integrated design of material and structure. The research scope and key issues of data-driven properties prediction and design at the material level was summarized first. The strategies and effects of crack resistance material-structure integrated design considering complex interactions of temperature, humidity and constraint was discussed. The method for durability design and the improving measures using chloride diffusion as an example were described. The method of high-performance design using ultra-high performance concrete as an example was also explained. Finally, the framework for future data-driven material-structure integrated design as well as a comprehensive research concept including material production, design, preparation and structural application were proposed. The further studies should focus on database construction, knowledge-informed machine learning algorithms and multi-scale correlation. © 2024 Science Press. All rights reserved.
引用
收藏
页码：20 / 33
页数：13
相关论文
共 87 条
  • [1] HIMANEN L, GEURTS A, FOSTER A S, Et al., Data-driven materials science: status, challenges, and perspectives[J ], Advanced Science, 6, 21, (2019)
  • [2] DE PABLO J J, JONES B, KOVACS C L, Et al., The materials genome initiative, the interplay of experiment, theory and computation [J ], Current Opinion in Solid State and Materials Science, 18, 2, pp. 99-117, (2014)
  • [3] ZHAO H, LI X, ZHANG Y, Et al., Perspective: NanoMine: a material genome approach for polymer nanocomposites analysis and design, APL Materials, 4, 5, (2016)
  • [4] SCHLEDER G R, PADILHA A C M, ACOSTA C M, Et al., From DFT to machine learning: recent approaches to materials science:a review, Journal of Physics: Materials, 2, 3, (2019)
  • [5] DIMA A, BHASKARLA S, BECKER C, Et al., Informatics infrastructure for the materials genome initiative, JOM, 68, 8, pp. 2053-2064, (2016)
  • [6] ZHANG Wenhua, Application of expert system in material processing field, Science and Technology of Overseas Building Materials, 2, pp. 1-6, (2000)
  • [7] FAN D, ZHU J, FAN M, Et al., Intelligent design and manufacturing of ultra-high performance concrete (UHPC): a review, Construction and Building Materials, 385, (2023)
  • [8] BUI D K, NGUYEN T, CHOU J S, Et al., A modified firefly algorithm-artificial neural network expert system for predicting compressive and tensile strength of high-performance concrete, Construction and Building Materials, 180, pp. 320-333, (2018)
  • [9] Specification for design of highway reinforced concrete and prestressed concrete bridges and culvcrts: JTG 3362—2018, (2018)
  • [10] LIU J, XIA Y., A hybrid intelligent genetic algorithm for truss optimization based on deep neutral network, Swarm and Evolutionary Computation, 73, (2022)
123456789