Roles of artificial intelligence in construction engineering and management: A critical review and future trends

被引:590
作者
Pan, Yue [1 ]
Zhang, Limao [1 ]
机构
[1] Nanyang Technol Univ, Sch Civil & Environm Engn, 50 Nanyang Ave, Singapore 639798, Singapore
关键词
Artificial intelligence; Construction engineering and management; Critical review; NEURAL-NETWORK MODEL; BUILDING ENERGY-CONSUMPTION; SUPPORT VECTOR REGRESSION; FAULT-TREE ANALYSIS; SAFETY RISK-ASSESSMENT; ROOT CAUSE ANALYSIS; POINT CLOUD DATA; BAYESIAN-NETWORK; MULTIOBJECTIVE OPTIMIZATION; DAMAGE DETECTION;
D O I
10.1016/j.autcon.2020.103517
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
With the extensive adoption of artificial intelligence (AI), construction engineering and management (CEM) is experiencing a rapid digital transformation. Since AI-based solutions in CEM has become the current research focus, it needs to be comprehensively understood. In this regard, this paper presents a systematic review under both scientometric and qualitative analysis to present the current state of AI adoption in the context of CEM and discuss its future research trends. To begin with, a scientometric review is performed to explore the characteristics of keywords, journals, and clusters based on 4,473 journal articles published in 1997-2020. It is found that there has been an explosion of relevant papers especially in the past 10 years along with the change in keyword popularity from expert systems to building information modeling (BIM), digital twins, and others. Then, a brief understanding of CEM is provided, which can be benefited from the emerging trend of AI in terms of automation, risk mitigation, high efficiency, digitalization, and computer vision. Special concerns have been put on six hot research topics that amply the advantage of AI in CEM, including (1) knowledge representation and reasoning, (2) information fusion, (3) computer vision, (4) natural language processing, (5) intelligence optimization, and (6) process mining. The goal of these topics is to model, predict, and optimize issues in a data-driven manner throughout the whole lifecycle of the actual complex project. To further narrow the gap between AI and CEM, six key directions of future researches, such as smart robotics, cloud virtual and augmented reality (cloud VR/AR), Artificial Intelligence of Things (AIoT), digital twins, 4D printing, and blockchains, are highlighted to constantly facilitate the automation and intelligence in CEM.
引用
收藏
页数:21
相关论文
共 252 条
[81]   A two-stage method to identify structural damage sites and extents by using evidence theory and micro-search genetic algorithm [J].
Guo, H. Y. ;
Li, Z. L. .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2009, 23 (03) :769-782
[82]   Damage detection in a novel deep-learning framework: a robust method for feature extraction [J].
Guo, Tian ;
Wu, Lianping ;
Wang, Cunjun ;
Xu, Zili .
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, 2020, 19 (02) :424-442
[83]   Data fusion of multi-scale representations for structural damage detection [J].
Guo, Tian ;
Xu, Zili .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2018, 98 :1020-1033
[84]   A multi-stage optimization method for cost-optimal and nearly-zero-energy building solutions in line with the EPBD-recast 2010 [J].
Hamdy, Mohamed ;
Hasan, Ala ;
Siren, Kai .
ENERGY AND BUILDINGS, 2013, 56 :189-203
[85]   Comparison of random forest, artificial neural networks and support vector machine for intelligent diagnosis of rotating machinery [J].
Han, Te ;
Jiang, Dongxiang ;
Zhao, Qi ;
Wang, Lei ;
Yin, Kai .
TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL, 2018, 40 (08) :2681-2693
[86]  
Hatami M, 2019, COMPUTING IN CIVIL ENGINEERING 2019: DATA, SENSING, AND ANALYTICS, P368
[87]   Critical evaluation of off-site construction research: A Scientometric analysis [J].
Hosseini, M. Reza ;
Martek, Igor ;
Zavadskas, Edmundas Kazimieras ;
Aibinu, Ajibade A. ;
Arashpour, Mehrdad ;
Chileshe, Nicholas .
AUTOMATION IN CONSTRUCTION, 2018, 87 :235-247
[88]   Understanding and visualizing schedule deviations in construction projects using fault tree analysis [J].
Hsu, Pei-Yuan ;
Aurisicchio, Marco ;
Angeloudis, Panagiotis ;
Whyte, Jennifer .
ENGINEERING CONSTRUCTION AND ARCHITECTURAL MANAGEMENT, 2020, 27 (09) :2501-2522
[89]   Clash Relevance Prediction Based on Machine Learning [J].
Hu, Yuqing ;
Castro-Lacouture, Daniel .
JOURNAL OF COMPUTING IN CIVIL ENGINEERING, 2019, 33 (02)
[90]   BIM-based integrated delivery technologies for intelligent MEP management in the operation and maintenance phase [J].
Hu, Zhen-Zhong ;
Tian, Pei-Long ;
Li, Sun-Wei ;
Zhang, Jian-Ping .
ADVANCES IN ENGINEERING SOFTWARE, 2018, 115 :1-16