Artificial Intelligence in Construction Engineering and Management
- 2021
- Book
- Authors
- Dr. Limao Zhang
- Dr. Yue Pan
- Prof. Xianguo Wu
- Prof. Dr. Mirosław J. Skibniewski
- Book Series
- Lecture Notes in Civil Engineering
- Publisher
- Springer Singapore
About this book
This book highlights the latest technologies and applications of Artificial Intelligence (AI) in the domain of construction engineering and management. The construction industry worldwide has been a late bloomer to adopting digital technology, where construction projects are predominantly managed with a heavy reliance on the knowledge and experience of construction professionals. AI works by combining large amounts of data with fast, iterative processing, and intelligent algorithms (e.g., neural networks, process mining, and deep learning), allowing the computer to learn automatically from patterns or features in the data. It provides a wide range of solutions to address many challenging construction problems, such as knowledge discovery, risk estimates, root cause analysis, damage assessment and prediction, and defect detection. A tremendous transformation has taken place in the past years with the emerging applications of AI. This enables industrial participants to operate projects more efficiently and safely, not only increasing the automation and productivity in construction but also enhancing the competitiveness globally.
Advertisement
Table of Contents
-
Frontmatter
-
Introduction to Artificial Intelligence
Limao Zhang, Yue Pan, Xianguo Wu, Mirosław J. SkibniewskiThe chapter begins with an introduction to Artificial Intelligence (AI), explaining its core concepts and historical development. It delves into various AI techniques such as expert systems, fuzzy logic, statistical models, machine learning, and process mining, illustrating how these can be applied to improve construction management. The significance of Construction Engineering and Management (CEM) is discussed, emphasizing its role in driving economic growth and addressing safety challenges. The chapter then explores how AI can revolutionize CEM by automating processes, mitigating risks, enhancing efficiency, and facilitating digitalization. Specific applications of AI in CEM, such as computer vision and dynamic Bayesian networks, are highlighted. The organization of the book is outlined, with each subsequent chapter focusing on a specific AI technique and its application in CEM. The chapter concludes by summarizing the potential of AI to transform the construction industry and pointing towards future directions in AI-driven construction management.AI Generated
This summary of the content was generated with the help of AI.
AbstractThe term Artificial Intelligence (AI) is a branch of computer science to make computers perform human-like tasks, and thus, computers can appropriately sense and learn inputs for perception, knowledge representation, reasoning, problem-solving, and planning. Various types of innovative AI technologies are designed to imitate the cognitive abilities of human beings, which can, therefore, deal with more complicated and ill-defined problems in an intentional, intelligent, and adaptive manner. Typically, AI can be regarded as a conjunction of machine learning and data analytics. -
Knowledge Representation and Discovery
Limao Zhang, Yue Pan, Xianguo Wu, Mirosław J. SkibniewskiThe chapter begins by highlighting the critical importance of safety leadership in the construction industry, given its high-risk nature. It introduces the concept of safety leadership and its key factors, including personality, emotional intelligence, and organizational aspects. The chapter then delves into the relationships among multiple stakeholders, such as owners, contractors, supervisors, and designers, using Structural Equation Modeling (SEM) to test hypotheses and reveal causal relationships. Through a thorough analysis of survey data, the chapter identifies the leading roles and factors influencing construction safety performance, providing valuable insights into how stakeholders can collaborate effectively to enhance safety outcomes. The use of SEM enables a dynamic perspective on these interactions, making the chapter a valuable resource for practitioners and researchers aiming to improve safety in the construction industry.AI Generated
This summary of the content was generated with the help of AI.
AbstractConstruction is one of the most dangerous industries worldwide, leading to a common interest in improving construction safety performance due to humanitarian reasons and rising costs of worker compensation. -
Fuzzy Modeling and Reasoning
Limao Zhang, Yue Pan, Xianguo Wu, Mirosław J. SkibniewskiThe chapter 'Fuzzy Modeling and Reasoning' explores the challenges and solutions in TBM performance assessment during tunnel construction. It introduces Fuzzy Cognitive Maps (FCM) as a tool for capturing expert knowledge and simulating complex systems. The chapter presents a holistic FCM-enabled Root Cause Analysis (RCA) approach, detailing its implementation and application in a case study of the Wuhan metro system. The approach is validated through various what-if experiments, demonstrating its effectiveness in predictive, diagnostic, and hybrid RCA. The chapter highlights the advantages of FCM over traditional methods and its potential as a decision support tool in complex project environments.AI Generated
This summary of the content was generated with the help of AI.
AbstractIn recent years, the construction of subway systems and underground utilities has increased dramatically due to population pressure and a lack of surface space. The tunnel boring machine (TBM) has been observed with widespread applications in tunnel construction, which can be used for excavating tunnels for nearly all types of rock and geological conditions. -
Time Series Prediction
Limao Zhang, Yue Pan, Xianguo Wu, Mirosław J. SkibniewskiThis chapter addresses the critical issue of tunnel-induced ground settlement in urban tunneling projects. It introduces a hybrid approach that integrates Wavelet Packet Transform (WPT) and Least Square Support Vector Machine (LSSVM) to enhance the accuracy and real-time capability of ground settlement predictions. The method is validated through a case study of a real tunnel project in China, demonstrating its practical applicability and superior performance compared to traditional methods. The chapter highlights the advantages of the WPT-LSSVM approach, including its ability to handle complex, time-dependent data and provide reliable predictions. This makes it a valuable resource for professionals in geotechnical engineering and data analysis seeking advanced solutions for construction safety and efficiency.AI Generated
This summary of the content was generated with the help of AI.
AbstractOver the past decades, the rapid development of big cities is raising the demands of underground space utilization. One of the favorable options for urban development is to build underground tunnels. Notably, a lot of tunnels are located at a low depth in soil or soft rock zones under densely populated areas, and thus the excavation works of shallow tunnels in the soft ground tend to result in both lateral and vertical surfaces. -
Information Fusion
Limao Zhang, Yue Pan, Xianguo Wu, Mirosław J. SkibniewskiThe chapter introduces information fusion techniques for structural health assessment (SHA) in tunnels, focusing on the advantages of combining data from multiple sensors. It discusses the application of Support Vector Machines (SVM) for detecting structural damage and the Dempster-Shafer (D-S) evidence theory for fusing information from different classifiers. The chapter also presents a case study in a Chinese metro tunnel, demonstrating the effectiveness of the proposed hybrid approach in improving the accuracy and reliability of risk assessment. Additionally, it highlights the importance of global sensitivity analysis for identifying critical risk factors and taking timely remedial actions to mitigate structural failures.AI Generated
This summary of the content was generated with the help of AI.
AbstractInformation fusion is a data-driven technique to combine data from multiple sources, which can generate improved information in higher quality and accuracy for detection, inference, or characterization of an object than a single sensor alone. -
Dynamic Bayesian Networks
Limao Zhang, Yue Pan, Xianguo Wu, Mirosław J. SkibniewskiThe chapter introduces the application of Dynamic Bayesian Networks (DBNs) in the dynamic risk analysis of tunnel construction, particularly focusing on tunnel-induced road damage. It discusses the limitations of traditional risk analysis methods and highlights the advantages of DBNs in capturing the dynamic behaviors of complex systems. The chapter provides a detailed case study of the Wuhan Yangtze Metro Tunnel, demonstrating how DBNs can be used to predict, diagnose, and mitigate risks in real-time. The methodology includes risk/hazard identification, DBN learning, and various types of analysis such as predictive, sensitivity, and diagnostic analysis. The chapter concludes by emphasizing the potential of DBNs in enhancing safety management in complex infrastructure projects.AI Generated
This summary of the content was generated with the help of AI.
AbstractUnderground transportation systems are in great demand in many large cities all over the world. Tunnel construction has presented a powerful momentum for rapid economic development worldwide. However, owing to various risk factors in complex project environments, safety violations occur frequently in tunnel construction, leading to large problems on the surface transport operation. -
Process Mining
Limao Zhang, Yue Pan, Xianguo Wu, Mirosław J. SkibniewskiThe chapter delves into the use of process mining to leverage BIM event logs for better understanding and managing construction projects. It introduces the concept of BIM and its rapid adoption in the AEC industry, highlighting the need for effective data mining techniques. Process mining is presented as a powerful tool to extract hidden knowledge from BIM event logs, enabling process discovery, conformance checking, and predictive analytics. The chapter also discusses the practical implementation of process mining in a real BIM design event log, showcasing its potential to improve project performance and collaboration. Key techniques such as inductive mining, fuzzy mining, and decision tree analysis are explored, providing a comprehensive guide for professionals seeking to enhance their project management capabilities through data-driven insights.AI Generated
This summary of the content was generated with the help of AI.
AbstractBIM, as a new digital revolution for civil engineering, provides a collaborative platform to facilitate information exchange and sharing among participants in different roles for better decision-making. -
Agent-Based Simulation
Limao Zhang, Yue Pan, Xianguo Wu, Mirosław J. SkibniewskiThe chapter delves into the challenges of urban transportation systems, particularly the subway systems, exacerbated by rapid urbanization. It highlights the significance of efficient evacuation planning in metro stations, where densely packed pedestrians and limited evacuation routes pose severe safety risks. The text introduces Agent-Based Simulation (ABS) as a powerful tool for modeling complex systems, emphasizing its advantages in predicting emergent phenomena and natural description. The social force model is employed to simulate pedestrian evacuation dynamics, considering factors such as evacuation length, time, and density. The chapter presents a systematic multi-attribute decision approach to optimize evacuation route planning, validated through a case study in China. The results demonstrate significant improvements in evacuation efficiency, offering valuable insights for enhancing safety and operational performance in metro stations.AI Generated
This summary of the content was generated with the help of AI.
AbstractIn recent years, with the continuous and rapid development of the urban economy, a large number of people have migrated into cities, especially in developing and thriving countries such as China and India, imposing a rigorous challenge on urban transportation systems. -
Expert Systems
Limao Zhang, Yue Pan, Xianguo Wu, Mirosław J. SkibniewskiThe chapter delves into the complexities of tunnel construction, highlighting the critical role of risk identification in ensuring public safety. It critiques existing qualitative and quantitative risk analysis tools and identifies deficiencies in current methods, such as over-reliance on domain experts, time-consuming manual processes, and inefficient knowledge transformation. The chapter introduces BIM as a digital solution that enhances safety management by providing a more realistic and enriched model of the construction process. It also explores the potential of expert systems in automating risk identification and inference. The core innovation is the development of the BIM-based Risk Identification Expert System (B-RIES), which integrates BIM extraction, knowledge base management, and risk identification modules. This system aims to systematize both explicit and tacit knowledge, enabling better communication and collaboration among stakeholders. A case study from China is presented to demonstrate the applicability and effectiveness of B-RIES, making this chapter a compelling read for professionals seeking advanced solutions in tunnel construction safety.AI Generated
This summary of the content was generated with the help of AI.
AbstractTunnel construction entails a highly complicated project with large potential risks, which can bring enormous dangers to public safety. Numerous accidents have led to growing public concerns about prior risk identification and assessment in relation to tunnel construction safety. Risk identification plays an important role in the safety assurance process, aiming to reveal the potential safety risk and determine risk factors’ contribution to the occurrence of an accident. -
Computer Vision
Limao Zhang, Yue Pan, Xianguo Wu, Mirosław J. SkibniewskiThe chapter delves into the critical issue of structural crack detection, highlighting the limitations of manual inspection methods and the advantages of automated visual inspection approaches. It introduces the SCHNet model, a novel hybrid deep learning approach that integrates a self-attention mechanism to capture long-range contextual dependencies. The model is designed to enhance feature extraction and pixel-level segmentation, addressing the challenges posed by complex backgrounds and varying crack patterns. The chapter also provides a comprehensive evaluation of the SCHNet model, demonstrating its superior performance and robustness in detecting cracks in various scenarios. Additionally, it discusses the potential applications of the SCHNet model in practical engineering projects and the use of unmanned aerial vehicles for data collection, showcasing the versatility and practicality of the proposed approach.AI Generated
This summary of the content was generated with the help of AI.
AbstractBecause of structure degradation, thermal movement, and other reasons, unwanted cracks will unavoidably appear in various types of structures, such as slabs, beams, columns, walls, etc. Unfortunately, harmful and corrosive chemicals, water, and salts will penetrate concrete layers through these existing cracks to exert negative impacts on structural integrity and durability (Adhikari et al. in Autom Constr 39:180–194, 2014). Thus, it is believed that cracks will speed up the degradation and aging of structure, bringing unreliability and failures in the structural systems. -
Conclusions and Future Directions
Limao Zhang, Yue Pan, Xianguo Wu, Mirosław J. SkibniewskiThe chapter explores the significant role of AI in revolutionizing the construction industry, particularly in construction engineering management (CEM). It highlights the key steps of AI-based CEM, including data acquisition, mining, and knowledge discovery, which enable deeper insights into big data. The text also delves into the practical applications of AI in modeling and pattern recognition, prediction, and optimization, showcasing how AI can tackle complex problems, predict project risks, and drive decision-making. Additionally, the chapter looks ahead to the future, identifying six promising directions for research, such as smart robotics, cloud VR/AR, AIoT, digital twins, 4D printing, and blockchain, which are set to further transform the construction industry. By integrating these advanced technologies, the construction sector can expect to become more efficient, safer, and more sustainable.AI Generated
This summary of the content was generated with the help of AI.
AbstractRecent decades have witnessed the rapid development of digital technology and the growth of big data in the construction industry. In particular, AI implementation, which attempts to equip machines with human-like intelligent behavior and reasoning, has gained a lot of attention.
- Title
- Artificial Intelligence in Construction Engineering and Management
- Authors
-
Dr. Limao Zhang
Dr. Yue Pan
Prof. Xianguo Wu
Prof. Dr. Mirosław J. Skibniewski
- Copyright Year
- 2021
- Publisher
- Springer Singapore
- Electronic ISBN
- 978-981-16-2842-9
- Print ISBN
- 978-981-16-2841-2
- DOI
- https://doi.org/10.1007/978-981-16-2842-9
Accessibility information for this book is coming soon. We're working to make it available as quickly as possible. Thank you for your patience.