Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Artificial Intelligence in Concrete Materials: A Scientometric View

Zhanzhao Li, Aleksandra Radlińska

TL;DR

The paper addresses how artificial intelligence has been applied to concrete materials and what knowledge patterns emerge from the literature. It uses scientometric methods to map 389 Web of Science articles from 1990 to 2020 via keyword co-occurrence and document co-citation analyses, revealing trends, clusters, and gaps. The findings show a dominant focus on neural networks for predicting compressive strength, with data scarcity, interpretability, and cross-disciplinary integration identified as major challenges, and opportunities in transfer learning, data extraction from texts, and physics-informed AI. This work provides a roadmap for accelerating AI adoption in the construction industry by outlining data, methodological, and collaboration gaps and suggesting avenues for building a more integrated AI ecosystem in concrete science.

Abstract

Artificial intelligence (AI) has emerged as a transformative and versatile tool, breaking new frontiers across scientific domains. Among its most promising applications, AI research is blossoming in concrete science and engineering, where it has offered new insights towards mixture design optimization and service life prediction of cementitious systems. This chapter aims to uncover the main research interests and knowledge structure of the existing literature on AI for concrete materials. To begin with, a total of 389 journal articles published from 1990 to 2020 were retrieved from the Web of Science. Scientometric tools such as keyword co-occurrence analysis and documentation co-citation analysis were adopted to quantify features and characteristics of the research field. The findings bring to light pressing questions in data-driven concrete research and suggest future opportunities for the concrete community to fully utilize the capabilities of AI techniques.

Artificial Intelligence in Concrete Materials: A Scientometric View

TL;DR

The paper addresses how artificial intelligence has been applied to concrete materials and what knowledge patterns emerge from the literature. It uses scientometric methods to map 389 Web of Science articles from 1990 to 2020 via keyword co-occurrence and document co-citation analyses, revealing trends, clusters, and gaps. The findings show a dominant focus on neural networks for predicting compressive strength, with data scarcity, interpretability, and cross-disciplinary integration identified as major challenges, and opportunities in transfer learning, data extraction from texts, and physics-informed AI. This work provides a roadmap for accelerating AI adoption in the construction industry by outlining data, methodological, and collaboration gaps and suggesting avenues for building a more integrated AI ecosystem in concrete science.

Abstract

Artificial intelligence (AI) has emerged as a transformative and versatile tool, breaking new frontiers across scientific domains. Among its most promising applications, AI research is blossoming in concrete science and engineering, where it has offered new insights towards mixture design optimization and service life prediction of cementitious systems. This chapter aims to uncover the main research interests and knowledge structure of the existing literature on AI for concrete materials. To begin with, a total of 389 journal articles published from 1990 to 2020 were retrieved from the Web of Science. Scientometric tools such as keyword co-occurrence analysis and documentation co-citation analysis were adopted to quantify features and characteristics of the research field. The findings bring to light pressing questions in data-driven concrete research and suggest future opportunities for the concrete community to fully utilize the capabilities of AI techniques.
Paper Structure (8 sections, 5 figures, 4 tables)

This paper contains 8 sections, 5 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Literature survey
  3. Main research interests: keyword co-occurrence analysis
  4. Citation patterns: document co-citation analysis
  5. Discussion and future trends
  6. Data
  7. Models
  8. Conclusion

Figures (5)

  • Figure 1: Top 10 journals in terms of numbers of publications and citations in the area of AI in concrete science. Journal titles are presented using abbreviations based on ISO (International Standards Organization) standards.
  • Figure 2: Number of publications for AI applications in concrete science during 1990--2020.
  • Figure 3: Network of co-occurring keywords related to research on AI in concrete materials (cluster view).
  • Figure 4: Network of co-occurring keywords related to research on AI in concrete materials (timeline view). Timeline covers a period of time from 2012 to 2018 in terms of average publication year.
  • Figure 5: Network of co-cited documents in the publications on AI in concrete materials (timeline view).