TY - JOUR
T1 - Knowledge graph-guided data-driven design of ultra-high-performance concrete (UHPC) with interpretability and physicochemical reaction discovery capability
AU - Guo, Pengwei
AU - Meng, Weina
AU - Bao, Yi
N1 - Publisher Copyright:
© 2024 Elsevier Ltd
PY - 2024/6/7
Y1 - 2024/6/7
N2 - Traditional methods for designing concrete materials typically rely on labor-intensive laboratory experiments, resulting in time and cost inefficiencies. Recently, designing concrete using artificial intelligence (AI) methods has shown high efficiency, but existing AI methods often rely solely on data, which can lead to violation with scientific principles and result in models lacking reasoning abilities. To overcome these challenges, this paper presents an interpretable knowledge graph-guided data-driven design approach. By integrating advanced computing techniques with domain knowledge via knowledge graphs, this approach enables the interpretation of data-driven models and uncovers the underlying mechanisms behind predictions. This approach is applied to ultra-high-performance concrete (UHPC) involving complex physicochemical reactions. The domain knowledge about UHPC is imparted using a knowledge graph, and UHPC properties are predicted using a machine learning model considering mixing proportions, processing methods, and physiochemical properties of materials via natural language processing. The results show that the knowledge graph displays crucial design variables and their effects on UHPC properties, aiding in selecting variables for machine learning models and interpreting their results. The prediction accuracy of the machine learning model reached 0.95. The research paves the way for more transparent and scientific AI models for material design and AI-enabled discovery of scientific knowledge.
AB - Traditional methods for designing concrete materials typically rely on labor-intensive laboratory experiments, resulting in time and cost inefficiencies. Recently, designing concrete using artificial intelligence (AI) methods has shown high efficiency, but existing AI methods often rely solely on data, which can lead to violation with scientific principles and result in models lacking reasoning abilities. To overcome these challenges, this paper presents an interpretable knowledge graph-guided data-driven design approach. By integrating advanced computing techniques with domain knowledge via knowledge graphs, this approach enables the interpretation of data-driven models and uncovers the underlying mechanisms behind predictions. This approach is applied to ultra-high-performance concrete (UHPC) involving complex physicochemical reactions. The domain knowledge about UHPC is imparted using a knowledge graph, and UHPC properties are predicted using a machine learning model considering mixing proportions, processing methods, and physiochemical properties of materials via natural language processing. The results show that the knowledge graph displays crucial design variables and their effects on UHPC properties, aiding in selecting variables for machine learning models and interpreting their results. The prediction accuracy of the machine learning model reached 0.95. The research paves the way for more transparent and scientific AI models for material design and AI-enabled discovery of scientific knowledge.
KW - Interpretable artificial intelligence
KW - Knowledge graph
KW - Machine learning
KW - Physicochemical reactions
KW - Solid wastes
KW - Ultra-high-performance concrete
UR - http://www.scopus.com/inward/record.url?scp=85192338840&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85192338840&partnerID=8YFLogxK
U2 - 10.1016/j.conbuildmat.2024.136502
DO - 10.1016/j.conbuildmat.2024.136502
M3 - Article
AN - SCOPUS:85192338840
SN - 0950-0618
VL - 430
JO - Construction and Building Materials
JF - Construction and Building Materials
M1 - 136502
ER -