TY - GEN
T1 - A Perspective Survey on Industrial Knowledge Graphs
T2 - 2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023
AU - Shang, Yuhu
AU - Ren, Yimeng
AU - Peng, Hao
AU - Wang, Yue
AU - Wang, Gang
AU - Li, Zhong Cheng
AU - Yang, Yangzhao
AU - Li, Yangyang
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - As a result of the development of a new generation of artificial intelligence and carbon-neutral technologies, traditional industries are undergoing dramatic transformations. The exploration of industrial intelligence is still in its nascent stages, particularly lacking technical approaches to distill experiential knowledge from heterogeneous data sources originating from various origins. Knowledge Graphs (KG), as cutting-edge artificial intelligence technologies, can enable knowledge management and reuse while condensing valuable knowledge. As a result, fully utilizing KG's potential in the industrial field is critical to the realization of autonomous sensing, cognition, and the evolution of next-generation intelligent manufacturing systems. This paper starts with an overview of the current state of industrial knowledge graph development and shows how to construct an industrial knowledge graph (IKG). Following that, we provide a thorough and in-depth review of various industrial scenarios supported by knowledge graphs. Furthermore, this paper identifies the current challenges confronting industrial applications and proposes future research directions for IKG. It is hoped that this research will draw the attention of more researchers to the knowledge graph-based smart manufacturing paradigm and benefit their work.
AB - As a result of the development of a new generation of artificial intelligence and carbon-neutral technologies, traditional industries are undergoing dramatic transformations. The exploration of industrial intelligence is still in its nascent stages, particularly lacking technical approaches to distill experiential knowledge from heterogeneous data sources originating from various origins. Knowledge Graphs (KG), as cutting-edge artificial intelligence technologies, can enable knowledge management and reuse while condensing valuable knowledge. As a result, fully utilizing KG's potential in the industrial field is critical to the realization of autonomous sensing, cognition, and the evolution of next-generation intelligent manufacturing systems. This paper starts with an overview of the current state of industrial knowledge graph development and shows how to construct an industrial knowledge graph (IKG). Following that, we provide a thorough and in-depth review of various industrial scenarios supported by knowledge graphs. Furthermore, this paper identifies the current challenges confronting industrial applications and proposes future research directions for IKG. It is hoped that this research will draw the attention of more researchers to the knowledge graph-based smart manufacturing paradigm and benefit their work.
KW - Artificial Intelligence
KW - Industrial Knowledge Graph
KW - Intelligent Manufacturing Systems
UR - http://www.scopus.com/inward/record.url?scp=85179836914&partnerID=8YFLogxK
U2 - 10.1109/ICMLC58545.2023.10327989
DO - 10.1109/ICMLC58545.2023.10327989
M3 - Conference contribution
AN - SCOPUS:85179836914
T3 - Proceedings - International Conference on Machine Learning and Cybernetics
SP - 194
EP - 200
BT - Proceedings of 2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023
PB - IEEE Computer Society
Y2 - 9 July 2023 through 11 July 2023
ER -