Engineering design is a knowledge-intensive task in which designers/engineers apply their creative and technical knowledge for product conceptualization, product structure design, design exploration and optimization, etc. As a bottleneck in the design process, recognizing knowledge needs and acquiring corresponding design knowledge require a lot of time and effort, resulting in low efficiency and high cost [1, 2]. To this end, massive knowledge-based systems (KBSs) and knowledge management tools have been developed in the design community and in the industry to push knowledge to their designers/engineers proactively. However, with the support of advanced information and communication technologies (ICTs) and collaborative design platforms, the knowledge in the different phases of engineering design becomes multi-sourced and multi-modal [3, 4], including images of design sketches, hierarchies in 3D virtual models, rules in evaluation criteria, textual data of customer comments, etc [5, 6]. Traditional keywords-based knowledge retrieval and shallow knowledge reasoning manners in the existing KBSs are deemed insufficient, which cannot capture and store semantic relations effectively to support systematic and comprehensive design reasoning and cause frequent interruptions to the original design process. A novel manner for a more sophisticated design knowledge representation, organization, and reasoning is hence desired, to better support designers/engineers in various engineering design contexts with less cognitive load.
Knowledge graph (KG) would be one of the most promising choices for this purpose [7, 8]. Different from the traditional KBSs based on relational databases, KGs have strengths in heterogeneous knowledge representation, self-learning capability on knowledge reasoning, efficient knowledge retrieval, and ease of maintenance. Meanwhile, KGs have potentials to be integrated with other leading-edge technologies (e.g., AR/VR, big data, digital twin, AI algorithms, etc.) to tackle complicated engineering design tasks and further extended to multi-modal KGs to accommodate multi-modal knowledge in engineering design. Relying on such novel features of KGs, more intelligent tools and systems for engineering design knowledge retrieval and reasoning can be foreseeable, which are endowed with the cognitive capability to cognize, interpret, and understand the multi-sourced and multi-modal engineering design knowledge. It offers the possibility of 1) capturing the high-level semantics of knowledge, 2) mitigating the fusion issues of redundant knowledge, and 3) reducing engineers’ cognitive load by proactively recommending relevant knowledge. Nevertheless, applying KGs to engineering design still faces many technical challenges, such as how to deploy domain-specific KGs in engineering design tasks, how to extract high-quality knowledge from engineering design documents, how to combine and represent data from heterogeneous sources, and how to extract knowledge when only small datasets of high-quality knowledge are available [9]. Besides, there is still a lack of sufficient practices for integrating KGs in engineering design.
To this end, as an emerging and promising research topic, this special issue calls for papers about the state-of-the-art reviews, methodologies, tools, systems, and practical applications of KGs for engineering design.
Topic Areas:
The following is a non-comprehensive list of representative topics within the scope of this Special Issue.
- KG-enabled engineering design tasks, such as requirement management, concept generation and evaluation, embodiment design, product family design, product-service system development
- Knowledge representation, knowledge discovery, knowledge extraction, knowledge reasoning, knowledge recommendation, and knowledge transfer approaches in engineering design
- Novel KG models to achieve a cognitive intelligence-enabled engineering design
- KG-as-a-service for engineering design
- Review of KG methodologies and applications in engineering design
- Case studies on applying KGs in engineering design
- KGs combined with other leading-edge technologies (e.g., AR/VR, big data, digital twin, AI algorithms, etc.) for engineering design
- Multi-modal KG models/approaches to handling multi-modal knowledge in engineering design
References:
[1] Z. Wang, J. Liu, and L. Zheng, "The Evolution, Framework, and Future of Cognitive Intelligence-enabled Product Design," Procedia CIRP, vol. 109, pp. 526-531, 2022.
[2] B. Song, B. Yan, G. Triulzi, J. Alstott, and J. Luo, "Overlay technology space map for analyzing design knowledge base of a technology domain: the case of hybrid electric vehicles," Res. Eng. Des., vol. 30, no. 3, pp. 405-423, 2019/07/01 2019, doi: 10.1007/s00163-019-00312-w.
[3] X. Li, M. Lyu, Z. Wang, C.-H. Chen, and P. Zheng, "Exploiting knowledge graphs in industrial products and services: A survey of key aspects, challenges, and future perspectives," Comput. Ind., vol. 129, p. 103449, 2021/08/01/ 2021, doi: https://doi.org/10.1016/j.compind.2021.103449.
[4] S. K. Chandrasegaran, K. Ramani, R. D. Sriram, I. Horváth, A. Bernard, R. F. Harik, and W. Gao, "The evolution, challenges, and future of knowledge representation in product design systems," Comput.-Aided Des., vol. 45, no. 2, pp. 204-228, 2013/02/01/ 2013, doi: https://doi.org/10.1016/j.cad.2012.08.006.
[5] P. Pradel, Z. Zhu, R. Bibb, and J. Moultrie, "A framework for mapping design for additive manufacturing knowledge for industrial and product design," J. Eng. Des., vol. 29, no. 6, pp. 291-326, 2018/06/03 2018, doi: 10.1080/09544828.2018.1483011.
[6] Y. Wan, Z. Chen, F. Hu, Y. Liu, M. Packianather, and R. Wang, "Exploiting Knowledge Graph for Multi-faceted Conceptual Modelling using GCN," Procedia Comput. Sci., vol. 200, pp. 1174-1183, 2022/01/01/ 2022, doi: https://doi.org/10.1016/j.procs.2022.01.317.
[7] A. Huet, R. Pinquié, P. Véron, A. Mallet, and F. Segonds, "CACDA: A knowledge graph for a context-aware cognitive design assistant," Comput. Ind., vol. 125, p. 103377, 2021/02/01/ 2021, doi: https://doi.org/10.1016/j.compind.2020.103377.
[8] P. Zheng, L. Xia, C. Li, X. Li, and B. Liu, "Towards Self-X cognitive manufacturing network: An industrial knowledge graph-based multi-agent reinforcement learning approach," J. Manuf. Syst., vol. 61, pp. 16-26, 2021/10/01/ 2021, doi: https://doi.org/10.1016/j.jmsy.2021.08.002.
[9] T. Baltrušaitis, C. Ahuja, and L.-P. Morency, "Multimodal machine learning: A survey and taxonomy," IEEE Trans. Pattern Anal. Mach. Intell., vol. 41, no. 2, pp. 423-443, 2018.
