Journal of Intelligent Manufacturing, Journal Year: 2024, Volume and Issue: unknown
Published: June 5, 2024
Language: Английский
Journal of Intelligent Manufacturing, Journal Year: 2024, Volume and Issue: unknown
Published: June 5, 2024
Language: Английский
Journal of Manufacturing Systems, Journal Year: 2023, Volume and Issue: 70, P. 417 - 435
Published: Aug. 24, 2023
Language: Английский
Citations
62Advanced Engineering Informatics, Journal Year: 2024, Volume and Issue: 59, P. 102333 - 102333
Published: Jan. 1, 2024
Language: Английский
Citations
41Journal of Engineering Design, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 40
Published: Jan. 6, 2024
With the support of advanced information and communication technologies open innovative design platforms, emerging blooming paradigm mass personalization drives process engineering to include knowledge with higher heterogeneity more complex modalities. To this end, Multi-Modal Knowledge Graphs (MMKG), evolved from semantic networks graphs, provide a powerful technology system for effectively organizing utilizing knowledge. understand state-of-the-art key aspects that enables MMKG, recognize potential challenges forefront applications in design, literature review MMKG-related publications is conducted. selected 131 representative papers together other 32 supplementary studies (up 11/11/2023), article summarizes technical practical efforts multi-modal extraction, fusion technology, specific process. Meantime, MMKG faces its foreseeable development potentials are discussed, which hoped basis futuristic explorations implementations MMKG-enhanced availability productivity design.
Language: Английский
Citations
15Journal of Manufacturing Systems, Journal Year: 2024, Volume and Issue: 76, P. 103 - 132
Published: July 29, 2024
Smart manufacturing (SM) confronts several challenges inherently suited to knowledge graphs (KGs) capabilities. The first key challenge lies in the synthesis of complex and varied data surrounding context, which demands advanced semantic analysis inference second main limitation is contextualization systems exploitation domain knowledge, requires a dynamic holistic representation knowledge. last major obstacle arises from facilitation intricate decision-making processes towards correlated ecosystems, benefit interconnected structures that KGs excel at organizing. However, existing survey studies concentrated on distinct facets SM offered isolated insights into KG applications while overlooking interconnections between various technologies their application across multiple domains. What specific role should play aforementioned challenges, how effectively harness for these essential topics methodologies required make functional remain underexplored. To explore potential SM, this study adopts systematic approach investigate, evaluate, analyse current research KGs, identifying core advancements implications future practices. Firstly, cutting-edge developments challenge-driven roles techniques are identified, extraction mining construction updates, further extending embedding, fusion, reasoning—central driving ecosystems. Specifically, depicted holistically, emphasizing interplay diverse with comprehensive framework. Subsequently, foundation outlines discusses scenarios engineering design predictive maintenance, covering representative stages life cycle. Lastly, explores practical advantages systems, pointing emerging avenues.
Language: Английский
Citations
15Journal of Engineering Design, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 28
Published: Jan. 12, 2025
Intelligent remanufacturing process planning is crucial for the efficient and high-quality of used parts with complex failure characteristics. However, due to varied characteristics parts, diversity processes, non-linear relationships among elements, relying solely on mathematical programming or manual empirical difficult effectively model optimise planning. To this end, a knowledge graph-based intelligent method processes proposed enhance efficiency quality by combining reuse. Firstly, as decision nodes, full-element ontology constructed, linking characteristics, corresponding plans. The BERT-BiLSTM-CRF extracts entities, graph (RPKG) constructed. Secondly, an decision-making based multi-node path retrieval proposed. Aim minimise carbon emissions, time, cost, feature similarity calculations nearest neighbour search (NNS) efficiently retrieve optimal plan each characteristic. Then, plans are merged constraints create complete plan. Finally, concrete case given verify effectiveness advantages method.
Language: Английский
Citations
1Advanced Engineering Informatics, Journal Year: 2025, Volume and Issue: 65, P. 103134 - 103134
Published: Jan. 23, 2025
Language: Английский
Citations
1Advanced Engineering Informatics, Journal Year: 2025, Volume and Issue: 65, P. 103244 - 103244
Published: March 8, 2025
Language: Английский
Citations
1Advanced Engineering Informatics, Journal Year: 2023, Volume and Issue: 58, P. 102172 - 102172
Published: Sept. 22, 2023
Language: Английский
Citations
20Advanced Engineering Informatics, Journal Year: 2023, Volume and Issue: 57, P. 102084 - 102084
Published: July 4, 2023
Language: Английский
Citations
18Journal of Engineering Design, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 31
Published: Jan. 31, 2024
Bio-inspired Design (BID) is a method that draws principles from biological systems to solve complex real-world problems. While diverse knowledge-based tools have served BID, the retrieval and reasoning capabilities of knowledge graphs not been explored in BID. This study introduces novel graph-based BID approach, exploiting power support In comprehensive ontology defined then applied construct BID-specific graph, enabling efficient representation rich knowledge. The graph supports by facilitating reasoning. Retrieval accomplished finding potential links between relevant design applications. Reasoning supported link prediction model follows process mapping Two case studies are conducted demonstrate effectiveness approach. first shows our approach outperforms other benchmarks retrieving related knowledge, second presents how aids generating inspirational ideas.
Language: Английский
Citations
9