Heterogeneous knowledge graph-driven subassembly identification with ensemble deep learning in Industry 4.0 DOI
Chao Zhang, Yanzhen Jing, Guanghui Zhou

et al.

International Journal of Production Research, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 17

Published: Dec. 5, 2024

In the context of Industry 4.0, model-based definition (MBD) has been an effective approach to creating 3D models contained all heterogeneous information needed define a product, which proposes new challenges for traditional subassembly identification method that only considers geometric product in assembly sequence planning. To bridge gap, we propose novel knowledge graph-driven enhance planning systems engineering (MBSE) paradigm. Specifically, graph is first constructed based on shape and details MBD model. Next, ensemble deep learning combines neural networks with community detection algorithm proposed effectively detect from Finally, feasibility effectiveness are demonstrated through example car suspension identification, providing insight into industrial implementation.

Language: Английский

A knowledge graph-based intelligent planning method for remanufacturing processes of used parts DOI
Shuo Zhu, L C Gao, Zhigang Jiang

et al.

Journal 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

1
Disassembly Plan Representation by Hypergraph DOI Creative Commons

Abboy Verkuilen,

Mirjam Zijderveld,

Niels de Buck

et al.

Automation, Journal Year: 2025, Volume and Issue: 6(1), P. 10 - 10

Published: Feb. 20, 2025

To be successful in a circular economy, it is important to keep the cost of operationalizing remanufacturing processes low order retain as much value product possible. Optimizing operations for disassembly, key process step, therefore an prerequisite economically viable manufacturing. The generation fit-to-resource disassembly instructions labor-intensive and challenging because (digital) information often lacking at End-of-Life. With upcoming EU regulations Eco-design Sustainable Products mind, including future use Digital Product Passports, time think about standardized methods capture products. First requirements from small medium-sized companies have been collected compared with available frameworks modeling topology, parameters, (dis)assembly rationale. Based on this, hypergraph presented concept recording ‘resource-agnostic guides’ (machine-readable) models determine required actions tools ‘smartly’. builds upon existing models. Additionally, suitable collection are explored, resulting preliminary insights data workshops. Although approach promising, work needed expand both guidelines setting up ontologies further systematic knowledge extraction apply this useful means rationalize their operations.

Language: Английский

Citations

0
Parallel Disassembly Sequence Planning Using a Discrete Whale Optimization Algorithm for Equipment Maintenance in Hydropower Station DOI Open Access
Ziwei Zhong,

Lingkai Zhu,

Wenlong Fu

et al.

Processes, Journal Year: 2024, Volume and Issue: 12(7), P. 1412 - 1412

Published: July 6, 2024

In a hydropower station, equipment needs maintenance to ensure safe, stable, and efficient operation. And the essence of is disassembly sequence planning problem. However, complexity arises from vast number components in leading significant proliferation potential combinations, which poses considerable challenges when devising optimal solutions for process. Consequently, improve efficiency decrease time, discrete whale optimization algorithm (DWOA) proposed this paper achieve excellent parallel (PDSP). To begin, composite nodes are added into constraint relationship graph based on characteristics equipment, time chosen as objective. Subsequently, DWOA solve PDSP problem by integrating precedence preservative crossover mechanism, heuristic mutation repetitive pairwise exchange operator. Meanwhile, hierarchical combination method used swiftly generate initial population. verify viability algorithm, classic genetic (GA), simplified teaching–learning-based (STLBO), self-adaptive swarm (SSO) were employed comparison three projects. The experimental results comparative analysis revealed that with achieved reduced only 19.96 min Experiment 3. Additionally, values standard deviation, average rate minimum 0.3282, 20.31, 71%, respectively, demonstrating its superior performance compared other algorithms. Furthermore, addresses inefficiencies dismantling processes stations enhances visual representation training Unity3D intelligent

Language: Английский

Citations

3
Multi-objective human-robot collaborative disassembly line balancing problem considering components remanufacture demand and hazard characteristics DOI
Zhu Li-xia,

Yarong Chen,

Jabir Mumtaz

et al.

Computers & Industrial Engineering, Journal Year: 2024, Volume and Issue: 197, P. 110621 - 110621

Published: Oct. 9, 2024

Language: Английский

Citations

2
Monitoring model for enhancing adaptability in human–robot collaborative mold assembly DOI
Yee Yeng Liau, Kwangyeol Ryu

International Journal of Computer Integrated Manufacturing, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 19

Published: Aug. 10, 2024

Molds are assembled manually due to their inherent characteristics of low-volume and high-variety production. Given the ergonomic risks caused by heavy-handling repetitive tasks diverse requirements in mold assembly, collaborative robots offer adaptability ease reconfiguration, making them potential solutions these challenges. This study introduces a monitoring model for human–robot assembly using two cobots. encompasses manual progress cobot execution position-sharing modules. Manual task actions detected You-Only-Look-Once-v8 Nano model. Detected subsequently classified into different states. These identified states relayed cobots, enabling early controlling cobots' entry area. proposes approach prevent collisions receiving coordinates via Modbus between Most existing research has developed separate models action part recognition, excluding utilization recognition results enable execution. contributes novel subsequent facilitate communication through position sharing during tasks. The show that time risk cobots can be reduced

Language: Английский

Citations

0
Solving a Stochastic Multi-Objective Sequence Dependence Disassembly Sequence Planning Problem with an Innovative Bees Algorithm DOI Creative Commons
Xinyue Huang, Xuesong Zhang,

Yanlong Gao

et al.

Automation, Journal Year: 2024, Volume and Issue: 5(3), P. 432 - 449

Published: Aug. 23, 2024

As the number of end-of-life products multiplies, issue their efficient disassembly has become a critical problem that urgently needs addressing. The field sequence planning consequently attracted considerable attention. In actual process, complex structures can lead to significant delays due interference between different tasks. Overlooking this result in inefficiencies and waste resources. Therefore, it is particularly important study sequence-dependent problem. Additionally, activities are inherently fraught with uncertainties, neglecting these further impact effectiveness disassembly. This first analyze an uncertain environment. It utilizes stochastic programming approach address uncertainties. Furthermore, mixed-integer optimization model constructed minimize time energy consumption simultaneously. Recognizing complexity problem, introduces innovative bees algorithm, which proven its by showing superior performance compared other state-of-the-art algorithms various test cases. research offers solutions for holds implications advancing sustainable development recycling

Language: Английский

Citations

0
Heterogeneous knowledge graph-driven subassembly identification with ensemble deep learning in Industry 4.0 DOI
Chao Zhang, Yanzhen Jing, Guanghui Zhou

et al.

International Journal of Production Research, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 17

Published: Dec. 5, 2024

In the context of Industry 4.0, model-based definition (MBD) has been an effective approach to creating 3D models contained all heterogeneous information needed define a product, which proposes new challenges for traditional subassembly identification method that only considers geometric product in assembly sequence planning. To bridge gap, we propose novel knowledge graph-driven enhance planning systems engineering (MBSE) paradigm. Specifically, graph is first constructed based on shape and details MBD model. Next, ensemble deep learning combines neural networks with community detection algorithm proposed effectively detect from Finally, feasibility effectiveness are demonstrated through example car suspension identification, providing insight into industrial implementation.

Language: Английский

Citations

0