BA-IKG: BiLSTM Embedded ALBERT for Industrial Knowledge Graph Generation and Reuse

Zhou, Bin; Bao, Jinsong; Liu, Yahui; Song, Dengqiang

doi:10.1109/indin45582.2020.9442198

Cited by 9 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [9], the authors established a knowledge graph facet model for the custom apparel production process, which provided an idea for building dynamic knowledge modeling. In addition, one of the key techniques for knowledge graph construction is knowledge extraction [18][19][20][21]. In [22], the authors designed a Chinesenamed entity recognition for clothing knowledge graph construction.…”

Section: Modeling Methods For Textile and Apparel Production Resourcesmentioning

confidence: 99%

Knowledge Graph-Embedded Time-Serial-Data-Driven Bottleneck Analysis of Textile and Apparel Production Processes

Wang,

Liu,

2023

Machines

View full text Add to dashboard Cite

There is a lack of high correlation and reuse potential among multiple manufacturing data for textiles and apparel. Moreover, the material flow traceability between production workstations is not clear, making it difficult to detect potential production bottlenecks. This paper proposes a knowledge graph embedded time serial data-driven bottleneck analysis of textile and apparel production processes. Firstly, a dynamic information association model is established to organize global manufacturing information, including the static data and time-series data features. Also, a textile-corpus-oriented knowledge extraction model is designed to construct a time-series knowledge graph for textile and apparel production (TKG4TA). Then, a temporal knowledge-driven production process bottleneck prediction model is presented based on manufacturing knowledge in the textile and apparel industry. Of these, textile knowledge is transformed into embeddings using a graph convolutional network (GCN). In turn, the context-associated information features are learned by the long short-term memory (LSTM) to predict the bottlenecks in the textile and apparel production process. Finally, a typical process flow in a shirt manufacturing workshop is used as a case study. It shows that the F1 value of the proposed method for named entity recognition and relationship extraction is up to 80.3%, and 50.6%, respectively. The performance of the proposed model for bottleneck prediction is improved by 8.2% and 14.92% compared to only the use of GCN or LSTM in the mean absolute error. This model may provide a solid foundation for the temporal knowledge-graph-driven bottleneck analysis of shirt manufacturing.

show abstract

Section: Modeling Methods For Textile and Apparel Production Resourcesmentioning

confidence: 99%

Knowledge Graph-Embedded Time-Serial-Data-Driven Bottleneck Analysis of Textile and Apparel Production Processes

Wang,

Liu,

2023

Machines

View full text Add to dashboard Cite

show abstract

“…These advantages are leading to growing use in industry and research into more sophisticated uses. Most commonly in terms of application are those related to knowledge management and analytics, either of company documentation [22] or to improve the representation of data found in models of products or machines [23]. Another common use of KGs, especially using RDF and SPARQL type technologies has been in integration between heterogeneous data and devices, a common problem in industrial settings and one that needs to be overcome to realise the benefits of industry 4.0 [24,25].…”

Section: Knowledge Graphsmentioning

confidence: 99%

Exploring Production System Knowledge Graph Applications Using a Simulation Framework

Birtic,

Senington,

Syberfeldt

2024

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

Knowledge graphs are generating significant interest in industry and research. These graphs can be enriched with data to represent aspects of production systems such as their structure, component interrelationships, and conditions. This provides opportunities to gain insights into system behavior, performance, and states. Such insights could potentially be leveraged by a wide range of technologies for a multitude of purposes and applications such as system control, process optimization, and informed decision making. However, the existing literature addressing industrial applications of knowledge graphs related to production systems remains limited in scope and depth. This underscores the importance of developing methods for exploring the potential use and implementation of knowledge graphs in such systems. The primary focus of this study centers on facilitating such exploration by developing a virtual commissioning simulation framework. A modular production system is modelled that leverages physics, moving product dynamics, and incorporates authentic PLC and robot programs. A knowledge graph is integrated and enriched with data representing various aspects of the system. An application is developed to facilitate product routing and prioritization. A service-oriented approach is used that leverages graph data processing and exchange for service registration and matching. System simulations are conducted and subsequently the framework is evaluated for outcomes and findings. This study demonstrates the successful design and implementation of a production system simulation framework that uses knowledge graphs for system functionality. It demonstrates the exploration of knowledge graph applications through the development of a modular and service-oriented system that includes system functionality supported by the graph. The results highlight the potential of simulation suggesting its capacity for valuable exploration regarding potential applications of knowledge graphs within production systems.

show abstract

An assembly process planning pipeline for industrial electronic equipment based on knowledge graph with bidirectional extracted knowledge from historical process documents

Xiao,

Zheng,

Leng

et al. 2024

J Intell Manuf

View full text Add to dashboard Cite

BA-IKG: BiLSTM Embedded ALBERT for Industrial Knowledge Graph Generation and Reuse

Cited by 9 publications

References 16 publications

Knowledge Graph-Embedded Time-Serial-Data-Driven Bottleneck Analysis of Textile and Apparel Production Processes

Knowledge Graph-Embedded Time-Serial-Data-Driven Bottleneck Analysis of Textile and Apparel Production Processes

Exploring Production System Knowledge Graph Applications Using a Simulation Framework

An assembly process planning pipeline for industrial electronic equipment based on knowledge graph with bidirectional extracted knowledge from historical process documents

Contact Info

Product

Resources

About