Scholarlink

<p>The deep integration of next-generation information technology and manufacturing is driving explosive growth and highly heterogeneous characteristics in aerospace intelligent workshop data. Traditional data management models are unable to meet the stringent requirements of aerospace manufacturing for data standardization, causal traceability, and dynamic adaptability. Therefore, based on the production characteristics of the aerospace industry, this paper proposes the self-evolving industrial data space framework (SIDSF), which achieves intelligent data management through a three-dimensional collaborative mechanism: (1) Data logic model construction: Construct a data logic model based on ontology to achieve semantic unification and standardized integration of multi-source heterogeneous manufacturing data; (2) Data causal logic association: Develop data-knowledge dual-driven association analysis technology to analyze explicit/implicit causal chains between manufacturing resources, reveal workshop operation patterns, and construct an explainable workshop inference framework; (3) Data spatio-temporal dynamic evolution: Develop a spatio-temporal evolution mechanism empowered by knowledge graphs to enhance the timely response capability to production disturbances such as workshop equipment failures and urgent orders for new models, supporting intelligent decision-making in aerospace workshops and optimizing production control. Additionally, this paper takes a certain aerospace enterprise in Shanghai as an example, utilizing data space technology to develop standardized knowledge models and data association analysis strategies, providing a theoretical foundation and practical guidance for data-driven decision-making in the aerospace manufacturing industry.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Self-evolving industrial data space: a knowledge-augmented framework for adaptive production in aerospace manufacturing

  • 期刊论文

  • 发表日期：

    2026年4月7日

查看全文
  • Ying Chu,
  • Youlong Lyu,
  • Jie Zhang,
  • Liling Zuo

摘要

The deep integration of next-generation information technology and manufacturing is driving explosive growth and highly heterogeneous characteristics in aerospace intelligent workshop data. Traditional data management models are unable to meet the stringent requirements of aerospace manufacturing for data standardization, causal traceability, and dynamic adaptability. Therefore, based on the production characteristics of the aerospace industry, this paper proposes the self-evolving industrial data space framework (SIDSF), which achieves intelligent data management through a three-dimensional collaborative mechanism: (1) Data logic model construction: Construct a data logic model based on ontology to achieve semantic unification and standardized integration of multi-source heterogeneous manufacturing data; (2) Data causal logic association: Develop data-knowledge dual-driven association analysis technology to analyze explicit/implicit causal chains between manufacturing resources, reveal workshop operation patterns, and construct an explainable workshop inference framework; (3) Data spatio-temporal dynamic evolution: Develop a spatio-temporal evolution mechanism empowered by knowledge graphs to enhance the timely response capability to production disturbances such as workshop equipment failures and urgent orders for new models, supporting intelligent decision-making in aerospace workshops and optimizing production control. Additionally, this paper takes a certain aerospace enterprise in Shanghai as an example, utilizing data space technology to develop standardized knowledge models and data association analysis strategies, providing a theoretical foundation and practical guidance for data-driven decision-making in the aerospace manufacturing industry.