导航

Acta Aeronautica et Astronautica Sinica ›› 2025, Vol. 46 ›› Issue (9): 431417.doi: 10.7527/S1000-6893.2024.31417

• Material Engineering and Mechanical Manufacturing • Previous Articles    

A knowledge-user behavior-driven aircraft assembly tooling design knowledge recommendation approach

Zuoxu WANG1,2,3, Xin WANG1, Shuang MENG1, Lianyu ZHENG1,2,3()   

  1. 1.School of Mechanical Engineering and Automation,Beihang University,Beijing 100191,China
    2.Beijing Key Laboratory of Digital Design and Manufacturing Technology,Beijing 100191,China
    3.MIIT Key Laboratory of Intelligent Manufacturing Technology for Aeronautics Advanced Equipments,Beijing 100191,China
  • Received:2024-10-17 Revised:2024-11-01 Accepted:2024-11-22 Online:2024-12-16 Published:2024-12-12
  • Contact: Lianyu ZHENG E-mail:lyzheng@buaa.edu.cn
  • Supported by:
    National Natural Science Foundation of China(52205244);China Advanced Manufacturing Technology Development Special Funding Program(62502500601)

Abstract:

Facing the challenge of frequent changes on aircraft models, it is necessary to achieve rapid design for aircraft assembly tooling. Aircraft product assembly tooling design is a long-term and high-cost tasks. Designers invest significant time and effort in tooling design, heavily relying on personal experience, with limited support and inheritance of tooling design knowledge. To address this issue, this study proposed an assembly tooling design knowledge recommendation approach based on knowledge graph and user behavior feedback. First, a knowledge document repository and a domain knowledge label network are constructed, forming a knowledge graph. Then, by constructing and activating a knowledge push scenario model, the priority of knowledge documents is computed based on their relevance between the knowledge push scenario and knowledge tags. Additionally, a knowledge push adjustment mechanism is proposed, and the priority of the knowledge documents will be adjusted based on user behaviors. Using aircraft wall panel tooling design as an example, this study validates the effectiveness of the user behavior-based parameter adjustment mechanism in knowledge recommendation. The example demonstrates that the accuracy of the proposed method in pushing the top 5 relevant knowledge documents is 0.83. Results also show that tags with higher search frequency are ranked higher, and user ratings of “helpful” significantly increase the priority of recommended knowledge under the same recommendation frequency. Additionally, a prototype system for aircraft panel assembly tooling design knowledge push is developed on the CATIA platform, applying the method to facilitate designers’ efficient access to relevant tooling knowledge.

Key words: aircraft tooling, tooling design, knowledge push, knowledge network, knowledge graph, user behavior feedback

CLC Number: