目的 解决航空航天复杂装配过程中传统人工巡检实时性差、静态仿真性能预测精度低的问题,满足装备装配质量与服役可靠性的严苛需求。方法 融合人机协同（Human-Machine Collaboration,HMC）与虚拟现实（Virtual Reality,VR）技术,设计“物理层-数据层-融合层-应用层”4层系统架构;基于模糊综合评价法实现人机动态功能分配,采用改进长短期记忆网络（LSTM）以构建性能预测模型,结合区块链技术实现质量数据追溯,通过多传感器协同采集与边缘计算完成数据处理。结果 以航空发动机短舱对接工序为对象开展20组实验验证,系统关键参数采集率达98.7%（较传统模式提升36.4个百分点）,故障响应时间缩短至8.2 s（较传统模式缩短74.8%）;振动幅值预测准确率达97.2%（较静态仿真提升22.7个百分点）,连接强度预测偏差≤2.5 MPa,且能提前24 h实现潜在风险预警;装配操作准确率提升至98%,新工培训周期缩短50%。结论 该系统实现了航空航天复杂装配过程质量的动态管控与性能的精准预测,解决了传统模式“数据断链、响应滞后、预测不准”的痛点,为高端装备装配智能化升级提供了可落地的技术方案。
Abstract
The work aims to tackle the poor real-time performance of manual inspections and the low accuracy of static-simulation-based performance prediction in complex aerospace assembly, so as to meet stringent requirements for assembly quality and in-service reliability. Through the integration of Human-Machine Collaboration (HMC) and Virtual Reality (VR) a four-layer system architecture (physical, data, fusion, and application) was designed. Then, the dynamic human-machine function allocation was achieved via a fuzzy comprehensive evaluation method, the improved Long Short-Term Memory (LSTM) network was used for performance prediction, the blockchain was combined to ensure traceability of quality data and the multi-sensor collaborative acquisition with edge computing was employed to complete data processing. Validated across 20 experiments on an aero-engine nacelle docking operation, the system achieved a 98.7% key-parameter acquisition rate (up by 36.4 percentage points compared to that of the conventional approach) and reduced fault response time to 8.2 s (a 74.8% reduction). Vibration amplitude prediction accuracy reached 97.2% (22.7 percentage points higher than static simulation), joint strength prediction error was ≤2.5 MPa, and potential risks could be flagged 24 h in advance. The assembly operation accuracy increased to 98%, and the training cycle for new workers was shortened by 50%. Overall, the system enables dynamic quality control and precise performance prediction for complex aerospace assembly, addressing the conventional pain points of "data discontinuity, delayed response, and inaccurate prediction", and offers a deployable pathway for the intelligent upgrading of high-end equipment assembly.
关键词
航空航天装配 /
人机协作 /
虚拟现实 /
质量控制 /
性能预测
Key words
aerospace assembly /
human-machine collaboration /
virtual reality /
quality control /
performance prediction
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] WANG J R.Anexternally Guided Spatial Augmented Reality Assembly Assistance System in the Aviation Manufacturing Industry." The International Journal of Advanced Manufacturing Technology[J]. 2024, 133(9): 4893-4906.
[2] LIU P.Optimization Method for Assembly Sequence Evaluation Based on Assembly Cost and Ontology of Aviation Reducers[J]. Applied Sciences, 2024, 14(12): 2076-3417.
[3] ZHOU B.Aviation Equipment Measurement and Assembly Analysis Method Based on Robotic System[J]. Measurement, 2024(234): 18.
[4] ZHAI J R.Analysis of the Influence of Assembly Deviation and Repeated Assembly on Sealing Performance of Detachable Aviation Pipe Joint[J]. International Journal of Pressure Vessels and Piping, 2024, 6(209): 1-3.
[5] 吴吉展, 魏沛堂, 吴少杰, 等. 航空齿轮钢滚动接触疲劳性能预测与表面完整性优化[J].机械工程学报, 2024, 60(8): 81-93.
WU J Z, WEI P T, WU S J, et al.Rolling Contact Fatigue Performance Prediction and Surface Integrity Optimization of Aviation Gear Steel[J]. State Key Laboratory of Mechanical Transmissions, 2024, 60(8): 81-93.
[6] 赵德望, 姜超, 赵延广, 等. 铝锂合金疲劳性能及预测研究——基于试验和“浅层”+“深度”混合神经网络方法[J]. 机械工程学报, 2024, 60(16): 190-199.
ZHAO D W, JIANG C, ZHAO Y G, et al.Fatigue Performance Prediction Study of Al-Li Alloy--based on Experimental and "Shallow" + "Deep" Hybrid Neural Network Methods[J]. State Key Laboratory of Mechanical Transmissions, 2024, 60(16): 190-199.
[7] 周运龙, 马毅, 管迎春. 面向航空发动机高性能制造的激光选区熔化技术研究进展[J]. 航空学报, 2024, 45(13): 43-80.
ZHOU Y L, MA Y, GUAN Y C.Research Progress on Laser Selective Melting Technology for High-performance Manufacturing of Aero-engines[J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(13): 43-80.
[8] 董宇. 航空航天用2050铝锂合金蠕变时效组织与性能调控研究[D]. 长沙: 中南大学, 2023.
DONG Y.Research on Structures and Properties Control of Creep-aged 2050 Al-Li Alloy for Aircraft[D]. Changsha: Central South University, 2023.
[9] 余海东, 高畅, 赵勇, 等. 机械产品装配偏差分析方法研究进展与展望[J]. 机械工程学报, 2023, 6(8): 6-9.
YU H D, GAO C, ZHAO Y, et al.Progress and Prospect on Assembly Deviation Propagation of Mechanical Products[J]. State Key Laboratory of Mechanical Transmissions, 2023, 6(8): 6-9.
[10] 胡雅楠, 余欢, 吴圣川, 等. 基于机器学习的增材制造合金材料力学性能预测研究进展与挑战[J]. 力学学报, 2024, 56(7): 1892-1915.
HU Y N, YU H, WU S C, et al.Research Progress and Challenges for the Prediction of Mechanical Properties of Alloy Materials for Additive Manufacturing Based on Machine Learning[J]. Chinese Journal of Theoretical and Applied Mechanics, 2024, 56(7): 1892-1915.
[1] 胡元杰, 陈绍雄, 朱书华, 等. 基于多尺度方法的平纹机织SiC/SiC复合材料力学性能预测[J]. 航空精密制造技术, 2024, 60(3): 13-19.
HU Y J, CHEN S X, ZHU S H, et al.Prediction of Mechanical Properties Using Multi-scale Approach for Plain Woven SiC/SiC Composites[J]. Aviation Precision Manufacturing Technology, 2024, 60(3): 13-19.
[11] 曹兴枫. 基于近场动力学的CFRP螺栓连接结构失效过程建模及仿真研究[D]. 天津: 天津大学, 2023.
CAO X F.Modeling and Simulation of the Failure Process of Carbon Fiber Reinforced Polymer Bolted Structure based on Peridynamics[D]. Tianjin: Tianjin University, 2023.
[12] 李壮. 数据驱动的非晶合金成分及性能预测[D]. 湘潭: 湘潭大学, 2023.
LI Z.Data-driven Prediction of Composition and Properties of Amorphous Alloys[D]. Tianjin: Tianjin University, 2023.
[13] 龚文驰, 包胜, 陈铭, 等. 一体化发电-制冷系统性能特性研究[J]. 北京航空航天大学学报, 2024, 56(7): 1892-1915.
GONG W C, BAO S, CHEN M, et al.Research on Performances and Features of Integrated Power Generation-Cooling System[J].Journal of Beijing University of Aeronautics and Astronautics, 2024, 56(7): 1892-1915.
[14] 李少敏, 隋鹏, 彭海春, 等. 先进复合材料制造过程仿真技术研究现状[J]. 科学技术与工程, 2024, 24(29): 12399-12410.
LI S M, SUI P, PENG H C, et al.Review of Advanced Composite Manufacturing Process Si-mulation Technology[J]. Science Technology and Engineering, 2024, 24(29): 123-124.
基金
辽宁省教育厅项目-基本科研业务费专项（特色学科）（纵20240170）
PDF(1538 KB)
渝公网安备 50010702501717号