The Model and Data-Driven Digital Twin Technology for Ultimate Load-Bearing Capacity of the Rocket Propellant Tank Structure
-
摘要: 针对航天运载火箭关键承载贮箱结构，提出了一种基于实测数据和模型的极限承载数字孪生构建方法. 首先，根据贮箱结构及制造工艺特征建立精细化有限元模型，对强度特性进行计算分析，并根据贮箱结构强度试验测点信息提取计算结果. 然后，对贮箱结构强度试验历史试验数据进行了处理分析，基于试验数据和仿真模型构建出贮箱结构承载数字孪生模型的训练数据集. 进一步，结合长短期记忆网络模型对孪生算法进行训练，实现了贮箱结构极限承载的预测. 最后，基于离线交互和在线交互模式，构建了贮箱结构极限承载数字孪生系统，有效提升了虚实试验能力和效率，降低了试验成本和风险.Abstract: A digital twin methodology integrating physical measurements with computational modeling was proposed for predicting the ultimate load-bearing capacity of the key propellant tank structure in aerospace launch vehicles. First, a refined finite element model (FEM) was established based on the tank structural design and manufacturing process characteristics, to compute and analyze the structure strength, with results extracted specifically in positions corresponding to physical measurement points. Historical experimental data from structural strength tests were subsequently processed and analyzed. With both the test data and the simulation outputs, a comprehensive training dataset was constructed for the tank structure ultimate load-bearing capacity digital twin model. A long short-term memory (LSTM) network was then trained with this dataset to predict the structure ultimate load-bearing capacity. Finally, a dual-mode (offline and online interactive) digital twin system was implemented to predict the tank structure ultimate load-bearing performance. This proposed method significantly enhances virtual-physical testing ability and efficiency and reduces related testing costs and risks.
-
Key words:
- tank structure /
- ultimate load-bearing capacity /
- digital twin /
- long short-term memory
-
图 1 LSTM网络单元及构成
注 为了解释图中的颜色，读者可以参考本文的电子网页版本，后同.
Figure 1. The LSTM network element and structure
图 2 贮箱结构强度仿真结果(以筒段部分为例)
Figure 2. The tank structure strength analysis result (with the cylindrical part for example)
图 3 基于坐标值的测点有限元模型映射(以筒段部分为例)
Figure 3. Measurement positions mapped to the FEM model (with the cylindrical part for example)
图 8 基于LSTM的贮箱承载预测结果
Figure 8. The tank structure ultimate load-bearing capacity forecast values by the LSTM
图 9 贮箱结构承载数字孪生模型预测值与实测值对比
Figure 9. Comparison of the tank structure ultimate load-bearing capacity forecast values by the digital twin model and the measured values
-
[1] ROSEN R, VON WICHERT G, LO G, et al. About the importance of autonomy and digital twins for the future of manufacturing[J]. IFAC-Papers on Line, 2015, 48 (3): 567-572. doi: 10.1016/j.ifacol.2015.06.141 [2] GRIEVES M, VICKERS J. Digital twin: mitigating unpredictable, undesirable emergent behavior in complex systems[M]//Transdisciplinary Perspectives on Complex Systems. Switzerland: Springer International Publishing, 2017: 85-113. [3] SHAFTO M, CONROY M, DOYLE R, et al. Modeling, simulation, information technology & processing roadmap[R]. National Aeronautics and Space Administration, 2010. [4] TUEGEL E J, INGRAFFEA A R, EASON T G, et al. Reengineering aircraft structural life prediction using a digital twin[J]. International Journal of Aerospace Engineering, 2011, 2011 (1): 154798. [5] WANG L P, ASHER I, RYAN K, et al. Airframe digital twin (ADT), delivery order 0001: scalable, accurate, flexible, efficient, robust, prognostic, and probabilistic individual aircraft tracking (SAFER-P2IAT), volume 1[R]. 2016. [6] WANG L P, ASHER I, RYAN K, et al. Airframe digital twin (ADT), delivery order 0002: scalable, accurate, flexible, efficient, robust, prognostic, and probabilistic individual aircraft tracking (SAFER-P2IAT) full scale wing experiment plans, requirements, and development[R]. 2017. [7] LI C Z, MAHADEVAN S, LING Y, et al. Dynamic Bayesian network for aircraft wing health monitoring digital twin[J]. AIAA Journal, 2017, 55 (3): 930-941. doi: 10.2514/1.J055201 [8] 尹晚, 渠晓溪, 武湛君, 等. 火箭贮箱结构健康监测传感器系统设计[J]. 压电与声光, 2017, 39 (1): 67-71.YIN Wan, QU Xiaoxi, WU Zhanjun, et al. Design of the structural health monitoring sensor system for the rocket tank[J]. Piezoelectrics & Acoustooptics, 2017, 39 (1): 67-71. (in Chinese) [9] 王卓群, 郝鹏, 王禹, 等. 网格加筋结构集中力扩散肋的传力机理研究[J]. 导弹与航天运载技术, 2023(3): 44-51.WANG Zhuoqun, HAO Peng, WANG Yu, et al. Research on concentrated force diffusion through radial ribs in grid stiffened structures[J]. Missiles and Space Vehicles, 2023(3): 44-51. (in Chinese) [10] 田阔. 基于多保真度建模的多层级筒壳屈曲分析及优化方法研究[D]. 大连: 大连理工大学, 2018.TIAN Kuo. Research on buckling analysis and optimization methods of hierarchical cylindrical shells based on multi-fidelity modeling[D]. Dalian: Dalian University of Technology, 2018. (in Chinese) [11] 姜洪开, 张世英, 华明军, 等. 运输环境中火箭贮箱强度可靠性仿真[J]. 上海航天, 2001, 18 (6): 38-41.JIANG Hongkai, ZHANG Shiying, HUA Mingjun, et al. Intensity reliability simulation for rocket tank in transportation environmet[J]. Aerospace Shanghai, 2001, 18 (6): 38-41. (in Chinese) [12] 孟松鹤, 叶雨玫, 杨强, 等. 数字孪生及其在航空航天中的应用[J]. 航空学报, 2020, 41 (9): 023615.MENG Songhe, YE Yumei, YANG Qiang, et al. Digital twin and its aerospace applications[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41 (9): 023615. (in Chinese) [13] 陈自强. 基于LSTM网络的设备健康状况评估与剩余寿命预测方法的研究[D]. 合肥: 中国科学技术大学, 2019.CHEN Ziqiang. Research on equipment health assessment and remaining useful life prediction method based on LSTM[D]. Hefei: University of Science and Technology of China, 2019. (in Chinese) [14] 李杰. 基于LSTM的轴承寿命预测方法研究与软件实现[D]. 成都: 电子科技大学, 2022.LI Jie. Research and software implementation of bearing life prediction method based on LSTM[D]. Chengdu: University of Electronic Science and Technology of China, 2022. (in Chinese) -
下载:
计量
- 文章访问数: 32
- HTML全文浏览量: 7
- PDF下载量: 3
- 被引次数: 0
渝公网安备50010802005915号