Solid Mechanics and Vehicle Conceptual Design

Physical embedded neural network model and method for dynamic load identification

  • Zhichun YANG ,
  • Te YANG
Expand
  • 1.School of Aeronautics,Northwestern Polytechnical University,Xi’an 710072,China
    2.National Key Laboratory of Strength and Structural Integrity,Xi’an 710072,China
    3.National Key Laboratory of Aerospace Physics in Fluids,Mianyang 621000,China
E-mail: yangzc@nwpu.edu.cn

Received date: 2024-10-28

  Revised date: 2024-11-07

  Accepted date: 2024-11-27

  Online published: 2024-12-10

Supported by

Aeronautical Science Foundation of China(20220015053002);Research Fund of National Key Laboratory of Aerospace Physics in Fluids(2024-APF-KFQMJJ-10)

Abstract

To address the ill-posedness caused by the inversion of the frequency response function matrix in traditional dynamic load identification methods, as well as the lack of physical interpretability in deep learning methods, a novel Physical Embedded Neural Network (PENN) for dynamic load identification is proposed. By embedding structural dynamic parameters, such as modal mass, modal stiffness, and modal damping, directly into the neural network, the PENN model is constructed to offer physical interpretability. The PENN model can directly identify the power spectral density of dynamic loads through a forward computational process, avoiding the need for inverting the frequency response function matrix as in traditional methods. Additionally, this model can adaptively adjust internal physical parameters, ensuring high-precision identification of dynamic loads even when prior physical parameters are inaccurate. The paper provides a detailed explanation of the method’s mechanism, the construction rules of the PENN model, parameter settings, and the training process. Numerical simulations and experimental validations were conducted under various conditions The results show that even when the prior dynamic system parameters are inaccurate and only one training sample is available, the Pearson correlation coefficient of dynamic load identification was consistently above 95%, demonstrating strong robustness and potential for engineering applications.

Cite this article

Zhichun YANG , Te YANG . Physical embedded neural network model and method for dynamic load identification[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2025 , 46(5) : 531450 -531450 . DOI: 10.7527/S1000-6893.2024.31450

References

1 杨智春, 王魏, 李斌, 等. 航空结构动强度分析与设计[M]. 西安: 西北工业大学出版社, 2021: 1-5.
  YANG Z C, WANG W, LI B, et al. Dynamic strength analysis and design of aviation structure?[M]. Xi’?an: Northwestern Polytechnical University Press, 2021: 1-5 (in Chinese).
2 王文睿. 炮舱结构在冲击载荷作用下的振动特性分析[D]. 西安: 西北工业大学, 2007.
  WANG W R. Analysis of vibration characteristics of Gun cabin structure under impact load[D]. Xi’?an: Northwestern Polytechnical University, 2007 (in Chinese).
3 赵志彬. 飞机炮舱结构有限元静力分析及疲劳寿命估算[D]. 西安: 西北工业大学, 2007.
  ZHAO Z B. Finite element static analysis and fatigue life estimation of aircraft Gun cabin structure?[D]. Xi’?an: Northwestern Polytechnical University, 2007 (in Chinese).
4 陈忠明, 何连珠. 炮舱结构段的动特性与动响应分析[J]. 飞机设计199818(3): 16-23.
  CHEN Z M, HE L Z. Dynamic characteristics and dynamic response analysis of Gun cabin structure section[J]. Aircraft Design199818(3): 16-23 (in Chinese).
5 杨智春, 贾有. 动载荷的识别方法[J]. 力学进展201545(0): 29-54.
  YANG Z C, JIA Y. The identification of dynamic loads[J]. Advances in Mechanics201545(0): 29-54 (in Chinese).
6 BARTLETT F D, FLANNELLY W G. Model verification of force determination for measuring vibratory loads[J]. Journal of the American Helicopter Society197924(2): 10-18.
7 张景绘, 李万新. 直升机六力素识别[J]. 航空学报19867(2): 139-147.
  ZHANG J H, LI W X. Six-force-factor identification of helicopters[J]. Acta Aeronautica et Astronautica Sinica19867(2): 139-147 (in Chinese).
8 方明新. 超高层建筑风荷载反演分析[D]. 武汉: 武汉理工大学, 2016.
  FANG M X. Inverse analysis of wind load on super high-rise building[D]. Wuhan: Wuhan University of Technology, 2016 (in Chinese).
9 黄坤. 基于高层建筑动力响应的动荷载反演研究[D]. 武汉: 武汉理工大学, 2019.
  HUANG K. Study on dynamic load inversion based on dynamic response of high-rise buildings?[D]. Wuhan: Wuhan University of Technology, 2019 (in Chinese).
10 LAW S S, CHAN T H T, ZENG Q H. Moving force identification: A time domain method?[J]. Journal of Sound and Vibration1997201(1): 1-22.
11 张方, 秦远田, 邓吉宏. 桥梁结构移动载荷识别的新方法[J]. 南京航空航天大学学报200638(1): 22-26.
  ZHANG F, QIN Y T, DENG J H. Dynamic moving load identification method for bridge structure[J]. Journal of Nanjing University of Aeronautics & Astronautics200638(1): 22-26 (in Chinese).
12 杜玲, 李范春. 西部高墩大跨径桥梁桥墩的失稳载荷识别方法[J]. 应用基础与工程科学学报201624(2): 304-314.
  DU L, LI F C. Research of buckling load identification method about piers of western high pier long-span bridges[J]. Journal of Basic Science and Engineering201624(2): 304-314 (in Chinese).
13 董庆锋, 徐兴平, 畅元江, 等. 时域载荷识别法在海洋结构中的应用[J]. 钢结构200520(5): 57-59.
  DONG Q F, XU X P, CHANG Y J, et al. Research on identification of dynamic forces on offshore platform[J]. Steel Construction200520(5): 57-59 (in Chinese).
14 OKUBO N, TANABE S, TATSUNO T. Identification of forces generated by a machine under operating condition?[C]?∥Proceedings of the 3rd International Modal Analysis Conference (IMAC). 1985: 920-927.
15 冀灵子. 基于电机电流的转子系统载荷识别方法研究[D]. 太原: 太原理工大学, 2016.
  JI L Z. Research on load identification method of rotor system based on motor current?[D]. Taiyuan: Taiyuan University of Technology, 2016 (in Chinese).
16 郑海起, 马吉胜. 基于铣削力识别的铣削监测与铣刀故障诊断[J]. 振动、测试与诊断200222(2): 89-92.
  ZHENG H Q, MA J S. Milling monitoring and its cutter fault diagnosis by milling forces[J]. Journal of Vibration, Measurement & Diagnosis, 200222(2): 89-92 (in Chinese).
17 赵继, 王立江, 孟继安. 超声振动切削系统中弯曲振动刀杆的谐振模式[J]. 声学学报199217(1): 22-29.
  ZHAO J, WANG L J, MENG J A. The resonance pattern of cutter bar in ultrasonic vibration cutting system[J]. Acta Acustica199217(1): 22-29 (in Chinese).
18 孟光, 周徐斌, 苗军. 航天重大工程中的力学问题[J]. 力学进展201646(0): 267-322.
  MENG G, ZHOU X B, MIAO J. Mechanical problems in momentous projects of aerospace engineering[J]. Advances in Mechanics201646(0)?: 267-322 (in Chinese).
19 WANG L, LIU Y R, XU H Y. Review: Recent developments in dynamic load identification for aerospace vehicles considering multi-source uncertainties[J]. Transactions of Nanjing University of Aeronautics and Astronautics202138(2): 271-287.
20 张曾, 张江监, 王裕昌. 飞机起落架滑行载荷识别[J]. 航空学报199415(1): 54-61.
  ZHANG Z, ZHANG J J, WANG Y C. Identification of airplane landing gear loads during taxiing[J]. Acta Aeronautica et Astronautica Sinica199415(1): 54-61 (in Chinese).
21 侯乔乔. 全机落震载荷识别方法研究[J]. 工程与试验201959(4): 24-26.
  HOU Q Q. Research on load recognition method of ship-borne aircraft’s full-scale drop?[J]. Engineering & Test201959(4): 24-26 (in Chinese).
22 王洪波, 赵长见, 廖选平, 等. 基于飞行工作模态分析的飞行器动载荷识别研究[J]. 动力学与控制学报201715(2): 178-183.
  WANG H B, ZHAO C J, LIAO X P, et al. Study on dynamic load identification of aircraft based on operational mode analysis[J]. Journal of Dynamics and Control201715(2): 178-183 (in Chinese).
23 刘恒春, 朱德懋, 孙久厚. 振动载荷识别的奇异值分解法[J]. 振动工程学报19903(1): 24-33.
  LIU H C, ZHU D M, SUN J H. A singular value decomposition method for the identification vibration loads?[J]. Journal of Vibration Engineering19903(1): 24-33 (in Chinese).
24 O’CALLAHAN J, PIERGENTILI F. Force estimation using operational data[C]∥Proceedings of the 14th International Modal Analysis Conference (IMAC). 1996: 1586-1592.
25 KARLSSON S E S. Identification of external structural loads from measured harmonic responses?[J]. Journal of Sound and Vibration1996196(1): 59-74.
26 田燕, 王菁, 郑海起. 多载荷识别频响函数矩阵求逆法的改进算法[J]. 军械工程学院学报200214(4): 13-17.
  TIAN Y, WANG J, ZHENG H Q. Improved algorithm of inverse matrix of frequency response function in multi-load identification?[J]. Journal of Ordnance Engineering College200214(4): 13-17 (in Chinese).
27 吕洪彬. 基于逆系统的动态载荷识别研究[D]. 大连: 大连理工大学, 2010.
  LüH B. Research on dynamic load identification based on inverse system?[D]. Dalian: Dalian University of Technology, 2010 (in Chinese).
28 YU L, CHAN T H T. Moving force identification based on the frequency-time domain method?[J]. Journal of Sound and Vibration2003261(2): 329-349.
29 JACQUELIN E, BENNANI A, HAMELIN P. Force reconstruction: Analysis and regularization of a deconvolution problem?[J]. Journal of Sound and Vibration2003265(1): 81-107.
30 LIU Y, SHEPARD W S. Dynamic force identification based on enhanced least squares and total least-squares schemes in the frequency domain?[J]. Journal of Sound and Vibration2005282(1-2): 37-60.
31 梅立泉, 崔维庚. 面载荷识别的TSVD正则化方法[J]. 应用力学学报201027(1): 140-144, 229-230.
  MEI L Q, CUI W G. TSVD regularization method for area load reconstruction?[J]. Chinese Journal of Applied Mechanics201027(1): 140-144, 229-230 (in Chinese).
32 毛玉明, 陈健, 刘靖华, 等. 考虑模型误差的动载荷反演问题研究[J]. 振动与冲击201231(24): 16-19.
  MAO Y M, CHEN J, LIU J H, et al. Dynamic loading estimation problem with structural model errors[J]. Journal of Vibration and Shock201231(24): 16-19 (in Chinese).
33 郑晓霞, 郑锡涛, 缑林虎. 多尺度方法在复合材料力学分析中的研究进展[J]. 力学进展201040(1): 41-56.
  ZHENG X X, ZHENG X T, GOU L H. The research progress on multiscale method for the mechanical analysis of composites?[J]. Advances in Mechanics201040(1): 41-56 (in Chinese).
34 ZHOU J, DONG L L, GUAN W, et al. Impact load identification of nonlinear structures using deep recurrent neural network?[J]. Mechanical Systems and Signal Processing2019133: 106292.
35 STASZEWSKI W J, WORDEN K, WARDLE R, et al. Fail-safe sensor distributions for impact detection in composite materials?[J]. Smart Materials and Structures20009(3): 298-303.
36 GHAJARI M, SHARIF-KHODAEI Z, ALIABADI M H, et al. Identification of impact force for smart composite stiffened panels?[J]. Smart Materials and Structures201322(8): 085014.
37 WANG J Y. MIMO SVM based uncorrelated multi-source dynamic random load identification algorithm in frequency domain?[J]. Journal of Computational In-formation Systems201511(22): 8165-8176.
38 WANG J G, ZHANG J, WANG Y J, et al. Nonlinear identification of one-stage spur gearbox based on pseudo-linear neural network?[J]. Neurocomputing2018308: 75-86.
39 REN S F, CHEN G R, LI T G, et al. A deep learning-based computational algorithm for identifying damage load condition: an artificial intelligence inverse problem solution for failure analysis[J]. Computer Modeling in Engineering & Sciences2018117(3): 287-307.
40 CHEN G R, LI T G, CHEN Q J, et al. Application of deep learning neural network to identify collision load conditions based on permanent plastic deformation of shell structures?[J]. Computational Mechanics201964(2): 435-449.
41 夏鹏. 利用深度学习的动载荷识别方法研究[D]. 西安: 西北工业大学, 2019.
  XIA P. Research on dynamic load identification method using deep learning?[D]. Xi’?an: Northwestern Polytechnical University, 2019 (in Chinese).
42 夏鹏, 杨特, 徐江, 等. 利用时延神经网络的动载荷倒序识别[J]. 航空学报202142(7): 224452.
  XIA P, YANG T, XU J, et al. Reversed time sequence dynamic load identification method using time delay neural network[J]. Acta Aeronautica et Astronautica Sinica202142(7): 224452 (in Chinese).
43 杨特, 杨智春, 梁舒雅, 等. 平稳随机载荷的信号特征提取与深度神经网络识别[J]. 航空学报202243(9): 225952.
  YANG T, YANG Z C, LIANG S Y, et al. Feature extraction and identification of stationary random dynamic load using deep neural network[J]. Acta Aeronautica et Astronautica Sinica2022, 43(9)?: 225952 (in Chinese).
44 张方, 朱德懋. 基于神经网络模型的动载荷识别[J]. 振动工程学报1997(2): 40-46.
  ZHANG F, ZHU D M. Dynamic load identification based on neural network model?[J]. Journal of Vibration Engineering1997(2): 40-46 (in Chinese).
45 JIA Y, YANG Z C, GUO N, et al. Random dynamic load identification based on error analysis and weighted total least squares method?[J]. Journal of Sound and Vibration2015358: 111-123.
46 伍旭强, 张雷, 朱继梅. 结构有限元模型的元素修正法[J]. 振动工程学报19925(2): 178-181.
  WU X Q, ZHANG L, ZHU J M. Element correction method for structural finite element models[J]. Journal of Vibration Engineering19925(2): 178-181 (in Chinese).
47 HU H Y. Vibration mechanics?[M]. Singapore: Springer, 2022: 45-51.
Outlines

/