Skip to main content

Advertisement

Comparative study on ballistic impact detection in helicopter transmission shafts using NARX and LSTM models

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Vibration-based techniques are vital for online structural health monitoring (SHM) of rotating machines, enabling fault detection through feature analysis and threshold establishment. Rotating shafts typically exhibit non-linear dynamic behaviour, often due to misalignment or manufacturing imperfections leading to eccentricity. This non-linear behaviour is amplified after ballistic impact, leading to significant asymmetries and increased vibration loads. In this study, we develop an advanced vibration-based method to address the gap in diagnostic tools used to identify ballistic impact damage in helicopter transmission shafts. The proposed scheme employs a non-linear autoregressive model with exogenous inputs (NARX), evaluated against a long short-term memory (LSTM) model, to estimate acceleration signals from a two-sensor cluster. It then uses the estimation error arising from significant variations in signals acquired before and after ballistic impact to assess the structural integrity of the operating structure. The efficiency of the models is validated using experimental data obtained during ballistics testing. The results show that the proposed method effectively detects various types of impact damage, offering a promising tool for ballistic impact diagnosis in helicopter transmission shafts.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23
Fig. 24

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data Availability

Data will be available on reasonable request.

References

  1. Zhang W, Sun Z, Lv D, Zuo Y, Wang H, Zhang R (2024) A Time Series Prediction-Based Method for Rotating Machinery Detection and Severity Assessment. Aerosp 11:537

    Article  MATH  Google Scholar 

  2. Panagiotopoulou V, Sbarufatti C, Giglio M (2024) Samas 2: Structural health and ballistic impact monitoring and prognosis on a military helicopter. Procedia Struct Integr 54:482–489

    Article  Google Scholar 

  3. Fossati M, Pagani M, Giglio M, Manes A (2021) Fatigue crack propagation in a helicopter component subjected to impact damage. Defence Technol 17:416–428

    Article  MATH  Google Scholar 

  4. Mironov A, Doronkin D (2021) The demonstrator of structural health monitoring system of helicopter composite blades. Procedia Struct Integr 37:241–249

    Article  MATH  Google Scholar 

  5. Stupar S, Simonovic A, Jovanović M (2012) Measurement and analysis of vibrations on the helicopter structure in order to detect defects of operating elements. Sci Tech Rev 62:58–63

    MATH  Google Scholar 

  6. Adetu C, Hadar A, Nastasescu V, Adetu AE, Voicu AD, Pastrama SD (2023) Ballistic protection plates for military helicopters structures: Experimental and numerical research. Mater Today Proc 93:618–624

    Article  Google Scholar 

  7. Zhang C, Zhu R, Wang D, Cao P, Li J, Peng L (2023) Dynamic characteristics analysis and the identification signal of the horizontal tail drive shaft system with the ballistic impact damage of a helicopter. Struct Health Monit 17:416–428

    MATH  Google Scholar 

  8. Goda I, Girardot J (2021) A computational framework for energy absorption and damage assessment of laminated composites under ballistic impact and new insights into target parameters. Aerosp Sci Technol 115:106835

    Article  MATH  Google Scholar 

  9. Ma Y, Wang J, Zhao G, Liu Y (2021) New insights into the damage assessment and energy dissipation weight mechanisms of ceramic/fiber laminated composites under ballistic impact. Ceram Int 49:21966–21977

    Article  Google Scholar 

  10. Steinke K, Groo L, Sodano HA (2021) Laser induced graphene for in-situ ballistic impact damage and delamination detection in aramid fiber reinforced composites. Compos Sci Technol 202:108551

    Article  Google Scholar 

  11. Zhang C, Wang D, Zhu R (2023) Dynamic modeling and vibration characteristics analysis for the helicopter horizontal tail drive shaft system with the ballistic impact vertical penetrating damage. Iran J Sci Technol Trans Mech Eng 47:1177–1190

    Article  MATH  Google Scholar 

  12. Cusido J, Romeral L, Ortega JA, Rosero JA, Espinosa AG (2008) Fault detection in induction machines using power spectral density in wavelet decompositionr. Trans Ind Electr 55:633–643

    Article  Google Scholar 

  13. Sinou JJ (2022) Damage Detection in a Rotor Dynamic System by Monitoring Nonlinear Vibrations and Antiresonances of Higher Orders. Appl Sci 12:11904

    Article  MATH  Google Scholar 

  14. Spagnol J, Wu H, Yang C (2020) Application of non-symmetric bending principles on modelling fatigue crack behaviour and vibration of a cracked rotor. Appl Sci 10:717

    Article  MATH  Google Scholar 

  15. Ou Y, Chatzi E, Spriridonakos M (2016) Vibration-based experimental damage detection of a small-scale wind turbine blades. Struct Health Monit 16

  16. Panagiotopoulos A, Tcherniak D, Fassois S (2022) Damage detection on the blade of an operating wind turbine via a single vibration sensor and statistical time series methods: Exploring the performance limits of robust methods. Struct Health Monit 22

  17. Li S, Li H, Liu Y, Lan C, Zhou W, Ou J (2014) Smc structural health monitoring benchmark problem using monitored data from an actual cable-stayed bridge. Struct Control Health Monit 21(2):156–172

    Article  MATH  Google Scholar 

  18. Ni F, Zhang J, Noori MN (2020) Deep learning for data anomaly detection and data compression of a long-span suspension bridge. Comput Aided Civ Infrastruct Eng 35:685–700

    Article  MATH  Google Scholar 

  19. Tiboni M, Remino C, Bussola R, Amici C (2022) A Review on Vibration-Based Condition Monitoring of Rotating Machinery. Appl Sci 12:972

    Article  Google Scholar 

  20. Liu H, Sun Y, Wang X, Wu H, Wang H (2025) Npformer: Interpretable rotating machinery fault diagnosis architecture design under heavy noise operating scenarios. Mech Syst Signal Process 223:111878

    Article  Google Scholar 

  21. Prasad S, Kumar D, Kalra S, Khandelwal A (2024) A real-time feature-based clustering approach for vibration-based shm of large structures. Meas 227:114222

    Article  Google Scholar 

  22. Ma Y, Liu H, Zhu Y, Wang F, Luo Z () The NARX model-based system identification on nonlinear, rotor - bearing systems. Appl Sci 7

  23. Rezende SWF (2023) ISHM for fault condition detection in rotating machines with deep learning models. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 45–212

  24. Hu L, Bao Y, Sun Z, Meng X, Tang C, Zhang D (2023) Outlier detection based on nelder-mead simplex robust kalman filtering for trustworthy bridge structural health monitoring. Remote Sens 15:2385

    Article  MATH  Google Scholar 

  25. Asadi D (2022) Model-based Fault Detection and Identification of a Quadrotor with Rotor Fault. Int J Aeronaut Space Sci 23:916–928

    Article  MATH  Google Scholar 

  26. Gao Y, Yu C, Zhu YP, Luo Z (2023) A NARX Model-Based Condition Monitoring Method for Rotor Systems. Sensors 23:6878

    Article  MATH  Google Scholar 

  27. Lin CL, Liang JW, Huang YM, Huang SC (2023) A novel model-based unbalance monitoring and prognostics for rotor-bearing systems. Adv Mech Eng 15:1–16

    Article  MATH  Google Scholar 

  28. Soualhi A, Medjaher K, Celrc G, Razik H (2020) Prediction of bearing failures by the analysis of the time series. Mech Syst Signal Process 139:106607

    Article  Google Scholar 

  29. Fan C, Wu Q, Zhao Y, Mo L (2024) Integrating active learning and semi-supervised learning for improved data-driven HVAC fault diagnosis performance. Appl Energy 356:122356

    Article  Google Scholar 

  30. Khashei M, Bijari M, Raissi AGA (2009) Improvement of auto-regressive integrated moving average models using fuzzy logic and artificial neural networks (anns). Neurocomput 72:956–967

    Article  MATH  Google Scholar 

  31. Santos A, Figueiredo E, Silva MFM, Sales CS, Costa JCWA (2016) Machine learning algorithms for damage detection: Kernel-based approaches. Sound Vib 363:584–599

    Article  MATH  Google Scholar 

  32. Shuo Zhang S, Robinson E, Basu M (2022) Hybrid gaussian process regression and fuzzy inference system based approach for condition monitoring at the rotor side of a doubly fed induction generator. Renew Energy 198:936–946

    Article  MATH  Google Scholar 

  33. Liu Y, Xu Z, Zhao J, Song C, Shao Z (2023) Multi-scale adaptive multivariate state estimation fault detection enhancement for time-varying industrial system based on multi-output gaussian process autoregression. Comput Ind Eng 170:109502

    Article  Google Scholar 

  34. Kaur J, Singh PK, Singh S (2023) Autoregressive models in environmental forecasting time series: a theoretical and application review. Environ Sci Pollut Res 30:19617–19641

    Article  MATH  Google Scholar 

  35. Imamura LY, Avila SL, Pacheco FS (2022) Diagnosis of unbalance in lightweight rotating machines using a recurrent neural network suitable for an edge-computing framework. J Control Autom Electr Syst 33:1272–1285

    Article  MATH  Google Scholar 

  36. Xu Y, Zheng D, Shao C, Zheng S, Gu H, Chen H (2023) Real-time diagnosis of structural damage based on narx neural network with dynamic response. Math 11:1281

    Article  MATH  Google Scholar 

  37. Xie Y, Zhang T (2020) A long short term memory recurrent neural network approach for rotating machinery fault prognosis. CSAA Guidance, Navigation and Control Conference 139:737–747

    MATH  Google Scholar 

  38. Rezazadeh N, de Oliveira M, Perfetto D, De Luca A, Caputo F (2020) Classification of unbalanced and bowed rotors under uncertainty using wavelet time scattering, lstm, and svm. Appl Sci 12:6861

  39. Mirzaei S, Kang JL, Chu KY (2022) A comparative study on long short-term memory and gated recurrent unit neural networks in fault diagnosis for chemical processes using visualization. J Taiwan Inst Chem Eng 130:104028

    Article  Google Scholar 

  40. Amirkhani S, Chaibakhsh A, Ghaffari A (2020) Nonlinear robust fault diagnosis of power plant gas turbine using Monte Carlo-based adaptive threshold approach. ISA Trans 100:171–184

    Article  MATH  Google Scholar 

  41. Yang R, Huang M, Lu Q, Zhong M (2018) Rotating machinery fault diagnosis using long-short-term memory recurrent neural network. IFAC-PapersOnLine 51:228–232

  42. Yu W, Gonzalez J, Li X (2021) Fast training of deep lstm networks with guaranteed stability for nonlinear system modeling. Neurocomput 422:85–94

    Article  MATH  Google Scholar 

  43. Keshun Y, Puzhou W, Yingkui G (2024) Toward efficient and interpretative rolling bearing fault diagnosis via quadratic neural network with bi-lstm. Internet Things J 11:23002–23019

    Article  Google Scholar 

  44. Nie S, Qingtong L, Ji H, Hong R, Nie S (2022) Integration of arima and lstm models for remaining useful life prediction of a water hydraulic high-speed on/off valve. Appl Sci 12:8071

    Article  MATH  Google Scholar 

  45. Sharifzadeh M, Sikinioti-Lock A, Shah N (2019) Machine-learning methods for integrated renewable power generation: A comparative study of artificial neural networks, support vector regression, and gaussian process regression. Renew Sust Energ Rev 108:513–538

    Article  Google Scholar 

  46. Mak MW, Ku KW, Lu YL (1999) On the improvement of the real time recurrent learning algorithm for recurrent neural networks. Neurocomput 24:13–36

    Article  MATH  Google Scholar 

  47. Menezes MP, Barreto GA (2008) Long-term time series prediction with the narx network: An empirical evaluation. Neurocomput 71:3335–3343

    Article  MATH  Google Scholar 

  48. Rai A, Upadhyay SH (2017) The use of md-cumsum and narx neural network for anticipating the remaining useful life of bearings. Meas 111:397–410

    Article  MATH  Google Scholar 

  49. Li Y, Luoa Z, Hea F, Zhub Y, Gea X (2021) Modeling of rotating machinery: A novel frequency sweep system identification approach. Sound Vib 494:115882

    Article  Google Scholar 

  50. Huang Y, Han X, Zhao L (2021) Recurrent neural networks for complicated seismic dynamic response prediction of a slope system. Eng Geol 289:106–198

    Article  MATH  Google Scholar 

  51. Yan L, Elgamal AW, Cottrell GW (2013) Substructure vibration narx neural network approach for statistical damage inference. J Eng Mech 139:737–747

    Article  MATH  Google Scholar 

  52. Amirkhani S, Tootchi A, Chaibakhsh A (2022) Fault detection and isolation of gas turbine using series-parallel NARX model. ISA Trans 120:205–221

    Article  MATH  Google Scholar 

  53. Lin T, Horne BG, Tino P, Giles CL (1996) Learning long-term dependencies in NARX recurrent neural networks. IEEE Trans Neural Netw 7:1329–1338

    Article  MATH  Google Scholar 

  54. Samudra S, Barbosh M, Sadhu A (2023) Machine learning-assisted improved anomaly detection for structural health monitoring. Sens 23:3365

  55. James G, Witten D, Hastie T, Tibshirani R (2013) An introduction to statistical learning: With applications in r. Compos Sci Techno

  56. Umar S, Vafaei M, Alih SC (2021) Sensor clustering-based approach for structural damage identification under ambient vibration. Autom Constr 121:103433

    Article  Google Scholar 

  57. Choi J, Jun Lee S (2020) Consistency Index-Based Sensor Fault Detection System for Nuclear Power Plant Emergency Situations Using an LSTM Network. Sens

  58. Zhang Q, Ljung L (2004) Multiple steps prediction with nonlinear ARX models. IFAC Proc 37:309–314

    MATH  Google Scholar 

  59. Garcia-Rodenas R, Jimenez Linares L, Lopez-Gomez JA (2020) Memetic algorithms for training feedforward neural networks: an approach based on gravitational search algorithm. Neural Comput & Applic 33:2561–2588

    Article  MATH  Google Scholar 

  60. Hochreiter S, Schmidhuber J (1997) Long Short-Term Memory. Neural Comput 9:1735–1780

    Article  MATH  Google Scholar 

  61. Yu Y, Si X, Hu C, Zhang J (2019) A review of recurrent neural networks: Lstm cells and network architectures. Neural Comput 31:1235–1270

    Article  MathSciNet  MATH  Google Scholar 

  62. Gustafsson F (1996) Determining the initial states in forward-backward filtering. Trans Signal Process 44:988–992

    Article  MATH  Google Scholar 

  63. Xiang L, Zhang Y, Hu A (2019) Crack characteristic analysis of multi-fault rotor system based on whirl orbits. Springer Link 95:2675–2690

    MATH  Google Scholar 

  64. COMSOL: Rotordynamics Module User’s Guide. COMSOL

  65. Worden K, Manson G, Fieller NRJ (2000) Damage detection using outlier analysis. JSound Vib 229:647–667

    Article  MATH  Google Scholar 

  66. Bayane I, Leander J, Karoumi R (2024) An unsupervised machine learning approach for real-time damage detection in bridges. Eng Struct 308:117971

    Article  Google Scholar 

  67. Sharma S, Sen S (2022) Real-time structural damage assessment using LSTM networks: regression and classification approaches. Neural Comput & Applic 35:557–572

    Article  MATH  Google Scholar 

  68. Khazaee M, Banakar A, Ghobadian B, Mirsalim M, Minaei S, Jafari M, Sharghi P (2016) Fault detection of engine timing belt based on vibration signals using data-mining techniques and a novel data fusion procedure. SHM 15:583–598

    Google Scholar 

Download references

Acknowledgements

This work has been developed based on the results from SAMAS 2 project (Structural health and ballistic impact monitoring and prognosis on a military helicopter), a Cat.-B project (B PRJ-RT 1074) coordinated by the European Defense Agency (EDA) and involving two nations, Italy and Poland.

Author information

Authors and Affiliations

Authors

Contributions

Vasiliki Panagiotopoulou: Conceptualization, Methodology, Algorithms, Experimental activities, Writing. Lorenzo Brancato: Conceptualization, Modelling, Writing. Emanuele Petriconi: Experimental activities, Writing. Andrea Baldi: Experimental activities, Writing-review and editing. Ugo Mariani: Experimental activities, Writing-review and editing. Marco Giglio: Resources, Funding acquisition. Claudio Sbarufatti: Conceptualization, Writing-review and editing, Supervision.

Corresponding authors

Correspondence to Vasiliki Panagiotopoulou or Andrea Baldi.

Ethics declarations

Competing financial interests

This study was founded by the SAMAS 2 project (Structural health and ballistic impact monitoring and prognosis on a military helicopter), a Cat.-B project (B PRJ-RT 1074) coordinated by the European Defense Agency (EDA) and involving two nations, Italy and Poland.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Panagiotopoulou, V., Brancato, L., Petriconi, E. et al. Comparative study on ballistic impact detection in helicopter transmission shafts using NARX and LSTM models. Appl Intell 55, 264 (2025). https://doi.org/10.1007/s10489-024-06118-1

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10489-024-06118-1

Keywords