Skip to main content
SpringerLink
Log in

A two stage neural network for choosing optimal ejection parameters in low altitude seat ejection based on novel injury parameter

  • Research Article
  • Published:
Optimization and Engineering Aims and scope Submit manuscript

Abstract

Aircraft ejection systems are lifesaving devices used, in case of emergencies for military pilots. As per current literature the success rate of ejections happening in low altitudes (below 150 m) is 51.2%. The success rate of an ejection depends on various parameters such as height for parachute full deployment, ejection posture, spinal alignment, restraints etc. This paper proposes a multi objective optimization based on a novel injury parameter and the dynamic conditions of the aircraft prevailing during the time of emergency to choose the optimal impulse required for safe ejection. This injury parameter is capable of modelling the spine in different postures. A non-linear seat restraint interaction is also modelled to include the effect of varying slackness of seat restraints there by optimizing force applied for the different physical conditions of the pilot, which hasn’t been reported in literature yet. The Pareto solutions obtained thereof indicates the dangers associated with posture during the ejection process. The optimal solutions after decision making are used to train a two stage Artificial Neural Network architecture to choose optimal parameters for different ejection scenarios. The ANN proposed was seen to give good results which were along the generated Pareto fronts for different simulated aircraft conditions instantaneously.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

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

Similar content being viewed by others

References

  • Bishop CM (2006) Pattern recognition and machine learning. Springer, Berlin

    MATH  Google Scholar 

  • Brinkley JW, Shaffer JT (1971) Dynamic simulation techniques for the design of escape systems: current applications and future air force requirements. Tech. rep, Air Force Aerospace Medical Research Lab Wright-Patterson AFB OH

  • Cheng Z, Rizer AL, Pellettiere JA (2003) Computational analyses of ejection seat cushions for optimal control of spinal injuries. Tech. rep, SAE Technical Paper

  • Deb K, Pratap A, Agarwal S, Meyarivan T (2002) A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans Evol Comput 6(2):182

    Article  Google Scholar 

  • Du C, Mo Z, Tian S, Wang L, Fan J, Liu S, Fan Y (2014) Biomechanical investigation of thoracolumbar spine in different postures during ejection using a combined finite element and multi-body approach. Int J Numer Methods Biomed Eng 30(11):1121

    Article  Google Scholar 

  • Griffith M (1990) Human vibration handbook

  • Kalavsky P, Socha V, Socha L, Kutilek P, Gazda J, Kimlickova M (2015) In: 2015 International conference on military technologies (ICMT). IEEE, pp 1–5

  • Kitazaki S, Griffin MJ (1997) A modal analysis of whole-body vertical vibration, using a finite element model of the human body. J Sound Vib 200(1):83

    Article  Google Scholar 

  • Lewis M (2002) Spinal injuries caused by the acceleration of ejection. J R Army Med Corps 148(1):22

    Article  Google Scholar 

  • Lou J, Sun J, Tang S, Li H (2014) Study on the optimization of the shock isolation system based on the limiting performance analysis. Int J Dyn Control 2(3):415

    Article  Google Scholar 

  • Liu Y, Pontius UR, Hosey RR (1973) The effects of initial spinal configuration on pilot ejection. Tech. rep, Army Aeromedical Research Lab Fort Rucker Al

  • Mao XD, Lin GP, Yu J (2011) Predicting ejection velocity of ejection seat via back propagation neural network. J Aircr 48(2):668

    Article  Google Scholar 

  • MATLAB (2018) Version 7.10.0 (R2018a). The MathWorks Inc., Natick, Massachusetts

  • Naveen Raj R, Shankar K (2020) An improved spinal injury parameter model for under body impulsive loading scenarios title. Int J Numer Methods Biomed Eng e3307

  • Newman DG (2013) Survival outcomes in low-level ejections from high performance aircraft. Aviat Space Environ Med 84(10):1061

    Article  Google Scholar 

  • Raj RN, Shankar K (2020) Human Factors and Mechanical Engineering for Defense and Safety 4(1):6

    Article  Google Scholar 

  • Robinson G, Jovanoski Z (2010) Fighter pilot ejection study as an educational tool. Teach Math Appl Int J IMA 29(4):176

    Google Scholar 

  • Saad EW, Wunsch DC II (2007) Neural network explanation using inversion. Neural Netw 20(1):78

    Article  Google Scholar 

  • Shanahan DF (2004) Human tolerance and crash survivability. Pathological aspects and associate biodynamics in aircraft accident investigation

  • Singh B (2007) Indian Journal of Aerospace Medicine: Special Commemorative Volume May, p 64

  • Stech EL, Payne PR (1969) Dynamic models of the human body. Tech. rep, Frost Engineering Development Corp Englewood Co

  • Stemper B, Yoganandan N, Paskoff G, Fijalkowski R, Storvik S, Baisden J, Pintar F, Shender B (2011) Thoracolumbar spine trauma in military environments. Minerva Ortopedica E Traumatologica 62(5):397

    Google Scholar 

  • Thyagarajan R, Ramalingam, J, Kulkarni KB (2014) Comparing the use of dynamic response index (DRI) and lumbar load as relevant spinal injury metrics. Tech. rep., Comparing the use of dynamic response index (DRI) and lumbar load as relevant spinal injury metrics

  • USAF (2007) Mil-dtl-9479 rev. e. Tech. rep

  • USAF (2016) Mil-hdbk-516cn-56. Tech. rep

  • U.S.O. of the Chief of Naval Operations (2001) NATOPS Flight Manual: Navy Model F/A-18E/F 165533 and Up Aircraft. Naval Air Technical Data and Engineering Services Command, Naval Air Station, North Island. https://books.google.co.in/books?id=Ol2jYgEACAAJ

  • U.S.O. of the Chief of Naval Operations, U.S.N.A.S. Command (2008) NATOPS Flight Manual: Navy Model AV-8B Aircraft 161573 and Up. The Command. https://books.google.co.in/books?id=7WguHQAACAAJ

  • Wenchun F, Guiping L (2007) Multi-parameter and multi-mode control simulation analyses of ejection seat. J Syst Simul 19(10):2283

    Google Scholar 

  • White A, Panjabi M (1978) Clinical biomechanics of the spine. Lippincott. https://books.google.co.in/books?id=U5NsAAAAMAAJ

  • Wise KA, Brinker JS (1996) Linear quadratic flight control for ejection seats. J Guid Control Dyn 19(1):15

    Article  Google Scholar 

  • Wolf E (2007) Development of seat shock isolation systems. Ph.D thesis, University of Nevada, Las Vegas

  • Zhang M, Wu M, Su Y, Zhang C (2016) Researching attitude-control algorithm of ejection seats based on time-sharing strategy. In: ICINCO (2) (2016), pp 262–267

Download references

Author information

Authors and Affiliations

  1. Department of Mechanical Engineering, Machine Design Section, IIT Madras, Chennai, India

    R. Naveen Raj & K. Shankar

Authors
  1. R. Naveen Raj
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. K. Shankar
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to K. Shankar.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Naveen Raj, R., Shankar, K. A two stage neural network for choosing optimal ejection parameters in low altitude seat ejection based on novel injury parameter. Optim Eng 23, 827–853 (2022). https://doi.org/10.1007/s11081-021-09607-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11081-021-09607-1

Keywords

Search

Navigation