Skip to main content Accessibility help
×
Home
Hostname: page-component-5c569c448b-bmzkg Total loading time: 0.208 Render date: 2022-07-05T14:24:05.357Z Has data issue: true Feature Flags: { "shouldUseShareProductTool": true, "shouldUseHypothesis": true, "isUnsiloEnabled": true, "useRatesEcommerce": false, "useNewApi": true } hasContentIssue true

Estimation of longitudinal aerodynamic parameters using recurrent neural network

Published online by Cambridge University Press:  12 May 2022

H. O. Verma*
Affiliation:
Centurion University of Technology and Management, Odisha, India
N. K. Peyada
Affiliation:
Indian Institute of Technology Kharagpur, West Bengal, India
*
*Corresponding author. Email: homverma@gmail.com

Abstract

The aerodynamic modelling is one of the challenging tasks that is generally established using the results of the computational fluid dynamic software and wind tunnel analysis performed either on the scaled model or the prototype. In order to improve the confidence of the estimates, the conventional parameter estimation methods such as equation error method (EEM) and output error method (OEM) are more often applied to extract the aircraft’s stability and control derivatives from its respective flight test data. The quality of the estimates gets influenced due to the presence of the measurement and process noises in the flight test data. With the advancement in the machine learning algorithms, the data driven methods have got more attention in the modelling of a system based on the input-output measurements and also, in the identification of the system/model parameters. The research article investigates the longitudinal stability and control derivatives of the aerodynamic models by using an integrated optimisation algorithm based on a recurrent neural network. The flight test data of Hansa-3 and HFB 320 aircraft were used as case studies to see the efficacy of the parameter estimation algorithm and further, the confidence of the estimates were demonstrated in terms of the standard deviations. Finally, the simulated variables obtained using the estimates demonstrate a qualitative estimation in the presence of the noise.

Type
Research Article
Copyright
© The Author(s), 2022. Published by Cambridge University Press on behalf of Royal Aeronautical Society

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Jategaonkar, R.V. Flight Vehicle System Identification: A Time Domain Methodology, 1 ed., vol. 216, Reston, VA: Progress in Astronautics and Aeronautics, AIAA, 2006.CrossRefGoogle Scholar
Raol, R., Jitendra, G.G. and Singh, J. Modelling and Parameter Estimation of Dynamic System, London: IET, 2004.CrossRefGoogle Scholar
Pamadi, B.N. Performance, Stability, Dynamics and Control of Airplanes, Virginia: AIAA Education Series, 1998.Google Scholar
Lie, F.A.P. and Go, T.H. A collision-free formation reconfiguration control approach for unmanned aerial vehicles. Int. J. Control Autom. Syst., 2010, 8, pp 11001107. doi: 10.1007/s12555-010-0519-7 CrossRefGoogle Scholar
Morelli, E.A. and Klein, V. Application of system identification to aircraft at NASA Langley Research Center. J. Aircraft, 2005, 42, (1), pp 1225. doi: 10.2514/1.3648 CrossRefGoogle Scholar
Morelli, E.A. Practical aspects of the equation error method for aircraft parameter estimation. AIAA Atmospheric Flight Mechanics Conference, Keystone, CO, USA, 2006. doi: 10.2514/6.2006-6144 CrossRefGoogle Scholar
Hamel, P.G. and Jategaonkar, R.V. Evolution of flight vehicle system identification. J. Aircraft, 1996, 33, (1), pp 928. doi: 10.2514/3.46898 CrossRefGoogle Scholar
Goman, M.G. and Khrabrov, A.N. State-space representation of aerodynamic characteristics of an aircraft at high angles of attack. J. Aircraft, 1994, 31, (5), pp 11091115. doi: 10.2514/3.46618 CrossRefGoogle Scholar
Jategaonkar, R.V. and Plaetschke, E. Identification of moderately nonlinear flight mechanics systems with additive process and measurement noise. J. Guid. Control Dyn., 1990, 13, (2), pp 277285. doi: 10.2514/3.20547 CrossRefGoogle Scholar
Kamali, C., Pashilkar, A.A. and Raol, J.R. Evaluation of recursive least squares algorithm for parameter estimation in aircraft real time applications. J. Aerosp. Sci. Technol., 2011, 15, (3), pp 165174. doi: 10.1016/j.ast.2010.12.007 CrossRefGoogle Scholar
Chowdhary, G. and Jategaonkar, R.V. Aerodynamic parameter estimation from flight data applying extended and unscented Kalman filter. J. Aerosp. Sci. Technol., 2010, 14, (2), pp 106117. doi: 10.1016/j.ast.2009.10.003 CrossRefGoogle Scholar
Seo, G., Kim, Y. and Saderla, S. Kalman-filter based online system identification of fixed-wing aircraft in upset condition. J Aerosp. Sci. Technol., 2019, 89, pp 307317. doi: 10.1016/j.ast.2019.04.012 CrossRefGoogle Scholar
Ignatyev, D., Khrabrov, A. and Alexander, N. Neural network modeling of unsteady aerodynamic characteristics at high angles of attack. J. Aerosp. Sci. Technol., 2015, 41, pp 106115. doi: 10.1016/j.ast.2014.12.017 CrossRefGoogle Scholar
Lyu, Y., Zhang, W., Shi, J., Qu, X. and Cao, Y. Unsteady aerodynamic modeling of biaxial coupled oscillation based on improved ELM. J. Aerosp. Sci. Technol., 2017, 60, pp 5867. doi: 10.1016/j.ast.2016.10.029 CrossRefGoogle Scholar
Wang, Q., Qian, W. and He, K. Unsteady aerodynamic modelling at high angles of attack using support vector machines. Chinese J. Aeronaut., 2015, 28, (3), pp 659668. doi: 10.1016/j.cja.2015.03.010 CrossRefGoogle Scholar
Linse, D.J. and Stengel, R. Identification of aerodynamic coefficients using computational neural networks. J. Guid. Control Dyn., 1993, 16, (6), pp 10181025. doi: 10.2514/3.21122 CrossRefGoogle Scholar
Das, S, Kutteri, R.A., Sinha, M. and Jategaonkar, R.V. Neural partial differential method for extracting aerodynamic derivatives from flight data. J. Guid. Control Dyn., 2010, 33, (2), pp 376384.CrossRefGoogle Scholar
Verma, H.O. and Peyada, N.K. Aircraft parameter estimation using ELM network. Aircraft Eng. Aerosp. Tech., 2020, 92, (6), pp 895907. doi: 10.1108/AEAT-01-2019-0003 CrossRefGoogle Scholar
Raol, J.R. and Jategaonkar, R.V. Aircraft parameter estimation using recurrent neural networks – a critical appraisal. AIAA Paper 95-3004, 1995. doi: 10.2514/6.1995-3504 Google Scholar
Raisinghani, S.C., Ghosh, A.K. and Kalra, P.K. Two new techniques for aircraft parameter estimation using neural networks. Aeronaut. J., 1998, 102, (1011), pp 2530. doi: 10.1017/S0001924000065702 Google Scholar
Singh, S. and Ghosh, A.K. Estimation of lateral-directional parameters using neural network based modified delta method. Aeronaut. J., 2007, 111, (1124), pp 659667. doi: 10.1017/S0001924000004838 CrossRefGoogle Scholar
Peyada, N.K. and Ghosh, A.K. Aircraft parameter estimation using new filtering technique based on neural network and gauss-newton method. Aeronaut. J., 2009, 113, (1142), pp 243252. doi: 10.1017/S00 01924000002918 CrossRefGoogle Scholar
Roy, A.G. and Peyada, N.K. Aircraft parameter estimation using hybrid neuro fuzzy and artificial bee colony optimization (HNFABC) algorithm. J. Aerosp. Sci. Technol., 2017, 71, pp 772782. doi: 10.1016/j.ast.2017.10.030 Google Scholar
Huang, G.B., Zhu, Q.Y. and Siew, C.K. Extreme learning machine: a new learning scheme of feed forward neural networks. IEEE Int. Joint Conf. Neural Netw., 2004. doi: 10.1109/IJCNN.2004.1380068 Google Scholar
Huang, G.B., Zhu, Q.Y. and Siew, C.K. Extreme learning machine: theory and applications. Neurocomputing, 2006; 70, (1–3), pp 489501. doi: 10.1016/j.neucom.2005.12.126 CrossRefGoogle Scholar
Verma, H.O. and Peyada, N.K. Parameter estimation of stable and unstable aircraft using extreme learning machine. AIAA 2018-0526, 2018. doi: 10.2514/6.2018-0526 Google Scholar
Verma, H.O. and Peyada, N.K. Parameter estimation of aircraft using extreme learning machine and Gauss-Newton algorithm. Aeronaut. J., 2020, 124, (1272), pp 271295. doi: 10.1017/aer.2019.123 CrossRefGoogle Scholar
Verma, H.O. and Peyada, N.K. Estimation of aerodynamic parameters near stall using maximum likelihood and extreme learning machine-based methods, Aeronaut. J., 2020, 125, (1285), pp 489509. doi: 10.1017/aer.2020.95 CrossRefGoogle Scholar
Ertugrul, O.F. Forecasting electricity load by a novel recurrent extreme learning machines approach. Int. J. Electr. Power Energy Syst., 2016, 78, pp 429435. doi: 10.1016/j.ijepes.2015.12.006 CrossRefGoogle Scholar
Park, J. and Kim, J. Online recurrent extreme learning machine and its application to time-series prediction. Int. Joint Conf. Neural Netw., 2017, pp 19831990. doi: 10.1109/IJCNN.2017.7966094 Google Scholar
Sola, J. and Sevilla, J. Importance of data normalization for the application of neural networks to complex industrial problems. IEEE Trans. Nucl. Sci., 1997, 44, (3), pp 14641468. doi: 10.1109/23.589532 CrossRefGoogle Scholar
Bartlett, P.L. The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network. IEEE Trans. Inf. Theory, 1998, 44, (2), pp 525536. doi: 10.1109/18.661502 CrossRefGoogle Scholar
Sahin, M. Comparison of modelling ANN and ELM to estimate solar radiation over Turkey using NOAA satellite data. Int. J. Remote Sensing, 2013, 34, (21), pp. 75087533. doi: 10.1080/014311 61.2013.822597 CrossRefGoogle Scholar
Peyada, N.K. Parameter estimation from flight data using feed forward neural networks, PhD Dissertation, IIT Kanpur, India, 2009.Google Scholar
Rangaranjan, R. and Vishwanathan, S. Wind Tunnel Test Results on a 1/5 Scale HANSA Model. NAL TR-01 1997.Google Scholar
Raol, J.R. and Girija, G. Modelling and parameter estimation for fly-by-wire aircraft/control systems, Sadhana, 1999, 24, pp. 97119. doi: 10.1007/BF02747554 CrossRefGoogle Scholar
Raol, J.R. and Madhuranath, H. Neural network architectures for parameter estimation of dynamical systems. IEE Proc.-Control Theory Appl., 1996, 143, (4), pp 387394.CrossRefGoogle Scholar

Save article to Kindle

To save this article to your Kindle, first ensure coreplatform@cambridge.org is added to your Approved Personal Document E-mail List under your Personal Document Settings on the Manage Your Content and Devices page of your Amazon account. Then enter the ‘name’ part of your Kindle email address below. Find out more about saving to your Kindle.

Note you can select to save to either the @free.kindle.com or @kindle.com variations. ‘@free.kindle.com’ emails are free but can only be saved to your device when it is connected to wi-fi. ‘@kindle.com’ emails can be delivered even when you are not connected to wi-fi, but note that service fees apply.

Find out more about the Kindle Personal Document Service.

Estimation of longitudinal aerodynamic parameters using recurrent neural network
Available formats
×

Save article to Dropbox

To save this article to your Dropbox account, please select one or more formats and confirm that you agree to abide by our usage policies. If this is the first time you used this feature, you will be asked to authorise Cambridge Core to connect with your Dropbox account. Find out more about saving content to Dropbox.

Estimation of longitudinal aerodynamic parameters using recurrent neural network
Available formats
×

Save article to Google Drive

To save this article to your Google Drive account, please select one or more formats and confirm that you agree to abide by our usage policies. If this is the first time you used this feature, you will be asked to authorise Cambridge Core to connect with your Google Drive account. Find out more about saving content to Google Drive.

Estimation of longitudinal aerodynamic parameters using recurrent neural network
Available formats
×
×

Reply to: Submit a response

Please enter your response.

Your details

Please enter a valid email address.

Conflicting interests

Do you have any conflicting interests? *