Identification of an unmanned helicopter system using optimised neural network structure

A method for offline system identification to model the attitude dynamics of an unmanned helicopter using neural network techniques has been developed. The processed test data obtained from various test flights were used to train a neural network ARX (autoregressive structure with extra inputs) using Levenberg-Marquardt computation. An optimised network structure was obtained using a combination of cross validation, correlation analysis, Lipschitz criterion and weights regularisation methods to ensure good generalisation ability of the model. Satisfactory correlation analysis results were achieved which indicated that the offline model using the proposed methods contain all information about the dynamics of the system. The proposed methods would allow users to design a better prediction model with the aid of the correlation analysis from estimation theory. The results show that the proposed method is effective in modelling the coupled UAS helicopter dynamics with acceptable accuracy.

[1]  Tsungnan Lin,et al.  What to remember: how memory order affects the performance of NARX neural networks , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[2]  Ji-Xin Qian,et al.  Recurrent neural networks for recursive identification of nonlinear dynamic process , 1994, Proceedings of 1994 IEEE International Conference on Industrial Technology - ICIT '94.

[3]  Yunhui Liu,et al.  System identification and attitude control of a small scale unmanned helicopter , 2009, 2008 IEEE International Conference on Robotics and Biomimetics.

[4]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[5]  Hao Yu,et al.  Levenberg—Marquardt Training , 2011 .

[6]  Alex Simpkins,et al.  System Identification: Theory for the User, 2nd Edition (Ljung, L.; 1999) [On the Shelf] , 2012, IEEE Robotics & Automation Magazine.

[7]  R. V. Jategaonkar,et al.  Aerodynamic parameter estimation from flight data applying extended and unscented Kalman filter , 2006 .

[8]  Stephen A. Billings,et al.  A comparison of the backpropagation and recursive prediction error algorithms for training neural networks , 1991 .

[9]  Darryll J. Pines,et al.  System Identification of a Miniature Helicopter , 2008 .

[10]  S. Shankar Sastry,et al.  Decentralized nonlinear model predictive control of multiple flying robots , 2003, 42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475).

[11]  Antonio Barrientos,et al.  Unmanned aerial vehicle (UAV) modelling based on supervised neural networks , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[12]  Matthew Garratt,et al.  Neural Network Based System Identification for Autonomous Flight of an Eagle Helicopter , 2008 .

[13]  G. Horvath,et al.  Improved model order estimation for nonlinear dynamic systems , 2003, Second IEEE International Workshop on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, 2003. Proceedings.

[14]  Jinhua Wang,et al.  Modelling and control system design of a small-scale unmanned helicopter , 2011, Int. J. Model. Identif. Control..

[15]  L. Sterling.  Intelligent Systems , 1993, Springer US.

[16]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[17]  M. O. Tokhi,et al.  Non-linear modelling of a one-degree-of-freedom twin-rotor multi-input multi-output system using radial basis function networks , 2002 .

[18]  Duc Truong Pham,et al.  Identification of linear and nonlinear dynamic systems using recurrent neural networks , 1993, Artif. Intell. Eng..

[19]  Agus Budiyono,et al.  Modeling of unmanned small scale rotorcraft based on Neural Network identification , 2009, 2008 IEEE International Conference on Robotics and Biomimetics.

[20]  Peter Tiño,et al.  Learning long-term dependencies in NARX recurrent neural networks , 1996, IEEE Trans. Neural Networks.

[21]  Bogdan M. Wilamowski,et al.  Neural Networks Learning , 2011, Intelligent Systems.

[22]  Vladislav Gavrilets,et al.  Autonomous aerobatic maneuvering of miniature helicopters , 2003 .

[23]  Sundaram Suresh,et al.  Lift coefficient prediction at high angle of attack using recurrent neural network , 2003 .

[24]  S. Shankar Sastry,et al.  HIERARCHICAL CONTROL SYSTEM SYNTHESIS FOR ROTORCRAFT-BASED UNMANNED AERIAL VEHICLES , 2000 .

[25]  S. Billings,et al.  Correlation based model validity tests for non-linear models , 1986 .

[26]  M. Hasan Shaheed.  Feedforward neural network based non‐linear dynamic modelling of a TRMS using RPROP algorithm , 2005 .

[27]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[28]  Dawn M. Tilbury,et al.  Mathematical Modeling and Experimental Identification of an Unmanned Helicopter Robot with Flybar Dynamics , 2004, J. Field Robotics.

[29]  Mark B. Tischler,et al.  Aircraft and Rotorcraft System Identification: Engineering Methods with Flight-Test Examples , 2006 .

[30]  G. D. Padfield,et al.  Helicopter Flight Dynamics: The Theory and Application of Flying Qualities and Simulation Modelling , 1995 .

[31]  Agus Budiyono,et al.  Integrated identification modeling of rotorcraft-based unmanned aerial vehicle , 2009, 2009 17th Mediterranean Conference on Control and Automation.

[32]  Bernard Mettler,et al.  Identification Modeling and Characteristics of Miniature Rotorcraft , 2002 .

[33]  Sundaram Suresh,et al.  Neural networks based identification of helicopter dynamics using flight data , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[34]  Abdelhakim Deboucha,et al.  Small-scale helicopter system identification model using recurrent neural networks , 2010, TENCON 2010 - 2010 IEEE Region 10 Conference.

[35]  Seref Sagiroglu,et al.  Elman Network with Embedded Memory for System Identification , 2006, J. Inf. Sci. Eng..

[36]  Bernard Mettler,et al.  System identification modeling of a small-scale unmanned rotorcraft for flight control design , 2002 .

[37]  B.M. Wilamowski,et al.  Neural network architectures and learning algorithms , 2009, IEEE Industrial Electronics Magazine.

[38]  Jinhua Wang,et al.  Simulation system design of a small-scale unmanned helicopter , 2011, Int. J. Model. Identif. Control..

[39]  Niels Kjølstad Poulsen,et al.  Neural Networks for Modelling and Control of Dynamic Systems: A Practitioner’s Handbook , 2000 .

[40]  Stephen A. Billings,et al.  Properties of neural networks with applications to modelling non-linear dynamical systems , 1992 .

[41]  Mohammad Yusoff Mashor,et al.  Modified Recursive Prediction Error Algorithm for Training Layered Neural Network , 2003 .

[42]  Akbar Rahideh,et al.  Dynamic modelling of a TRMS using analytical and empirical approaches , 2008 .

[43]  M. Osman Tokhi,et al.  Dynamic modelling of a single-link flexible manipulator: parametric and non-parametric approaches , 2002, Robotica.

[44]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[45]  Morten Bisgaard,et al.  Modeling, Estimation, and Control of Helicopter Slung Load System , 2008 .

[46]  Yahya Chetouani.  Use of a neural-network-based approach for a reliable modelling of a distillation column , 2010, Int. J. Model. Identif. Control..

[47]  C. Lee Giles,et al.  An experimental comparison of recurrent neural networks , 1994, NIPS.