Synopsis: From the nostalgic remembrance of the first dynamic flight test this Survey Paper traces several milestones in the history of flight vehicle system identification. A comprehensive account of modern system identification techniques is provided. Several challenging examples bring out the fact that these techniques have reached a high level of maturity, making them a sophisticated and powerful tool not only for research purposes, but also to support the needs of the aircraft industry. This survey paper includes 183 references and provides a consolidated list of publications on the subject.

https://dlr.de/ft/en/portaldata/2/resources/dokumente/ft/jategaonkar/evol_sysid.pdf

Evolution of flight vehicle system identification

A recently proposed method (christened ‘ ‘ the Delta method’ ’) of estimating aircraft parameters from e ight data using feed-forward neural networks is applied for the extraction of lateral ‐directional parameters from simulated as well as real-e ight data. The neural network is trained using aircraft motion and control variables as the network inputs and aerodynamic coefe cients as the network outputs; the trained network is used to predict aerodynamic coefe cients for a suitably modie ed input e le. An appropriate interpretation and manipulation of such input ‐output e les yields the estimates of the parameters. Flight data for lateral ‐directional dynamics are analyzed for various combinations and types of control inputs, and suitable control input forms are identie ed for better estimation via the proposed method. Robustness of the method with respect to measurement noise is demonstrated by its applicability to simulated e ight data with pseudomeasurement noise, and to real-e ight data.

Estimation of Aircraft Lateral-Directional Parameters Using Neural Networks

Dynamic model identification of unmanned surface vehicles using deep learning network

Safety is of paramount importance in all transportation systems, but especially in civil aviation. Therefore, in civil aviation, a lot of developments focus on the improvement of safety levels and reducing the risks that critical failures occur. When one analyses recent aircraft accident statistics, it is clear that a significant portion is attributed to “loss of control in flight”. A recent worldwide civil aviation accident survey for the 1989 to 2003 period, conducted by the Civil Aviation Authority of the Netherlands (CAA-NL) and based on data from the National Aerospace Laboratory NLR, indicates that this category accounts for as much as 17% of all aircraft accident cases. This has led to a common conclusion: from a flight dynamics point of view, with the technology and computing power available on this moment, it might have been possible to recover a part of the aircraft in the accident category described above on the condition that non-conventional control strategies would have been applied. These non-conventional control strategies involve the so-called concept of fault tolerant flight control (FTFC), where the control system is capable to detect and adapt for changes in the aircraft behaviour. One FTFC strategy option is using a model based control routine. This research focuses on a physical modular approach. In this setup, not only a reconfiguring controller is needed, but also a suitable FDI/identification strategy. This research focuses on both components. In this reseach project, a real-time aerodynamic model identification procedure has been combined with a model based adaptive control method. A manual as well as an autopilot version have been developed. The autopilot version has been evaluated on desktop simulations, the manual version has been tested in the Simona Research Simulator involving professional airline pilots. Both tests have demonstrated promising results. The autopilot performance is very good, and the manual controller has demonstrated to increase handling qualities and to reduce pilot workload of the damaged aircraft. These are very promising results that motivate further research in this field.

/pdf/fault-tolerant-flight-control-a-physical-model-approach-rr2dh4ddm4.pdf

Fault Tolerant Flight Control, a Physical Model Approach

A new parameter estimation method based upon neural network is proposed. The method proposed here uses feed forward neural networks to establish a neural model that could be used to predict subsequent time histories given the suitable measured initial conditions. The proposed neural model would not represent a generic flight dynamic model. The neural model in this case develops point to point fitting of the input and the output data. Thus, it could at best be referred to as flight dynamic model in restricted sense. Gauss-Newton method is then used to obtain optimal values of the aerodynamic parameters by minimising a suitable defined error cost function. The method has been validated using longitudinal and lateral-directional flight data of various test aircraft. The results thus obtained were compared with those obtained through wind tunnel test, or those obtained using Maximum likelihood and/or Filter error methods. Unlike, most of the parameter estimation methods, the proposed method does not require a prior description of the model. It also bypasses the requirement of solving equations of motion. This feature of the proposed method may have special significance in handling flight data of an unstable aircraft.

Aircraft parameter estimation using a new filtering technique based upon a neural network and Gauss-Newton method

Two new techniques for estimating aircraft stability and control derivatives (parameters) from flight data using feed forward neural networks are proposed. Both techniques use motion variables and control inputs as the input file, while aerodynamic coefficients are presented as the output file for training a neural network. For the purpose of parameter estimation, the trained neural network is presented with a suitably modified input file, and the corresponding predicted output file of aerodynamic coefficients is obtained. Suitable interpretation and manipulation of such input-output files yields the estimated values of the parameters. The methods are validated first on the simulated flight data and then on real flight data obtained by digitising analogue data from a published report. Results are presented to show how the accuracy of the estimates is affected by the topology of the network, the number of iterations and the intensity of the measurement noise in simulated flight data. One of the significant features of the proposed methods is that they do not require guessing of a reasonable set of starting values of the parameters as a popular parameter estimator like the maximum likelihood method does.

Two new techniques for aircraft parameter estimation using neural networks

Application of neural networks to the problem of aerodynamic modelling and parameter estimation for aeroelastic aircraft is addressed. A neural model capable of predicting generalized force and moment coefficients using measured motion and control variables only, without any need for conventional normal elastic variables or their time derivatives, is proposed. Furthermore, it is shown that such a neural model can be used to extract equivalent stability and control derivatives of a flexible aircraft. Results are presented for aircraft with different levels of flexibility to demonstrate the utility of the neural approach for both modelling and estimation of parameters.

/pdf/parameter-estimation-of-an-aeroelastic-aircraft-using-neural-29ifqiobou.pdf

Parameter estimation of an aeroelastic aircraft using neural networks

Equations of motion for a rolling finned projectile presented by an earlier investigator are corrected. Steady resonant lock-in solutions, both normal and reverse, are presented and their stability investigated. Two-dimensional topological models are constructed to explain how the occurrence of resonant lock-in depends on initial conditions. Results from numerical simulations are used to validate the suggested models. Quasisteady-state (QSS) resonant lock-in is shown to be possible for an unstable equilibrium solution at resonance. QSS solutions are found to lead to divergent yaw behavior typical of catastrophic yaw. It is suggested that catastrophic yaw can be demonstrated by modeling the effect of the nonlinear induced side forces and moments at resonance as a reduction in yaw damping.

S. C. Raisinghani

Papers

Estimation of Aircraft Lateral-Directional Parameters Using Neural Networks

Two new techniques for aircraft parameter estimation using neural networks

Parameter estimation of an aeroelastic aircraft using neural networks

Steady and Quasisteady Resonant Lock-In of Finned Projectiles

Parameter Estimation from Flight Data of an Unstable Aircraft Using Neural Networks