Generalization of ANN-based aircraft dynamics identification techniques into the entire flight envelope

Roudbari, Alireza; Saghafi, Fariborz

doi:10.1109/taes.2016.140693

Cited by 16 publications

(13 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Subsequently, the validity of the obtained model is ensured using the new pairs of inputs‐outputs data. Among the various structures of system identification in both the time and frequency domains, NNs have attracted a great deal of attention due to their universal approximations and other unique capabilities . Neural networks, themselves can be generally classified into two categories, ie, feed‐forward and recurrent networks .…”

Section: Nonlinear Dynamic Model Of a Conventional Aircraftmentioning

confidence: 99%

“…Among the various structures of system identification in both the time and frequency domains, 27 NNs have attracted a great deal of attention due to their universal approximations and other unique capabilities. 28 Neural networks, themselves can be generally classified into two categories, ie, feed-forward and recurrent networks. 29,30 Recurrent NNs can be used effectively to model the dynamic systems due to the existence of the feedback loop in their structures.…”

Section: Nonlinear Dynamic Model Of a Conventional Aircraftmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent trajectory tracking of an aircraft in the presence of internal and external disturbances

Emami

Banazadeh

2019

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

Summary This research deals with developing an intelligent trajectory tracking control approach for an aircraft in the presence of internal and external disturbances. Internal disturbances including actuators faults, unmodeled dynamics, and model uncertainties as well as the external disturbances such as wind turbulence significantly affect the performance of the common trajectory tracking control approaches. There are several fault‐tolerant control approaches in the literature to overcome the effects of specific actuator or sensor faults during the flight. However, trajectory tracking control of an air vehicle in the presence of unexpected faults and simultaneous presence of wind turbulence is still a challenging problem. In this paper, an intelligent neural network‐based model predictive control structure is proposed, where the prediction model is updated in each iteration based on a novel proposed online sequential multimodel structure. A hybrid offline‐online learning algorithm is adopted in the introduced online sequential multimodel structure to identify the time‐varying dynamics of the system. The proposed control structure can satisfactorily deal with unexpected actuator faults and structural damages as well as unmodeled dynamics and wind turbulence. The stability of the closed‐loop system is proved under some realistic assumptions. The simulation results demonstrate the high capability of the proposed approach for trajectory tracking control of a conventional aircraft in the simultaneous presence of system faults and external disturbances.

show abstract

Section: Nonlinear Dynamic Model Of a Conventional Aircraftmentioning

confidence: 99%

Section: Nonlinear Dynamic Model Of a Conventional Aircraftmentioning

confidence: 99%

Intelligent trajectory tracking of an aircraft in the presence of internal and external disturbances

Emami

Banazadeh

2019

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

show abstract

“…A conventional aircraft has a coupled nonlinear dynamic model. In addition, the dynamic model of an aerial vehicle changes significantly by altering two scheduling variables, namely, the Equivalent Air Speed (EAS) and the vehicle altitude 1 . More precisely, the stability and control derivatives of an aircraft dynamic model vary by changing the flight speed.…”

Section: Introductionmentioning

confidence: 99%

“…Nevertheless, in the case of more complex dynamic systems, there is a need to employ complicated network structures such as deep neural networks, convolutional neural networks, or the previously proposed four‐dimensional neural network in Reference 1. However, these network structures typically do not apply any correction to the model during the flight simulation.…”

Section: Introductionmentioning

confidence: 99%

“…There are different approaches in the literature in order to adapt the initially estimated model of a dynamic system to the changes in the system parameters. They include the use of online learning approaches 24 or consideration of the variable parameters of the system as the new inputs of the trained network 1 . Nevertheless, these approaches suffer from several difficulties and complexities.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identification of nonlinear time‐varying systems using wavelet neural networks

Emami

Roudbari

2020

Adv Control Appl

Self Cite

View full text Add to dashboard Cite

The dynamic model of an aircraft changes significantly by altering the flight speed and the vehicle altitude. Thus, a conventional aircraft has a nonlinear time‐varying dynamic model in different regions of the flight envelope, and a dynamic model developed for a specific operating point is not valid in the entire flight envelope. This paper presents a novel identification approach that can deal with nonlinear and time‐varying characteristics of complex dynamic systems, especially an aerial vehicle in the entire flight envelope. In this regard, a set of local submodels are first developed at different operating points of the system, and subsequently, a multimodel structure is introduced to aggregate the outputs of the local models as a single model. Wavelet Neural Networks (WNNs), which combine both the universal approximation property of neural networks and the wavelet decomposition capability, are used as the local models of the proposed scheme. Also, three different approaches for determining the validity functions of the local models are introduced to allow for identifying the time‐varying dynamics of the system. The simulation results obtained for the Generic Transport Model aircraft suggest that the proposed WNN‐based multimodel structure can be used satisfactorily as the prediction model of model‐based flight control systems for long prediction horizons.

show abstract

Online Identification of Aircraft Dynamics in the Presence of Actuator Faults

Emami

Banazadeh

2019

J Intell Robot Syst

View full text Add to dashboard Cite

Generalization of ANN-based aircraft dynamics identification techniques into the entire flight envelope

Cited by 16 publications

References 30 publications

Intelligent trajectory tracking of an aircraft in the presence of internal and external disturbances

Intelligent trajectory tracking of an aircraft in the presence of internal and external disturbances

Identification of nonlinear time‐varying systems using wavelet neural networks

Online Identification of Aircraft Dynamics in the Presence of Actuator Faults

Contact Info

Product

Resources

About