Neural networks based identification of helicopter dynamics using flight data

Sundaram, Suresh; Kumar, M. Vijaya; Omkar, S. N.; Mani, V.; Sampath, Prasad

doi:10.1109/iconip.2002.1202121

Cited by 14 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For this reason NARX networks were trained using the real sensor data. Their performances are superior compared not only to the linear ones, but also compared to the performances obtained in studies by Suresh et al and San Martin et al 20,29 The drawback in the case of this kind of model is that no model-based control algorithms can be implemented. But, since one of the purposes of the research project is to design a predictive controller based on neural models, the results obtained at this point are promising.…”

Section: Discussionmentioning

confidence: 83%

Identification and modeling of the three rotational movements of a miniature coaxial helicopter

et al. 2013

View full text Add to dashboard Cite

This paper presents the identification of a miniature coaxial helicopter system. First, the helicopter flying principles are described and the hardware setup of the developed platform is presented. Further, linear models are developed for the movements of the helicopter using prediction error identification methods. The results in this case are accurate and can be used for performant controller design in some operating points. But in order to model the complete dynamics of the helicopter, nonlinear models are developed using recurrent dynamic neural networks. In this case the models obtained present a higher accuracy compared with the linear case and also with the results published until now. In the end, the advantages of nonlinear modeling based on neural networks is emphasized and some conclusions are drawn.

show abstract

Section: Discussionmentioning

confidence: 83%

Identification and modeling of the three rotational movements of a miniature coaxial helicopter

et al. 2013

View full text Add to dashboard Cite

show abstract

“…ϬӴඣՈᴎˊᓎᮍ⊩ [2] ᓎএָछᴎՈӓ‫ף‬ൟᰃৃ ᜐՈˈԚᰃẝᮍ⊩◄ᡅा⇨ᄺ‫ک‬ˈ◄ᡅₓՈ⇨ ᭄ᴹᓎএ⇨ி᭄ǃ⇨ᇐ᭄ൟǄ໐ϨᮟເႮḰ ┊ẋᶤѯĽ⅞ᜐᚙ‫މ‬ϟˈẝѯ⇨᭄ᰃϡৃᑨ ϬՈǄℸẝѯᚙ‫މ‬ϟˈᴎˊᓎᮍ⊩Т᮴⊩ᓎএָ छᴎӓ‫ף‬ൟǄϵѢࠢඓตච‫‬᳝ᄳདՈ☢ඃᗻᇘ࿁ˈ ᆊႮ✊ᄺₕ-ֲ˄ᰈো˖60474069˅ ℸৃҹᑨϬࠢඓตචᓎএָछᴎՈӓ‫ף‬ൟǄSuresh [3] ߚ߿ϬᏺඃᗻⒸ⊶ᩴᖚऩ‫ܗ‬ՈࠢඓตචᓎএָछᴎՈ ῾൹ᄺൟˈҹቻᕫợᑺ࿓ᗕᇍ῾൹਼ᳳব ‫ڭ‬ՈડᑨǄSaleh Zein-Sabatto [4] …”

Section: ѣᬃᣕₓᴎոָछᴎᮟເⴎḱ┊ẋᓎunclassified

Modeling for landing process of a helicopter with rotator self-rotating based on support vector machine

Wang

Zhang

2008

2008 7th World Congress on Intelligent Control and Automation

View full text Add to dashboard Cite

As a system identification method, Neural Network can be applied to build the simulation model of a helicopter. But it has some difficulties such as the hardness of selecting network structure, slow convergence speed, local minimum, and generalization ability question. To avoid the question above, the Support Vector Machine (SVM) method is introduced to the field of flight simulation for the first time, and the rotator speed model for landing process of a helicopter with rotator self-rotating is built. Compared with the Neural Network model, the SVM simulation model of a helicopter owns some advantages such as simple structure, fast convergence speed and high generalization ability. It is shown by theoretic analysis and simulation result that the SVM method is feasible.

show abstract

“…In [19], neural networks with linear filter also known as Narendra's model and recurrent neural networks with internal memory (Memory Neuron Networks) are used for the purpose. From the simulation studies it is shown that MNN approach is better than Narendra's approach.…”

Section: Introductionmentioning

confidence: 99%