Intelligent multi-resolution modelling: Application to synthetic jet actuation and flow control

Puneet Singla, John L. Junkins, Othon Rediniotis, Kamesh Subbarao

Research output: Contribution to conferencePaper

3 Citations (Scopus)

Abstract

A novel "directed graph" based algorithm is presented that facilitates intelligent learning and adaptation of the parameters appearing in a Radial Basis Function Network (RBFN) description of input output behavior of nonlinear dynamical systems. Several alternate formulations, that enforce minimal parameterization of the RBFN parameters are presented. An Extended Kalman Filter algorithm is incorporated to estimate the model parameters using multiple windows of the batch input-output data. The efficacy of the learning algorithms are evaluated on judiciously constructed test data before implementing them on real aerodynamic lift and pitching moment data obtained from experiments on a Synthetic Jet Actuation based Smart Wing.

Original languageEnglish (US)
Pages8870-8883
Number of pages14
StatePublished - Jul 1 2004
Event42nd AIAA Aerospace Sciences Meeting and Exhibit - Reno, NV, United States
Duration: Jan 5 2004Jan 8 2004

Other

Other42nd AIAA Aerospace Sciences Meeting and Exhibit
CountryUnited States
CityReno, NV
Period1/5/041/8/04

Fingerprint

Radial basis function networks
Flow control
Nonlinear dynamical systems
Directed graphs
Extended Kalman filters
Parameterization
Learning algorithms
Aerodynamics
Experiments

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Singla, P., Junkins, J. L., Rediniotis, O., & Subbarao, K. (2004). Intelligent multi-resolution modelling: Application to synthetic jet actuation and flow control. 8870-8883. Paper presented at 42nd AIAA Aerospace Sciences Meeting and Exhibit, Reno, NV, United States.
Singla, Puneet ; Junkins, John L. ; Rediniotis, Othon ; Subbarao, Kamesh. / Intelligent multi-resolution modelling : Application to synthetic jet actuation and flow control. Paper presented at 42nd AIAA Aerospace Sciences Meeting and Exhibit, Reno, NV, United States.14 p.
@conference{0f0348e271a34b4b9feb98e55d884994,
title = "Intelligent multi-resolution modelling: Application to synthetic jet actuation and flow control",
abstract = "A novel {"}directed graph{"} based algorithm is presented that facilitates intelligent learning and adaptation of the parameters appearing in a Radial Basis Function Network (RBFN) description of input output behavior of nonlinear dynamical systems. Several alternate formulations, that enforce minimal parameterization of the RBFN parameters are presented. An Extended Kalman Filter algorithm is incorporated to estimate the model parameters using multiple windows of the batch input-output data. The efficacy of the learning algorithms are evaluated on judiciously constructed test data before implementing them on real aerodynamic lift and pitching moment data obtained from experiments on a Synthetic Jet Actuation based Smart Wing.",
author = "Puneet Singla and Junkins, {John L.} and Othon Rediniotis and Kamesh Subbarao",
year = "2004",
month = "7",
day = "1",
language = "English (US)",
pages = "8870--8883",
note = "42nd AIAA Aerospace Sciences Meeting and Exhibit ; Conference date: 05-01-2004 Through 08-01-2004",

}

Singla, P, Junkins, JL, Rediniotis, O & Subbarao, K 2004, 'Intelligent multi-resolution modelling: Application to synthetic jet actuation and flow control', Paper presented at 42nd AIAA Aerospace Sciences Meeting and Exhibit, Reno, NV, United States, 1/5/04 - 1/8/04 pp. 8870-8883.

Intelligent multi-resolution modelling : Application to synthetic jet actuation and flow control. / Singla, Puneet; Junkins, John L.; Rediniotis, Othon; Subbarao, Kamesh.

2004. 8870-8883 Paper presented at 42nd AIAA Aerospace Sciences Meeting and Exhibit, Reno, NV, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Intelligent multi-resolution modelling

T2 - Application to synthetic jet actuation and flow control

AU - Singla, Puneet

AU - Junkins, John L.

AU - Rediniotis, Othon

AU - Subbarao, Kamesh

PY - 2004/7/1

Y1 - 2004/7/1

N2 - A novel "directed graph" based algorithm is presented that facilitates intelligent learning and adaptation of the parameters appearing in a Radial Basis Function Network (RBFN) description of input output behavior of nonlinear dynamical systems. Several alternate formulations, that enforce minimal parameterization of the RBFN parameters are presented. An Extended Kalman Filter algorithm is incorporated to estimate the model parameters using multiple windows of the batch input-output data. The efficacy of the learning algorithms are evaluated on judiciously constructed test data before implementing them on real aerodynamic lift and pitching moment data obtained from experiments on a Synthetic Jet Actuation based Smart Wing.

AB - A novel "directed graph" based algorithm is presented that facilitates intelligent learning and adaptation of the parameters appearing in a Radial Basis Function Network (RBFN) description of input output behavior of nonlinear dynamical systems. Several alternate formulations, that enforce minimal parameterization of the RBFN parameters are presented. An Extended Kalman Filter algorithm is incorporated to estimate the model parameters using multiple windows of the batch input-output data. The efficacy of the learning algorithms are evaluated on judiciously constructed test data before implementing them on real aerodynamic lift and pitching moment data obtained from experiments on a Synthetic Jet Actuation based Smart Wing.

UR - http://www.scopus.com/inward/record.url?scp=2942708029&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2942708029&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:2942708029

SP - 8870

EP - 8883

ER -

Singla P, Junkins JL, Rediniotis O, Subbarao K. Intelligent multi-resolution modelling: Application to synthetic jet actuation and flow control. 2004. Paper presented at 42nd AIAA Aerospace Sciences Meeting and Exhibit, Reno, NV, United States.