Limit Margin Prediction For Helicopters Using Long Term Learning Adaptive Neural Networks

Date

2011-09-13

Author

Yavrucuk, İlkay

Metadata

Show full item record

Item Usage Stats

127
views

0
downloads

In this paper a methodology is presented for estimating helicopter limit margins using real-time learning dynamic models featuring long term (concurrent) learning adaptive neural networks. Limit margin estimations can be used in envelope protection systems of fly-by-wire helicopters. Linear models are compensated with adaptive neural networks to construct adaptive models of relevant aircraft dynamics. A stack of data collected during flight is used to update the network weights. The data stack for learning is made up of instantaneous measured data and recorded data. Rules for recording relevant data are established. It is observed that using recorded data in a stack can cancel out modeling errors faster and result in better predictions of approaching steady state limits compared to using instantaneous measured data only.

Subject Keywords

Flight envelopes, Helicopters, Commutativity

URI

https://hdl.handle.net/11511/78584

Conference Name

37th European Rotorcraft Forum, 13 September 2011

Collections

Department of Aerospace Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Estimation of Locally Stationary Graph Processes from Incomplete Realizations Canbolat, Abdullah; Vural, Elif (2022-01-01) Stationarity is a well-studied concept in signal processing and the concept of stationary random processes has been extended to graph domains in several recent works. Meanwhile, in many scenarios a globally stationary process model may fail to accurately represent the correlation patterns of the data on the whole graph, e.g. when data is acquired on big graphs or when the behavior of the process varies significantly throughout the graph. In this work, we first propose a locally stationary graph process mode...
Dynamic optimization of long term primary electric distribution network investments based on planning metrics Tor, Osman Bulent; CEBECI, Mahmut Erkut; KOC, Mehmet; Güven, Ali Nezih (2018-01-01) This paper presents methodologies of dynamic planning algorithms which are developed for optimizing long-term primary electric distribution network investments taking into account some planning metrics. First, an algorithm which calculates a representative primary network model of distribution grids whose primary and secondary networks are intricate is developed. It is aimed to facilitate assessment of primary distribution network investment requirements and thereby defining grid investment candidates effec...
Evaluation of rotorcraft system identification approaches Kaymak, Serkan; Tekinalp, Ozan; Kutay, Ali Türker; Department of Aerospace Engineering (2013) This thesis addresses rotorcraft system identification approaches and estimating the stability and control parameters for linear system identification of a helicopter in hover. Output error and least square methods are used for the system identification. Inputs of the system identification analysis are obtained from the nonlinear helicopter model written in FLIGHTLAB commercial software environment. A linear helicopter model is used for identification. For validation, results obtained from identified helico...
Prioritized sequential 3D reconstruction in video sequences of dynamic scenes degrees Imre, Evren; Alatan, Abdullah Aydın; Knorr, Sebastian; Sikora, Thomas (2006-04-19) In this study, an algorithm is proposed to solve the multiframe structure from motion (MFSfM) problem for monocular video sequences in dynamic scenes. The algorithm uses the epipolar criterion to segment the features belonging to the independently moving objects. Once the features are segmented, the corresponding objects are reconstructed individually by using a sequential algorithm, which is also capable prioritizing the frame pairs with respect to their reliability and information content, thus achieving ...
Performance Comparison of Different Sparse Array Configurations for Ultra-Wideband, Near-field Imaging Applications Cetin, Beyzat Talat; Alatan, Lale (2017-03-24) The aim of this study is to compare the performance of different multiple-input multiple-output (MIMO) array topologies, intended to be used in ultra-wideband (UWB) near-field imaging applications, by using an analysis method that does not include the effects of image reconstruction algorithm. For this purpose, maximum projection method, previously proposed for the analysis of UWB arrays under far-field conditions, is utilized and modified to obtain two way beam patterns of UWB arrays operating in the near-...

Citation Formats

İ. Yavrucuk, “Limit Margin Prediction For Helicopters Using Long Term Learning Adaptive Neural Networks,” Italy, 2011, p. 1187, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/78584.