Aircraft Aerodynamic Parameter Estimation from Flight Data Using Neural Partial Differentiation
Aircraft Aerodynamic Parameter Estimation from Flight Data Using Neural Partial Differentiation

Author: Majeed Mohamed

Publisher: Springer Nature

Published: 2021-02-23

Total Pages: 66

ISBN-13: 9811601046

DOWNLOAD EBOOK

This book presents neural partial differentiation as an estimation algorithm for extracting aerodynamic derivatives from flight data. It discusses neural modeling of the aircraft system. The neural partial differentiation approach discussed in the book helps estimate parameters with their statistical information from the noisy data. Moreover, this method avoids the need for prior information about the aircraft model parameters. The objective of the book is to extend the use of the neural partial differentiation method to the multi-input multi-output aircraft system for the online estimation of aircraft parameters from an established neural model. This approach will be relevant for the design of an adaptive flight control system. The book also discusses the estimation of aerodynamic derivatives of rigid and flexible aircraft which are treated separately. The longitudinal and lateral-directional derivatives of aircraft are estimated from flight data. Besides the aerodynamic derivatives, mode shape parameters of flexible aircraft are also identified in the book as part of identification for the state space aircraft model. Since the detailed description of the approach is illustrated through the block diagram and their results are presented in tabular form with figures of parameters converge to their estimates, the contents of this book are intended for readers who want to pursue a postgraduate and doctoral degree in science and engineering. This book is useful for practicing scientists, engineers, and teachers in the field of aerospace engineering.

A Neural Network Approach to Aircraft Performance Model Forecasting
A Neural Network Approach to Aircraft Performance Model Forecasting

Author: Nicolas Vincent-Boulay

Publisher:

Published: 2020

Total Pages: 0

ISBN-13:

DOWNLOAD EBOOK

Performance models used in the aircraft development process are dependent on the assumptions and approximations associated with the engineering equations used to produce them. The design and implementation of these highly complex engineering models are typically associated with a longer development process. This study proposes a non-deterministic approach where machine learning techniques using Artificial Neural Networks are used to predict specific aircraft parameters using available data. The approach yields results that are independent of the equations used in conventional aircraft performance modeling methods and rely on stochastic data and its distribution to extract useful patterns. To test the viability of the approach, a case study is performed comparing a conventional performance model describing the takeoff ground roll distance with the values generated from a neural network using readily-available flight data. The neural network receives as input, and is trained using, aircraft performance parameters including atmospheric conditions (air temperature, air pressure, air density), performance characteristics (flap configuration, thrust setting, MTOW, etc.) and runway conditions (wet, dry, slope angle, etc.). The proposed predictive modeling approach can be tailored for use with a wider range of flight mission profiles such as climb, cruise, descent and landing.

Modern Computational Aeroelasticity
Modern Computational Aeroelasticity

Author: Min Xu

Publisher: Walter de Gruyter GmbH & Co KG

Published: 2020-12-07

Total Pages: 326

ISBN-13: 3110576686

DOWNLOAD EBOOK

The book provides a state-of-art overview of computational methods for nonlinear aeroelasticity and load analysis, focusing on key techniques and fundamental principles for CFD/CSD coupling in temporal domain. CFD/CSD coupling software design and applications of CFD/CSD coupling techniques are discussed in detail as well. It is an essential reference for researchers and students in mechanics and applied mathematics.

The Acccuracy of Parameter Estimation in System Identification of Noisy Aircraft Load Measurement
The Acccuracy of Parameter Estimation in System Identification of Noisy Aircraft Load Measurement

Author: Jeffrey Knog

Publisher:

Published: 1994

Total Pages:

ISBN-13:

DOWNLOAD EBOOK

"This thesis focuses on the subject of the accuracy of parameter estimation and system identification techniques. Motivated by a complicated load measurement from NASA Dryden Flight Research Center, advanced system identification techniques are needed. The objective of the problem is to accurately predict the load experienced by the aircraft wing structure during flight determined from a set of calibrated load and gage response relationship. We can then model the problem as a black box input-output system identification from which the system parameter has to be estimated. Traditional LS techniques and the issues of noisy data and model accuracy are addressed. A statistical bound reflecting the change in residual is derived in order to understand the effects of the perturbations on the data. Due to the intrinsic nature of the LS problem, LS solution faces the dilemma of the tradeoff between model accuracy and noise sensitivity. A method of relating the two conflicting performance indices is presented, thus allowing us to improve the noise sensitivity while at the same time confining the degradation of the model accuracy. SVD techniques for data reduction are studied and the equivalence of the Correspondence Analysis (CA) and Total Least Squares Criteria are proved. We also looked at nonlinear LS problems with NASA F-111 data set as an example. Conventional methods are neither easily applicable or suitable for the specific load problem since the exact model of the system is unknown. Neural Network (NN) does not require prior information on the model of the system. This robustness motivated us to apply the NN techniques on our load problem. Simulation results for the NN methods used in both the single load and the "warning signal" problems are both useful and encouraging. The performance of the NN (for single load estimate) is better than the LS approach, whereas no conventional approach was tried for the "warning signals" problem. The NN design methodology is also presented. The use of SVD, CA and Collinearity Index methods are used to reduce the number of neurons in a layer."--Page i.