A neuro-wavelet techniques for GPS INS system integration
Other Title(s)
تقنيات الشبكة العصبية-المويجة في تكامل منظومتي GPS و INS
Dissertant
Thesis advisor
Said, Waladin K.
Ismail, Salam A.
University
University of Technology
Faculty
-
Department
Department of Control and Systems Engineering
University Country
Iraq
Degree
Master
Degree Date
2005
English Abstract
Global Positioning System (GPS) and Strapdown Inertial Navigation System (SDINS) can be integrated together to provide a reliable navigation system.
GPS provides position information and possibly velocity when there is direct line of sight to four or more satellites; and SDINS utilizes the local measurements of angular velocity and linear acceleration to determine both the vehicle’s position and velocity.
Thus integration leads to reliable navigation solution by overcoming each of their respective shortcomings.
Integration of GPS and SDINS are expected to become more widespread as a result of low cost inertial sensors.
This work offers a new method for error estimation in a GPS/INS augmented system based on Artificial Neural Network (ANN) and Wavelet Transform (WT).
The wavelet analysis was beneficial in filtering out the noise components and disturbances that may exist at the INS and GPS outputs.
In addition, it provides the advantage of comparing the INS and GPS position and velocity components at different levels of resolution.
This work describes the results obtained by implementing a conceptual intelligent navigator for reducing the GPS/INS errors, for several types of GPS and INS errors.
An ANN was adopted in this work to model the GPS/INS position and velocity errors in real time to predict the error in the integrated system and provide accurate navigation information of the moving vehicle.
Several testing data types were processed in this work, when the simulation results based on MatLab7 programming language was used.
it was found that the proposed technique reduces the standard deviation error in the position by about 91% for X, Y, and Z axes, while in velocity it was reduced by about 94% for North, East, and Down directions.
Also, in this work the problems of the difference between INS and GPS data rate as well as the blockage problem in GPS were solved by using three different methods which are Newton, Spline, and Artificial Neural Network.
Simulation results show that the proposed neural network give more accurate results than the Newton and Spline methods.
In spite of the problem associated with the neural network method.
Main Subjects
Information Technology and Computer Science
No. of Pages
119
Table of Contents
Table of contents.
Abstract.
Abstract in Arabic.
Chapter One : General introduction.
Chapter Two : INS and GPS systems implementation and error estimation.
Chapter Three : Wavelet decomposition for Denoising GPS / INS outputs.
Chapter Four : Ann model for velocity and position error estimation.
Chapter Five : Conclusions and future work.
References.
American Psychological Association (APA)
Hasan, Ahmad Mazhar. (2005). A neuro-wavelet techniques for GPS INS system integration. (Master's theses Theses and Dissertations Master). University of Technology, Iraq
https://search.emarefa.net/detail/BIM-749817
Modern Language Association (MLA)
Hasan, Ahmad Mazhar. A neuro-wavelet techniques for GPS INS system integration. (Master's theses Theses and Dissertations Master). University of Technology. (2005).
https://search.emarefa.net/detail/BIM-749817
American Medical Association (AMA)
Hasan, Ahmad Mazhar. (2005). A neuro-wavelet techniques for GPS INS system integration. (Master's theses Theses and Dissertations Master). University of Technology, Iraq
https://search.emarefa.net/detail/BIM-749817
Language
English
Data Type
Arab Theses
Record ID
BIM-749817
