Dynamic modelling of twin rotor multi system in horizontal motion
This paper investigates the parametric linear approach and utilisation of neural networks (NNs) for modelling of a twin rotor multi system (TRMS) in horizontal motion. Parametric modelling using Auto Regressive Modelling (ARX) model using Recursive Least Squares (RLS) algorithm. On the other hand, n...
Saved in:
Main Authors: | , |
---|---|
Format: | Article |
Language: | English English |
Published: |
Faculty of Mechanical Engineering
2010
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/36669/1/IntanZaurahMat2010_DynamicModellingofTwinRotorMulti.pdf http://eprints.utm.my/id/eprint/36669/2/201026211.pdf http://eprints.utm.my/id/eprint/36669/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Universiti Teknologi Malaysia |
Language: | English English |
Summary: | This paper investigates the parametric linear approach and utilisation of neural networks (NNs) for modelling of a twin rotor multi system (TRMS) in horizontal motion. Parametric modelling using Auto Regressive Modelling (ARX) model using Recursive Least Squares (RLS) algorithm. On the other hand, non-parametric modelling, makes use of Multi Layer Perceptron-Neural Network (MLP-NN) technique. All of these techniques will be used to characterize the behaviour of TRMS. Comparative assessment between these two techniques was conducted and the MLP-NN shows better results compared to RLS for modelling the TRMS. Mean Square Error (MSE), One Step Ahead (OSA) prediction and Correlation Tests were used for verification and validation of both models. Both models are found to be within the 95% confident level. |
---|