Neural Network Based Robust Filtering Designs
碩士 === 國立臺灣海洋大學 === 導航與通訊系 === 92 === In general, the navigation information has been processed by the Kalman filter. The filtering algorithm requires the knowledge that all the system strength (i.e., the system model , initial condition, and noise characteristics) have to be specified a priori. How...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2004
|
Online Access: | http://ndltd.ncl.edu.tw/handle/07303848502284650130 |
id |
ndltd-TW-092NTOU5300017 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-092NTOU53000172016-06-01T04:21:57Z http://ndltd.ncl.edu.tw/handle/07303848502284650130 Neural Network Based Robust Filtering Designs 以類神經網路實現強健濾波之設計 Rong-Jyh Chen 陳榮志 碩士 國立臺灣海洋大學 導航與通訊系 92 In general, the navigation information has been processed by the Kalman filter. The filtering algorithm requires the knowledge that all the system strength (i.e., the system model , initial condition, and noise characteristics) have to be specified a priori. However, if there is uncertainty in any of these characteristics, the filter may not be robust enough. The robust filter is expected to perform better solutions than the Kalman filter when there are uncertainties in both process and measurement models. Howerver, the filters that perform robust estimation usually require iteration proceduce before the robust estimate is obtained, In this thesis, we propose a neural network learning algorithm to implement the relationship between the input covariances and the optimal Kalman gain. After the learning process is completed, a mapping that relates the input covariance matrices to the optimal Kalman gains can be obtained. In this case, we do not need the iteration process for obtaining optimal Kalman gains. Dah - Jing Jwo 卓大靖 2004 學位論文 ; thesis 52 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立臺灣海洋大學 === 導航與通訊系 === 92 === In general, the navigation information has been processed by the Kalman filter. The filtering algorithm requires the knowledge that all the system strength (i.e., the system model , initial condition, and noise characteristics) have to be specified a priori. However, if there is uncertainty in any of these characteristics, the filter may not be robust enough. The robust filter is expected to perform better solutions than the Kalman filter when there are uncertainties in both process and measurement models. Howerver, the filters that perform robust estimation usually require iteration proceduce before the robust estimate is obtained, In this thesis, we propose a neural network learning algorithm to implement the relationship between the input covariances and the optimal Kalman gain. After the learning process is completed, a mapping that relates the input covariance matrices to the optimal Kalman gains can be obtained. In this case, we do not need the iteration process for obtaining optimal Kalman gains.
|
author2 |
Dah - Jing Jwo |
author_facet |
Dah - Jing Jwo Rong-Jyh Chen 陳榮志 |
author |
Rong-Jyh Chen 陳榮志 |
spellingShingle |
Rong-Jyh Chen 陳榮志 Neural Network Based Robust Filtering Designs |
author_sort |
Rong-Jyh Chen |
title |
Neural Network Based Robust Filtering Designs |
title_short |
Neural Network Based Robust Filtering Designs |
title_full |
Neural Network Based Robust Filtering Designs |
title_fullStr |
Neural Network Based Robust Filtering Designs |
title_full_unstemmed |
Neural Network Based Robust Filtering Designs |
title_sort |
neural network based robust filtering designs |
publishDate |
2004 |
url |
http://ndltd.ncl.edu.tw/handle/07303848502284650130 |
work_keys_str_mv |
AT rongjyhchen neuralnetworkbasedrobustfilteringdesigns AT chénróngzhì neuralnetworkbasedrobustfilteringdesigns AT rongjyhchen yǐlèishénjīngwǎnglùshíxiànqiángjiànlǜbōzhīshèjì AT chénróngzhì yǐlèishénjīngwǎnglùshíxiànqiángjiànlǜbōzhīshèjì |
_version_ |
1718290400255410176 |