東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Neural network based wheel bearing f...

Xu, Peng.

FindBook

Google Book

Amazon

博客來

Neural network based wheel bearing fault detection and diagnosis using wavelets.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Neural network based wheel bearing fault detection and diagnosis using wavelets./
作者:	Xu, Peng.
面頁冊數:	124 p.
附註:	Source: Dissertation Abstracts International, Volume: 63-11, Section: B, page: 5430.
Contained By:	Dissertation Abstracts International63-11B.
標題:	Engineering, Electronics and Electrical. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3072557
ISBN:	0493922830

Neural network based wheel bearing fault detection and diagnosis using wavelets.
Xu, Peng.

Neural network based wheel bearing fault detection and diagnosis using wavelets. - 124 p.

Source: Dissertation Abstracts International, Volume: 63-11, Section: B, page: 5430.

Thesis (Ph.D.)--Texas A&M University, 2002.

In this dissertation, we introduce neural network based algorithms to classify signals with the conjunction of <italic>Wavelet Transform</italic> and <italic>Genetic Algorithm</italic> techniques. Specifically, we use these algorithms on wheel bearing fault detection and diagnosis systems. <italic> Wavelet Transforms</italic> have been widely used for pattern recognition applications. Features extracted from scales (sub-bands) produced by <italic> Wavelet Transforms</italic> are highly correlated due to the redundancy of the scales (sub-bands). These correlated features may cause the classifiers to converge very slowly and reduce the classification performance. Feature dimension reduction techniques are essential to making wavelets more powerful. In this dissertation, we introduce <italic>Genetic Algorithm</italic> to reduce the feature dimension in two steps: (1) selecting the subset of sub-bands, and (2) selecting features belonging to these sub-bands. We use both multilayer perceptron (MLP) and support vector machine (SVM) as classifiers. The original SVMs are developed for a two-class problem. To extend the SVMs to our applications, we develop a multi-SVM that is optimized by adjusting the cost-factor of each individual SVM. In addition, we provide some advanced topics that will be helpful for the future research of railroad wheel bearing condition monitoring applications.

ISBN: 0493922830Subjects--Topical Terms:

626636
Engineering, Electronics and Electrical.

Neural network based wheel bearing fault detection and diagnosis using wavelets.
LDR:02292nmm 2200277 4500 001 1810672
005 20040329092833.5
008 130610s2002 eng d
020 $a 0493922830
035 $a (UnM)AAI3072557
035 $a AAI3072557
040 $a UnM $c UnM
100 1 $a Xu, Peng. $3 1900274
245 1 0 $a Neural network based wheel bearing fault detection and diagnosis using wavelets.
300 $a 124 p.
500 $a Source: Dissertation Abstracts International, Volume: 63-11, Section: B, page: 5430.
500 $a Chair: Andrew K. Chan.
502 $a Thesis (Ph.D.)--Texas A&M University, 2002.
520 $a In this dissertation, we introduce neural network based algorithms to classify signals with the conjunction of <italic>Wavelet Transform</italic> and <italic>Genetic Algorithm</italic> techniques. Specifically, we use these algorithms on wheel bearing fault detection and diagnosis systems. <italic> Wavelet Transforms</italic> have been widely used for pattern recognition applications. Features extracted from scales (sub-bands) produced by <italic> Wavelet Transforms</italic> are highly correlated due to the redundancy of the scales (sub-bands). These correlated features may cause the classifiers to converge very slowly and reduce the classification performance. Feature dimension reduction techniques are essential to making wavelets more powerful. In this dissertation, we introduce <italic>Genetic Algorithm</italic> to reduce the feature dimension in two steps: (1) selecting the subset of sub-bands, and (2) selecting features belonging to these sub-bands. We use both multilayer perceptron (MLP) and support vector machine (SVM) as classifiers. The original SVMs are developed for a two-class problem. To extend the SVMs to our applications, we develop a multi-SVM that is optimized by adjusting the cost-factor of each individual SVM. In addition, we provide some advanced topics that will be helpful for the future research of railroad wheel bearing condition monitoring applications.
590 $a School code: 0803.
650 4 $a Engineering, Electronics and Electrical. $3 626636
650 4 $a Engineering, Mechanical. $3 783786
690 $a 0544
690 $a 0548
710 2 0 $a Texas A&M University. $3 718977
773 0 $t Dissertation Abstracts International $g 63-11B.
790 1 0 $a Chan, Andrew K., $e advisor
790 $a 0803
791 $a Ph.D.
792 $a 2002
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3072557