東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Intelligent fault detection and diag...

Li, Xiaolin.

Linked to FindBook

Google Book

Amazon

博客來

Intelligent fault detection and diagnosis of mechanical-pneumatic systems.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Intelligent fault detection and diagnosis of mechanical-pneumatic systems./
Author:	Li, Xiaolin.
Description:	135 p.
Notes:	Source: Dissertation Abstracts International, Volume: 66-09, Section: B, page: 5050.
Contained By:	Dissertation Abstracts International66-09B.
Subject:	Engineering, Mechanical. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3189414
ISBN:	054232136X

Intelligent fault detection and diagnosis of mechanical-pneumatic systems.
Li, Xiaolin.

Intelligent fault detection and diagnosis of mechanical-pneumatic systems. - 135 p.

Source: Dissertation Abstracts International, Volume: 66-09, Section: B, page: 5050.

Thesis (Ph.D.)--State University of New York at Stony Brook, 2005.

The supervision of systems is important in modern engineering process and manufacturing automation. In order to improve maintainability and availability and to protect environment and personnel, faults have to be detected early enough for counter-measures. During the last few years, many research efforts were presented in the field of process supervision and fault diagnosis.

ISBN: 054232136XSubjects--Topical Terms:

783786
Engineering, Mechanical.

Intelligent fault detection and diagnosis of mechanical-pneumatic systems.
LDR:03027nmm 2200301 4500 001 1816564
005 20060717100403.5
008 130610s2005 eng d
020 $a 054232136X
035 $a (UnM)AAI3189414
035 $a AAI3189414
040 $a UnM $c UnM
100 1 $a Li, Xiaolin. $3 1030681
245 1 0 $a Intelligent fault detection and diagnosis of mechanical-pneumatic systems.
300 $a 135 p.
500 $a Source: Dissertation Abstracts International, Volume: 66-09, Section: B, page: 5050.
500 $a Adviser: Imin Kao.
502 $a Thesis (Ph.D.)--State University of New York at Stony Brook, 2005.
520 $a The supervision of systems is important in modern engineering process and manufacturing automation. In order to improve maintainability and availability and to protect environment and personnel, faults have to be detected early enough for counter-measures. During the last few years, many research efforts were presented in the field of process supervision and fault diagnosis.
520 $a This dissertation presents the research in fault detection and diagnosis (FDD) for mechanical and pneumatic systems, which are often found in manufacturing floors for automation. The research in intelligent FDD utilizes data obtained from sensors and sensor network of manufacturing systems to prevent failure of devices that causes shutdown and loss of precious production time and profits in automation. The diagnosis systems presented in this dissertation include the model-based and signal-based approaches. In the model-based approach, the physical model of the system is employed in the analysis of fault detection and diagnosis (FDD) of pneumatic systems using the electro-pneumatic analogy. In the signal-based approach, methodology of pattern recognition is used in the construction of the FDD system. To this end, the wavelet methodology has been employed to reduce the redundancy which exists in various sensory signals. The signatures (features) of the sampled signals with known leakage are drawn from the coefficients of the wavelet decomposition to establish the relationship between the signature and the targeted faults. Vectorized maps are employed for the diagnosis of unknown faults based on the established FDD information. The step-wise Voronoi diagrams, which take advantage of the Voronoi but avoid the overhead of building a high-dimensional Voronoi diagram, are employed in fast search for fault diagnosis. Experimental results and analysis are presented to illustrate the FDD technique.
520 $a Finally, sensor reduction and resolution improvement are discussed. A wavelet manager, a cost function manager, and a classifier manager are proposed to increase the flexibility and error resistance of the system.
590 $a School code: 0771.
650 4 $a Engineering, Mechanical. $3 783786
650 4 $a Computer Science. $3 626642
690 $a 0548
690 $a 0984
710 2 0 $a State University of New York at Stony Brook. $3 1019194
773 0 $t Dissertation Abstracts International $g 66-09B.
790 1 0 $a Kao, Imin, $e advisor
790 $a 0771
791 $a Ph.D.
792 $a 2005
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3189414