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

Vision-based automatic process control.

Cheng, Yuan.

FindBook

Google Book

Amazon

博客來

Vision-based automatic process control.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Vision-based automatic process control./
作者:	Cheng, Yuan.
面頁冊數:	108 p.
附註:	Source: Dissertation Abstracts International, Volume: 66-05, Section: B, page: 2761.
Contained By:	Dissertation Abstracts International66-05B.
標題:	Engineering, Industrial. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3176158
ISBN:	9780542155987

Vision-based automatic process control.
Cheng, Yuan.

Vision-based automatic process control. - 108 p.

Source: Dissertation Abstracts International, Volume: 66-05, Section: B, page: 2761.

Thesis (Ph.D.)--Rutgers The State University of New Jersey - New Brunswick, 2005.

This dissertation combines automated visual inspection and process control strategy into an efficient vision-based process control system. The purpose of our surface inspection, in addition to monitoring and classification of defects, is to improve the manufacturing process to reduce defects in subsequent stages.

ISBN: 9780542155987Subjects--Topical Terms:

626639
Engineering, Industrial.

Vision-based automatic process control.
LDR:03424nmm 2200337 4500 001 1827175
005 20061222091112.5
008 130610s2005 eng d
020 $a 9780542155987
035 $a (UnM)AAI3176158
035 $a AAI3176158
040 $a UnM $c UnM
100 1 $a Cheng, Yuan. $3 1916120
245 1 0 $a Vision-based automatic process control.
300 $a 108 p.
500 $a Source: Dissertation Abstracts International, Volume: 66-05, Section: B, page: 2761.
500 $a Director: Mohsen Jafari.
502 $a Thesis (Ph.D.)--Rutgers The State University of New Jersey - New Brunswick, 2005.
520 $a This dissertation combines automated visual inspection and process control strategy into an efficient vision-based process control system. The purpose of our surface inspection, in addition to monitoring and classification of defects, is to improve the manufacturing process to reduce defects in subsequent stages.
520 $a In the defect detection module, we examine the surface pattern using intensity image combined with CAD information. The CAD-based model is used to define shape and dimension of the surface, as well as the way the surface is constructed. A hybrid strategy is used for defect analysis, where the randomly occurred defects are detected by 2D texture analysis and assignable defects are obtained from 3D shape reconstruction using shape-from-shading. In 3D shape reconstruction we reconstruct 2D profile from representative signatures) and the 3D surface is obtained from sweeping the profile along the path defined in CAD file. In the profile reconstruction, we apply a parametric approach to improve efficiency. Compared with traditional 3D shape-from-shading, our approach is more computationally efficient in reconstructing patterned surface shapes.
520 $a For process control we take defect information obtained from defect detection module as input to determine the appropriate control parameters in order to minimize the possible defects in later stages of production. Our global control scheme considers process dynamics, disturbances and inter-surface relationships. A linear autoregressive model is developed based on deposition mechanics. The results show the existence of correlations among adjacent layers and validate our presented model.
520 $a In addition to the linear model, we developed a fuzzy controller based on Takagi-Sugeno model. The fuzzy model serves as an alternative process controller considering complexity and uncertainties for both process dynamics and defect measurements. It enhances the linear model by considering overfills and underfills separately. The results show that the fuzzy model performs as well as the linear model when the data is linear and improves when the data demonstrates non-linearity.
520 $a A Matlab simulation model is developed to illustrate the concepts and evaluate our vision-based process control results. It simulates the manufacturing and vision-based process control system, which includes deposition process, surface construction, intensity image generation, defect detection, and process control.
590 $a School code: 0190.
650 4 $a Engineering, Industrial. $3 626639
650 4 $a Computer Science. $3 626642
650 4 $a Engineering, Materials Science. $3 1017759
690 $a 0546
690 $a 0984
690 $a 0794
710 2 0 $a Rutgers The State University of New Jersey - New Brunswick. $3 1017590
773 0 $t Dissertation Abstracts International $g 66-05B.
790 1 0 $a Jafari, Mohsen, $e advisor
790 $a 0190
791 $a Ph.D.
792 $a 2005
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3176158