الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 265 |  |  |
| | | from | 265 | | |
Abstract
Machining conditions such as speed, feed, and depth of cut deeply affect surface quality and has been investigated by several researchers. With growing emphasis of industrial automation in manufacturing, vision techniques play an important role in many applications. One of the important applications of computer vision is texture analysis. Although many researchers employed texture analysis in many applications, very few applied it to predict the cutting conditions of machined surfaces. This thesis introduces an investigation of the relationship between the cutting conditions in milling operations (feed, speed and depth of cut) and statistical texture features using a vision system. A software, named AutoITA (Automatic Image TextureAnalysis), has been fully developed inhouse to calculate all texture features for captured images of machined surfaces. The results showed some of texture features have good correlations with feed, others have good correlations with the speed, while few texture features have good correlations with the depth of cut in milling operation. Additionally, the software is developed to predict the cutting conditions of specimens machined by milling operations from their captured images. The prediction process depends on equations database, which was built from the results obtained from this investigation. The system was verified by predicting cutting conditions for various specimens and the maximum error between the predicted and the actual cutting conditions did not exceed 11%.