ISE Seminar Series

Thesis Defense: Computer Vision-Based Monitoring of Abrasive Loading During Wood Machining

Bhavin Vora
Master of SciencecCandidate
Industrial & Systems Engineering Department

Date: Tuesday, June 7, 2005
Time: 1:00pm
Location: Room 09-1149 (Kate Gleason Engineering Building)

Abstract

Surface quality is an important characteristic commonly assessed in wooden products. Sanding relies on coated abrasives as tooloing for both dimensioning and surface finishing but their performance is dependent on chip loading and grit wear. Traditionally, the uselife life of abrasive belts in sanding operation has been manually assessed. This type of inspection is highly subjective and dependent upon individual expertise, consequently leading to under utilization or over utilization of the abrasive. This, in turn, affects the production costs and quality of the product. In this work, an intelligent classification method that determines the optimal replacement policy for a belt exposed to known manufacturing parameters is developed. Controlled experiments were conducted to develop abrasive belts of known exposure, followed with digital microscopy to capture images and process them with pattern recognition and classification algorithms. Grit size, times were the parameters of interest and the response of the experiments was the images of the abrasive sheets after every experimental run. These images were used in training an artificial neural network that is turn, help in determining data to categorize the useful life of the abrasive. The results show a 95% success rate in accurately classifying abrasive images of similar conditional abrasives. Also, the results show that the classification of interpolated and extrapolated times of abrasive images is proposed to be used as one of the inputs to a decision system that would help in evaluating the life of the abrasive and replacement policies. Further research on the relationship between the different parameters affecting the useful life of the abrasive is required.

Thesis Committee:
Dr. Andres Carrano (Chair), Industrial & Systems Engineering Department
Dr. Ferat Sahin, Electrical Engineering Department

Questions?
Contact Dr. Michael Kuhl at 475-2134 or mekeie@rit.edu