Back to search

Rochester Institute of Technology

Computer vision-based monitoring of abrasive loading during wood machining

Abstract

dc:description.abstract

Surface quality is an important characteristic commonly assessed in wooden products. Sanding relies on coated abrasives as tooling for both dimensioning and surface finishing but their performance is dependent on chip loading and grit wear. Traditionally, the useful 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 and machining time were the parameters of interest while response of the experiments included image information from the abrasive sheets after every experimental run. These images were used in training an artificial neural network that in 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 similarly conditioned abrasives. Also, the results show that the classification of interpolated and extrapolated times of abrasive usage are classified with a 95% success rate. A classification 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 proposed.

Degree

thesis:*
Name thesis:degree_name
Industrial and Systems Engineering (MS)
Level thesis:degree_level
Thesis
Discipline thesis:degree_discipline
Industrial and Systems Engineering (KGCOE)

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Vora, Bhavin S.
Contributors dc:contributor
  • Andres Carrano

Identifiers

dc:identifier.*
Repository record dc:identifier
https://repository.rit.edu/theses/7733

Chain of custody

source
Harvested from
Rochester Institute of Technology
Base URL
repository.rit.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Vora, Bhavin S.. Computer vision-based monitoring of abrasive loading during wood machining. Thesis thesis, https://repository.rit.edu/theses/7733