ROUGHNESS ESTIMATION OF INCLINED SURFACES USING ARTIFICIAL INTELLIGENCE |
|---|
| B. Ramamoorthy, P. Priya |
- Abstract:
- Practical use of Machine Vision for surface roughness estimation faces many challenges, as in this case only image is used for evaluation and not the component. In such cases, if the component is kept at an angle during imaging, there is a possibility of getting distorted information and therefore the consistency of evaluation/ quantification would become a problem. So, there is a need to ensure that the measured surface is kept horizontal and flat when the image is being taken. In this work, estimation of the surface roughness has been done and analysed using digital images of machined surfaces obtained by a Machine Vision system deliberately maintained at varying angles. The quantitative measures of surface roughness are extracted in the spatial frequency domain using a two dimensional Fourier Transform. An artificial neural network (ANN) is trained and tested to arrive at the Ra values using the input obtained from the digital images of inclined surfaces which include optical roughness parameters estimated and angular of inclination of test parts. The estimated optical roughness parameter results based on the images of the surfaces are compared with the surfaces that are kept horizontal and the results are presented and analysed in this paper. In addition optimal combination of calculated roughness parameters which act as input to the ANN in order to obtain best correlation between estimated Ra using ANN and stylus measured Ra value is determined.
- Keywords:
- Machine vision, Artificial neural networks, Surface roughness
- Download:
- PWC-2006-TC14-018u.pdf
- DOI:
- -
- Event details
- Event name:
- XVIII IMEKO World Congress
- Title:
Metrology for a Sustainable Development
- Place:
- Rio de Janeiro, BRAZIL
- Time:
- 17 September 2006 - 22 September 2006