Correlation statistics of a Fourier transform feature with flank wear on different sections of turned surface images for real time monitoring applications
Measurement: Journal of the International Measurement Confederation, cilt.207, 2023 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 207
- Basım Tarihi: 2023
- Doi Numarası: 10.1016/j.measurement.2022.112399
- Dergi Adı: Measurement: Journal of the International Measurement Confederation
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, INSPEC
- Anahtar Kelimeler: Flank wear, Fourier transform, Image cropping, Image processing, Tool wear monitoring, Turning
- Karadeniz Teknik Üniversitesi Adresli: Evet
Özet
© 2022 Elsevier LtdTextural features extracted from turned surface images have been used by several researchers to identify corresponding flank wear status of the tool for real time monitoring applications. In this work, fast Fourier transform were applied to the turned surface images and mean values of the magnitude spectra were used as a feature to capture the effects of subsequently added wear marks. Also a novel method based on column projection was used to crop the images into single feed marks and feature extraction was performed on; whole images, single feed mark images and, crest and trough sections of the single feed mark images. A linear relationship was found between wear and the feature for all image groups. And with a less than %5 difference in correlation attributes it was found that; whole images, single feed marks and crest sections can be used interchangeably for the relevant feature in a monitoring application.