Implementation of the hybrid binarisation method for thermogram analysis.
DOI:
https://doi.org/10.15276/opu.2.70.2024.14Keywords:
image processing, infrared camera, binarization algorithm, digital technologiesAbstract
The object of this study is thermograms obtained as a result of thermal imaging control of the machining process during the external turning operation. The implementation of thermal imaging control enables rapid visualisation of the thermal state of the external surfaces of the tool, workpiece, and chips in the cutting zone by obtaining thermograms. The article presents developments in creating a hybrid binarisation method for thermograms to enable further processing using neural networks. To realisation this project, an analysis of existing technologies and algorithms was conducted, selecting those that, in the authors' opinion, have the highest efficiency. A working prototype was developed using the Python 3.13 and the OpenCV framework for processing raster images. Due to the specific format of thermograms, the first step involved converting colour images into monochrome. The second step then applied a fixed binarisation method to highlight the hottest areas corresponding to the cutting zone (the contact area between the tool and the workpiece). The third step involves adaptive binarisation, which processes the highlighted frame area using Gaussian distribution, as a result, the necessary objects in the frame-corresponding to the cutting tool, workpiece, and occasionally hot chips-are accurately highlighted. The resulting algorithm turned out to be simple and fast, despite the execution of two sequential binarization algorithms, while maintaining an adequate level of frame conversion accuracy. This allows its further use in training neural networks on the obtained dataset.
Downloads
References
Brili, N., Ficko, M., & Klančnik, S. (2021). Tool Condition Monitoring of the Cutting Capability of a Turning Tool Based on Thermography. Sensors, 21(19), 6687. DOI: https://doi.org/10.3390/s21196687.
De Maddis, M., Lunetto, V., Razza, V., & Russo Spena, P. (2022). Infrared Thermography for Investigation of Surface Quality in Dry Finish Turning of Ti6Al4V. Metals, 12(1), 154. DOI: https://doi.org/10.3390/met12010154.
Zgórniak, P., Stachurski, W., & Ostrowski, D. (2016). Application of Thermographic Measurements for the Determination of the Impact of Selected Cutting Parameters on the Temperature in the Workpiece During Milling Process. Strojniški vestnik - Journal of Mechanical Engineering, 62(11), 657–664. DOI: http://dx.doi.org/10.5545/sv-jme.2015.3259.
Inţă, M. & Muntean, A. (2018). Researches regarding introducing temperature as a factor in cutting tool wear monitoringю. MATEC Web Conf. DOI: https://doi.org/0.1051/matecconf/201817801013.
Goloborodko, V.V., Oborskyi, G.O., & Perperi, L.M. (2024). Application of a thermal imager to measure the temperature in the cutting zone during turning. New and unconventional technologies in resource and energy saving: Proceedings of the International Scientific and Technical Conference, (December 11–12, 2024, Odesa. Odesa, 188–190.
Wilson, A. N., Gupta, K. A., Koduru, B. H., Kumar, A., Jha A. & Cenkeramaddi, L. R. (2023). Recent Advances in Thermal Imaging and its Applications Using Machine Learning: A Review. IEEE Sensors Journal, 23 (4), 3395–3407. DOI: https://doi.org/10.1109/JSEN.2023.3234335.
Sarı, T., Gules, H.K., Yiğitol, B. (2020). Awareness and Readiness of Industry 4.0: The Case of Turkish Manufacturing Industry. Adv. Prod. Eng. Manag., 15, 57–68. DOI: https://doi.org/10.14743/ apem2020.1.349.
Gade, R., & Moeslund, T. B. (2013). Thermal cameras and applications: a survey. Machine Vision and Applications, 25(1), 245–262. DOI: https://doi.org/10.1007/s00138-013-0570-5.
Cerci, Y., Demircioglu, P., Bogrekci, I., Deniz, C., & Durakbasa, M. N. (2013). Case study in thermal and wear analyses for cutting tools. In Proceedings of the 11th International Symposium on Measurement and Quality Control (p. 4). Osaka University. Retrieved from: https://www.imeko.org/publications/tc14-2013/IMEKO-TC14-2013-34.pdf.
Arrazola, P.-J., Aristimuno, P., Soler, D., & Childs, T. (2015). Metal cutting experiments and modelling for improved determination of chip/tool contact temperature by infrared thermography. CIRP Annals, 64(1), 57–60. DOI:10.1016/j.cirp.2015.04.061.
Podchashynskyi, Y., Luhovykh, O., & Chepiuk, L. (2023). Analysis of methods for processing video images with measurement information from a thermal imager / spectral camera. Technical Engineering, 1(91), 214–221. DOI: https://doi.org/10.26642/ten-2023-1(91)-214-221.
Sezgin, M., & Sankur, B. (2004). Survey over image thresholding techniques and quantitative performance evaluation. J. Electron. Imag. 13(1). DOI: https://doi.org/10.1117/1.1631315.
OpenCV (Open Source Computer Vision Library) Retrieved from: https://docs.opencv.org/3.4/d7/d1b/ group__imgproc__misc.html#ggaa42a3e6ef26247da787bf34030ed772caf262a01e7a3f112bbab4e8d8e28182dd.
