Publications
2024
1.
García-Ordás, María Teresa; Alegre-Gutiérrez, Enrique; Alaíz-Rodríguez, Rocío; González-Castro, Víctor
Tool wear monitoring using an online, automatic and low cost system based on local texture Artículo de revista
En: arXiv preprint arXiv:2402.05977, 2024.
Resumen | Enlaces | BibTeX | Etiquetas: Computer vision, machine learning, Milling, Tool wear
@article{garcia-ordas_tool_2024,
title = {Tool wear monitoring using an online, automatic and low cost system based on local texture},
author = {María Teresa García-Ordás and Enrique Alegre-Gutiérrez and Rocío Alaíz-Rodríguez and Víctor González-Castro},
url = {https://arxiv.org/abs/2402.05977},
year = {2024},
date = {2024-01-01},
journal = {arXiv preprint arXiv:2402.05977},
abstract = {This work presents a fast and cost-effective method using computer vision and machine learning to assess cutting tool wear in edge profile milling. A new dataset of 577 images was created, including functional and disposable cutting edges. The method divides the edges into regions (Wear Patches) and classifies them using texture descriptors (LBP). A Support Vector Machine (SVM) achieved 90.26% accuracy in detecting worn tools, demonstrating strong potential for automatic wear monitoring in milling.},
keywords = {Computer vision, machine learning, Milling, Tool wear},
pubstate = {published},
tppubtype = {article}
}
This work presents a fast and cost-effective method using computer vision and machine learning to assess cutting tool wear in edge profile milling. A new dataset of 577 images was created, including functional and disposable cutting edges. The method divides the edges into regions (Wear Patches) and classifies them using texture descriptors (LBP). A Support Vector Machine (SVM) achieved 90.26% accuracy in detecting worn tools, demonstrating strong potential for automatic wear monitoring in milling.
2018
2.
García-Ordás, María Teresa; Alegre, Enrique; González-Castro, Víctor; Alaiz-Rodríguez, Rocío
Combining shape and contour features to improve tool wear monitoring in milling processes Artículo de revista
En: International Journal of Production Research, vol. 56, no 11, pp. 3901–3913, 2018, (Publisher: Taylor & Francis).
Resumen | Enlaces | BibTeX | Etiquetas: B-ORCHIZ, Contour Features, Feature Fusion, Shape Description, ShapeFeat, Tool wear
@article{garcia-ordas_combining_2018,
title = {Combining shape and contour features to improve tool wear monitoring in milling processes},
author = {María Teresa García-Ordás and Enrique Alegre and Víctor González-Castro and Rocío Alaiz-Rodríguez},
url = {https://www.tandfonline.com/doi/abs/10.1080/00207543.2018.1435919},
year = {2018},
date = {2018-01-01},
journal = {International Journal of Production Research},
volume = {56},
number = {11},
pages = {3901–3913},
abstract = {This paper proposes a vision-based system combining ShapeFeat and BORCHIZ descriptors to classify milling tool wear. Using late fusion, the approach improves classification accuracy, achieving 91.44% for binary classification and 82.90% for three wear levels, outperforming individual descriptors. The method offers a promising solution for automated tool wear monitoring.},
note = {Publisher: Taylor & Francis},
keywords = {B-ORCHIZ, Contour Features, Feature Fusion, Shape Description, ShapeFeat, Tool wear},
pubstate = {published},
tppubtype = {article}
}
This paper proposes a vision-based system combining ShapeFeat and BORCHIZ descriptors to classify milling tool wear. Using late fusion, the approach improves classification accuracy, achieving 91.44% for binary classification and 82.90% for three wear levels, outperforming individual descriptors. The method offers a promising solution for automated tool wear monitoring.
3.
García-Ordás, María Teresa; Alegre, Enrique; Alaiz-Rodríguez, Rocío; González-Castro, Víctor
Tool wear monitoring using an online, automatic and low cost system based on local texture Artículo de revista
En: Mechanical systems and signal processing, vol. 112, pp. 98–112, 2018, (Publisher: Academic Press).
Resumen | Enlaces | BibTeX | Etiquetas: Patches, texture description, Tool wear, Wear Region
@article{garcia-ordas_tool_2018,
title = {Tool wear monitoring using an online, automatic and low cost system based on local texture},
author = {María Teresa García-Ordás and Enrique Alegre and Rocío Alaiz-Rodríguez and Víctor González-Castro},
url = {https://www.sciencedirect.com/science/article/pii/S088832701830236X},
year = {2018},
date = {2018-01-01},
journal = {Mechanical systems and signal processing},
volume = {112},
pages = {98–112},
abstract = {This work presents a new, cost-effective, and fast approach for determining whether cutting tools in edge profile milling processes are serviceable or disposable, based on wear levels. A new dataset of 254 images of edge profile cutting heads was created, with 577 images of segmented cutting edges, classified as either functional (301) or disposable (276). The proposed method involves dividing the cutting edge into regions (Wear Patches, WP), characterizing them using texture descriptors based on Local Binary Patterns (LBP), and using a Support Vector Machine (SVM) with an intersection kernel to classify the patches. The best configuration achieved an accuracy of 90.26% in detecting disposable cutting edges, showing great potential for automatic wear monitoring in milling.},
note = {Publisher: Academic Press},
keywords = {Patches, texture description, Tool wear, Wear Region},
pubstate = {published},
tppubtype = {article}
}
This work presents a new, cost-effective, and fast approach for determining whether cutting tools in edge profile milling processes are serviceable or disposable, based on wear levels. A new dataset of 254 images of edge profile cutting heads was created, with 577 images of segmented cutting edges, classified as either functional (301) or disposable (276). The proposed method involves dividing the cutting edge into regions (Wear Patches, WP), characterizing them using texture descriptors based on Local Binary Patterns (LBP), and using a Support Vector Machine (SVM) with an intersection kernel to classify the patches. The best configuration achieved an accuracy of 90.26% in detecting disposable cutting edges, showing great potential for automatic wear monitoring in milling.
4.
Fernández-Robles, Laura; Charro, Noelia; Sánchez-González, Lidia; Pérez, Hilde; Castejón-Limas, Manuel; Alfonso-Cendón, Javier
Tool wear estimation and visualization using image sensors in micro milling manufacturing Artículo de revista
En: Hybrid Artificial Intelligent Systems: 13th International Conference, HAIS 2018, Oviedo, Spain, June 20-22, 2018, Proceedings 13, pp. 399–410, 2018, (Publisher: Springer International Publishing).
Resumen | Enlaces | BibTeX | Etiquetas: Micro Milling, Tool wear, Wear Estimation, Wear Visualization
@article{fernandez-robles_tool_2018,
title = {Tool wear estimation and visualization using image sensors in micro milling manufacturing},
author = {Laura Fernández-Robles and Noelia Charro and Lidia Sánchez-González and Hilde Pérez and Manuel Castejón-Limas and Javier Alfonso-Cendón},
url = {https://link.springer.com/chapter/10.1007/978-3-319-92639-1_33},
year = {2018},
date = {2018-01-01},
journal = {Hybrid Artificial Intelligent Systems: 13th International Conference, HAIS 2018, Oviedo, Spain, June 20-22, 2018, Proceedings 13},
pages = {399–410},
abstract = {This paper introduces a reliable machine vision system for automatically estimating and visualizing tool wear in micro milling. The system aims to ensure high-quality machining and prevent tool failure by accurately determining when a tool needs replacement. The process involves defining the area of interest and identifying the worn area using morphological operations and the k-means algorithm. The system's performance, evaluated with precision and recall (harmonic mean of 90.24 ± 2.78%), demonstrates its effectiveness and suitability for on-line integration in micro milling machines. Other tested methods include pure morphological operations and Otsu multi-threshold algorithms.},
note = {Publisher: Springer International Publishing},
keywords = {Micro Milling, Tool wear, Wear Estimation, Wear Visualization},
pubstate = {published},
tppubtype = {article}
}
This paper introduces a reliable machine vision system for automatically estimating and visualizing tool wear in micro milling. The system aims to ensure high-quality machining and prevent tool failure by accurately determining when a tool needs replacement. The process involves defining the area of interest and identifying the worn area using morphological operations and the k-means algorithm. The system's performance, evaluated with precision and recall (harmonic mean of 90.24 ± 2.78%), demonstrates its effectiveness and suitability for on-line integration in micro milling machines. Other tested methods include pure morphological operations and Otsu multi-threshold algorithms.
2015
5.
González-Laguna, Adalberto; Barreiro, Joaquín; Fernández-Abia, A; Alegre, Enrique; González-Castro, Víctor
Design of a TCM system based on vibration signal for metal turning processes Artículo de revista
En: Procedia engineering, vol. 132, pp. 405–412, 2015, (Publisher: No longer published by Elsevier).
Resumen | Enlaces | BibTeX | Etiquetas: Monitoring, TCM, Tool wear, Turning, Vibration
@article{gonzalez-laguna_design_2015,
title = {Design of a TCM system based on vibration signal for metal turning processes},
author = {Adalberto González-Laguna and Joaquín Barreiro and A Fernández-Abia and Enrique Alegre and Víctor González-Castro},
url = {https://www.sciencedirect.com/science/article/pii/S1877705815044239},
year = {2015},
date = {2015-01-01},
journal = {Procedia engineering},
volume = {132},
pages = {405–412},
abstract = {This paper investigates the identification of cutting tool wear in steel dry turning operations using vibration signal analysis. By analyzing RMS value evolution and FFT frequency spectra, an on-line tool condition monitoring system was developed to determine when the tool condition becomes unacceptable, affecting machining quality. The study concludes that both RMS values and specific frequency amplitude ranges are correlated with tool wear.},
note = {Publisher: No longer published by Elsevier},
keywords = {Monitoring, TCM, Tool wear, Turning, Vibration},
pubstate = {published},
tppubtype = {article}
}
This paper investigates the identification of cutting tool wear in steel dry turning operations using vibration signal analysis. By analyzing RMS value evolution and FFT frequency spectra, an on-line tool condition monitoring system was developed to determine when the tool condition becomes unacceptable, affecting machining quality. The study concludes that both RMS values and specific frequency amplitude ranges are correlated with tool wear.
6.
García-Olalla, Óscar; Alegre, Enrique; Barreiro, Joaquín; Fernández-Robles, Laura; García-Ordás, María Teresa
Tool wear classification using LBP-based descriptors combined with LOSIB-based enhancers Artículo de revista
En: Procedia engineering, vol. 132, pp. 950–957, 2015, (Publisher: No longer published by Elsevier).
Resumen | Enlaces | BibTeX | Etiquetas: LBP, LOSIB, Monitoring, TCM, texture description, Tool wear
@article{garcia-olalla_tool_2015,
title = {Tool wear classification using LBP-based descriptors combined with LOSIB-based enhancers},
author = {Óscar García-Olalla and Enrique Alegre and Joaquín Barreiro and Laura Fernández-Robles and María Teresa García-Ordás},
url = {https://www.sciencedirect.com/science/article/pii/S187770581504494X},
year = {2015},
date = {2015-01-01},
journal = {Procedia engineering},
volume = {132},
pages = {950–957},
abstract = {This paper presents an automatic tool wear detection method using computer vision and texture recognition. Two LBP-based methods combined with the LOSIB texture booster were evaluated on a dataset of 577 images. Binary (Low-High) and ternary (Low-Medium-High) classifications were performed, achieving 80.58% and 67.76% accuracy, respectively. Results highlight the potential for cost and time savings in industrial tool condition monitoring systems (TCMS).},
note = {Publisher: No longer published by Elsevier},
keywords = {LBP, LOSIB, Monitoring, TCM, texture description, Tool wear},
pubstate = {published},
tppubtype = {article}
}
This paper presents an automatic tool wear detection method using computer vision and texture recognition. Two LBP-based methods combined with the LOSIB texture booster were evaluated on a dataset of 577 images. Binary (Low-High) and ternary (Low-Medium-High) classifications were performed, achieving 80.58% and 67.76% accuracy, respectively. Results highlight the potential for cost and time savings in industrial tool condition monitoring systems (TCMS).
2008
7.
Alegre, Enrique; Aláiz-Rodríguez, Rocío; Barreiro, Joaquín; Ruiz, J
Tool wear classification using shape signatures from digital images and neural networks Miscelánea
2008.
Resumen | Enlaces | BibTeX | Etiquetas: Contour Signature, Neural Network Classification, Tool Life, Tool wear
@misc{alegre_tool_2008,
title = {Tool wear classification using shape signatures from digital images and neural networks},
author = {Enrique Alegre and Rocío Aláiz-Rodríguez and Joaquín Barreiro and J Ruiz},
url = {https://d1wqtxts1xzle7.cloudfront.net/44449799/TOOL_WEAR_CLASSIFICATION_USING_SHAPE_SIG20160405-3188-z6pcbc-libre.pdf?1459894371=&response-content-disposition=inline%3B+filename%3DTool_Wear_Classification_Using_Shape_Sig.pdf&Expires=1739807418&Signature=EvzaKBJe-t9uYSU0VHYfIsHLonQIni35AX6MmZfYX-OGZpEp8t2BJx27qJd32s9rE2Cc9pvkE7~9h~snb0YBv54nDj8YR4vULhHEIdJeYDH3ggm0seHqVpOg0pkE5KRCJByFN6SpvJdwTX6zzuuuXMbbQ0kTnZ0a~pzRBxr4yuCiHStUIcT7gpfiHcYVtBgznT0XiC~AM1vif5Wed6giDaCYv3YT7bs2Hn8h3DYoE0VJGSpQwIe8rhe9GBeQE0gJmfRsc4hacjCdf2ROSX-TJqo4CEPlVk97SWMlmOoEGa3ZfDGfaIMozuJUFUptedp7W8U-0-bsAIQJQihJHdch7g__&Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA},
year = {2008},
date = {2008-01-01},
publisher = {na},
abstract = {This paper presents a computer vision-based method with a neural network classifier to estimate wear in metal cutting inserts and determine replacement timing. A supervised classification approach distinguishes between low and excessive wear to ensure timely tool replacement. A dataset of 1,383 wear flank images was processed into binary images, and the wear perimeter was described using a normalized shape signature resized to 40 and 100 values. Classification using k-NN and MLP achieved error rates of 5.5% and 5.1%, respectively.},
keywords = {Contour Signature, Neural Network Classification, Tool Life, Tool wear},
pubstate = {published},
tppubtype = {misc}
}
This paper presents a computer vision-based method with a neural network classifier to estimate wear in metal cutting inserts and determine replacement timing. A supervised classification approach distinguishes between low and excessive wear to ensure timely tool replacement. A dataset of 1,383 wear flank images was processed into binary images, and the wear perimeter was described using a normalized shape signature resized to 40 and 100 values. Classification using k-NN and MLP achieved error rates of 5.5% and 5.1%, respectively.
2007
8.
Castejón, M.; Alegre, E.; Barreiro, J.; Hernández, L. K.
On-line tool wear monitoring using geometric descriptors from digital images Artículo de revista
En: International Journal of Machine Tools and Manufacture, vol. 47, no 12, pp. 1847-1853, 2007, ISSN: 0890-6955.
Resumen | Enlaces | BibTeX | Etiquetas: Computer vision, Image classification, Monitoring, Tool wear
@article{CASTEJON20071847,
title = {On-line tool wear monitoring using geometric descriptors from digital images},
author = {M. Castejón and E. Alegre and J. Barreiro and L. K. Hernández},
url = {https://www.sciencedirect.com/science/article/pii/S0890695507000892},
doi = {https://doi.org/10.1016/j.ijmachtools.2007.04.001},
issn = {0890-6955},
year = {2007},
date = {2007-01-01},
journal = {International Journal of Machine Tools and Manufacture},
volume = {47},
number = {12},
pages = {1847-1853},
abstract = {A new method based on a computer vision and statistical learning system is proposed to estimate the wear level in cutting inserts in order to identify the time for its replacement. A CNC parallel lathe and a computer vision system have been used to obtain 1383 flank images. A binary image for each of the former wear flank images have been obtained by applying several pre-processing and segmenting operations. Every wear flank region has been described by means of nine geometrical descriptors. LDA (linear discriminant analysis) shows that three out of the nine descriptors provide the 98.63% of the necessary information to carry out the classification, which are eccentricity, extent and solidity. The result obtained using a finite mixture model approach shows the presence of three clusters using these descriptors, which correspond with low, medium and high wear level. A monitoring approach is performed using the tool wear evolution for each insert along machining and the discriminant analysis. This evolution represents the probability of belonging to each one of the wear classes (low, medium and high). The estimate of the wear level allows to replace the tool when the wear level is located at the end of the M class (medium), preventing that the tool enters into the H class (high).},
keywords = {Computer vision, Image classification, Monitoring, Tool wear},
pubstate = {published},
tppubtype = {article}
}
A new method based on a computer vision and statistical learning system is proposed to estimate the wear level in cutting inserts in order to identify the time for its replacement. A CNC parallel lathe and a computer vision system have been used to obtain 1383 flank images. A binary image for each of the former wear flank images have been obtained by applying several pre-processing and segmenting operations. Every wear flank region has been described by means of nine geometrical descriptors. LDA (linear discriminant analysis) shows that three out of the nine descriptors provide the 98.63% of the necessary information to carry out the classification, which are eccentricity, extent and solidity. The result obtained using a finite mixture model approach shows the presence of three clusters using these descriptors, which correspond with low, medium and high wear level. A monitoring approach is performed using the tool wear evolution for each insert along machining and the discriminant analysis. This evolution represents the probability of belonging to each one of the wear classes (low, medium and high). The estimate of the wear level allows to replace the tool when the wear level is located at the end of the M class (medium), preventing that the tool enters into the H class (high).
9.
Castejón, Manuel; Alegre, Enrique; García, Joaquín Barreiro; Hernández, LK
On-line tool wear monitoring using geometric descriptors from digital images Artículo de revista
En: International Journal of Machine Tools and Manufacture, vol. 47, no 12-13, pp. 1847–1853, 2007, (Publisher: Pergamon).
Resumen | Enlaces | BibTeX | Etiquetas: Computer vision, Image classification, Monitoring, Tool wear
@article{castejon_-line_2007,
title = {On-line tool wear monitoring using geometric descriptors from digital images},
author = {Manuel Castejón and Enrique Alegre and Joaquín Barreiro García and LK Hernández},
url = {https://www.sciencedirect.com/science/article/pii/S0890695507000892},
year = {2007},
date = {2007-01-01},
journal = {International Journal of Machine Tools and Manufacture},
volume = {47},
number = {12-13},
pages = {1847–1853},
abstract = {A computer vision and statistical learning system is proposed to estimate wear levels in cutting inserts and determine the optimal replacement time. Using a CNC lathe and vision system, 1383 flank images were processed, extracting nine geometrical descriptors. Linear Discriminant Analysis identified three key descriptors—eccentricity, extent, and solidity—capturing 98.63% of relevant information. A finite mixture model classified wear into three levels: low, medium, and high. The monitoring approach tracks tool wear evolution, ensuring replacement before reaching high wear, optimizing performance and preventing failures.},
note = {Publisher: Pergamon},
keywords = {Computer vision, Image classification, Monitoring, Tool wear},
pubstate = {published},
tppubtype = {article}
}
A computer vision and statistical learning system is proposed to estimate wear levels in cutting inserts and determine the optimal replacement time. Using a CNC lathe and vision system, 1383 flank images were processed, extracting nine geometrical descriptors. Linear Discriminant Analysis identified three key descriptors—eccentricity, extent, and solidity—capturing 98.63% of relevant information. A finite mixture model classified wear into three levels: low, medium, and high. The monitoring approach tracks tool wear evolution, ensuring replacement before reaching high wear, optimizing performance and preventing failures.
2005
10.
Alegre, Enrique; Aláiz-Rodríguez, Rocío; Barreiro, Joaquín; Viñuela, M
Tool insert wear classification using statistical descriptors and neuronal networks Artículo de revista
En: Progress in Pattern Recognition, Image Analysis and Applications: 10th Iberoamerican Congress on Pattern Recognition, CIARP 2005, Havana, Cuba, November 15-18, 2005. Proceedings 10, pp. 786–793, 2005, (Publisher: Springer Berlin Heidelberg).
Resumen | Enlaces | BibTeX | Etiquetas: image processing, machine vision, Manufacturing, neural networks, Tool wear
@article{alegre_tool_2005,
title = {Tool insert wear classification using statistical descriptors and neuronal networks},
author = {Enrique Alegre and Rocío Aláiz-Rodríguez and Joaquín Barreiro and M Viñuela},
url = {https://link.springer.com/chapter/10.1007/11578079_82},
year = {2005},
date = {2005-01-01},
journal = {Progress in Pattern Recognition, Image Analysis and Applications: 10th Iberoamerican Congress on Pattern Recognition, CIARP 2005, Havana, Cuba, November 15-18, 2005. Proceedings 10},
pages = {786–793},
abstract = {This work proposes an automated method to determine tool insert wear levels using image analysis. Images of tungsten carbide inserts were acquired during machining of AISI SAE 1045 and 4140 steel bars. After pre-processing and wear area segmentation, statistical moment-based descriptors were extracted. Two classification experiments (binary and three-class) were conducted using Lp2, k-NN, and neural networks. Zernike and Legendre descriptors achieved the best results with a multilayer perceptron (MLP) neural network.},
note = {Publisher: Springer Berlin Heidelberg},
keywords = {image processing, machine vision, Manufacturing, neural networks, Tool wear},
pubstate = {published},
tppubtype = {article}
}
This work proposes an automated method to determine tool insert wear levels using image analysis. Images of tungsten carbide inserts were acquired during machining of AISI SAE 1045 and 4140 steel bars. After pre-processing and wear area segmentation, statistical moment-based descriptors were extracted. Two classification experiments (binary and three-class) were conducted using Lp2, k-NN, and neural networks. Zernike and Legendre descriptors achieved the best results with a multilayer perceptron (MLP) neural network.
0000
11.
Martın, Guillermo Martınez San; Robles, Laura Fernández; Alegre, Enrique; Olalla, Oscar Garcıa
A segmentation approach for evaluating wear of inserts in milling machines with computer vision techniques Artículo de revista
En: 0000.
Resumen | Enlaces | BibTeX | Etiquetas: Computer vision, milling machines, segmentation, Tool wear
@article{martinez_san_martin_segmentation_nodate,
title = {A segmentation approach for evaluating wear of inserts in milling machines with computer vision techniques},
author = {Guillermo Martınez San Martın and Laura Fernández Robles and Enrique Alegre and Oscar Garcıa Olalla},
url = {https://scholar.google.es/citations?view_op=view_citation&hl=es&user=4jZgNVkAAAAJ&sortby=title&citation_for_view=4jZgNVkAAAAJ:Se3iqnhoufwC},
abstract = {Measuring tool wear in milling machines is an important task to evaluate the lifetime of the cutting parts (inserts) and deciding whether we should replace them. In our research, we propose to use computer vision algorithms to perform this task. Part of the research is to evaluate the accuracy of different segmentation algorithms that segment the area of wear. We have used two methods: k-Means and Mean Shift. To evaluate the segmentation results the Dice coefficient was used, obtaining with Mean Shift a QS= 0.5923 for all the edges and a QS= 0.6831 just for edges with high wear.},
keywords = {Computer vision, milling machines, segmentation, Tool wear},
pubstate = {published},
tppubtype = {article}
}
Measuring tool wear in milling machines is an important task to evaluate the lifetime of the cutting parts (inserts) and deciding whether we should replace them. In our research, we propose to use computer vision algorithms to perform this task. Part of the research is to evaluate the accuracy of different segmentation algorithms that segment the area of wear. We have used two methods: k-Means and Mean Shift. To evaluate the segmentation results the Dice coefficient was used, obtaining with Mean Shift a QS= 0.5923 for all the edges and a QS= 0.6831 just for edges with high wear.
12.
García-Olalla, Óscar; Alegre, Enrique; Barreiro, Joaquín; Fernández-Robles, Laura; García-Ordás, Marıa Teresa
Tool wear classification using texture descriptors based on Local Binary Pattern Artículo de revista
En: 0000.
Resumen | Enlaces | BibTeX | Etiquetas: Machine Learing, Manufacturing, SVM, texture analysis, Tool wear
@article{garcia-olalla_tool_nodate,
title = {Tool wear classification using texture descriptors based on Local Binary Pattern},
author = {Óscar García-Olalla and Enrique Alegre and Joaquín Barreiro and Laura Fernández-Robles and Marıa Teresa García-Ordás},
url = {https://scholar.google.es/citations?view_op=view_citation&hl=en&user=opCbArQAAAAJ&cstart=100&pagesize=100&sortby=title&citation_for_view=opCbArQAAAAJ:RHpTSmoSYBkC},
abstract = {This paper presents a new approach for tool wear identification in metal milling using texture descriptors LBP and ALBP, enhanced with LOSIB (Local Oriented Statistical Information Booster). Two datasets are considered: Cutting Edges (gray-scale images of worn cutting edges) and Edge Wear (cropped worn areas). Both datasets are labeled into two (low/high wear) and three (low/medium/high wear) classes. Classification using Support Vector Machine with Least Squares training achieved a 74.05% accuracy for two classes and 53.77% for three classes in the Edge Wear dataset.},
keywords = {Machine Learing, Manufacturing, SVM, texture analysis, Tool wear},
pubstate = {published},
tppubtype = {article}
}
This paper presents a new approach for tool wear identification in metal milling using texture descriptors LBP and ALBP, enhanced with LOSIB (Local Oriented Statistical Information Booster). Two datasets are considered: Cutting Edges (gray-scale images of worn cutting edges) and Edge Wear (cropped worn areas). Both datasets are labeled into two (low/high wear) and three (low/medium/high wear) classes. Classification using Support Vector Machine with Least Squares training achieved a 74.05% accuracy for two classes and 53.77% for three classes in the Edge Wear dataset.