Classifiers ensemble of transfer learning for improved drill wear classification using convolutional neural network

Kurek, Jarosław; Aleksiejuk-Gawron, Joanna; Antoniuk, Izabella; Górski, J.; Jegorowa, Albina; Kruk, Michał; Orłowski, Arkadiusz; Pach, Jakub; Świderski, Bartosz; Wieczorek, Grzegorz

doi:10.22630/mgv.2019.28.1.2

Cited by 13 publications

(14 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A detailed overview of all the results of the scientific research obtained in the framework of the new approach to drill condition monitoring in wood-based panels machining [27][28][29][30][31][32][33][34][35][36][37][38] seems to be beyond the scope of the article. Besides, it is not necessary because all the original publications are widely available.…”

Section: Resultsmentioning

confidence: 99%

“…Generally, tool condition monitoring in the field of woodworking has also been popular for a long time [24][25][26]. Therefore, at the end of this introductory (and as concisely as possible) overview of the latest research trends, it is also worth noting the new and quite spectacular approach to drill condition monitoring in wood-based panels machining [27][28][29][30][31][32][33][34][35][36][37][38].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Review of New Scientific Developments in Drilling in Wood-Based Panels with Particular Emphasis on the Latest Research Trends in Drill Condition Monitoring

Górski

2022

Forests

Self Cite

View full text Add to dashboard Cite

Drilling is still one of the basic cutting processes that are of particular interest to wood science and technology professionals. As a result, considerable (and very diverse thematically) research has been recently carried out on drilling. The article focuses on the new and quite spectacular approach to drill condition monitoring in wood-based panels machining. One of the most innovative elements in the analyzed research trend is the adoption of the new general methodological assumptions that allow one to define the drill condition monitoring problem as a standard three-class classification. The general effectiveness of the tested monitoring systems (accuracy of classification ACC [%]), ranged between 67% and 82%. The critical classification error (CCE [%]) ranged between 0% and 1.6%. These results seem very promising, yet are still not good enough to develop a commercial monitoring system. A more useful form of obtaining diagnostic data and more effective classification strategies (algorithms) are likely to be required.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The Review of New Scientific Developments in Drilling in Wood-Based Panels with Particular Emphasis on the Latest Research Trends in Drill Condition Monitoring

Górski

2022

Forests

Self Cite

View full text Add to dashboard Cite

show abstract

“…If for the selected object more than one class has an identical number of neighbours, the distance to each of them will be checked. Final classification will be then assigned according to the neighbourhood, with smaller “distance” to the current example [ 30 , 46 , 47 , 48 ].…”

Section: Materials and Methodsmentioning

confidence: 99%

“…Especially, transfer and deep learning methodologies were proven to be accurate in such applications [ 28 , 29 ]. Additional improvements were made with data augmentation and classifier ensemble approaches [ 30 , 31 ]. The type of used classifiers also significantly influenced the overall solution quality [ 32 , 33 , 34 , 35 ].…”

Section: Introductionmentioning

confidence: 99%

“…The problem used as a base for evaluation is a well-defined one. Various works present working solutions with good accuracy [ 8 , 9 , 20 , 24 , 28 , 29 , 30 , 31 , 33 , 34 , 35 , 36 , 37 , 38 ], including both image- and sensor-based approaches. Similarly, as in most of them, three wear classes were defined to describe the drill bit state.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Advanced Feature Extraction Methods from Images of Drillings in Melamine Faced Chipboard for Automatic Diagnosis of Drill Wear

Antoniuk

Kurek

Krupa

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

In this paper, a novel approach to evaluation of feature extraction methodologies is presented. In the case of machine learning algorithms, extracting and using the most efficient features is one of the key problems that can significantly influence overall performance. It is especially the case with parameter-heavy problems, such as tool condition monitoring. In the presented case, images of drilled holes are considered, where state of the edge and the overall size of imperfections have high influence on product quality. Finding and using a set of features that accurately describes the differences between the edge that is acceptable or too damaged is not always straightforward. The presented approach focuses on detailed evaluation of various feature extraction approaches. Each chosen method produced a set of features, which was then used to train a selected set of classifiers. Five initial feature sets were obtained, and additional ones were derived from them. Different voting methods were used for ensemble approaches. In total, 38 versions of the classifiers were created and evaluated. Best accuracy was obtained by the ensemble approach based on Weighted Voting methodology. A significant difference was shown between different feature extraction methods, with a total difference of 11.14% between the worst and best feature set, as well as a further 0.2% improvement achieved by using the best voting approach.

show abstract

Deep learning methods for drill wear classification based on images of holes drilled in melamine faced chipboard

et al. 2020

View full text Add to dashboard Cite

In this paper, a set of improvements made in drill wear recognition algorithm obtained during previous work is presented. Images of the drilled holes made on melamine faced particleboard were used as its input values. During the presented experiments, three classes were recognized: green, yellow and red, which directly correspond to a tool that is in good shape, shape that needs to be confirmed by an operator, and which should be immediately replaced, since its further use in production process can result in losses due to low product quality. During the experiments, and as a direct result of a dialog with a manufacturer it was noted that while overall accuracy is important, it is far more crucial that the used algorithm can properly distinguish red and green classes and make no (or as little as possible) misclassifications between them. The proposed algorithm is based on an ensemble of possibly diverse models, which performed best under the above conditions. The model has relatively high overall accuracy, with close to none misclassifications between indicated classes. Final classification accuracy reached 80.49% for biggest used window, while making only 7 critical errors (misclassifications between red and green classes).

show abstract

Classifiers ensemble of transfer learning for improved drill wear classification using convolutional neural network

Cited by 13 publications

References 12 publications

The Review of New Scientific Developments in Drilling in Wood-Based Panels with Particular Emphasis on the Latest Research Trends in Drill Condition Monitoring

The Review of New Scientific Developments in Drilling in Wood-Based Panels with Particular Emphasis on the Latest Research Trends in Drill Condition Monitoring

Advanced Feature Extraction Methods from Images of Drillings in Melamine Faced Chipboard for Automatic Diagnosis of Drill Wear

Deep learning methods for drill wear classification based on images of holes drilled in melamine faced chipboard

Contact Info

Product

Resources

About