Unsupervised and Semisupervised Machine Learning Frameworks for Multiclass Tool Wear Recognition
Tool condition monitoring (TCM) is crucial to ensure good quality products and avoid downtime. Machine learning has proven to be vital for TCM. However, existing works are predominately based on supervised learning, which hinders their applicability in real-world manufacturing settings, where data l...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of the Industrial Electronics Society |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10668405/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526371161997312 |
|---|---|
| author | Maryam Assafo Peter Langendoerfer |
| author_facet | Maryam Assafo Peter Langendoerfer |
| author_sort | Maryam Assafo |
| collection | DOAJ |
| description | Tool condition monitoring (TCM) is crucial to ensure good quality products and avoid downtime. Machine learning has proven to be vital for TCM. However, existing works are predominately based on supervised learning, which hinders their applicability in real-world manufacturing settings, where data labeling is cumbersome and costly with in-service machines. Additionally, the existing unsupervised solutions mostly handle binary decision-based TCM which is unable to fully reflect the dynamics of tool wear progression. To address these issues, we propose different unsupervised and semisupervised five-class tool wear recognition frameworks to handle fully unlabeled and partially labeled data, respectively. The underlying methods include Laplacian score, sparse autoencoder (SAE), stacked SAE (SSAE), self-organizing map, Softmax, support vector machine, and random forest. For the semisupervised frameworks, we considered designs where labeled data influence only feature learning, classifier building, or both. We also investigated different training configurations of SSAE regarding the supervision level. We applied the frameworks on two run-to-failure datasets of milling tools, recorded using a microphone and an accelerometer. Single sensor and multisensor data under different percentages of labeled training data were considered in the evaluation. The results showed which of the frameworks led to the best predictive performance under which data settings, and highlighted the significance of sensor fusion and discriminative feature representations in combating the unavailability and scarcity of labels, among other findings. The highest macro-F1 achieved for the two datasets with fully unlabeled data reached 87.52% and 75.80%, respectively, and over 90% when only 25% of the training observations were labeled. |
| format | Article |
| id | doaj-art-bb42d5512dc647df93e183ee78509082 |
| institution | Kabale University |
| issn | 2644-1284 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of the Industrial Electronics Society |
| spelling | doaj-art-bb42d5512dc647df93e183ee785090822025-01-17T00:01:11ZengIEEEIEEE Open Journal of the Industrial Electronics Society2644-12842024-01-015993101010.1109/OJIES.2024.345526410668405Unsupervised and Semisupervised Machine Learning Frameworks for Multiclass Tool Wear RecognitionMaryam Assafo0https://orcid.org/0000-0002-3924-3355Peter Langendoerfer1https://orcid.org/0000-0002-6209-9048Chair of Wireless Systems, BTU Cottbus-Senftenberg, Cottbus, GermanyChair of Wireless Systems, BTU Cottbus-Senftenberg, Cottbus, GermanyTool condition monitoring (TCM) is crucial to ensure good quality products and avoid downtime. Machine learning has proven to be vital for TCM. However, existing works are predominately based on supervised learning, which hinders their applicability in real-world manufacturing settings, where data labeling is cumbersome and costly with in-service machines. Additionally, the existing unsupervised solutions mostly handle binary decision-based TCM which is unable to fully reflect the dynamics of tool wear progression. To address these issues, we propose different unsupervised and semisupervised five-class tool wear recognition frameworks to handle fully unlabeled and partially labeled data, respectively. The underlying methods include Laplacian score, sparse autoencoder (SAE), stacked SAE (SSAE), self-organizing map, Softmax, support vector machine, and random forest. For the semisupervised frameworks, we considered designs where labeled data influence only feature learning, classifier building, or both. We also investigated different training configurations of SSAE regarding the supervision level. We applied the frameworks on two run-to-failure datasets of milling tools, recorded using a microphone and an accelerometer. Single sensor and multisensor data under different percentages of labeled training data were considered in the evaluation. The results showed which of the frameworks led to the best predictive performance under which data settings, and highlighted the significance of sensor fusion and discriminative feature representations in combating the unavailability and scarcity of labels, among other findings. The highest macro-F1 achieved for the two datasets with fully unlabeled data reached 87.52% and 75.80%, respectively, and over 90% when only 25% of the training observations were labeled.https://ieeexplore.ieee.org/document/10668405/Autoencoderfeature learningLaplacian score (LS)machine learning (ML)multiclass classificationpredictive maintenance (PdM) |
| spellingShingle | Maryam Assafo Peter Langendoerfer Unsupervised and Semisupervised Machine Learning Frameworks for Multiclass Tool Wear Recognition IEEE Open Journal of the Industrial Electronics Society Autoencoder feature learning Laplacian score (LS) machine learning (ML) multiclass classification predictive maintenance (PdM) |
| title | Unsupervised and Semisupervised Machine Learning Frameworks for Multiclass Tool Wear Recognition |
| title_full | Unsupervised and Semisupervised Machine Learning Frameworks for Multiclass Tool Wear Recognition |
| title_fullStr | Unsupervised and Semisupervised Machine Learning Frameworks for Multiclass Tool Wear Recognition |
| title_full_unstemmed | Unsupervised and Semisupervised Machine Learning Frameworks for Multiclass Tool Wear Recognition |
| title_short | Unsupervised and Semisupervised Machine Learning Frameworks for Multiclass Tool Wear Recognition |
| title_sort | unsupervised and semisupervised machine learning frameworks for multiclass tool wear recognition |
| topic | Autoencoder feature learning Laplacian score (LS) machine learning (ML) multiclass classification predictive maintenance (PdM) |
| url | https://ieeexplore.ieee.org/document/10668405/ |
| work_keys_str_mv | AT maryamassafo unsupervisedandsemisupervisedmachinelearningframeworksformulticlasstoolwearrecognition AT peterlangendoerfer unsupervisedandsemisupervisedmachinelearningframeworksformulticlasstoolwearrecognition |