Machine Tool Component Health Identification with Unsupervised Learning
Unforeseen machine tool component failures cause considerable losses. This study presents a new approach to unsupervised machine component condition identification. It uses test cycle data of machine components in healthy and various faulty conditions for modelling. The novelty in the approach consi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Journal of Manufacturing and Materials Processing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-4494/4/3/86 |
| _version_ | 1797554867278970880 |
|---|---|
| author | Thomas Gittler Stephan Scholze Alisa Rupenyan Konrad Wegener |
| author_facet | Thomas Gittler Stephan Scholze Alisa Rupenyan Konrad Wegener |
| author_sort | Thomas Gittler |
| collection | DOAJ |
| description | Unforeseen machine tool component failures cause considerable losses. This study presents a new approach to unsupervised machine component condition identification. It uses test cycle data of machine components in healthy and various faulty conditions for modelling. The novelty in the approach consists of the time series representation as features, the filtering of the features for statistical significance, and the use of this feature representation to train a clustering model. The benefit in the proposed approach is its small engineering effort, the potential for automation, the small amount of data necessary for training and updating the model, and the potential to distinguish between multiple known and unknown conditions. Online measurements on machines in unknown conditions are performed to predict the component condition with the aid of the trained model. The approach was exemplarily tested and verified on different healthy and faulty states of a grinding machine axis. For the accurate classification of the component condition, different clustering algorithms were evaluated and compared. The proposed solution demonstrated encouraging results as it accurately classified the component condition. It requires little data, is straightforward to implement and update, and is able to precisely differentiate minor differences of faults in test cycle time series. |
| first_indexed | 2024-03-10T16:38:12Z |
| format | Article |
| id | doaj.art-c96fa9184b964e53901429a1fef2c5ee |
| institution | Directory Open Access Journal |
| issn | 2504-4494 |
| language | English |
| last_indexed | 2024-03-10T16:38:12Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Manufacturing and Materials Processing |
| spelling | doaj.art-c96fa9184b964e53901429a1fef2c5ee2023-11-20T12:15:55ZengMDPI AGJournal of Manufacturing and Materials Processing2504-44942020-09-01438610.3390/jmmp4030086Machine Tool Component Health Identification with Unsupervised LearningThomas Gittler0Stephan Scholze1Alisa Rupenyan2Konrad Wegener3Institute of Machine Tools and Manufacturing (IWF), ETH Zürich, CH-8092 Zurich, SwitzerlandAgathon AG, CH-4512 Bellach, SwitzerlandInspire AG, ETH Zürich, CH-8005 Zurich, SwitzerlandInstitute of Machine Tools and Manufacturing (IWF), ETH Zürich, CH-8092 Zurich, SwitzerlandUnforeseen machine tool component failures cause considerable losses. This study presents a new approach to unsupervised machine component condition identification. It uses test cycle data of machine components in healthy and various faulty conditions for modelling. The novelty in the approach consists of the time series representation as features, the filtering of the features for statistical significance, and the use of this feature representation to train a clustering model. The benefit in the proposed approach is its small engineering effort, the potential for automation, the small amount of data necessary for training and updating the model, and the potential to distinguish between multiple known and unknown conditions. Online measurements on machines in unknown conditions are performed to predict the component condition with the aid of the trained model. The approach was exemplarily tested and verified on different healthy and faulty states of a grinding machine axis. For the accurate classification of the component condition, different clustering algorithms were evaluated and compared. The proposed solution demonstrated encouraging results as it accurately classified the component condition. It requires little data, is straightforward to implement and update, and is able to precisely differentiate minor differences of faults in test cycle time series.https://www.mdpi.com/2504-4494/4/3/86condition monitoringmachine learningprognostics and health monitoringunsupervised learningmachine toolsmanufacturing |
| spellingShingle | Thomas Gittler Stephan Scholze Alisa Rupenyan Konrad Wegener Machine Tool Component Health Identification with Unsupervised Learning Journal of Manufacturing and Materials Processing condition monitoring machine learning prognostics and health monitoring unsupervised learning machine tools manufacturing |
| title | Machine Tool Component Health Identification with Unsupervised Learning |
| title_full | Machine Tool Component Health Identification with Unsupervised Learning |
| title_fullStr | Machine Tool Component Health Identification with Unsupervised Learning |
| title_full_unstemmed | Machine Tool Component Health Identification with Unsupervised Learning |
| title_short | Machine Tool Component Health Identification with Unsupervised Learning |
| title_sort | machine tool component health identification with unsupervised learning |
| topic | condition monitoring machine learning prognostics and health monitoring unsupervised learning machine tools manufacturing |
| url | https://www.mdpi.com/2504-4494/4/3/86 |
| work_keys_str_mv | AT thomasgittler machinetoolcomponenthealthidentificationwithunsupervisedlearning AT stephanscholze machinetoolcomponenthealthidentificationwithunsupervisedlearning AT alisarupenyan machinetoolcomponenthealthidentificationwithunsupervisedlearning AT konradwegener machinetoolcomponenthealthidentificationwithunsupervisedlearning |