AutoML for Feature Selection and Model Tuning Applied to Fault Severity Diagnosis in Spur Gearboxes
Gearboxes are widely used in industrial processes as mechanical power transmission systems. Then, gearbox failures can affect other parts of the system and produce economic loss. The early detection of the possible failure modes and their severity assessment in such devices is an important field of...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Mathematical and Computational Applications |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2297-8747/27/1/6 |
| _version_ | 1797478272484769792 |
|---|---|
| author | Mariela Cerrada Leonardo Trujillo Daniel E. Hernández Horacio A. Correa Zevallos Jean Carlo Macancela Diego Cabrera René Vinicio Sánchez |
| author_facet | Mariela Cerrada Leonardo Trujillo Daniel E. Hernández Horacio A. Correa Zevallos Jean Carlo Macancela Diego Cabrera René Vinicio Sánchez |
| author_sort | Mariela Cerrada |
| collection | DOAJ |
| description | Gearboxes are widely used in industrial processes as mechanical power transmission systems. Then, gearbox failures can affect other parts of the system and produce economic loss. The early detection of the possible failure modes and their severity assessment in such devices is an important field of research. Data-driven approaches usually require an exhaustive development of pipelines including models’ parameter optimization and feature selection. This paper takes advantage of the recent Auto Machine Learning (AutoML) tools to propose proper feature and model selection for three failure modes under different severity levels: broken tooth, pitting and crack. The performance of 64 statistical condition indicators (SCI) extracted from vibration signals under the three failure modes were analyzed by two AutoML systems, namely the H2O Driverless AI platform and TPOT, both of which include feature engineering and feature selection mechanisms. In both cases, the systems converged to different types of decision tree methods, with ensembles of XGBoost models preferred by H2O while TPOT generated different types of stacked models. The models produced by both systems achieved very high, and practically equivalent, performances on all problems. Both AutoML systems converged to pipelines that focus on very similar subsets of features across all problems, indicating that several problems in this domain can be solved by a rather small set of 10 common features, with accuracy up to 90%. This latter result is important in the research of useful feature selection for gearbox fault diagnosis. |
| first_indexed | 2024-03-09T21:30:33Z |
| format | Article |
| id | doaj.art-7c705836ba49480c97c6e49f2038258b |
| institution | Directory Open Access Journal |
| issn | 1300-686X 2297-8747 |
| language | English |
| last_indexed | 2024-03-09T21:30:33Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematical and Computational Applications |
| spelling | doaj.art-7c705836ba49480c97c6e49f2038258b2023-11-23T20:58:29ZengMDPI AGMathematical and Computational Applications1300-686X2297-87472022-01-01271610.3390/mca27010006AutoML for Feature Selection and Model Tuning Applied to Fault Severity Diagnosis in Spur GearboxesMariela Cerrada0Leonardo Trujillo1Daniel E. Hernández2Horacio A. Correa Zevallos3Jean Carlo Macancela4Diego Cabrera5René Vinicio Sánchez6GIDTEC, Universidad Politécnica Salesiana, Cuenca 010105, EcuadorTecnológico Nacional de México/IT de Tijuana, Tijuana 22414, MexicoTecnológico Nacional de México/IT de Tijuana, Tijuana 22414, MexicoTecnológico Nacional de México/IT de Tijuana, Tijuana 22414, MexicoGIDTEC, Universidad Politécnica Salesiana, Cuenca 010105, EcuadorGIDTEC, Universidad Politécnica Salesiana, Cuenca 010105, EcuadorGIDTEC, Universidad Politécnica Salesiana, Cuenca 010105, EcuadorGearboxes are widely used in industrial processes as mechanical power transmission systems. Then, gearbox failures can affect other parts of the system and produce economic loss. The early detection of the possible failure modes and their severity assessment in such devices is an important field of research. Data-driven approaches usually require an exhaustive development of pipelines including models’ parameter optimization and feature selection. This paper takes advantage of the recent Auto Machine Learning (AutoML) tools to propose proper feature and model selection for three failure modes under different severity levels: broken tooth, pitting and crack. The performance of 64 statistical condition indicators (SCI) extracted from vibration signals under the three failure modes were analyzed by two AutoML systems, namely the H2O Driverless AI platform and TPOT, both of which include feature engineering and feature selection mechanisms. In both cases, the systems converged to different types of decision tree methods, with ensembles of XGBoost models preferred by H2O while TPOT generated different types of stacked models. The models produced by both systems achieved very high, and practically equivalent, performances on all problems. Both AutoML systems converged to pipelines that focus on very similar subsets of features across all problems, indicating that several problems in this domain can be solved by a rather small set of 10 common features, with accuracy up to 90%. This latter result is important in the research of useful feature selection for gearbox fault diagnosis.https://www.mdpi.com/2297-8747/27/1/6AutoMLfeature selectionfault severity assessmentgearboxesXGBoost classifiers |
| spellingShingle | Mariela Cerrada Leonardo Trujillo Daniel E. Hernández Horacio A. Correa Zevallos Jean Carlo Macancela Diego Cabrera René Vinicio Sánchez AutoML for Feature Selection and Model Tuning Applied to Fault Severity Diagnosis in Spur Gearboxes Mathematical and Computational Applications AutoML feature selection fault severity assessment gearboxes XGBoost classifiers |
| title | AutoML for Feature Selection and Model Tuning Applied to Fault Severity Diagnosis in Spur Gearboxes |
| title_full | AutoML for Feature Selection and Model Tuning Applied to Fault Severity Diagnosis in Spur Gearboxes |
| title_fullStr | AutoML for Feature Selection and Model Tuning Applied to Fault Severity Diagnosis in Spur Gearboxes |
| title_full_unstemmed | AutoML for Feature Selection and Model Tuning Applied to Fault Severity Diagnosis in Spur Gearboxes |
| title_short | AutoML for Feature Selection and Model Tuning Applied to Fault Severity Diagnosis in Spur Gearboxes |
| title_sort | automl for feature selection and model tuning applied to fault severity diagnosis in spur gearboxes |
| topic | AutoML feature selection fault severity assessment gearboxes XGBoost classifiers |
| url | https://www.mdpi.com/2297-8747/27/1/6 |
| work_keys_str_mv | AT marielacerrada automlforfeatureselectionandmodeltuningappliedtofaultseveritydiagnosisinspurgearboxes AT leonardotrujillo automlforfeatureselectionandmodeltuningappliedtofaultseveritydiagnosisinspurgearboxes AT danielehernandez automlforfeatureselectionandmodeltuningappliedtofaultseveritydiagnosisinspurgearboxes AT horacioacorreazevallos automlforfeatureselectionandmodeltuningappliedtofaultseveritydiagnosisinspurgearboxes AT jeancarlomacancela automlforfeatureselectionandmodeltuningappliedtofaultseveritydiagnosisinspurgearboxes AT diegocabrera automlforfeatureselectionandmodeltuningappliedtofaultseveritydiagnosisinspurgearboxes AT reneviniciosanchez automlforfeatureselectionandmodeltuningappliedtofaultseveritydiagnosisinspurgearboxes |