Severity of Failures in Spur Gearboxes by Vibration Signal Analysis
[EN] Gearboxes are a fundamental component in the operation of rotating machinery due to their efficiency in power transmission. Therefore, determining the severity level of a failure at an early stage not only avoids machine downtime but also unexpected maintenance activities. This chapter presents...
| Authors: | , , |
|---|---|
| Format: | book part |
| Publication Date: | 2025 |
| Country: | España |
| Institution: | Universitat Politècnica de València (UPV) |
| Repository: | RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia |
| Language: | English |
| OAI Identifier: | oai:riunet.upv.es:10251/231389 |
| Online Access: | https://riunet.upv.es/handle/10251/231389 |
| Access Level: | Open access |
| Keyword: | Fault severity Machine learning Principal component analysis Spur gearboxes Vibration signal Condition indicators Feature extraction 09.- Desarrollar infraestructuras resilientes, promover la industrialización inclusiva y sostenible, y fomentar la innovación |
| Summary: | [EN] Gearboxes are a fundamental component in the operation of rotating machinery due to their efficiency in power transmission. Therefore, determining the severity level of a failure at an early stage not only avoids machine downtime but also unexpected maintenance activities. This chapter presents a methodology to determine the severity level of different failures in spur gearboxes by analysing the vibration signal, for which a data mining process is carried out using artificial intelligence (AI) techniques. The condition indicators (CIs) in the time, frequency, and time-frequency domains extract the vibration signal features. The CIs from all three domains are merged into a single database (DB), the dimensionality is reduced through a principal component analysis (PCA), and the main factors are used to determine the failure severity level through random forest (RF) and k-nearest neighbour (KNN) classification models, and factorial analysis of variance (ANOVA) tests are performed. Excellent results were obtained in classification accuracy and the area under the curve (AUC) of the receiver operating characteristic (ROC). |
|---|