Institutional Repository of Vilnius University
Hipoidinės pavaros gedimų šablono atpažinimas naudojant autoenkoderį ir giliuosius neuroninius tinklus /
Abstract
dc:descriptionThis bachelor thesis investigates the fault pattern recognition of hypoid gears using autoencoders and deep neural networks. The study focuses on developing an efficient classification model to identify and categorize the fault patterns of hypoid gear conditions based on vibration signal data. Various data transformations and augmentations were applied to enhance the model's performance. The effectiveness of the proposed autoencoder-based models was evaluated against traditional classification models. The results showed that the autoencoder-based models achieved an overall accuracy of 83% using FFT data and 81% using Mel spectrogram data, compared to the 81% accuracy of the CNN-2D model. The autoencoder-based models performed better in classifying fault levels 3 and 4 but worse in classifying fault level 6. The study also explored the performance of these models when trained with a limited amount of labeled data, demonstrating an 11% higher accuracy of the autoencoder-based model compared to the CNN model when only 6.25% of the data was labeled.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Čibiras, Vaidas,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD210645404&prefLang=en_US