University of Twente Student Theses
Interpreting Fault Prediction in Induction Motors Using Explainable Artificial Intelligence
Akın, Serkan (2024) Interpreting Fault Prediction in Induction Motors Using Explainable Artificial Intelligence.
|
PDF
1MB |
| Abstract: | This research explores the effectiveness of machine learning (ML) and deep learning (DL) models in fault prediction of induction motors, focusing on fault detection through the analyzes of sensor data. The study examines the performance of gradient boosting and feedforward neural networks. Both models are evaluated on their ability to classify the health status of induction motors, using data provided by Fraunhofer Innovation Platform at the University of Twente. Key to this research is the integration of Explainable Artificial Intelligence (XAI) methods, specifically SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations), to get insights on the decision-making process of the models. These XAI techniques reveal how specific features influence model predictions, making them transperent for the end-user in industrial settings. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Computer Science BSc (56964) |
| Link to this item: | https://purl.utwente.nl/essays/101027 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page