Data-driven methods for power converter fault diagnosis
This Final Year Project (FYP) report investigates the efficacy of data-driven methods for power converter fault analysis, employing three distinct algorithms: Extreme Learning Machine (ELM), Random Vector Functional Link (RVFL), and Random Forest. The study aims to assess the performance of these al...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/176909 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | This Final Year Project (FYP) report investigates the efficacy of data-driven methods for power converter fault analysis, employing three distinct algorithms: Extreme Learning Machine (ELM), Random Vector Functional Link (RVFL), and Random Forest. The study aims to assess the performance of these algorithms in detecting faults under varying noise conditions. The experimental setup involves testing the algorithms against different noise samples to simulate real-world scenarios. Through comprehensive analysis and evaluation, it is concluded that the ELM algorithm exhibits superior robustness in handling noisy data compared to RVFL and Random Forest. The findings of this study contribute to the advancement of fault analysis techniques in power converters and highlight the effectiveness of ELM as a reliable method for fault detection in noisy environments. |
|---|