Integrating empirical mode decomposition and convolutional neural network for efficient fault diagnosis in metallurgical machinery
The paper introduces an innovative framework for rotating machinery fault recognition by combining Empirical Mode Decomposition (EMD) and Convolutional Neural Network (CNN). This novel approach integrates feature extraction and selection, utilizing deep learning for precise classification of transmi...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Croatian Metallurgical Society
2024-01-01
|
| Series: | Metalurgija |
| Subjects: | |
| Online Access: | https://hrcak.srce.hr/file/456135 |
| Summary: | The paper introduces an innovative framework for rotating machinery fault recognition by combining Empirical Mode Decomposition (EMD) and Convolutional Neural Network (CNN). This novel approach integrates feature extraction and selection, utilizing deep learning for precise classification of transmission components faults. Our method achieves an impressive accuracy of 98,97 %. This robust technology significantly enhances the detection and diagnosis of transmission faults in metallurgical plant, providing an efficient solution for intelligent manufacturing applications. |
|---|---|
| ISSN: | 0543-5846 1334-2576 |