Bibliographic Details
| Title: |
Pipeline and Rotating Pump Condition Monitoring Based on Sound Vibration Feature-Level Fusion |
| Authors: |
Yu Wan, Shaochen Lin, Yan Gao |
| Source: |
Machines, Vol 12, Iss 12, p 921 (2024) |
| Publisher Information: |
MDPI AG, 2024. |
| Publication Year: |
2024 |
| Collection: |
LCC:Mechanical engineering and machinery |
| Subject Terms: |
sound vibration feature, feature-level fusion, rotating pump, condition monitoring, abnormal sound, Mechanical engineering and machinery, TJ1-1570 |
| More Details: |
The rotating pump of pipelines are susceptible to damage based on extended operations in a complex environment of high temperature and high pressure, which leads to abnormal vibrations and noises. Currently, the method for detecting the conditions of pipelines and rotating pumps primarily involves identifying their abnormal sounds and vibrations. Due to complex background noise, the performance of condition monitoring is unsatisfactory. To overcome this issue, a pipeline and rotating pump condition monitoring method is proposed by extracting and fusing sound and vibration features in different ways. Firstly, a hand-crafted feature set is established from two aspects of sound and vibration. Moreover, a convolutional neural network (CNN)-derived feature set is established based on a one-dimensional CNN (1D CNN). For the hand-crafted and CNN-derived feature sets, a feature selection method is presented for significant features by ranking features according to their importance, which is calculated by ReliefF and the random forest score. Finally, pipeline and rotating pump condition monitoring is applied by fusing the significant sound and vibration features at the feature level. According to the sound and vibration signals obtained from the experimental platform, the proposed method was evaluated, showing an average accuracy of 93.27% for different conditions. The effectiveness and superiority of the proposed method are manifested through comparison and ablation experiments. |
| Document Type: |
article |
| File Description: |
electronic resource |
| Language: |
English |
| ISSN: |
2075-1702 |
| Relation: |
https://www.mdpi.com/2075-1702/12/12/921; https://doaj.org/toc/2075-1702 |
| DOI: |
10.3390/machines12120921 |
| Access URL: |
https://doaj.org/article/0d7900477fa54195bf515c335128c253 |
| Accession Number: |
edsdoj.0d7900477fa54195bf515c335128c253 |
| Database: |
Directory of Open Access Journals |
