|
| A Fault Diagnosis Strategy Based on Multi-level Feature Extraction for Grid-Connected Inverter |
| 投稿时间：2021-01-22 修订日期：2021-02-26 |
| 查看/发表评论 下载PDF阅读器 |
| DOI： |
| Keywords:cascaded H-bridge multilevel inverters, grid-connected, feature extraction, faults diagnosis. |
| Fund Project:The National Natural Science Foundation of China (General Program, Key Program, Major Research Plan) |
| Author | Institution | Email |
| GENG Junchao |
Shanghai Maritime University |
gjc0927@163.com |
| WANG Tianzhen |
Shanghai Maritime University |
tzwang@shmtu.edu.cn;wtz0@sina.com |
| HAN Jingang |
|
jghan@shmtu.edu.cn |
| CHEN Guodong |
|
chengd@shanghai-electric.com |
| TANG Tianhao |
|
thtang@shmtu.edu.cn |
|
| 摘要点击次数: 54 |
| 全文下载次数: 0 |
| Abstract: |
| Due to reduced harmonic content, reduced switching losses, and easy modularization, the cascaded H-bridge multilevel inverter is widely used in renewable energy grid-connected system. As the number of levels increases, the number of power switches (IGBTs) also increases, and the corresponding fault probability and fault types are also increasing. Under multi-fault conditions, the traditional fault feature extraction method cannot effectively extract the key features of the fault, resulting in a decrease in the accuracy. To solve this problem, a fault diagnosis strategy based on multi-level feature extraction is proposed. Firstly, PCA is used to preliminarily extract the fault features, then the key fault features are extracted based on the Euclidean distance threshold, and finally the ELM classifier is used to complete the fault diagnosis. Experimental results show that the proposed method has fewer input feature vector dimensions and higher fault diagnosis accuracy. |
| 关闭 |
|
|
|
