New correlation features for dissolved gas analysis based transformer fault diagnosis based on the maximal information coefficient
Abstract Online monitoring of gases dissolved in transformer oil is widely applied. Improving the performance of dissolved gas analysis (DGA)‐based fault diagnosis methods by exploring new features of time‐series data has become an appealing topic. In this study, a new type of correlation features b...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-04-01
|
| Series: | High Voltage |
| Online Access: | https://doi.org/10.1049/hve2.12136 |
| _version_ | 1811320942348992512 |
|---|---|
| author | Yongliang Liang Zhongyi Zhang Ke‐Jun Li Yu‐Chuan Li |
| author_facet | Yongliang Liang Zhongyi Zhang Ke‐Jun Li Yu‐Chuan Li |
| author_sort | Yongliang Liang |
| collection | DOAJ |
| description | Abstract Online monitoring of gases dissolved in transformer oil is widely applied. Improving the performance of dissolved gas analysis (DGA)‐based fault diagnosis methods by exploring new features of time‐series data has become an appealing topic. In this study, a new type of correlation features between characteristic gases was extracted from time‐series data based on the maximal information coefficient (MIC), and a fuzzy inference system was established. After the introduction of the principle of the MIC and a method for calculating the MIC‐based correlation features, the dominant symptom features that can be used to classify fault types were extracted through the receiver operating characteristic curve. Then, fuzzy rules were learnt, and a fuzzy inference system was designed. In addition, to improve the feasibility of the method, the Newton interpolation method was used for adaptation to the existing sampling cycle. The diagnostic results of the test data show that the proposed method has excellent performance and outperforms some prevailing traditional rule‐based methods as well as some artificial intelligent methods. The results also show that by exploring new correlation features from time‐series data based on the MIC, the performance of DGA‐based methods can be improved. |
| first_indexed | 2024-04-13T13:08:15Z |
| format | Article |
| id | doaj.art-4b584815c99e400380dcaf5191b8e679 |
| institution | Directory Open Access Journal |
| issn | 2397-7264 |
| language | English |
| last_indexed | 2024-04-13T13:08:15Z |
| publishDate | 2022-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | High Voltage |
| spelling | doaj.art-4b584815c99e400380dcaf5191b8e6792022-12-22T02:45:42ZengWileyHigh Voltage2397-72642022-04-017230231310.1049/hve2.12136New correlation features for dissolved gas analysis based transformer fault diagnosis based on the maximal information coefficientYongliang Liang0Zhongyi Zhang1Ke‐Jun Li2Yu‐Chuan Li3School of Electrical Engineering Shandong University Jinan ChinaSchool of Electrical Engineering Shandong University Jinan ChinaSchool of Electrical Engineering Shandong University Jinan ChinaDepartment of Electrical & Electronic Engineering Imperial College London South Kensington Campus London UKAbstract Online monitoring of gases dissolved in transformer oil is widely applied. Improving the performance of dissolved gas analysis (DGA)‐based fault diagnosis methods by exploring new features of time‐series data has become an appealing topic. In this study, a new type of correlation features between characteristic gases was extracted from time‐series data based on the maximal information coefficient (MIC), and a fuzzy inference system was established. After the introduction of the principle of the MIC and a method for calculating the MIC‐based correlation features, the dominant symptom features that can be used to classify fault types were extracted through the receiver operating characteristic curve. Then, fuzzy rules were learnt, and a fuzzy inference system was designed. In addition, to improve the feasibility of the method, the Newton interpolation method was used for adaptation to the existing sampling cycle. The diagnostic results of the test data show that the proposed method has excellent performance and outperforms some prevailing traditional rule‐based methods as well as some artificial intelligent methods. The results also show that by exploring new correlation features from time‐series data based on the MIC, the performance of DGA‐based methods can be improved.https://doi.org/10.1049/hve2.12136 |
| spellingShingle | Yongliang Liang Zhongyi Zhang Ke‐Jun Li Yu‐Chuan Li New correlation features for dissolved gas analysis based transformer fault diagnosis based on the maximal information coefficient High Voltage |
| title | New correlation features for dissolved gas analysis based transformer fault diagnosis based on the maximal information coefficient |
| title_full | New correlation features for dissolved gas analysis based transformer fault diagnosis based on the maximal information coefficient |
| title_fullStr | New correlation features for dissolved gas analysis based transformer fault diagnosis based on the maximal information coefficient |
| title_full_unstemmed | New correlation features for dissolved gas analysis based transformer fault diagnosis based on the maximal information coefficient |
| title_short | New correlation features for dissolved gas analysis based transformer fault diagnosis based on the maximal information coefficient |
| title_sort | new correlation features for dissolved gas analysis based transformer fault diagnosis based on the maximal information coefficient |
| url | https://doi.org/10.1049/hve2.12136 |
| work_keys_str_mv | AT yongliangliang newcorrelationfeaturesfordissolvedgasanalysisbasedtransformerfaultdiagnosisbasedonthemaximalinformationcoefficient AT zhongyizhang newcorrelationfeaturesfordissolvedgasanalysisbasedtransformerfaultdiagnosisbasedonthemaximalinformationcoefficient AT kejunli newcorrelationfeaturesfordissolvedgasanalysisbasedtransformerfaultdiagnosisbasedonthemaximalinformationcoefficient AT yuchuanli newcorrelationfeaturesfordissolvedgasanalysisbasedtransformerfaultdiagnosisbasedonthemaximalinformationcoefficient |