Evaluation method for moisture content of oil‐paper insulation based on segmented frequency domain spectroscopy: From curve fitting to machine learning
Abstract In recent years, frequency domain spectroscopy (FDS) is often used to evaluate oil paper insulation state in power transformer bushing. But it is still very difficult to evaluate the moisture content accurately and quickly. In order to solve this problem, this paper proposes an intelligent...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-08-01
|
| Series: | IET Science, Measurement & Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/smt2.12052 |
| _version_ | 1798035588825219072 |
|---|---|
| author | Huanmin Yao Haibao Mu Ning Ding Daning Zhang ZhaoJie Liang Jie Tian Guanjun Zhang |
| author_facet | Huanmin Yao Haibao Mu Ning Ding Daning Zhang ZhaoJie Liang Jie Tian Guanjun Zhang |
| author_sort | Huanmin Yao |
| collection | DOAJ |
| description | Abstract In recent years, frequency domain spectroscopy (FDS) is often used to evaluate oil paper insulation state in power transformer bushing. But it is still very difficult to evaluate the moisture content accurately and quickly. In order to solve this problem, this paper proposes an intelligent algorithm based on random forest regression (RFR) to construct an efficient evaluation method through segmented FDS curves. Furthermore, the characteristics of FDS curves were studied and the intelligent method was compared with support vector regression (SVR) and deep neural networks (DNN). The results show that the dielectric loss, the real part and imaginary part of complex capacitance all move upward with the moisture increasing, so they can be used as the input feature of the evaluation model; The moisture content evaluation accuracy of the RFR model in the whole frequency band is higher than that of SVR and DNN models; With the increase of lower cut off frequency (FDS test stop frequency), the FDS test time is greatly shortened, and the accuracy of the RFR model can still meet the evaluation requirements. Therefore, the data in a compromise frequency band can be used to evaluate the moisture content of oil paper insulation accurately and quickly. |
| first_indexed | 2024-04-11T20:59:12Z |
| format | Article |
| id | doaj.art-772aa5599e3f4b39a57f14fbe2e4467c |
| institution | Directory Open Access Journal |
| issn | 1751-8822 1751-8830 |
| language | English |
| last_indexed | 2024-04-11T20:59:12Z |
| publishDate | 2021-08-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Science, Measurement & Technology |
| spelling | doaj.art-772aa5599e3f4b39a57f14fbe2e4467c2022-12-22T04:03:33ZengWileyIET Science, Measurement & Technology1751-88221751-88302021-08-0115651752610.1049/smt2.12052Evaluation method for moisture content of oil‐paper insulation based on segmented frequency domain spectroscopy: From curve fitting to machine learningHuanmin Yao0Haibao Mu1Ning Ding2Daning Zhang3ZhaoJie Liang4Jie Tian5Guanjun Zhang6State Key Laboratory of Electrical Insulation and Power Equipment Xi'an Jiaotong University 28 Xianning West Road Xi'an Shaanxi 710049 People's Republic of ChinaState Key Laboratory of Electrical Insulation and Power Equipment Xi'an Jiaotong University 28 Xianning West Road Xi'an Shaanxi 710049 People's Republic of ChinaState Key Laboratory of Electrical Insulation and Power Equipment Xi'an Jiaotong University 28 Xianning West Road Xi'an Shaanxi 710049 People's Republic of ChinaState Key Laboratory of Electrical Insulation and Power Equipment Xi'an Jiaotong University 28 Xianning West Road Xi'an Shaanxi 710049 People's Republic of ChinaShenzhen Power Supply Co., Ltd. Shenzhen Guangdong People's Republic of ChinaShenzhen Power Supply Co., Ltd. Shenzhen Guangdong People's Republic of ChinaState Key Laboratory of Electrical Insulation and Power Equipment Xi'an Jiaotong University 28 Xianning West Road Xi'an Shaanxi 710049 People's Republic of ChinaAbstract In recent years, frequency domain spectroscopy (FDS) is often used to evaluate oil paper insulation state in power transformer bushing. But it is still very difficult to evaluate the moisture content accurately and quickly. In order to solve this problem, this paper proposes an intelligent algorithm based on random forest regression (RFR) to construct an efficient evaluation method through segmented FDS curves. Furthermore, the characteristics of FDS curves were studied and the intelligent method was compared with support vector regression (SVR) and deep neural networks (DNN). The results show that the dielectric loss, the real part and imaginary part of complex capacitance all move upward with the moisture increasing, so they can be used as the input feature of the evaluation model; The moisture content evaluation accuracy of the RFR model in the whole frequency band is higher than that of SVR and DNN models; With the increase of lower cut off frequency (FDS test stop frequency), the FDS test time is greatly shortened, and the accuracy of the RFR model can still meet the evaluation requirements. Therefore, the data in a compromise frequency band can be used to evaluate the moisture content of oil paper insulation accurately and quickly.https://doi.org/10.1049/smt2.12052Organic insulationInterpolation and function approximation (numerical analysis)Interpolation and function approximation (numerical analysis)Power engineering computingTransformers and reactorsRegression analysis |
| spellingShingle | Huanmin Yao Haibao Mu Ning Ding Daning Zhang ZhaoJie Liang Jie Tian Guanjun Zhang Evaluation method for moisture content of oil‐paper insulation based on segmented frequency domain spectroscopy: From curve fitting to machine learning IET Science, Measurement & Technology Organic insulation Interpolation and function approximation (numerical analysis) Interpolation and function approximation (numerical analysis) Power engineering computing Transformers and reactors Regression analysis |
| title | Evaluation method for moisture content of oil‐paper insulation based on segmented frequency domain spectroscopy: From curve fitting to machine learning |
| title_full | Evaluation method for moisture content of oil‐paper insulation based on segmented frequency domain spectroscopy: From curve fitting to machine learning |
| title_fullStr | Evaluation method for moisture content of oil‐paper insulation based on segmented frequency domain spectroscopy: From curve fitting to machine learning |
| title_full_unstemmed | Evaluation method for moisture content of oil‐paper insulation based on segmented frequency domain spectroscopy: From curve fitting to machine learning |
| title_short | Evaluation method for moisture content of oil‐paper insulation based on segmented frequency domain spectroscopy: From curve fitting to machine learning |
| title_sort | evaluation method for moisture content of oil paper insulation based on segmented frequency domain spectroscopy from curve fitting to machine learning |
| topic | Organic insulation Interpolation and function approximation (numerical analysis) Interpolation and function approximation (numerical analysis) Power engineering computing Transformers and reactors Regression analysis |
| url | https://doi.org/10.1049/smt2.12052 |
| work_keys_str_mv | AT huanminyao evaluationmethodformoisturecontentofoilpaperinsulationbasedonsegmentedfrequencydomainspectroscopyfromcurvefittingtomachinelearning AT haibaomu evaluationmethodformoisturecontentofoilpaperinsulationbasedonsegmentedfrequencydomainspectroscopyfromcurvefittingtomachinelearning AT ningding evaluationmethodformoisturecontentofoilpaperinsulationbasedonsegmentedfrequencydomainspectroscopyfromcurvefittingtomachinelearning AT daningzhang evaluationmethodformoisturecontentofoilpaperinsulationbasedonsegmentedfrequencydomainspectroscopyfromcurvefittingtomachinelearning AT zhaojieliang evaluationmethodformoisturecontentofoilpaperinsulationbasedonsegmentedfrequencydomainspectroscopyfromcurvefittingtomachinelearning AT jietian evaluationmethodformoisturecontentofoilpaperinsulationbasedonsegmentedfrequencydomainspectroscopyfromcurvefittingtomachinelearning AT guanjunzhang evaluationmethodformoisturecontentofoilpaperinsulationbasedonsegmentedfrequencydomainspectroscopyfromcurvefittingtomachinelearning |