Power transformer oil temperature prediction based on empirical mode decomposition-bidirectional long short-term memory
Power transformers are crucial components of power transmission and transformation networks. Their operational status has a direct impact on the reliability of power supply systems. As such, the security and stability of power systems depend heavily on the state of transformers within them. The oil...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2023-06-01
|
| Series: | Journal of Algorithms & Computational Technology |
| Online Access: | https://doi.org/10.1177/17483026231176196 |
| _version_ | 1797804657255383040 |
|---|---|
| author | Haomin Chen Lingwen Meng Yu Xi Changbao Xu Yu Wang Mingyong Xin Guangqin Chen Yumin Chen |
| author_facet | Haomin Chen Lingwen Meng Yu Xi Changbao Xu Yu Wang Mingyong Xin Guangqin Chen Yumin Chen |
| author_sort | Haomin Chen |
| collection | DOAJ |
| description | Power transformers are crucial components of power transmission and transformation networks. Their operational status has a direct impact on the reliability of power supply systems. As such, the security and stability of power systems depend heavily on the state of transformers within them. The oil temperature of a transformer is a critical indicator of its working condition. Accurately and rapidly predicting transformer oil temperature is therefore of significant practical importance for ensuring the safe and effective operation of power systems. To address this prediction problem, this article proposes a transformer oil temperature prediction method based on empirical mode decomposition-bidirectional long short-term memory (EMD-BiLSTM). The time series of oil temperature is first cleaned before being processed. Next, the EMD algorithm is used to decompose the time series into relatively stable components. The BiLSTM neural network is then utilized to predict the complex nonlinear long-term series. The proposed method is evaluated using the open data set Electricity Transformer Temperature (ETT)-small. Experimental results show that the EMD-BiLSTM model outperforms traditional LSTM, BiLSTM, EMD-BP, and Wavelet Transform-Bidirectional Long Short-Term Memory (WT-BiLSTM) methods, demonstrating that it is an effective and accurate prediction method for transformer oil temperature. |
| first_indexed | 2024-03-13T05:40:31Z |
| format | Article |
| id | doaj.art-481c6f85b9d045aabb62846c92e411ad |
| institution | Directory Open Access Journal |
| issn | 1748-3026 |
| language | English |
| last_indexed | 2024-03-13T05:40:31Z |
| publishDate | 2023-06-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Journal of Algorithms & Computational Technology |
| spelling | doaj.art-481c6f85b9d045aabb62846c92e411ad2023-06-14T01:03:19ZengSAGE PublishingJournal of Algorithms & Computational Technology1748-30262023-06-011710.1177/17483026231176196Power transformer oil temperature prediction based on empirical mode decomposition-bidirectional long short-term memoryHaomin Chen0Lingwen Meng1Yu Xi2Changbao Xu3Yu Wang4Mingyong Xin5Guangqin Chen6Yumin Chen7 Digital Grid Research Institute, China Southern Power Grid, Guangzhou, Guangdong, China Institute of Electric Power Research of Guizhou Power Grid, Guiyang, Guizhou, China Digital Grid Research Institute, China Southern Power Grid, Guangzhou, Guangdong, China Institute of Electric Power Research of Guizhou Power Grid, Guiyang, Guizhou, China Institute of Electric Power Research of Guizhou Power Grid, Guiyang, Guizhou, China Institute of Electric Power Research of Guizhou Power Grid, Guiyang, Guizhou, China Digital Grid Research Institute, China Southern Power Grid, Guangzhou, Guangdong, China Digital Grid Research Institute, China Southern Power Grid, Guangzhou, Guangdong, ChinaPower transformers are crucial components of power transmission and transformation networks. Their operational status has a direct impact on the reliability of power supply systems. As such, the security and stability of power systems depend heavily on the state of transformers within them. The oil temperature of a transformer is a critical indicator of its working condition. Accurately and rapidly predicting transformer oil temperature is therefore of significant practical importance for ensuring the safe and effective operation of power systems. To address this prediction problem, this article proposes a transformer oil temperature prediction method based on empirical mode decomposition-bidirectional long short-term memory (EMD-BiLSTM). The time series of oil temperature is first cleaned before being processed. Next, the EMD algorithm is used to decompose the time series into relatively stable components. The BiLSTM neural network is then utilized to predict the complex nonlinear long-term series. The proposed method is evaluated using the open data set Electricity Transformer Temperature (ETT)-small. Experimental results show that the EMD-BiLSTM model outperforms traditional LSTM, BiLSTM, EMD-BP, and Wavelet Transform-Bidirectional Long Short-Term Memory (WT-BiLSTM) methods, demonstrating that it is an effective and accurate prediction method for transformer oil temperature.https://doi.org/10.1177/17483026231176196 |
| spellingShingle | Haomin Chen Lingwen Meng Yu Xi Changbao Xu Yu Wang Mingyong Xin Guangqin Chen Yumin Chen Power transformer oil temperature prediction based on empirical mode decomposition-bidirectional long short-term memory Journal of Algorithms & Computational Technology |
| title | Power transformer oil temperature prediction based on empirical mode decomposition-bidirectional long
short-term memory |
| title_full | Power transformer oil temperature prediction based on empirical mode decomposition-bidirectional long
short-term memory |
| title_fullStr | Power transformer oil temperature prediction based on empirical mode decomposition-bidirectional long
short-term memory |
| title_full_unstemmed | Power transformer oil temperature prediction based on empirical mode decomposition-bidirectional long
short-term memory |
| title_short | Power transformer oil temperature prediction based on empirical mode decomposition-bidirectional long
short-term memory |
| title_sort | power transformer oil temperature prediction based on empirical mode decomposition bidirectional long short term memory |
| url | https://doi.org/10.1177/17483026231176196 |
| work_keys_str_mv | AT haominchen powertransformeroiltemperaturepredictionbasedonempiricalmodedecompositionbidirectionallongshorttermmemory AT lingwenmeng powertransformeroiltemperaturepredictionbasedonempiricalmodedecompositionbidirectionallongshorttermmemory AT yuxi powertransformeroiltemperaturepredictionbasedonempiricalmodedecompositionbidirectionallongshorttermmemory AT changbaoxu powertransformeroiltemperaturepredictionbasedonempiricalmodedecompositionbidirectionallongshorttermmemory AT yuwang powertransformeroiltemperaturepredictionbasedonempiricalmodedecompositionbidirectionallongshorttermmemory AT mingyongxin powertransformeroiltemperaturepredictionbasedonempiricalmodedecompositionbidirectionallongshorttermmemory AT guangqinchen powertransformeroiltemperaturepredictionbasedonempiricalmodedecompositionbidirectionallongshorttermmemory AT yuminchen powertransformeroiltemperaturepredictionbasedonempiricalmodedecompositionbidirectionallongshorttermmemory |