Prediction accuracy improvement of pressure pulsation signals of reversible pump‐turbine: A LSTM and VMD‐based optimization approach
Abstract The reversible pump‐turbine plays an important role in hydropower stations, but pressure pulsation during their operation affects their performance and lifespan. Accurate prediction of pressure pulsation signals can provide an important basis for energy planning and stable operation of pump...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2024-01-01
|
Series: | Energy Science & Engineering |
Subjects: | |
Online Access: | https://doi.org/10.1002/ese3.1620 |
_version_ | 1797362147484762112 |
---|---|
author | Mingkun Fang Fangfang Zhang Zhong Cao Ran Tao Wei Xiao Di Zhu Zhonghua Gui Ruofu Xiao |
author_facet | Mingkun Fang Fangfang Zhang Zhong Cao Ran Tao Wei Xiao Di Zhu Zhonghua Gui Ruofu Xiao |
author_sort | Mingkun Fang |
collection | DOAJ |
description | Abstract The reversible pump‐turbine plays an important role in hydropower stations, but pressure pulsation during their operation affects their performance and lifespan. Accurate prediction of pressure pulsation signals can provide an important basis for energy planning and stable operation of pumped storage units, thereby promoting sustainable development of the environment. This study introduces an optimization method that combines long short‐term memory (LSTM) and variable mode decomposition (VMD) to enhance the prediction accuracy of pressure pulsation signals. First, by decomposing the pressure pulsation signal into multiple relatively stable subsequence components using VMD, the characteristics of the original signal become more distinct. Subsequently, individual LSTM‐based time series prediction models were constructed for each modal function, and the hyperparameters related to subsequence were optimized using the sparrow search algorithm. To validate the efficacy of the proposed approach, this paper conducted experiments using pressure pulsation signals of a pump‐turbine obtained through numerical simulation. The experimental data was divided into training and testing sets, with the former used to train the LSTM model and the latter used for validation. The experimental results show that the optimized VMD with an optimized LSTM method can effectively improve the prediction accuracy of pressure pulsation signals in reversible pump‐turbine. |
first_indexed | 2024-03-08T16:04:12Z |
format | Article |
id | doaj.art-2551adfddd2d4960998166d5f0f42b81 |
institution | Directory Open Access Journal |
issn | 2050-0505 |
language | English |
last_indexed | 2024-03-08T16:04:12Z |
publishDate | 2024-01-01 |
publisher | Wiley |
record_format | Article |
series | Energy Science & Engineering |
spelling | doaj.art-2551adfddd2d4960998166d5f0f42b812024-01-08T07:19:29ZengWileyEnergy Science & Engineering2050-05052024-01-0112110211610.1002/ese3.1620Prediction accuracy improvement of pressure pulsation signals of reversible pump‐turbine: A LSTM and VMD‐based optimization approachMingkun Fang0Fangfang Zhang1Zhong Cao2Ran Tao3Wei Xiao4Di Zhu5Zhonghua Gui6Ruofu Xiao7College of Water Resources and Civil Engineering China Agricultural University Beijing ChinaCollege of Water Resources and Civil Engineering China Agricultural University Beijing ChinaOperation Management Department CTG (Hainan) Green Development Investment Co., Ltd Hainan ChinaCollege of Water Resources and Civil Engineering China Agricultural University Beijing ChinaPumped Storage Technology and Economy Research Institute State Grid Xinyuan Company Ltd. Beijing ChinaCollege of Engineering China Agricultural University Beijing ChinaPumped Storage Technology and Economy Research Institute State Grid Xinyuan Company Ltd. Beijing ChinaCollege of Water Resources and Civil Engineering China Agricultural University Beijing ChinaAbstract The reversible pump‐turbine plays an important role in hydropower stations, but pressure pulsation during their operation affects their performance and lifespan. Accurate prediction of pressure pulsation signals can provide an important basis for energy planning and stable operation of pumped storage units, thereby promoting sustainable development of the environment. This study introduces an optimization method that combines long short‐term memory (LSTM) and variable mode decomposition (VMD) to enhance the prediction accuracy of pressure pulsation signals. First, by decomposing the pressure pulsation signal into multiple relatively stable subsequence components using VMD, the characteristics of the original signal become more distinct. Subsequently, individual LSTM‐based time series prediction models were constructed for each modal function, and the hyperparameters related to subsequence were optimized using the sparrow search algorithm. To validate the efficacy of the proposed approach, this paper conducted experiments using pressure pulsation signals of a pump‐turbine obtained through numerical simulation. The experimental data was divided into training and testing sets, with the former used to train the LSTM model and the latter used for validation. The experimental results show that the optimized VMD with an optimized LSTM method can effectively improve the prediction accuracy of pressure pulsation signals in reversible pump‐turbine.https://doi.org/10.1002/ese3.1620machine learningoptimization algorithmpump turbinesignal decompositionvariational mode decomposition |
spellingShingle | Mingkun Fang Fangfang Zhang Zhong Cao Ran Tao Wei Xiao Di Zhu Zhonghua Gui Ruofu Xiao Prediction accuracy improvement of pressure pulsation signals of reversible pump‐turbine: A LSTM and VMD‐based optimization approach Energy Science & Engineering machine learning optimization algorithm pump turbine signal decomposition variational mode decomposition |
title | Prediction accuracy improvement of pressure pulsation signals of reversible pump‐turbine: A LSTM and VMD‐based optimization approach |
title_full | Prediction accuracy improvement of pressure pulsation signals of reversible pump‐turbine: A LSTM and VMD‐based optimization approach |
title_fullStr | Prediction accuracy improvement of pressure pulsation signals of reversible pump‐turbine: A LSTM and VMD‐based optimization approach |
title_full_unstemmed | Prediction accuracy improvement of pressure pulsation signals of reversible pump‐turbine: A LSTM and VMD‐based optimization approach |
title_short | Prediction accuracy improvement of pressure pulsation signals of reversible pump‐turbine: A LSTM and VMD‐based optimization approach |
title_sort | prediction accuracy improvement of pressure pulsation signals of reversible pump turbine a lstm and vmd based optimization approach |
topic | machine learning optimization algorithm pump turbine signal decomposition variational mode decomposition |
url | https://doi.org/10.1002/ese3.1620 |
work_keys_str_mv | AT mingkunfang predictionaccuracyimprovementofpressurepulsationsignalsofreversiblepumpturbinealstmandvmdbasedoptimizationapproach AT fangfangzhang predictionaccuracyimprovementofpressurepulsationsignalsofreversiblepumpturbinealstmandvmdbasedoptimizationapproach AT zhongcao predictionaccuracyimprovementofpressurepulsationsignalsofreversiblepumpturbinealstmandvmdbasedoptimizationapproach AT rantao predictionaccuracyimprovementofpressurepulsationsignalsofreversiblepumpturbinealstmandvmdbasedoptimizationapproach AT weixiao predictionaccuracyimprovementofpressurepulsationsignalsofreversiblepumpturbinealstmandvmdbasedoptimizationapproach AT dizhu predictionaccuracyimprovementofpressurepulsationsignalsofreversiblepumpturbinealstmandvmdbasedoptimizationapproach AT zhonghuagui predictionaccuracyimprovementofpressurepulsationsignalsofreversiblepumpturbinealstmandvmdbasedoptimizationapproach AT ruofuxiao predictionaccuracyimprovementofpressurepulsationsignalsofreversiblepumpturbinealstmandvmdbasedoptimizationapproach |