A Symbol Conditional Entropy-Based Method for Incipient Cavitation Prediction in Hydraulic Turbines

The accurate prediction of incipient cavitation is of great significance for ensuring the stable operation of hydraulic turbines. Hydroacoustic signals contain essential information about the turbine’s operating state. Considering that traditional entropy methods are easily affected by environmental...

Full description

Saved in:
Bibliographic Details
Main Authors: Mengge Lv, Feng Li, Yi Wang, Tianzhen Wang, Demba Diallo, Xiaohang Wang
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Journal of Marine Science and Engineering
Subjects:
Online Access:https://www.mdpi.com/2077-1312/13/3/538
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850203945140486144
author Mengge Lv
Feng Li
Yi Wang
Tianzhen Wang
Demba Diallo
Xiaohang Wang
author_facet Mengge Lv
Feng Li
Yi Wang
Tianzhen Wang
Demba Diallo
Xiaohang Wang
author_sort Mengge Lv
collection DOAJ
description The accurate prediction of incipient cavitation is of great significance for ensuring the stable operation of hydraulic turbines. Hydroacoustic signals contain essential information about the turbine’s operating state. Considering that traditional entropy methods are easily affected by environmental noise when the state pattern is chaotic, leading to the extracted cavitation features not being obvious, a Symbol Conditional Entropy (SCE) feature extraction method is proposed to classify the original variables according to different state patterns. The uncertainty is reduced, and the ability to extract fault information is improved, so more effective cavitation features can be extracted to describe the evolving trend of cavitation. The extracted cavitation features are used as indicators to predict incipient cavitation. In order to avoid missing critical information in the prediction process, an interval mean (IM) algorithm is proposed to determine the initial prediction point. The effectiveness of the proposed method is validated with hydroacoustic signals collected at the Harbin Institute of Large Electric Machinery. The root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) of incipient cavitation prediction results decreased to 0.0018, 0.0015, and 1.59%, respectively. The RMSE, MAE, and MAPE of the proposed SCE decreased by 84.62%, 85.29%, and 87% compared with the Permutation Entropy (PE) method. The comparison results with different prediction algorithms show that the proposed SCE has excellent trend prediction performance and high precision.
format Article
id doaj-art-e735454ffc2a4b0286d98be4fb7f4089
institution OA Journals
issn 2077-1312
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Journal of Marine Science and Engineering
spelling doaj-art-e735454ffc2a4b0286d98be4fb7f40892025-08-20T02:11:24ZengMDPI AGJournal of Marine Science and Engineering2077-13122025-03-0113353810.3390/jmse13030538A Symbol Conditional Entropy-Based Method for Incipient Cavitation Prediction in Hydraulic TurbinesMengge Lv0Feng Li1Yi Wang2Tianzhen Wang3Demba Diallo4Xiaohang Wang5Logistics Engineering College, Shanghai Maritime University, Pudong District, Shanghai 201306, ChinaLogistics Engineering College, Shanghai Maritime University, Pudong District, Shanghai 201306, ChinaLogistics Engineering College, Shanghai Maritime University, Pudong District, Shanghai 201306, ChinaLogistics Engineering College, Shanghai Maritime University, Pudong District, Shanghai 201306, ChinaCentraleSupelec, CNRS, Group of Electrical Engineering Paris, Université Paris Saclay, 91192 Gif-sur-Yvette, FranceHarbin Electric Machinery Company Limited, Harbin 150040, ChinaThe accurate prediction of incipient cavitation is of great significance for ensuring the stable operation of hydraulic turbines. Hydroacoustic signals contain essential information about the turbine’s operating state. Considering that traditional entropy methods are easily affected by environmental noise when the state pattern is chaotic, leading to the extracted cavitation features not being obvious, a Symbol Conditional Entropy (SCE) feature extraction method is proposed to classify the original variables according to different state patterns. The uncertainty is reduced, and the ability to extract fault information is improved, so more effective cavitation features can be extracted to describe the evolving trend of cavitation. The extracted cavitation features are used as indicators to predict incipient cavitation. In order to avoid missing critical information in the prediction process, an interval mean (IM) algorithm is proposed to determine the initial prediction point. The effectiveness of the proposed method is validated with hydroacoustic signals collected at the Harbin Institute of Large Electric Machinery. The root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) of incipient cavitation prediction results decreased to 0.0018, 0.0015, and 1.59%, respectively. The RMSE, MAE, and MAPE of the proposed SCE decreased by 84.62%, 85.29%, and 87% compared with the Permutation Entropy (PE) method. The comparison results with different prediction algorithms show that the proposed SCE has excellent trend prediction performance and high precision.https://www.mdpi.com/2077-1312/13/3/538hydroacoustic signalincipient cavitation predictionentropyinitial prediction pointhydraulic turbine
spellingShingle Mengge Lv
Feng Li
Yi Wang
Tianzhen Wang
Demba Diallo
Xiaohang Wang
A Symbol Conditional Entropy-Based Method for Incipient Cavitation Prediction in Hydraulic Turbines
Journal of Marine Science and Engineering
hydroacoustic signal
incipient cavitation prediction
entropy
initial prediction point
hydraulic turbine
title A Symbol Conditional Entropy-Based Method for Incipient Cavitation Prediction in Hydraulic Turbines
title_full A Symbol Conditional Entropy-Based Method for Incipient Cavitation Prediction in Hydraulic Turbines
title_fullStr A Symbol Conditional Entropy-Based Method for Incipient Cavitation Prediction in Hydraulic Turbines
title_full_unstemmed A Symbol Conditional Entropy-Based Method for Incipient Cavitation Prediction in Hydraulic Turbines
title_short A Symbol Conditional Entropy-Based Method for Incipient Cavitation Prediction in Hydraulic Turbines
title_sort symbol conditional entropy based method for incipient cavitation prediction in hydraulic turbines
topic hydroacoustic signal
incipient cavitation prediction
entropy
initial prediction point
hydraulic turbine
url https://www.mdpi.com/2077-1312/13/3/538
work_keys_str_mv AT menggelv asymbolconditionalentropybasedmethodforincipientcavitationpredictioninhydraulicturbines
AT fengli asymbolconditionalentropybasedmethodforincipientcavitationpredictioninhydraulicturbines
AT yiwang asymbolconditionalentropybasedmethodforincipientcavitationpredictioninhydraulicturbines
AT tianzhenwang asymbolconditionalentropybasedmethodforincipientcavitationpredictioninhydraulicturbines
AT dembadiallo asymbolconditionalentropybasedmethodforincipientcavitationpredictioninhydraulicturbines
AT xiaohangwang asymbolconditionalentropybasedmethodforincipientcavitationpredictioninhydraulicturbines
AT menggelv symbolconditionalentropybasedmethodforincipientcavitationpredictioninhydraulicturbines
AT fengli symbolconditionalentropybasedmethodforincipientcavitationpredictioninhydraulicturbines
AT yiwang symbolconditionalentropybasedmethodforincipientcavitationpredictioninhydraulicturbines
AT tianzhenwang symbolconditionalentropybasedmethodforincipientcavitationpredictioninhydraulicturbines
AT dembadiallo symbolconditionalentropybasedmethodforincipientcavitationpredictioninhydraulicturbines
AT xiaohangwang symbolconditionalentropybasedmethodforincipientcavitationpredictioninhydraulicturbines