Fault Prediction of Hydropower Station Based on CNN-LSTM-GAN with Biased Data
Fault prediction of hydropower station is crucial for the stable operation of generator set equipment, but the traditional method struggles to deal with data with an imbalanced distribution and untrustworthiness. This paper proposes a fault detection method based on a convolutional neural network (C...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/18/14/3772 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849246629415092224 |
|---|---|
| author | Bei Liu Xiao Wang Zhaoxin Zhang Zhenjie Zhao Xiaoming Wang Ting Liu |
| author_facet | Bei Liu Xiao Wang Zhaoxin Zhang Zhenjie Zhao Xiaoming Wang Ting Liu |
| author_sort | Bei Liu |
| collection | DOAJ |
| description | Fault prediction of hydropower station is crucial for the stable operation of generator set equipment, but the traditional method struggles to deal with data with an imbalanced distribution and untrustworthiness. This paper proposes a fault detection method based on a convolutional neural network (CNNs) and long short-term memory network (LSTM) with a generative adversarial network (GAN). Firstly, a reliability mechanism based on principal component analysis (PCA) is designed to solve the problem of data bias caused by multiple monitoring devices. Then, the CNN-LSTM network is used to predict time series data, and the GAN is used to expand fault data samples to solve the problem of an unbalanced data distribution. Meanwhile, a multi-scale feature extraction network with time–frequency information is designed to improve the accuracy of fault detection. Finally, a dynamic multi-task training algorithm is proposed to ensure the convergence and training efficiency of the deep models. Experimental results show that compared with RNN, GRU, SVM, and threshold detection algorithms, the proposed fault prediction method improves the accuracy performance by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>5.5</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>4.8</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>7.8</mn><mo>%</mo></mrow></semantics></math></inline-formula>, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>9.3</mn><mo>%</mo></mrow></semantics></math></inline-formula>, with at least a <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>160</mn><mo>%</mo></mrow></semantics></math></inline-formula> improvement in the fault recall rate. |
| format | Article |
| id | doaj-art-43dbeadaa4c649ab9eebada762698776 |
| institution | Kabale University |
| issn | 1996-1073 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj-art-43dbeadaa4c649ab9eebada7626987762025-08-20T03:58:26ZengMDPI AGEnergies1996-10732025-07-011814377210.3390/en18143772Fault Prediction of Hydropower Station Based on CNN-LSTM-GAN with Biased DataBei Liu0Xiao Wang1Zhaoxin Zhang2Zhenjie Zhao3Xiaoming Wang4Ting Liu5SDIC Gansu Xiaosanxia Power Co., Ltd., Lanzhou 730050, ChinaSDIC Gansu Xiaosanxia Power Co., Ltd., Lanzhou 730050, ChinaSDIC Gansu Xiaosanxia Power Co., Ltd., Lanzhou 730050, ChinaSchool of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaSchool of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaSchool of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaFault prediction of hydropower station is crucial for the stable operation of generator set equipment, but the traditional method struggles to deal with data with an imbalanced distribution and untrustworthiness. This paper proposes a fault detection method based on a convolutional neural network (CNNs) and long short-term memory network (LSTM) with a generative adversarial network (GAN). Firstly, a reliability mechanism based on principal component analysis (PCA) is designed to solve the problem of data bias caused by multiple monitoring devices. Then, the CNN-LSTM network is used to predict time series data, and the GAN is used to expand fault data samples to solve the problem of an unbalanced data distribution. Meanwhile, a multi-scale feature extraction network with time–frequency information is designed to improve the accuracy of fault detection. Finally, a dynamic multi-task training algorithm is proposed to ensure the convergence and training efficiency of the deep models. Experimental results show that compared with RNN, GRU, SVM, and threshold detection algorithms, the proposed fault prediction method improves the accuracy performance by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>5.5</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>4.8</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>7.8</mn><mo>%</mo></mrow></semantics></math></inline-formula>, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>9.3</mn><mo>%</mo></mrow></semantics></math></inline-formula>, with at least a <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>160</mn><mo>%</mo></mrow></semantics></math></inline-formula> improvement in the fault recall rate.https://www.mdpi.com/1996-1073/18/14/3772failure predictionhydropower stationbiased dataCNN-LSTMmulti-scale feature extraction |
| spellingShingle | Bei Liu Xiao Wang Zhaoxin Zhang Zhenjie Zhao Xiaoming Wang Ting Liu Fault Prediction of Hydropower Station Based on CNN-LSTM-GAN with Biased Data Energies failure prediction hydropower station biased data CNN-LSTM multi-scale feature extraction |
| title | Fault Prediction of Hydropower Station Based on CNN-LSTM-GAN with Biased Data |
| title_full | Fault Prediction of Hydropower Station Based on CNN-LSTM-GAN with Biased Data |
| title_fullStr | Fault Prediction of Hydropower Station Based on CNN-LSTM-GAN with Biased Data |
| title_full_unstemmed | Fault Prediction of Hydropower Station Based on CNN-LSTM-GAN with Biased Data |
| title_short | Fault Prediction of Hydropower Station Based on CNN-LSTM-GAN with Biased Data |
| title_sort | fault prediction of hydropower station based on cnn lstm gan with biased data |
| topic | failure prediction hydropower station biased data CNN-LSTM multi-scale feature extraction |
| url | https://www.mdpi.com/1996-1073/18/14/3772 |
| work_keys_str_mv | AT beiliu faultpredictionofhydropowerstationbasedoncnnlstmganwithbiaseddata AT xiaowang faultpredictionofhydropowerstationbasedoncnnlstmganwithbiaseddata AT zhaoxinzhang faultpredictionofhydropowerstationbasedoncnnlstmganwithbiaseddata AT zhenjiezhao faultpredictionofhydropowerstationbasedoncnnlstmganwithbiaseddata AT xiaomingwang faultpredictionofhydropowerstationbasedoncnnlstmganwithbiaseddata AT tingliu faultpredictionofhydropowerstationbasedoncnnlstmganwithbiaseddata |