Ruixu Zhou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Ruixu Zhou has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
Wensheng Gao
Department of Electrical Engineering, State Key Laboratory of Power System and Generation Equipment, Tsinghua University, Beijing 100084, China
6 shared publications- Jianbo Yu
School of Mechanical Engineering, Tongji University, Shanghai, China
5 shared publications - Pu Yang
Tencent Incorporation, Shenzhen, China
5 shared publications - Shang Yue
Tencent Incorporation, Shenzhen, China
4 shared publications Bowen Zhang
China Electric Power Research Institute
3 shared publicationsQinzhu Chen
Hainan Power Grid Corporation
3 shared publications
Latest Publications
- 14 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (5) , 3901-3912
Multi-Tasks Joint Network for Anomaly Diagnosis and Inconsistent Identification of VRLA Battery in Large Data Center
Valve-regulated lead–acid (VRLA) battery module is one of the important components of the uninterruptible power supply system in a large Internet data center. Battery health monitoring and anomaly diagnosis in time is significant to ensure the safe operation of a data center. In this article, a multitask joint network (MTJNet) is proposed to perform anomaly diagnosis and inconsistency identification simultaneously. First, an unsupervised learning-based encoder-decoder structure is proposed in MTJNet for battery inconsistency identification, where only health data are required for training. Second, the other branch with a classifier is further constructed to recognize the anomaly of the battery module. Third, a multitask joint training method is used to update the parameters of the two task models in MTJNet. The reconstruction error obtained by inconsistency identification task is fed into the anomaly diagnosis task. The predicted pseudo labels by the anomaly diagnosis task are feedback to inconsistency identification task to guide the encoder-decoder to provide the discriminate features. Finally, the effectiveness of MTJNet is verified on VRLA battery modules in a large data center. The experimental results illustrate that MTJNet is a good tool for anomaly diagnosis and inconsistency identification of VRLA battery modules.
- 14 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (5) , 3901-3912
Multi-Tasks Joint Network for Anomaly Diagnosis and Inconsistent Identification of VRLA Battery in Large Data Center
Valve-regulated lead–acid (VRLA) battery module is one of the important components of the uninterruptible power supply system in a large Internet data center. Battery health monitoring and anomaly diagnosis in time is significant to ensure the safe operation of a data center. In this article, a multitask joint network (MTJNet) is proposed to perform anomaly diagnosis and inconsistency identification simultaneously. First, an unsupervised learning-based encoder-decoder structure is proposed in MTJNet for battery inconsistency identification, where only health data are required for training. Second, the other branch with a classifier is further constructed to recognize the anomaly of the battery module. Third, a multitask joint training method is used to update the parameters of the two task models in MTJNet. The reconstruction error obtained by inconsistency identification task is fed into the anomaly diagnosis task. The predicted pseudo labels by the anomaly diagnosis task are feedback to inconsistency identification task to guide the encoder-decoder to provide the discriminate features. Finally, the effectiveness of MTJNet is verified on VRLA battery modules in a large data center. The experimental results illustrate that MTJNet is a good tool for anomaly diagnosis and inconsistency identification of VRLA battery modules.
- 29 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Electronics
- Vol. 39 (11) , 15085-15100
Source-Free Dynamic Weighted Federated Transfer Learning for State-of-Health Estimation of Lithium-Ion Batteries With Data Privacy
Most existing methods for battery state-of-health (SOH) estimation rely on centralized training mode. However, in practical applications, it is difficult for a single user to collect sufficient battery degradation data to train a model. In addition, in order to protect data privacy, users are unwilling to share data, where centralized training mode is not the best choice. To overcome these barriers, a source-free dynamic weighted federated transfer (SF-DWFT) method for battery SOH estimation is proposed, which utilizes a distributed learning paradigm to combine multiple source clients to train a global model while protecting data privacy. First, a Gaussian mixture model is used to model the high-level features extracted by the client model, thus the feature representation can be shared without needing access to the source data; then, in order to reduce the effect of distribution differences between the source and target clients on the global model, a dynamic weighted federated aggregation algorithm is proposed according to their contributions, which is measured by calculating the modified Bhattacharya distance between the source and target clients and testing error. Finally, the effectiveness of SF-DWFT is verified on several battery datasets and it achieves a statistic estimation error of 1.12% on 18 650 lithium-ion battery datasets and 4.46% on NASA battery dataset.
- 29 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Electronics
- Vol. 39 (11) , 15085-15100
Source-Free Dynamic Weighted Federated Transfer Learning for State-of-Health Estimation of Lithium-Ion Batteries With Data Privacy
Most existing methods for battery state-of-health (SOH) estimation rely on centralized training mode. However, in practical applications, it is difficult for a single user to collect sufficient battery degradation data to train a model. In addition, in order to protect data privacy, users are unwilling to share data, where centralized training mode is not the best choice. To overcome these barriers, a source-free dynamic weighted federated transfer (SF-DWFT) method for battery SOH estimation is proposed, which utilizes a distributed learning paradigm to combine multiple source clients to train a global model while protecting data privacy. First, a Gaussian mixture model is used to model the high-level features extracted by the client model, thus the feature representation can be shared without needing access to the source data; then, in order to reduce the effect of distribution differences between the source and target clients on the global model, a dynamic weighted federated aggregation algorithm is proposed according to their contributions, which is measured by calculating the modified Bhattacharya distance between the source and target clients and testing error. Finally, the effectiveness of SF-DWFT is verified on several battery datasets and it achieves a statistic estimation error of 1.12% on 18 650 lithium-ion battery datasets and 4.46% on NASA battery dataset.
- 13 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Electronics
- Vol. 39 (10) , 13758-13770
Densely-Connected Contrastive Observer for Fault Diagnosis of VRLA Battery in Large Data Center Based on Semisupervised Few-Shot Learning
Valve-regulated lead-acid (VRLA) batteries are of paramount importance in ensuring the safety and stability of large intelligent data centers (IDCs). The health management of VRLA battery suffers from the limitation of sparse charge-discharge data and nonideal samples in the high-voltage direct current system of IDC. In this article, a novel semisupervised few-shot model, i.e., densely-connected contrastive observer (DCober), is proposed for feature self-extraction of multisource signals and few-shot diagnosis of VRLA batteries. First, a view-augmented method is proposed to implement image augmentation for multichannel temporal images, which improves the feature self-extraction performance. Second, self-supervised contrastive learning is used in DCober to implement feature representation learning on massive nonlabeled data in real industrial scenarios. Finally, a similarity-based few-shot finetuning method is proposed for finetuning enhancement on the extension of limited labeled data, which improves the fault recognition performance of DCober in few-shot scenarios. The effectiveness of DCober is validated through a real industrial application of VRLA battery in Tencent T-block IDC. The testing results show that DCober outperforms other state-of-the-art methods and obtains a recognition accuracy of 95.63% in 1-shot data scenario.
- 13 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Electronics
- Vol. 39 (10) , 13758-13770
Densely-Connected Contrastive Observer for Fault Diagnosis of VRLA Battery in Large Data Center Based on Semisupervised Few-Shot Learning
Valve-regulated lead-acid (VRLA) batteries are of paramount importance in ensuring the safety and stability of large intelligent data centers (IDCs). The health management of VRLA battery suffers from the limitation of sparse charge-discharge data and nonideal samples in the high-voltage direct current system of IDC. In this article, a novel semisupervised few-shot model, i.e., densely-connected contrastive observer (DCober), is proposed for feature self-extraction of multisource signals and few-shot diagnosis of VRLA batteries. First, a view-augmented method is proposed to implement image augmentation for multichannel temporal images, which improves the feature self-extraction performance. Second, self-supervised contrastive learning is used in DCober to implement feature representation learning on massive nonlabeled data in real industrial scenarios. Finally, a similarity-based few-shot finetuning method is proposed for finetuning enhancement on the extension of limited labeled data, which improves the fault recognition performance of DCober in few-shot scenarios. The effectiveness of DCober is validated through a real industrial application of VRLA battery in Tencent T-block IDC. The testing results show that DCober outperforms other state-of-the-art methods and obtains a recognition accuracy of 95.63% in 1-shot data scenario.
- 29 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (11) , 18172-18184
Bearing Compound Fault Diagnosis Using Energy-Constrained Swarm Decomposition and Adaptive Spectral Amplitude Modulation
In real industry, local damages often appear on multiple parts of bearings simultaneously and these compound faults coupling heavily troubles those regular diagnosis methods. In this paper, an energy-constrained swarm decomposition and adaptive spectral amplitude modulation method (ECSWD-ASAM) is proposed to extract compound fault features from bearing vibration signals. Firstly, a rectangular window is convolved with the energy spectrum to generate a smooth upper envelope curve to overcome the instant noisy peaks and highlight dominant frequencies in the vibration signals. Secondly, an energy filter is constructed to concentrate the energy of each oscillating component and suppress the spectrum overlap during the signal decomposition. Thirdly, envelope correlation coefficient (ECC) is used as the evaluation criterion to constraint the over decomposition between adjacent components. Finally, a new index called kurtosis-enhanced entropy (KEE) is proposed to adaptively locate the optimal fault frequency band of the SAM results, which can enhance the weak fault features in the extracted components. ECSWD-ASAM effectively separates different fault components on simulated data, Paderborn university (PU) dataset and vibration signals of bearing-gearbox testbed. The testing results indicate that ECSWD-ASAM has better denoising and compound fault extraction performance than these representative methods, i.e., successive variational mode decomposition (SVMD), improved complete ensemble empirical mode decomposition adaptive noise (ICEEMDAN) and local mean decomposition (LMD).
- 29 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (11) , 18172-18184
Bearing Compound Fault Diagnosis Using Energy-Constrained Swarm Decomposition and Adaptive Spectral Amplitude Modulation
In real industry, local damages often appear on multiple parts of bearings simultaneously and these compound faults coupling heavily troubles those regular diagnosis methods. In this paper, an energy-constrained swarm decomposition and adaptive spectral amplitude modulation method (ECSWD-ASAM) is proposed to extract compound fault features from bearing vibration signals. Firstly, a rectangular window is convolved with the energy spectrum to generate a smooth upper envelope curve to overcome the instant noisy peaks and highlight dominant frequencies in the vibration signals. Secondly, an energy filter is constructed to concentrate the energy of each oscillating component and suppress the spectrum overlap during the signal decomposition. Thirdly, envelope correlation coefficient (ECC) is used as the evaluation criterion to constraint the over decomposition between adjacent components. Finally, a new index called kurtosis-enhanced entropy (KEE) is proposed to adaptively locate the optimal fault frequency band of the SAM results, which can enhance the weak fault features in the extracted components. ECSWD-ASAM effectively separates different fault components on simulated data, Paderborn university (PU) dataset and vibration signals of bearing-gearbox testbed. The testing results indicate that ECSWD-ASAM has better denoising and compound fault extraction performance than these representative methods, i.e., successive variational mode decomposition (SVMD), improved complete ensemble empirical mode decomposition adaptive noise (ICEEMDAN) and local mean decomposition (LMD).
- 22 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-12
Deep Morphological Shrinkage Convolutional Autoencoder-Based Feature Learning of Vibration Signals for Gearbox Fault Diagnosis
Fault diagnosis is significant to guarantee the safety and reliability of the machinery. Local fault will make the collected vibration signals deviate from the normal signals. In order to extract fault-related features from vibration signals, many deep learning-based methods have been proposed for machinery fault diagnosis recently. However, due to the extreme conditions (e.g., high background noise, limited labeled training samples), it is a challenging task to implement features extraction from the collected signals with non-linear and non-stationary characteristics. To implement feature extraction and noise reduction of vibration signals, this paper proposes a novel network, i.e., deep morphological shrinkage convolutional auto-encoder (DMSCAE) for gearbox fault diagnosis considering the insufficient labeled training samples. Firstly, a morphological convolutional auto-encoder is proposed for noise filtering and feature extraction. Secondly, a multi-branch structure with different structural elements (SEs) is used in the morphological layer to extract impulsive components. Finally, a soft thresholding-based shrinkage is employed to filter ineffective features, where an adaptative method is developed to adjust the threshold automatically in the back-propagation procedure. The experiments on two gearbox fault diagnosis tests are conducted to verify the performance of DMSCAE. The results indicate that DMSCAE obtains a better performance for fault diagnosis than other DNNs, e.g., efficient channel attention network (ECANet), self-calibrated convolutional network (SCNet).
- 22 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-12
Deep Morphological Shrinkage Convolutional Autoencoder-Based Feature Learning of Vibration Signals for Gearbox Fault Diagnosis
Fault diagnosis is significant to guarantee the safety and reliability of the machinery. Local fault will make the collected vibration signals deviate from the normal signals. In order to extract fault-related features from vibration signals, many deep learning-based methods have been proposed for machinery fault diagnosis recently. However, due to the extreme conditions (e.g., high background noise, limited labeled training samples), it is a challenging task to implement features extraction from the collected signals with non-linear and non-stationary characteristics. To implement feature extraction and noise reduction of vibration signals, this paper proposes a novel network, i.e., deep morphological shrinkage convolutional auto-encoder (DMSCAE) for gearbox fault diagnosis considering the insufficient labeled training samples. Firstly, a morphological convolutional auto-encoder is proposed for noise filtering and feature extraction. Secondly, a multi-branch structure with different structural elements (SEs) is used in the morphological layer to extract impulsive components. Finally, a soft thresholding-based shrinkage is employed to filter ineffective features, where an adaptative method is developed to adjust the threshold automatically in the back-propagation procedure. The experiments on two gearbox fault diagnosis tests are conducted to verify the performance of DMSCAE. The results indicate that DMSCAE obtains a better performance for fault diagnosis than other DNNs, e.g., efficient channel attention network (ECANet), self-calibrated convolutional network (SCNet).
- 1 April 2022
- Published by Elsevier in Pattern Recognition
- Vol. 124, 108450
Supervised dimensionality reduction technology of generalized discriminant component analysis and its kernelization forms
- 1 April 2022
- Published by Elsevier in Pattern Recognition
- Vol. 124, 108450
Supervised dimensionality reduction technology of generalized discriminant component analysis and its kernelization forms
- Open Access
Statistical Feature Extraction Combined with Generalized Discriminant Component Analysis Driven SVM for Fault Diagnosis of HVDC GIS
Accurately identifying the types of insulation defects inside a gas-insulated switchgear (GIS) is of great significance for guiding maintenance work as well as ensuring the safe and stable operation of GIS. By building a set of 220 kV high-voltage direct current (HVDC) GIS experiment platforms and manufacturing four different types of insulation defects (including multiple sizes and positions), 180,828 pulse current signals under multiple voltage levels are successfully measured. Then, the apparent discharge quantity and the discharge time, two inherent physical quantities unaffected by the experimental platform and measurement system, are obtained after the pulse current signal is denoised, according to which 70 statistical features are extracted. In this paper, a pattern recognition method based on generalized discriminant component analysis driven support vector machine (SVM) is detailed and the corresponding selection criterion of involved parameters is established. The results show that the newly proposed pattern recognition method greatly improves the recognition accuracy of fault diagnosis in comparison with 36 kinds of state-of-the-art dimensionality reduction algorithms and 44 kinds of state-of-the-art classifiers. This newly proposed method not only solves the difficulty that phase-resolved partial discharge (PRPD) cannot be applied under DC condition but also immensely facilitates the fault diagnosis of HVDC GIS.
Open AccessStatistical Feature Extraction Combined with Generalized Discriminant Component Analysis Driven SVM for Fault Diagnosis of HVDC GIS
Accurately identifying the types of insulation defects inside a gas-insulated switchgear (GIS) is of great significance for guiding maintenance work as well as ensuring the safe and stable operation of GIS. By building a set of 220 kV high-voltage direct current (HVDC) GIS experiment platforms and manufacturing four different types of insulation defects (including multiple sizes and positions), 180,828 pulse current signals under multiple voltage levels are successfully measured. Then, the apparent discharge quantity and the discharge time, two inherent physical quantities unaffected by the experimental platform and measurement system, are obtained after the pulse current signal is denoised, according to which 70 statistical features are extracted. In this paper, a pattern recognition method based on generalized discriminant component analysis driven support vector machine (SVM) is detailed and the corresponding selection criterion of involved parameters is established. The results show that the newly proposed pattern recognition method greatly improves the recognition accuracy of fault diagnosis in comparison with 36 kinds of state-of-the-art dimensionality reduction algorithms and 44 kinds of state-of-the-art classifiers. This newly proposed method not only solves the difficulty that phase-resolved partial discharge (PRPD) cannot be applied under DC condition but also immensely facilitates the fault diagnosis of HVDC GIS.
- 9 November 2017
- Published by Springer Nature in Meteorology and Atmospheric Physics
- Vol. 131 (2) , 137-156
A new prediction model of daily weather elements in Hainan province under the typhoon weather
- 9 November 2017
- Published by Springer Nature in Meteorology and Atmospheric Physics
- Vol. 131 (2) , 137-156
A new prediction model of daily weather elements in Hainan province under the typhoon weather
- Open Access
- 2 August 2017
- Published by Institution of Engineering and Technology (IET) in IET Generation, Transmission & Distribution
- Vol. 11 (14) , 3644-3653
Improved calculation model for swing angle of suspension insulator string
In modern power systems, increasing faults of overhead transmission lines are caused by wind swing discharge especially in weather‐sensitive regions such as coastal hurricane‐prone areas. Since the vast majority of wind swing discharge accidents occur at the working voltage and existing models established for the suspension insulator wind swing discharge are not adequate to analyse all cases, an improved model under wind with arbitrary directions is proposed in this paper. Comprehensive factors are taken into consideration including exposure factor of wind pressure under different landforms and different elevations, wind pressure asymmetric factor, iced conductors, the coupling effect of conductors to insulators, the shielding wake flow effect of bundled conductor, the fluctuating wind amplification effect, mechanical oscillating of insulators, etc. IEEE model and design manual model are chosen as comparisons with the simulation results of ANSYS. Test results show that the improved model proposed in this paper coincides with ANSYS results better than the other two models almost in all the working conditions considering different spans and altitude differences. The results demonstrate that the improved model can make contribution to the economical and reasonable design of towers as well as early warning of wind swing discharge of suspension insulators.
- 2 August 2017
- Published by Institution of Engineering and Technology (IET) in IET Generation, Transmission & Distribution
- Vol. 11 (14) , 3644-3653
Open AccessImproved calculation model for swing angle of suspension insulator string
In modern power systems, increasing faults of overhead transmission lines are caused by wind swing discharge especially in weather‐sensitive regions such as coastal hurricane‐prone areas. Since the vast majority of wind swing discharge accidents occur at the working voltage and existing models established for the suspension insulator wind swing discharge are not adequate to analyse all cases, an improved model under wind with arbitrary directions is proposed in this paper. Comprehensive factors are taken into consideration including exposure factor of wind pressure under different landforms and different elevations, wind pressure asymmetric factor, iced conductors, the coupling effect of conductors to insulators, the shielding wake flow effect of bundled conductor, the fluctuating wind amplification effect, mechanical oscillating of insulators, etc. IEEE model and design manual model are chosen as comparisons with the simulation results of ANSYS. Test results show that the improved model proposed in this paper coincides with ANSYS results better than the other two models almost in all the working conditions considering different spans and altitude differences. The results demonstrate that the improved model can make contribution to the economical and reasonable design of towers as well as early warning of wind swing discharge of suspension insulators.
- Open Access
- 1 March 2017
- Published by Institution of Engineering and Technology (IET) in IET Generation, Transmission & Distribution
- Vol. 11 (4) , 935-942
Heuristic failure prediction model of transmission line under natural disasters
Natural disasters caused by tropical cyclones such as Typhoon, Hurricane, Tornados, etc., are bringing severe damage to modern power transmission systems throughout the world. These natural disasters each have their individual patterns at specific locations, and the current pre‐disaster analysis is performed primarily relying on simple weather forecasting results, which lacks the acknowledgment of microclimate analytics. This paper presents heuristic transmission line failure model regarding microclimate analysis, which serves as more accurate and active prediction reference for regional transmission lines. Anti‐disaster preventive activities can be thereafter designed prior to the occurrence of the disaster, and post‐disaster remedy actions can be well prepared accordingly as well to prevent severe damages. This paper provides detailed modelling of Typhoon in typical areas of China as examples, and comes up with the corresponding transmission line failure model by accounting the microclimate prediction method and historical line tripping data sets. Validation process of the model returns a passing result of the vast majority of prediction equations for trip‐out rate of transmission lines on the significant test with the confidence level of 95%, and a reasonable prediction ratio of all the transmission lines.
- 1 March 2017
- Published by Institution of Engineering and Technology (IET) in IET Generation, Transmission & Distribution
- Vol. 11 (4) , 935-942
Open AccessHeuristic failure prediction model of transmission line under natural disasters
Natural disasters caused by tropical cyclones such as Typhoon, Hurricane, Tornados, etc., are bringing severe damage to modern power transmission systems throughout the world. These natural disasters each have their individual patterns at specific locations, and the current pre‐disaster analysis is performed primarily relying on simple weather forecasting results, which lacks the acknowledgment of microclimate analytics. This paper presents heuristic transmission line failure model regarding microclimate analysis, which serves as more accurate and active prediction reference for regional transmission lines. Anti‐disaster preventive activities can be thereafter designed prior to the occurrence of the disaster, and post‐disaster remedy actions can be well prepared accordingly as well to prevent severe damages. This paper provides detailed modelling of Typhoon in typical areas of China as examples, and comes up with the corresponding transmission line failure model by accounting the microclimate prediction method and historical line tripping data sets. Validation process of the model returns a passing result of the vast majority of prediction equations for trip‐out rate of transmission lines on the significant test with the confidence level of 95%, and a reasonable prediction ratio of all the transmission lines.