Chen Zhang
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
Chen Zhang has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Tao Yang
Huazhong University of Science and Technology
7 shared publications - Sheng Guo
Digital Research Institute, ENN Group, Langfang, China
2 shared publications - Wei Gao
School of Energy and Power Engineering, Huazhong University of Science and Technology, Wuhan 430074, China
2 shared publications - Bixiang Wang
Department of Mathematics, New Mexico Institute of Mining and Technology, Socorro, USA
1 shared publication Di Hu
1 shared publication- Di Hu
School of Energy and Power Engineering, Huazhong University of Science and Technology, Wuhan 430074, China
1 shared publication
Latest Publications
- Open Access
Physics-Informed Anomaly Detection and Fault Localization for Wind Turbines Using Multi-Strategy DASVDD and Bidirectionally Adjusted Reconstruction Error
Anomaly detection and fault localization are essential for the safe and economic operation of wind turbines and the mitigation of unplanned outages. A novel physics-informed anomaly detection and fault localization method is developed to address high false alarm rates and insufficient localization accuracy in small-sample scenarios. First, a physics-informed autoencoder, integrated with explicit algebraic physical constraints, is developed to verify the effective embedding of inherent physical relationships. Second, building upon this autoencoder, a multi-strategy deep autoencoder-based support vector data description (MS-DASVDD) for anomaly detection that incorporates physical constraint regularization, latent variable alignment, and transfer learning is developed, significantly reducing false alarms and missed detections with limited training data. Finally, a physics-informed method for bidirectional reconstruction error adjustment is proposed, which penalizes errors consistent with physical constraints while accentuating inconsistent ones, thus significantly boosting error-driven fault feature localization accuracy under limited fault samples. Case studies on two wind farms (40 MW and 30 MW) in Northern China show that the proposed physics-informed method markedly improves precision, recall, and F1 score, suppresses spiky anomaly scores, and enhances the contribution of fault features, confirming its effectiveness and robustness; sensitivity and comparative analyses further validate its superiority.
Open AccessPhysics-Informed Anomaly Detection and Fault Localization for Wind Turbines Using Multi-Strategy DASVDD and Bidirectionally Adjusted Reconstruction Error
Anomaly detection and fault localization are essential for the safe and economic operation of wind turbines and the mitigation of unplanned outages. A novel physics-informed anomaly detection and fault localization method is developed to address high false alarm rates and insufficient localization accuracy in small-sample scenarios. First, a physics-informed autoencoder, integrated with explicit algebraic physical constraints, is developed to verify the effective embedding of inherent physical relationships. Second, building upon this autoencoder, a multi-strategy deep autoencoder-based support vector data description (MS-DASVDD) for anomaly detection that incorporates physical constraint regularization, latent variable alignment, and transfer learning is developed, significantly reducing false alarms and missed detections with limited training data. Finally, a physics-informed method for bidirectional reconstruction error adjustment is proposed, which penalizes errors consistent with physical constraints while accentuating inconsistent ones, thus significantly boosting error-driven fault feature localization accuracy under limited fault samples. Case studies on two wind farms (40 MW and 30 MW) in Northern China show that the proposed physics-informed method markedly improves precision, recall, and F1 score, suppresses spiky anomaly scores, and enhances the contribution of fault features, confirming its effectiveness and robustness; sensitivity and comparative analyses further validate its superiority.
- Open Access
Anomaly Detection for Wind Turbines Using Long Short-Term Memory-Based Variational Autoencoder Wasserstein Generation Adversarial Network under Semi-Supervised Training
Intelligent anomaly detection for wind turbines using deep-learning methods has been extensively researched and yielded significant results. However, supervised learning necessitates sufficient labeled data to establish the discriminant boundary, while unsupervised learning lacks prior knowledge and heavily relies on assumptions about the distribution of anomalies. A long short-term memory-based variational autoencoder Wasserstein generation adversarial network (LSTM-based VAE-WGAN) was established in this paper to address the challenge of small and noisy wind turbine datasets. The VAE was utilized as the generator, with LSTM units replacing hidden layer neurons to effectively extract spatiotemporal factors. The similarity between the model-fit distribution and true distribution was quantified using Wasserstein distance, enabling complex high-dimensional data distributions to be learned. To enhance the performance and robustness of the proposed model, a two-stage adversarial semi-supervised training approach was implemented. Subsequently, a monitoring indicator based on reconstruction error was defined, with the threshold set at a 99.7% confidence interval for the distribution curve fitted by kernel density estimation (KDE). Real cases from a wind farm in northeast China have confirmed the feasibility and advancement of the proposed model, while also discussing the effects of various applied parameters.
Open AccessAnomaly Detection for Wind Turbines Using Long Short-Term Memory-Based Variational Autoencoder Wasserstein Generation Adversarial Network under Semi-Supervised Training
Intelligent anomaly detection for wind turbines using deep-learning methods has been extensively researched and yielded significant results. However, supervised learning necessitates sufficient labeled data to establish the discriminant boundary, while unsupervised learning lacks prior knowledge and heavily relies on assumptions about the distribution of anomalies. A long short-term memory-based variational autoencoder Wasserstein generation adversarial network (LSTM-based VAE-WGAN) was established in this paper to address the challenge of small and noisy wind turbine datasets. The VAE was utilized as the generator, with LSTM units replacing hidden layer neurons to effectively extract spatiotemporal factors. The similarity between the model-fit distribution and true distribution was quantified using Wasserstein distance, enabling complex high-dimensional data distributions to be learned. To enhance the performance and robustness of the proposed model, a two-stage adversarial semi-supervised training approach was implemented. Subsequently, a monitoring indicator based on reconstruction error was defined, with the threshold set at a 99.7% confidence interval for the distribution curve fitted by kernel density estimation (KDE). Real cases from a wind farm in northeast China have confirmed the feasibility and advancement of the proposed model, while also discussing the effects of various applied parameters.
- Open Access
Image Recognition of Wind Turbine Blade Defects Using Attention-Based MobileNetv1-YOLOv4 and Transfer Learning
Recently, the machine-vision-based blades surface damage detection technique has received great attention for its low cost, easy operation, and lack of a need for prior knowledge. The rapid progress of deep learning has contributed to the promotion of this technology with automatic feature extraction, a broader scope of application, and stronger expansibility. An image recognition method of wind turbine blade defects using attention-based MobileNetv1-YOLOv4 and transfer learning is proposed in this paper. The backbone convolution neural network of YOLOv4 is replaced by the lightweight MobileNetv1 for feature extraction to reduce complexity and computation. Attention-based feature refinement with three distinctive modules, SENet, ECANet, and CBAM, is introduced to realize adaptive feature optimization. To solve the problem of slow network convergence and low detection accuracy caused by insufficient data, a two-stage transfer learning approach is introduced to fine-tune the pre-trained network. Comparative experiments verify the efficacy of the proposed model, with higher detection accuracy but a significantly faster response speed and less computational complexity, compared with other state-of-the-art networks by using images of the wind turbine blades taken by an unmanned aerial vehicle (UAV). A sensitivity study is also conducted to present the effects of different training dataset sizes on the model performance.
Open AccessImage Recognition of Wind Turbine Blade Defects Using Attention-Based MobileNetv1-YOLOv4 and Transfer Learning
Recently, the machine-vision-based blades surface damage detection technique has received great attention for its low cost, easy operation, and lack of a need for prior knowledge. The rapid progress of deep learning has contributed to the promotion of this technology with automatic feature extraction, a broader scope of application, and stronger expansibility. An image recognition method of wind turbine blade defects using attention-based MobileNetv1-YOLOv4 and transfer learning is proposed in this paper. The backbone convolution neural network of YOLOv4 is replaced by the lightweight MobileNetv1 for feature extraction to reduce complexity and computation. Attention-based feature refinement with three distinctive modules, SENet, ECANet, and CBAM, is introduced to realize adaptive feature optimization. To solve the problem of slow network convergence and low detection accuracy caused by insufficient data, a two-stage transfer learning approach is introduced to fine-tune the pre-trained network. Comparative experiments verify the efficacy of the proposed model, with higher detection accuracy but a significantly faster response speed and less computational complexity, compared with other state-of-the-art networks by using images of the wind turbine blades taken by an unmanned aerial vehicle (UAV). A sensitivity study is also conducted to present the effects of different training dataset sizes on the model performance.
- 1 November 2021
- Published by Science China Press., Co. Ltd. in SCIENTIA SINICA Mathematica
- Vol. 52 (9) , 1015
Invariant measures of stochastic Schrödinger delay lattice systems
In this paper, we investigate stochastic Schrödinger lattice systems with time delay, whose drift and diffusion coefficientsare locally Lipschitz continuous. Firstly, some uniform estimates of solutions areestablished which include higher-order moment estimates and uniform tail-ends estimates. Then the tightness of a family ofprobability distributions of solutions in $C([-\\rho,0];l^2)$ is proved by the Arzel${\\rm~\\grave{a}}$-Ascoli theorem and the technique of diadicdivision. Finally, the existence of invariant measures for the Markov semigroup of the system is provedby the Krylov-Bogolyubov method.- 1 November 2021
- Published by Science China Press., Co. Ltd. in SCIENTIA SINICA Mathematica
- Vol. 52 (9) , 1015
Invariant measures of stochastic Schrödinger delay lattice systems
In this paper, we investigate stochastic Schrödinger lattice systems with time delay, whose drift and diffusion coefficientsare locally Lipschitz continuous. Firstly, some uniform estimates of solutions areestablished which include higher-order moment estimates and uniform tail-ends estimates. Then the tightness of a family ofprobability distributions of solutions in $C([-\\rho,0];l^2)$ is proved by the Arzel${\\rm~\\grave{a}}$-Ascoli theorem and the technique of diadicdivision. Finally, the existence of invariant measures for the Markov semigroup of the system is provedby the Krylov-Bogolyubov method.- 1 September 2021
- Published by Elsevier in Sustainable Energy, Grids and Networks
- Vol. 27
Peer-to-Peer energy trading in a microgrid based on iterative double auction and blockchain
- 1 September 2021
- Published by Elsevier in Sustainable Energy, Grids and Networks
- Vol. 27
Peer-to-Peer energy trading in a microgrid based on iterative double auction and blockchain
- 30 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2261-2266
Research on Collaborative optimization Decision Method of Source-Grid-Load-Storage
Significant changes have taken place in power grid regulation resources and power balance characteristics of the power grid, and there is an urgent need to explore regulation techniques suitable for the participation of a wide range of load-side resources. In this paper, based on the needs of power grid scheduling, combined with the control characteristics of electric vehicles, load aggregators, energy storage and other resources, the optimal allocation strategy of source grid load storage resources in different scenarios is studied to provide technical support for incorporating load-side resources into grid coordinated scheduling. It is beneficial to enriching the grid’s plan and arrangement and operation adjustment methods within the day, promoting the friendly interaction of the source grid and storage and the improvement of the power balance of the grid, and can further enhance the grid’s ability and flexibility to respond to emergencies.
- 30 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2261-2266
Research on Collaborative optimization Decision Method of Source-Grid-Load-Storage
Significant changes have taken place in power grid regulation resources and power balance characteristics of the power grid, and there is an urgent need to explore regulation techniques suitable for the participation of a wide range of load-side resources. In this paper, based on the needs of power grid scheduling, combined with the control characteristics of electric vehicles, load aggregators, energy storage and other resources, the optimal allocation strategy of source grid load storage resources in different scenarios is studied to provide technical support for incorporating load-side resources into grid coordinated scheduling. It is beneficial to enriching the grid’s plan and arrangement and operation adjustment methods within the day, promoting the friendly interaction of the source grid and storage and the improvement of the power balance of the grid, and can further enhance the grid’s ability and flexibility to respond to emergencies.
- Open Access
Anomaly Detection of Power Plant Equipment Using Long Short-Term Memory Based Autoencoder Neural Network
Anomaly detection is of great significance in condition-based maintenance of power plant equipment. The conventional fixed threshold detection method is not able to perform early detection of equipment abnormalities. In this study, a general anomaly detection framework based on a long short-term memory-based autoencoder (LSTM-AE) network is proposed. A normal behavior model (NBM) is established to learn the normal behavior patterns of the operating variables of the equipment in space and time. Based on the similarity analysis between the NBM output distribution and the corresponding measurement distribution, the Mahalanobis distance (MD) is used to describe the overall residual (OR) of the model. The reasonable range is obtained using kernel density estimation (KDE) with a 99% confidence interval, and the OR is monitored to detect abnormalities in real-time. An induced draft fan is chosen as a case study. Results show that the established NBM has excellent accuracy and generalizability, with average root mean square errors of 0.026 and 0.035 for the training and test data, respectively, and average mean absolute percentage errors of 0.027%. Moreover, the abnormal operation case shows that the proposed framework can be effectively used for the early detection of abnormalities.
Open AccessAnomaly Detection of Power Plant Equipment Using Long Short-Term Memory Based Autoencoder Neural Network
Anomaly detection is of great significance in condition-based maintenance of power plant equipment. The conventional fixed threshold detection method is not able to perform early detection of equipment abnormalities. In this study, a general anomaly detection framework based on a long short-term memory-based autoencoder (LSTM-AE) network is proposed. A normal behavior model (NBM) is established to learn the normal behavior patterns of the operating variables of the equipment in space and time. Based on the similarity analysis between the NBM output distribution and the corresponding measurement distribution, the Mahalanobis distance (MD) is used to describe the overall residual (OR) of the model. The reasonable range is obtained using kernel density estimation (KDE) with a 99% confidence interval, and the OR is monitored to detect abnormalities in real-time. An induced draft fan is chosen as a case study. Results show that the established NBM has excellent accuracy and generalizability, with average root mean square errors of 0.026 and 0.035 for the training and test data, respectively, and average mean absolute percentage errors of 0.027%. Moreover, the abnormal operation case shows that the proposed framework can be effectively used for the early detection of abnormalities.
- Open Access
Iterative Auction for P2P Renewable Energy Trading with Dynamic Energy Storage Management
In this paper, a peer-to-peer (P2P) renewable energy trading mechanism for microgrids when energy suppliers are equipped with storage devices is studied. A dynamic energy storage management strategy based on the local trading price is proposed and each supplier decides the amount of energy to be sold and stored in real time. An iterative auction algorithm is presented to obtain the market equilibrium and optimal energy allocation schedule. The economic analysis of introducing energy storage devices in this trading market is further studied. Numerical examples of two 7 × 24-h energy trading scenarios with 20 consumers and 20 solar energy producers are used to illustrate the feasibility of this proposed trading mechanism, with sensitivity analysis of different parameters on social welfare. A comparison of the hourly optimal local trading price of these two markets is demonstrated to explain the dynamic process. It is found that in those days with high solar radiation, compared with the market with no storage device, the total cost for buyers in the market when storage devices are used shows a decline of 1.52% and the total profit for sellers shows an increase of 1.27%, which leads to a substantial relative improvement of 118.94% in the overall social welfare. Moreover, a brief economic analysis shows that the advantage of using energy storage in this example is guaranteed after five years of operation. Longer operation time does not mean more benefits considering the deterioration of battery packs and increase of operation and maintenance costs, and the profit reaches its maximum value at the 15th year.
Open AccessIterative Auction for P2P Renewable Energy Trading with Dynamic Energy Storage Management
In this paper, a peer-to-peer (P2P) renewable energy trading mechanism for microgrids when energy suppliers are equipped with storage devices is studied. A dynamic energy storage management strategy based on the local trading price is proposed and each supplier decides the amount of energy to be sold and stored in real time. An iterative auction algorithm is presented to obtain the market equilibrium and optimal energy allocation schedule. The economic analysis of introducing energy storage devices in this trading market is further studied. Numerical examples of two 7 × 24-h energy trading scenarios with 20 consumers and 20 solar energy producers are used to illustrate the feasibility of this proposed trading mechanism, with sensitivity analysis of different parameters on social welfare. A comparison of the hourly optimal local trading price of these two markets is demonstrated to explain the dynamic process. It is found that in those days with high solar radiation, compared with the market with no storage device, the total cost for buyers in the market when storage devices are used shows a decline of 1.52% and the total profit for sellers shows an increase of 1.27%, which leads to a substantial relative improvement of 118.94% in the overall social welfare. Moreover, a brief economic analysis shows that the advantage of using energy storage in this example is guaranteed after five years of operation. Longer operation time does not mean more benefits considering the deterioration of battery packs and increase of operation and maintenance costs, and the profit reaches its maximum value at the 15th year.
- Open Access
An Intelligent Fault Diagnosis Method for Bearings with Variable Rotating Speed Based on Pythagorean Spatial Pyramid Pooling CNN
Deep learning methods have been introduced for fault diagnosis of rotating machinery. Most methods have good performance when processing bearing data at a certain rotating speed. However, most rotating machinery in industrial practice has variable working speed. When processing the bearing data with variable rotating speed, the existing methods have low accuracies, or need complex parameter adjustments. To solve this problem, a fault diagnosis method based on continuous wavelet transform scalogram (CWTS) and Pythagorean spatial pyramid pooling convolutional neural network (PSPP-CNN) is proposed in this paper. In this method, continuous wavelet transform is used to decompose vibration signals into CWTSs with different scale ranges according to the rotating speed. By adding a PSPP layer, CNN can process CWTSs in different sizes. Then the fault diagnosis of variable rotating speed bearing can be carried out by a single CNN model without complex parameter adjustment. Compared with a spatial pyramid pooling (SPP) layer that has been used in CNN, a PSPP layer locates as front layer of CNN. Thus, the features obtained by PSPP layer can be delivered to convolutional layers for further feature extraction. According to experiment results, this method has higher diagnosis accuracy for variable rotating speed bearing than other methods. In addition, the PSPP-CNN model trained by data at some rotating speeds can be used to diagnose bearing fault at full working speed.
Open AccessAn Intelligent Fault Diagnosis Method for Bearings with Variable Rotating Speed Based on Pythagorean Spatial Pyramid Pooling CNN
Deep learning methods have been introduced for fault diagnosis of rotating machinery. Most methods have good performance when processing bearing data at a certain rotating speed. However, most rotating machinery in industrial practice has variable working speed. When processing the bearing data with variable rotating speed, the existing methods have low accuracies, or need complex parameter adjustments. To solve this problem, a fault diagnosis method based on continuous wavelet transform scalogram (CWTS) and Pythagorean spatial pyramid pooling convolutional neural network (PSPP-CNN) is proposed in this paper. In this method, continuous wavelet transform is used to decompose vibration signals into CWTSs with different scale ranges according to the rotating speed. By adding a PSPP layer, CNN can process CWTSs in different sizes. Then the fault diagnosis of variable rotating speed bearing can be carried out by a single CNN model without complex parameter adjustment. Compared with a spatial pyramid pooling (SPP) layer that has been used in CNN, a PSPP layer locates as front layer of CNN. Thus, the features obtained by PSPP layer can be delivered to convolutional layers for further feature extraction. According to experiment results, this method has higher diagnosis accuracy for variable rotating speed bearing than other methods. In addition, the PSPP-CNN model trained by data at some rotating speeds can be used to diagnose bearing fault at full working speed.