Huaiyuan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Huaiyuan Wang has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Qifan Chen
Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong
8 shared publications - Nan Lin
State Key Laboratory of Internet of Things for Smart City and the Department of Electrical and Computer Engineering, University of Macau, Macau, China
4 shared publications Buying Wen
Fujian Key Laboratory of New Energy Generation and Power Conversion, College of Electrical Engineering and Automation, Fuzhou University, 350108 China
3 shared publicationsJian Li
State Grid Qinghai Electric Power Company, Xining, China
3 shared publications- Siqi Bu
The Hong Kong Polytechnic University
3 shared publications Baohui Zhang
College of Electrical Engineering, Xian Jiaotong University, Xian, Peoples Republic of China
2 shared publications
Latest Publications
- 24 August 2026
- Published by Elsevier in Sustainable Energy, Grids and Networks
- Vol. 47
Dynamic imbalance correction for transient stability assessment based on interval sample impact norm
- 24 August 2026
- Published by Elsevier in Sustainable Energy, Grids and Networks
- Vol. 47
Dynamic imbalance correction for transient stability assessment based on interval sample impact norm
- 11 June 2026
- Published by Elsevier in Applied Energy
- Vol. 420
Physical information-guided training method for transient voltage stability assessment
- 11 June 2026
- Published by Elsevier in Applied Energy
- Vol. 420
Physical information-guided training method for transient voltage stability assessment
- 10 April 2026
- Published by Elsevier in Measurement
- Vol. 277
The denoising network with embedded physics-informed layers for power systems
- 10 April 2026
- Published by Elsevier in Measurement
- Vol. 277
The denoising network with embedded physics-informed layers for power systems
- 23 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-12
Adaptive Critical Cost-Sensitive Detection of High-Impedance Faults Based on Impedance Criticality
High-impedance fault (HIF) in distribution networks is notoriously difficult to detect, as its high impedance results in weak fault currents that evade conventional protection schemes. In addition, for both HIF and non-HIF samples, the impact of critical samples on the detection rules is regarded as more important than that of non-critical samples. Therefore, a critical cost-sensitive factor distribution (CCFD) method based on impedance criticality is proposed in this study. A higher cost factor is assigned to critical samples than to non-critical samples. To better learn from the misclassified samples and reduce the interference of anomalous samples, an adaptive critical cost-sensitivity factor distribution (ACCFD) method is further proposed. During model training, the distribution factors of consecutively misclassified and correctly classified samples within the critical sample set are adaptively adjusted to optimize the detection rules. Experiments are conducted on a 10 kV distribution network simulation model and a field experiment platform. The results demonstrate that the proposed ACCFD method exhibits high classification accuracy and excellent generalization ability, effectively enhancing the reliability and security of power grids.
- 23 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-12
Adaptive Critical Cost-Sensitive Detection of High-Impedance Faults Based on Impedance Criticality
High-impedance fault (HIF) in distribution networks is notoriously difficult to detect, as its high impedance results in weak fault currents that evade conventional protection schemes. In addition, for both HIF and non-HIF samples, the impact of critical samples on the detection rules is regarded as more important than that of non-critical samples. Therefore, a critical cost-sensitive factor distribution (CCFD) method based on impedance criticality is proposed in this study. A higher cost factor is assigned to critical samples than to non-critical samples. To better learn from the misclassified samples and reduce the interference of anomalous samples, an adaptive critical cost-sensitivity factor distribution (ACCFD) method is further proposed. During model training, the distribution factors of consecutively misclassified and correctly classified samples within the critical sample set are adaptively adjusted to optimize the detection rules. Experiments are conducted on a 10 kV distribution network simulation model and a field experiment platform. The results demonstrate that the proposed ACCFD method exhibits high classification accuracy and excellent generalization ability, effectively enhancing the reliability and security of power grids.
- Open Access
Physics-Informed SDAE-Based Denoising Model for High-Impedance Fault Detection
The accurate detection of high-impedance faults (HIFs) in distribution systems is fundamentally dependent on the extraction of weak fault signatures. However, these features are often obscured by complex and high-level noise present in current transformer (CT) measurement data. To address this challenge, an energy-proportion-guided channel-wise attention stacked denoising autoencoder (EPGCA-SDAE) model is proposed. In this model, wavelet decomposition is employed to transform the signal into informative frequency band components. A channel attention mechanism is utilized to adaptively assign weights to each component, thereby enhancing model interpretability. Furthermore, a physics-informed prior, based on energy distribution, is introduced to guide the loss function and regulate the attention learning process. Extensive simulations using both synthetic and real-world distribution network data are conducted. The superiority of the EPGCA-SDAE over traditional wavelet-based methods, stacked denoising autoencoders (SDAE), denoising convolutional neural network (DnCNN), and Transformer-based networks across various noise conditions is demonstrated. The lowest average mean squared error (MSE) is achieved by the proposed model (simulated: ; real: ), along with enhanced noise robustness, generalization capability, and physical interpretability. These results verify the method’s feasibility within the tested 10 kV distribution system, providing a reliable data recovery framework for fault diagnosis in noise-contaminated distribution network environments.Open AccessPhysics-Informed SDAE-Based Denoising Model for High-Impedance Fault Detection
The accurate detection of high-impedance faults (HIFs) in distribution systems is fundamentally dependent on the extraction of weak fault signatures. However, these features are often obscured by complex and high-level noise present in current transformer (CT) measurement data. To address this challenge, an energy-proportion-guided channel-wise attention stacked denoising autoencoder (EPGCA-SDAE) model is proposed. In this model, wavelet decomposition is employed to transform the signal into informative frequency band components. A channel attention mechanism is utilized to adaptively assign weights to each component, thereby enhancing model interpretability. Furthermore, a physics-informed prior, based on energy distribution, is introduced to guide the loss function and regulate the attention learning process. Extensive simulations using both synthetic and real-world distribution network data are conducted. The superiority of the EPGCA-SDAE over traditional wavelet-based methods, stacked denoising autoencoders (SDAE), denoising convolutional neural network (DnCNN), and Transformer-based networks across various noise conditions is demonstrated. The lowest average mean squared error (MSE) is achieved by the proposed model (simulated: ; real: ), along with enhanced noise robustness, generalization capability, and physical interpretability. These results verify the method’s feasibility within the tested 10 kV distribution system, providing a reliable data recovery framework for fault diagnosis in noise-contaminated distribution network environments. - 4 October 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 162
Hybrid physics-based and data-driven method for the rotor angle prediction
- 4 October 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 162
Hybrid physics-based and data-driven method for the rotor angle prediction
- 13 May 2025
- Published by Elsevier in Electric Power Systems Research
- Vol. 247
Time-adaptive High Impedance Fault Detection Model Based on Cost-sensitive Method
- 13 May 2025
- Published by Elsevier in Electric Power Systems Research
- Vol. 247
Time-adaptive High Impedance Fault Detection Model Based on Cost-sensitive Method
- 26 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
Hybrid Physical-Data Driven Model for Denoising of Generator State Measurements
The measurement data of power systems are often mixed with a lot of noise due to the interference of the external environment. In order to eliminate the effect of noise, it is significant to denoise the noisy data to obtain the real state measurements. To deal with the problem of insufficient interpretability in existing data-driven denoising methods, a hybrid physical-data driven denoising model (PDDM) based on the stacked denoising autoencoder (SDAE) is proposed. First, the prior knowledge is extracted from the physical model of the generator. Physical constraints are designed based on the inherent relationships between rotor angle, angular frequency, and power. Secondly, based on SDAE deep learning model, physical constraints are embedded into the loss function to guide the training of neutral network. The derivatives of denoised data are leveraged in anticipation of satisfying the differential-algebraic equations. The physical process is directly approximated by the neural network in this method, making the outputs satisfy the physical laws. The reliability and interpretability of the denoising results are improved. Meanwhile, the dependence on datasets is reduced by virtue of the hybrid physical-data driven mode. And the robustness is still maintained. Finally, it is verified in the 39-bus new England system and a realistic regional power system. The real noisy data are also taken into account in testing to verify its extensibility. The test results show that the method proposed can achieve satisfactory effect in both denoising accuracy and generalization capability.
- 26 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
Hybrid Physical-Data Driven Model for Denoising of Generator State Measurements
The measurement data of power systems are often mixed with a lot of noise due to the interference of the external environment. In order to eliminate the effect of noise, it is significant to denoise the noisy data to obtain the real state measurements. To deal with the problem of insufficient interpretability in existing data-driven denoising methods, a hybrid physical-data driven denoising model (PDDM) based on the stacked denoising autoencoder (SDAE) is proposed. First, the prior knowledge is extracted from the physical model of the generator. Physical constraints are designed based on the inherent relationships between rotor angle, angular frequency, and power. Secondly, based on SDAE deep learning model, physical constraints are embedded into the loss function to guide the training of neutral network. The derivatives of denoised data are leveraged in anticipation of satisfying the differential-algebraic equations. The physical process is directly approximated by the neural network in this method, making the outputs satisfy the physical laws. The reliability and interpretability of the denoising results are improved. Meanwhile, the dependence on datasets is reduced by virtue of the hybrid physical-data driven mode. And the robustness is still maintained. Finally, it is verified in the 39-bus new England system and a realistic regional power system. The real noisy data are also taken into account in testing to verify its extensibility. The test results show that the method proposed can achieve satisfactory effect in both denoising accuracy and generalization capability.
- Open Access
- 16 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 12002-12013
Physics-Informed Denoising Model for Dynamic Data Recovery of Power Systems
For a variety of applications within power systems, the precision of data acquisition is of paramount importance. However, the actual data may be corrupted by noise in the process of measurement or transmission, and the accuracy of dynamic security assessment (DSA) will be affected. In light of the poor interpretability exhibited by traditional machine learning (ML) methods in denoising, a physics-guided denoising model (PIDM) for dynamic data recovery is proposed. The differential equations of physical models in power systems are employed to guide the training of PIDM. They are transformed into physical constraints and subsequently incorporated into the loss function of stacked denoising autoencoder (SDAE) to cleanse noisy data. By integrating the powerful learning capabilities of ML with the rigorous constraints of physical laws, the noisy data recovered by PIDM can better satisfy the dynamic equations. Consequently, a more pronounced denoising effect can be achieved. The improvement of the PIDM over common ML-based models is explored when dealing with the noisy data with varying degrees of interference or those of unexpected faults. The effectiveness is validated through simulation results in IEEE 39-bus system and the East China power grid. The results show that this method can lead to a minimum enhancement of over 28.68% in the mean square error (MSE) for the total recovery of noisy data compared to traditional methods. In addition to demonstrating superior denoising performance, the generalization capability under diverse noise conditions is also deemed excellent.
- 16 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 12002-12013
Open AccessPhysics-Informed Denoising Model for Dynamic Data Recovery of Power Systems
For a variety of applications within power systems, the precision of data acquisition is of paramount importance. However, the actual data may be corrupted by noise in the process of measurement or transmission, and the accuracy of dynamic security assessment (DSA) will be affected. In light of the poor interpretability exhibited by traditional machine learning (ML) methods in denoising, a physics-guided denoising model (PIDM) for dynamic data recovery is proposed. The differential equations of physical models in power systems are employed to guide the training of PIDM. They are transformed into physical constraints and subsequently incorporated into the loss function of stacked denoising autoencoder (SDAE) to cleanse noisy data. By integrating the powerful learning capabilities of ML with the rigorous constraints of physical laws, the noisy data recovered by PIDM can better satisfy the dynamic equations. Consequently, a more pronounced denoising effect can be achieved. The improvement of the PIDM over common ML-based models is explored when dealing with the noisy data with varying degrees of interference or those of unexpected faults. The effectiveness is validated through simulation results in IEEE 39-bus system and the East China power grid. The results show that this method can lead to a minimum enhancement of over 28.68% in the mean square error (MSE) for the total recovery of noisy data compared to traditional methods. In addition to demonstrating superior denoising performance, the generalization capability under diverse noise conditions is also deemed excellent.