FDFeng Deng

Feng Deng

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Feng Deng has a total of 27 co-authors. Here are the top co-authors by number of shared publications:

  • Xiangjun Zeng

    Hunan Province Key Laboratory of Smart Grids Operation and Control, School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha, China

    3 shared publications
  • Gongping Wu

    College of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha, China

    2 shared publications
  • Wenshan Feng

    School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha, China

    2 shared publications
  • Zhiwen Huang

    School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha, China

    2 shared publications
  • Zhuo Long

    College of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha, China

    2 shared publications
  • Dongli Jia

    China Electric Power Research Institute Company Ltd., Haidian, Beijing, China

    1 shared publication

Latest Publications

  • Open Access

    A Single-Ended Fault Location Method for DC Transmission Lines Based on Inverse Distance Weighted Interpolation

    by Dongli Jia, Xiaoyu Yang, Kaiyuan He, Feng Deng, Zhentong Wang, Tianle Li

    The accuracy and reliability of single-ended fault location methods are often affected by boundary elements and transition resistances. This paper proposes a single-ended fault location method for DC transmission lines based on the initial traveling wave dominant frequency (ITWDF) attenuation characteristics. Firstly, the attenuation characteristics of the initial traveling wave frequency component are analyzed, and the attenuation law and distribution differences between the frequency component and fault distance are revealed. Secondly, to accurately extract and describe the trend of the initial traveling wave frequency component with the change of fault distance, the energy of the initial traveling wave is constructed, and the mathematical expression of the ITWDF related to the fault distance and unit length distortion coefficient is obtained. Theoretical analysis verifies that the ITWDF exhibits a monotonic attenuation mapping relationship with increasing fault distance. In addition, the attenuation characteristics of the ITWDF are not affected by fault impedance. Finally, a fault sample set containing the ITWDF and reference unit length distortion coefficients at different positions is constructed. The fault location is calculated using the ITWDF and the reference unit length distortion coefficient, with continuous wavelet transform and inverse distance weighting interpolation algorithms applied, respectively. Simulation results show that the proposed method can reliably locate faults under high-impedance conditions of up to 800Ω, and the absolute error is less than 200m. Moreover, the proposed method can be applied to DC lines with various boundary structures, improving the reliability of single-ended fault location.


  • Parallel Spatial-Temporal Graph Attention Network for Short Term Multi-Sequence Load Forecasting

    by Zhuo Long, Zhiyuan Xu, Gongping Wu, Feng Deng, Xiangyuan Chen, Wenshan Feng, Zhiwen Huang

    Short-term load forecasting is a crucial task within the power system. However, existing studies have overlooked the spatial-temporal relationships between multiple series loads. Accounting for this spatial-temporal adjacency can lead to more accurate forecasting in certain scenarios. In this paper, we propose a short-term load forecasting model named Parallel Spatial-Temporal Graph Attention Network (PST-GAT). The method encodes the multi-sequence loads as nodes and constructs the adjacency matrix using the Dynamic Time Warping (DTW) technique to form a fully connected graph of the load data. Combining the sliding window concept, the constructed fully connected graph is partitioned into a series of subgraphs, and the Graph Attention Network (GAT) performs feature extraction on each subgraph individually. To realize learning at multiple scales, PST-GAT adopts a parallel multi-branching approach, where each branch splits the subgraphs with varying lengths. Finally, the feature vectors extracted by each branch are concatenated, and forecasting is accomplished using a fully connected layer. Moreover, the unique structural design of PST-GAT allows for the simultaneous prediction of multiple sequence loadings. Experimental results based on real-world load data validate the superior prediction accuracy of this method compared to existing algorithms.


  • Motor Diagnosis Based on 3-D Spherical Projected Point Cloud

    by Zhuo Long, Zhiyuan Xu, Gongping Wu, Feng Deng, Meidi Sun, Ming-Hao Wang, Zhiwen Huang, Wenshan Feng

    The frequent occurrence of motor faults has been a great disturbance to the development of production in various fields. Traditional fault diagnosis methods primarily use 1-D data or 2-D data. However, 3-D data holds significant promise for motor fault diagnosis due to its voluminous data and unique spatial information. This paper aims to explore a motor fault diagnosis method leveraging 3-D data. Nonetheless, motor fault 3-D data exhibits the limitation of lacking geometric structure. To address this limitation, This paper proposes a fault diagnosis method named SP-PointCNN. This method utilizes the proposed spherical projection (SP) method to mitigate the limitations present in the 3D data of the motor. Meanwhile, a neural network based on PointCNN is constructed to enable the utilization of 3D data in fault diagnosis. A series of experiments demonstrated the validity of the proposed method. After tested, the diagnosis accuracy of SP-PointCNN can reach 99.36%.

  • A Single-Ended Fault Location Method for Transmission Line Based on Full Waveform Features Extractions of Traveling Waves

    by Feng Deng, Yihan Zhong, Zhe Zeng, Yarui Zu, Zhen Zhang, Yifei Huang, Sixu Feng, Xiangjun Zeng

    Conventional single-ended traveling wave fault location methods, which commonly depend on partial features of traveling wavefronts, may lead to fault location failure, especially for weak-signal faults such as high impedance or zero-crossing faults and close-in faults. To tackle it, this paper presents a fault location method according to the extracted panoramic features of traveling wave full waveform (TWFW) in time-frequency domains. Firstly, two rules of the TWFW features are probed, that is, the wavefront arrival sequence is varied from fault sections, as well as the frequency distribution of wavefronts is strongly related to the precise fault distance. Ergo, the mapping relationships between the TWFW and fault distance are qualitatively confirmed in order to demonstrate the uniqueness of the TWFW subsequently. Next, a LeNet-5-based convolution neural network (CNN) model is constructed to quantitatively evaluate such mapping relationships. In this model, various TWFW features will be extracted to the convolution channels when the CNN parameters are optimized adaptively, and the mapping relations can be formed in light of these sensitive features to estimate the fault distance. Finally, a Grad-CAM visualization method is deployed in the case study, and the accuracy along with the robustness of the proposed method in various fault conditions can be validated consequently.


  • Open Access

    Single‐ended travelling wave protection algorithm based on full waveform in the time and frequency domains

    by Feng Deng, Xinran Li, Xiangjun Zeng

    Single‐ended travelling‐wave‐based protection has been available for several years, providing the advantages of low cost and no requirement for communication and synchronisation with the remote end. However, conventional single‐ended travelling‐wave‐based protection has low reliability due to its use of only partial fault information, and it has high dependence on extracting a second reflected wavefront. A new single‐ended travelling‐wave‐based protection algorithm using the 2 ms full‐waveform post‐fault signal in the time–frequency domain, which avoids the discrimination of the reflected wavefront, is presented. First, the full‐waveform representation of the travelling wave in 3D subspace is proposed. The fault characteristics of the wideband travelling wave are analysed at different scales. Second, for faults that occur within one line or on adjacent lines, the propagation characteristics and reflection and refraction process are analysed in detail. Then, the correlation and difference of the full waveform are presented qualitatively and quantitatively. Finally, a time–frequency spectrum matrix is established based on the full waveform, and the protection algorithm is developed by using a time–frequency spectrum matrix and wave matching technology. Extensive simulations under different conditions verify the wide applicability and high reliability of the proposed algorithm.


  • Open Access

    Research on multi-terminal traveling wave fault location method in complicated networks based on cloud computing platform

    by Feng Deng, Xiangjun Zeng, Lanlan Pan

    Cloud computing technology is used in traveling wave fault location, which establishes a new technology platform for multi-terminal traveling wave fault location in complicated power systems. In this paper, multi-terminal traveling wave fault location network is developed, and massive data storage, management, and algorithm realization are implemented in the cloud computing platform. Based on network topology structure, the section connecting points for any lines and corresponding detection placement in the loop are determined first. The loop is divided into different sections, in which the shortest transmission path for any of the fault points is directly and uniquely obtained. In order to minimize the number of traveling wave acquisition unit (TWU), multi-objective optimal configuration model for TWU is then set up based on network full observability. Finally, according to the TWU distribution, fault section can be located by using temporal correlation, and the final fault location point can be precisely calculated by fusing all the times recorded in TWU. PSCAD/EMTDC simulation results show that the proposed method can quickly, accurately, and reliably locate the fault point under limited TWU with optimal placement.