Wenshan Feng

Ms. Wenshan Feng

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 August 2024 in Energies
Verified
Journal Article
Open access
PDF file
ZMZhuoyao Miao
Zhuoyao Miao
WFWenshan Feng
Wenshan Feng
ZLZhuo Long
Zhuo Long
GWgongping wu
gongping wu
LDLe Deng
Le Deng
LXLiwei Xie
Liwei Xie
In order to reduce the influence of environmental noise and different operating conditions on the accuracy of motor fault diagnosis, this paper proposes a capsule network method combining multi-channel signals and the efficient channel attention (ECA) mechanism, sampling the data from multiple sensors and visualizing the one-dimensional time-frequency domain as a two-dimensional symmetric dot pattern (SDP) image, then fusing the multi-channel image data and extracting the image using a capsule network combining the ECA attention mechanism features to match eight different fault types for fault classification. In order to guarantee the universality of the suggested model, data from Case Western Reserve University (CWRU) is used for validation. The suggested multi-channel signal fusion ECA attention capsule network (MSF-ECA-CapsNet) model fault identification accuracy may reach 99.21%, according to the experimental findings, which is higher than the traditional method. Meanwhile, the method of multi-sensor data fusion and the use of the ECA attention mechanism make the diagnosis accuracy much higher.

16 March 2026 in Measurement Science and Technology
Verified
Journal Article
Closed access
ZLZhuo Long
Zhuo Long
WFWenshan Feng
Wenshan Feng
GWgongping wu
gongping wu
MWMing-Hao Wang
Ming-Hao Wang
HWHui Wang
Hui Wang
XZXuan Zhou
Xuan Zhou
In response to the challenge of effectively integrating time-frequency domain information while enhancing the richness of fault information in motor vibration signal feature extraction, this paper introduces a novel fault diagnosis method based on Chladni pattern visualization and deep feature matching. The approach begins by converting one-dimensional vibration signals into two-dimensional Chladni images, which not only preserve critical time-frequency characteristics but also intuitively display distinct resonance patterns corresponding to different fault types.Next, deep learning-based feature extraction and matching techniques—SuperPoint and SuperGlue—are employed to identify and match salient image features, establishing a robust mapping relationship between specific fault conditions and Chladni pattern. Andexperimental results demonstrate that the proposed method achieves a diagnostic accuracy of 98%, significantly outperforming traditional image-matching algorithms. This technology offers an efficient and highly applicable solution for motor fault detection and monitoring, particularly in smart industrial settings where accuracy and real-time performance are critical.