Wensheng Gao

Wensheng Gao

Auto-generated profile, based on publicly available information

Wensheng Gao

Department of Electrical Engineering, Tsinghua University, Beijing 100084, China

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
1 December 2014 in International Journal of Geomechanics
Verified
Journal Article
Closed access
DWDongyuan Wang
Dongyuan Wang
ZGZhirong Gao
Zhirong Gao
JLJeffrey L. Lee
Jeffrey L. Lee
WGWensheng Gao
Wensheng Gao

16 April 2024 in IEEE Transactions on Power Delivery
Verified
Journal Article
Closed access
QSQiang Sun
Qiang Sun
ZZZiwei Zhang
Ziwei Zhang
WGWensheng Gao
Wensheng Gao
DDDengwei Ding
Dengwei Ding
YGYanpeng Ge
Yanpeng Ge
JQJiaqi Qu
Jiaqi Qu
In 3D full-Maxwell simulations of very fast transients (VFTs), both accuracy and simulation efficiency pose challenges. The existing method cannot set simulation conditions appropriately, resulting in subpar simulation accuracy for the VFT process and unnecessary time consumption. Moreover, for the very fast transient overvoltage (VFTO) waveforms estimated by simulations, there is still a lack of specific analysis on waveform characteristics and appropriate verification methods. In this paper, a novel method that significantly improves both the accuracy and the time efficiency of the 3D full-Maxwell simulation of the VFT process is proposed. The wave process generated by breakdown is also analyzed to obtain the VFTO waveform characteristics for subsequent verification. Simulation cases, based on both a simplified GIS model and an actual GIS model, are demonstrated and discussed. Furthermore, a specially designed field test on the typical 1100 kV GIS, taking into account the residual voltage, is conducted for the simulation verification for the first time. The simulation and field test results align well in both the time domain and the time-frequency domain. Additionally, the novelty of this proposed method is demonstrated by comparing it with other existing method in case studies. The accuracy of the method has been shown to improve significantly, and the simulation time consumption can be reduced with the same computational machine and simulation configuration.

25 December 2020 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
HNHamid Esmaeili Najafabadi
Hamid Esmaeili Najafabadi
Henry LeungHenry Leung
Henry Leung
JGJingbo Guo
Jingbo Guo
THTiehua Hu
Tiehua Hu
GCGuang Chang
Guang Chang
WGWenshen Gao
Wenshen Gao
Compressive sensing (CS) has emerged as a promising technique for collecting and reconstructing digital signals. In this article, we design a CS method for magnetic flux leakage (MFL) detectors based on the problem’s physics. A method is presented to reconstruct $x$ and $y$ components of magnetic $\overrightarrow {B}$ field using a few samples. First, the problem is formulated into an optimization framework where the goal is to minimize Euclidean distance between real and reconstructed signals while preserving the CS acquisition criteria. The resulting optimizations are then simplified and solved through the established majorization minimization (MM) method. Meanwhile, a Gaussian sampling strategy is adopted where samples with more information have a higher chance of being selected. Validation of the proposed method is accomplished through the performance comparison among the proposed method and several established high-performance CS techniques on gathered experimental data. The extensive validation of the signals gathered from 17 artificial defects on the 12-m pipe reveals that the signals can be compressed and recovered with exceptional fidelity when the problem’s physical structure is known.

8 January 2026 in Electronics
Verified
Journal Article
Open access
PDF file
WXWei Xiao
Wei Xiao
JJJun Jia
Jun Jia
WGWensheng Gao
Wensheng Gao
HLHaibo Li
Haibo Li
HXHong Xu
Hong Xu
KHKe He
Ke He
In complex energy storage operating scenarios, batteries seldom undergo complete charge–discharge cycles required for periodic capacity calibration. Methods based on accelerated aging experiments can indicate possible aging paths; however, due to uncertainties like changing operating conditions, environmental variations, and manufacturing inconsistencies, the degradation information obtained from such experiments may not be applicable to the entire lifecycle. To address this, we developed a stage-wise state-of-health (SOH) prediction approach that combined offline training with online updating. During the offline training phase, multiple single-cell experiments were conducted under various combinations of depth of discharge (DOD) and C-rate. Multi-dimensional health features (HFs) were extracted, and an accelerated aging probability pAA was defined. Based on the correlation statistics between HFs, kHF, the SOH, and pAA, all cells in the dataset were divided into general early, middle, and late aging stages. For each stage, cells were further classified by their longevity (long, medium, and short), and multiple models were trained offline for each category. The results show that models trained on cells following similar aging paths achieve significantly better performance than a model trained on all data combined. Meanwhile, HF optimization was performed via a three-step process: an initial screening based on expert knowledge, a second screening using Spearman correlation coefficients, and an automatic feature importance ranking using a random forest regression (RFR) model. The proposed method is innovative in the following ways: (1) The stage-wise multi-model strategy significantly improves the SOH prediction accuracy across the entire lifecycle, maintaining the mean absolute percentage error (MAPE) within 1%. (2) The improved model provides uncertainty quantification, issuing a warning signal at least 50 cycles before the onset of accelerated aging. (3) The analysis of feature importance from the model outputs allows the indirect identification of the primary aging mechanisms at different stages. (4) The model is robust against missing or low-quality HFs. If certain features cannot be obtained or are of poor quality, the prediction process does not fail.

16 November 2021 in Energies
Verified
Journal Article
Open access
PDF file
RZRuixu Zhou
Ruixu Zhou
WGWensheng Gao
Wensheng Gao
Weidong LiuWeidong Liu
Weidong Liu
DDDengwei Ding
Dengwei Ding
BZBowen Zhang
Bowen Zhang
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.

14 October 2025 in IEEE Transactions on Power Delivery
Verified
Journal Article
Closed access
YSYang Shao
Yang Shao
ZZZiwei Zhang
Ziwei Zhang
JWJianwen Wu
Jianwen Wu
ZZZiqi Zhou
Ziqi Zhou
WGWensheng Gao
Wensheng Gao
Research on the mechanical fault diagnosis of high voltage circuit breakers (HVCBs) often relies on a single sensor as the data foundation, resulting in issues such as a limited variety of sensor types and insufficient depth in feature evaluation. Therefore, this paper addresses these challenges by considering the sensitivity of sensors to various faults and proposes a novel decision fusion method based on the sensitivity assessment of multiple sensor types at various measurement points. This approach involves constructing a fault sensitivity assessment function using multiple distance metrics and optimizing parameters through the Genetic Algorithm-SoftMax (GA-SoftMax) model. Finally, the SoftMax model is employed to estimate potential fault probabilities, and a novel probability-weighted decision fusion framework is introduced, adjusting diagnostic results based on the fault sensitivity of each sensor. Through a comparative analysis of four typical decision-making scenarios, the diagnostic accuracy of the method proposed in this paper reaches 91.1%, with an F1-Score of 0.98. This represents a substantial improvement over single-sensor approaches, demonstrating superior diagnostic performance compared to other decision fusion framework. This research provides a novel perspective for advancing mechanical fault diagnosis in HVCBs.