Baohua Wang

Prof. Dr. Baohua Wang

School of Electrical Engineering, Beijing Jiaotong University, Beijing, China
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
1 January 2025 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
XWXuan Wang
Xuan Wang
XWXilian Wang
Xilian Wang
ZHZhuliang Huang
Zhuliang Huang
BWBaohua Wang
Baohua Wang
RYRuikang Yang
Ruikang Yang
Traditional proportion integration differentiation (PID) controller is difficult to solve the contradiction between response speed and overshoot, and its anti-interference ability is limited. To solve the problem, an integrated control strategy of bearingless switched reluctance motor based on active disturbance rejection control (ADRC) is proposed. A first-order speed ADRC controller and a second-order displacement ADRC controller are designed for direct instantaneous torque control and direct instantaneous force control system, respectively. With the integral time-weighted absolute error (ITAE) as the optimization objective, the particle swarm optimization algorithm is used to tune the main parameters of the ADRC controllers, overcoming the drawbacks of adjusting parameters manually, such as complex operation and time consumption. Simulations and experiments are carried out. The results demonstrate that the control strategy has superior dynamic and static response performance in both speed and displacement control and has good application prospects.

13 February 2025 in IEEE Transactions on Transportation Electrification
Verified
Journal Article
Closed access
RWRenyu Wang
Renyu Wang
ZGZhang Gang
Zhang Gang
WXWei Xiong
Wei Xiong
BWBaohua Wang
Baohua Wang
WWWei Wei
Wei Wei
MWMing Wei
Ming Wei
In the traction power supply system (TPSS) of urban rail transit, heavy load fluctuation and the dynamically changing system structure are inherent. Traditional power flow (PF) calculation based on Newton-Raphson (N-R) method frequently experiences non-convergence issues, resulting in severe ill-conditioned PF scenarios. It impedes accurate deduction and analysis of the operational state. This article offers a thorough examination of the TPSS under ill-conditioned PF scenarios and proposes an enhanced approach to PF calculation. First, a thorough analysis is conducted to identify the primary factors contributing to ill-conditioned PF under three typical circumstances: improper initial value, nonlinear characteristics, and large system scale. It uncovers the fundamental causes of ill-conditioned PF in urban rail systems, thereby providing opportunities for enhancing the PF algorithm. Subsequently, an improved PF algorithm is adopted that integrates the Levenberg-Marquardt (L-M) method. This approach leverages the convergence advantages of the L-M method near singular points to refine the iterative step update strategy in the N-R method. Finally, simulation and field test demonstrates that the proposed method not only ensures calculation accuracy but also significantly enhances convergence speed and simulation efficiency. This article contributes valuable perspectives and approaches for enhancing algorithms in PF calculation, thus facilitating the stable operation of urban rail systems.

3 January 2026 in Neurocomputing
Verified
Journal Article
Closed access
SDShouxin Du
Shouxin Du
QTQingbin Tong
Qingbin Tong
XJXuedong Jiang
Xuedong Jiang
BWBaohua Wang
Baohua Wang
FLFang Liu
Fang Liu
JHJingyi Huo
Jingyi Huo

13 May 2026 in Sensors
Verified
Journal Article
Open access
PDF file
JXJianjun Xu
Jianjun Xu
QTQingbin Tong
Qingbin Tong
RZRuize Zhu
Ruize Zhu
SDShouxin Du
Shouxin Du
JZJilong Zhao
Jilong Zhao
BWBaohua Wang
Baohua Wang
Few-shot fault diagnosis of intelligent high-speed train components remains challenging because fault samples are scarce and highly imbalanced. To address this issue, this paper proposes MR-DDIM, a class-conditional diffusion-based data augmentation framework for generating high-fidelity fault vibration signals from limited labeled data. A WT-UNet denoising backbone is developed by combining one-dimensional wavelet convolution with Feature-Wise Linear Modulation (FiLM) to capture multiscale time–frequency structures and enable class-controllable generation. To improve training stability and spectral fidelity, log-σ regularization and a multi-resolution STFT consistency loss are introduced into the optimization process. In addition, this paper proposed the multi-resolution spectral correlation coefficient (MR-SCC) and class-intrinsic maximum mean discrepancy (cMMD) to evaluate generation quality from spectral and distributional perspectives. Experiments on the BJTU-RAO datasets show that the proposed method can generate fault samples with high spectral consistency and reasonable intra-class diversity, thereby improving the robustness of downstream few-shot fault diagnosis. The results indicate that MR-DDIM provides an effective data augmentation solution for intelligent fault diagnosis in high-speed railway systems.

11 June 2025 in Electronics
Verified
Journal Article
Open access
PDF file
KZKaiyu Zhang
Kaiyu Zhang
BWBaohua Wang
Baohua Wang
HCHongyan Chen
Hongyan Chen
HPHuaijun Peng
Huaijun Peng
LXLei Xue
Lei Xue
YLYuzhang Liu
Yuzhang Liu
This paper explores the application of artificial intelligence in urban energy infrastructure construction and enhances the operation and maintenance safety of infrastructure through edge computing and advanced sensors. At present, urban manhole covers cover a large number of roads, but there is a lack of effective real-time monitoring methods. In order to effectively solve these problems, this study proposes a domain adaptive network algorithm (EDDNet) based on data fusion. By optimizing the loss function, the attention mechanism is used to make the model pay more attention to the deep features related to the abnormal state of the inspection cover. The algorithm solves the problem of broadband vibration analysis and reduces the misclassification rate in various behavioral scenarios, including pedestrian traffic, slow-moving vehicles, and intentional surface collisions. A data acquisition sensor network is established, and a six-degree-of-freedom coupled vibration model and a structural vibration model of the inspection cover are established. The vibration peak under high load conditions is modeled and simulated using impact load data, and a fitting curve is generated to achieve deep optimization of the model and enhance robustness. The experimental results show that the classification accuracy of the network reaches 95.23%, which is at least 10.2% higher than the baseline model.

23 February 2022
Verified
Book Chapter
Closed access
PDF file
WMWenhua Ma
Wenhua Ma
XWXin Wang
Xin Wang
BWBaohua Wang
Baohua Wang