Fan Wu

Fan Wu

Auto-generated profile, based on publicly available information

Fan Wu

Chengdu University of Technology

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
9 January 2024 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
FWFan Wu
Fan Wu
KCKai Chen
Kai Chen
Gen QiuGen Qiu
Gen Qiu
WZWenjian Zhou
Wenjian Zhou
Data-driven methods have shown promising performance in power converter fault diagnosis. However, the existing methods are bothered by the inadequacy of accuracy and robustness, due to the feature variation in the different operating points, especially in nonstationary fault signals. This article proposes a robust data-driven fault diagnosis method combining automatic feature extraction (AFE) and improved random forests (IRFs). In AFE, this method uses optimal discrete wavelet transform, optimized by the defined information component function, to extract multiresolution time-frequency features from nonstationary fault signals, and the improved ReliefF algorithm is used to select important fault features considering both the independent and interactive weights to overcome nonstationary influence. To enhance the robustness, the IRFs adjusts the weight of decision trees by robustness testing based on out-of-bag data, which extracts the mapping relationship between fault features and fault labels for fault location. The comparative experimental results show that the proposed method achieves 99.94% fault diagnosis accuracy, and has superior fault diagnosis robustness compared to existing methods.

1 April 2026 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
JZJiusi Zhang
Jiusi Zhang
KCKai Chen
Kai Chen
FWFan Wu
Fan Wu
Gen QiuGen Qiu
Gen Qiu
YCYuhua Cheng
Yuhua Cheng
Shen YinShen Yin
Shen Yin
As the core component of modern power electronic systems, power converters have widespread applications in renewable energy generation, smart grids, and aerospace. The open-circuit fault of power converters is highly concealed and easily derived from secondary faults, whose diagnosis technology has become a key research direction to ensure safe operation. Considering that power converters usually need to operate under different load conditions and complex environments, it is of great significance to achieve efficient open-circuit fault diagnosis while protecting data privacy. Therefore, this article proposes an open-circuit fault diagnosis approach for power converters from the perspective of source-free domain adaptation. In detail, this article proposes an attention-guided power converter fault diagnosis model to enhance the ability to capture key features. Without the need for source domain data to participate in joint training, this article proposes a dynamic clustering loss to achieve pseudolabel generation and iterative self-training, so that the model can make full use of target domain data. Furthermore, this article proposes uncertainty entropy loss and diversity entropy loss to decrease the uncertainty of fault diagnosis output while preventing the model from being over-confident. To demonstrate the reliability of the open-circuit fault diagnosis methodology, this research implements a functional power conversion system.

4 December 2024 in IEEE Transactions on Power Electronics
Verified
Journal Article
Closed access
FWFan Wu
Fan Wu
KCKai Chen
Kai Chen
Gen QiuGen Qiu
Gen Qiu
HYHao Ying
Hao Ying
HSHanmin Sheng
Hanmin Sheng
YWYifan Wang
Yifan Wang
The data-driven fault diagnosis method, which eliminates the need for additional sensors while preserving the system's original structure, offers a promising approach to enhancing converter reliability. However, diagnosing multiple device faults presents significant challenges due to difficulties in fault sample acquisition, detectability uncertainty, and unexplained decisions. This article addresses these challenges by presenting a detectability-based data-driven fault diagnosis method. First, a model-based fault detectability analysis method is proposed to establish the measurement conditions necessary for reliably detecting various fault types. Utilizing these measurement condition constraints, a mechanism-enhanced neural network is designed to locate faults by fitting the changes in fault parameters. The consistency between the fitting fault parameters and the actual fault process ensures the interpretability of the diagnosis results. Additionally, by guaranteeing the identification of fault parameters, the fault circuit model assists in training, significantly reducing the number of actual fault samples required for mechanism-enhanced neural network training. Finally, experiments on a representative converter are conducted to verify the effectiveness of the proposed method. Comparisons with state-of-the-art techniques show the proposed scheme's superiority in terms of diagnostic accuracy, decision explainability, sample dependence.

4 September 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
HGHang Geng
Hang Geng
YWYifan Wang
Yifan Wang
KCKai Chen
Kai Chen
YCYuhua Cheng
Yuhua Cheng
FWFan Wu
Fan Wu
The Duffing chaotic system serves as an excellent tool for detecting single frequency weak signals obscured by strong noises, but exhibits poor performance when it comes to the multi-frequency case which is pervasive in numerous engineering applications. By introducing a nonlinear damping term into the original system, this paper establishes an enhanced Duffing chaotic system to surmount this issue whose minimum detectable Signal-to-Noise Ratio (SNR) is largely improved compared with that of the traditional Duffing chaotic system. Based on the Poincar´e map, a quantitative phase state judgment method is proposed to reduce the computational complexity required for phase state determination, and an automatic multi-frequency weak signal detection method is finally formulated by further resorting to a frequency shift module. Experiment results show that this proposed method can detect multi-frequency weak signals with an SNR of -31 dB with the maximum frequency measurement relative error of 0.15%, showing the effectiveness and advantage of the proposed weak detection method.

17 April 2026 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
Gen QiuGen Qiu
Gen Qiu
SYShang Yang
Shang Yang
JZJiusi Zhang
Jiusi Zhang
FWFan Wu
Fan Wu
Hao LuoHao Luo
Hao Luo
LFLeopoldo Franquelo
Leopoldo Franquelo
Power electronic systems serve as core infrastructure for modern energy conversion and power control. Their reliability is crucial for the stable operation of key fields, such as industrial power systems, transportation, and aerospace. Open-circuit faults are difficult to detect, which can lead to serious consequences. While effective in data-rich environments, existing data-driven approaches’ reliance on extensive labeled data hinders their practical deployment. The reason is that acquiring comprehensive fault data in real-world settings is often prohibitively expensive. To address this, this article proposes a dual Bayesian zero-shot fault diagnosis approach based on prior-knowledge injected with attention mechanism (PKIDBAAM). This approach constructs a fault attribute space with clear physical meaning by analyzing the physical relationship between the Vienna rectifier topology and fault modes. It employs a multihead attention mechanism to dynamically fuse multidomain fault features from three-phase current signals. A dual Bayesian inference framework combining naive Bayes and integrated multiple Gaussian Bayesian algorithms is designed to achieve high accuracy recognition of inaccessible open-circuit faults. The verification results on a Vienna rectifier experimental platform show that it significantly outperforms conventional classical machine learning models, which provides a new solution for intelligent fault diagnosis in power electronic systems.

1 August 2019
Verified
Conference Paper
Closed access
FLFei Li
Fei Li
YHYao Huang
Yao Huang
FWFan Wu
Fan Wu
Xin ZhangXin Zhang
Xin Zhang
WZWei Zhao
Wei Zhao