Yongqi Chang

Dr. Yongqi Chang

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
13 March 2024 in IET Power Electronics
Verified
Journal Article
Open access
Huamin JieHuamin Jie
Huamin Jie
ZZZhenyu Zhao
Zhenyu Zhao
YZYu Zeng
Yu Zeng
Yongqi ChangYongqi Chang
Yongqi Chang
FFFei Fan
Fei Fan
SSSee See
See See
With the advancements in Industry 4.0 and the global demand for sustainable energy, power electronics devices are emerging as pivotal components for modern industrial, transportation, and energy delivery. Ensuring the security of these devices is of paramount importance for safeguarding the reliable operation of critical systems against any threats. In recent years, the issue of intentional electromagnetic interference (IEMI) attack and their related countermeasures have gained widespread attention in both military and civilian power electronics sectors. Here, a review of IEMI in power electronics is provided. Starting from the electromagnetic compatibility standards, the test setups for evaluating the device immunity are introduced. Due to different attack modes and propagation paths, IEMI illuminations are typically categorized into conduction and radiation, where their susceptibility studies, applications, and defence strategies are discussed, respectively. Finally, the existing challenges, ongoing trends, and future topics in this field are discussed.

5 February 2025 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
CWChangdong Wang
Changdong Wang
ZSZhou Shu
Zhou Shu
JYJingli Yang
Jingli Yang
ZZZhenyu Zhao
Zhenyu Zhao
Huamin JieHuamin Jie
Huamin Jie
SSSee See
See See
To alleviate data distribution under different operating conditions, domain generalization (DG) has been applied in mechanical diagnosis. Still, its effectiveness is limited when unknown fault states appear in the target domain. Consequently, open set DG (OSDG) has emerged to identify unknown classes in unknown domains. However, data collection costs and safety concerns have resulted in a significant class imbalance in OSDG. This imbalance causes the decision boundary to be skewed toward abundant positive classes, ultimately leading to misclassifying unknown states and increasing security risks. Currently, there is a lack of methods to simultaneously address domain shift and class shift in an imbalanced unknown domain. To tackle this issue, this article proposes a multisource domain-class gradient coordination meta-learning (MDGCML) framework, which can learn the generalized boundaries of all tasks by coordinating gradients between interdomains and interclasses. Based on the MDGCML, a joint learning paradigm involving the sharing of parameters between open-set classifiers and closed-set classifiers is constructed to enable quick adaption of the model to unknown domains. The superior performance of the proposed framework has been verified on two datasets.

3 September 2024 in IEEE Transactions on Power Electronics
Verified
Journal Article
Closed access
Huamin JieHuamin Jie
Huamin Jie
ZZZhenyu Zhao
Zhenyu Zhao
HLHong Li
Hong Li
CWChangdong Wang
Changdong Wang
Yongqi ChangYongqi Chang
Yongqi Chang
SSSee See
See See
With the evolution of Industry 4.0 and the surge in demand for sustainable energy, power electronics are becoming essential in various applications. Considering the reliability and safety of power electronics devices, studying and addressing the conducted electromagnetic interference (EMI) issues are of paramount importance. Due to the merits of versatility, flexibility, and effectiveness, passive filters containing EMI filtering chokes and capacitors are commonly used. Among them, EMI filtering chokes have been widely investigated in recent years because they account for most of the weight and size of a passive filter and mitigate considerable EMI noises. To the best of our knowledge, this article presents the first review of EMI filtering chokes used in power electronics that specifically focuses on their characterization and circuit modeling. These topics help to evaluate choke performance, optimize choke configuration, and facilitate systematic simulation, ultimately refining filtering design. Starting with an overview, the type, structure, principles, information, and modes of chokes are demonstrated. For choke characterization, various analytical, numerical, and measurement methods are compared. Using the characterized information, their distributed, lumped, and multistage circuit models along with the relevant parameterization process are summarized. Finally, existing challenges, ongoing innovations, and future topics are explored.

9 July 2020 in Sensors
Verified
Journal Article
Open access
PDF file
JYJingli Yang
Jingli Yang
SYShuangyan Yin
Shuangyan Yin
Yongqi ChangYongqi Chang
Yongqi Chang
TGTianyu Gao
Tianyu Gao
Aiming at the fault diagnosis issue of rotating machinery, a novel method based on the deep learning theory is presented in this paper. By combining one-dimensional convolutional neural networks (1D-CNN) with self-normalizing neural networks (SNN), the proposed method can achieve high fault identification accuracy in a simple and compact architecture configuration. By taking advantage of the self-normalizing properties of the activation function SeLU, the stability and convergence of the fault diagnosis model are maintained. By introducing α -dropout mechanism twice to regularize the training process, the overfitting problem is resolved and the generalization capability of the model is further improved. The experimental results on the benchmark dataset show that the proposed method possesses high fault identification accuracy and excellent cross-load fault diagnosis capability.

23 December 2021 in IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
Verified
Journal Article
Closed access
Yongqi ChangYongqi Chang
Yongqi Chang
XZXin Zhang
Xin Zhang
CLChunhu Lin
Chunhu Lin
JLJinming Liu
Jinming Liu
YSYi Shen
Yi Shen
Recent research studies show that acoustic emission (AE) technologies have great potential in detecting the flattened defects of wheel; however, the wheel-rail rolling interference (WRRI) significantly influences the accuracy of wheel defect detection. Aiming to solve the above-mentioned problem, a novel detection method, which combines an improved synthesized health index (ISHI) with a time adaptive threshold (time-ATH), is proposed in this article. In order to obtain the defect information from the signals generated by the wheels, a completed feature set that contains many types of features is extracted from AE signals. Then, the ISHI is fused by several effective features that are selected from the completed feature set, according to detection rate and accuracy. Besides, a time-ATH calculation is proposed to detect the defective signals of wheels and reduce the influence of the WRRI. The method is fully verified in actual datasets, and the results show that the proposed method achieves a better detection rate and accuracy. Moreover, it provides an effective way for the AE detection of wheel-flattened defects under strong and numerous WRRI.

28 November 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
SSShuzhi Song
Shuzhi Song
XZXin Zhang
Xin Zhang
Yongqi ChangYongqi Chang
Yongqi Chang
YSYi Shen
Yi Shen
The structural health of rails significantly impacts the safety of railway transport, which requires long-term and accurate monitoring. An improved structural health monitoring method is proposed to enhance the damage information and construct an adaptive weighted index for evaluating the structural health states of rails. In this method, a modified singular value decomposition with a double-layer Hankel matrix compensation algorithm enhances the damage information and ensures real-time detection. Based on the inflection point of the inner product gradient, the step-size of the sparsity adaptive matching pursuit algorithm is adaptively adjusted to reconstruct damage signals. Subsequently, an innovative index is constructed with adaptive weighting for structural health monitoring of rails. Tensile tests are performed to verify the effectiveness of the proposed method. The results show that, the proposed method avoids the defects of traditional nondestructive testing techniques that rely on a priori information about the damage signal (such as damage frequency AE hits rate and waveform characteristics). Furthermore, using the variation in signal energy, the proposed method has the capability to accurately delineate the three structural health stages under complex waveform conditions, which is not possible with conventional detection methods. This method provides a guidance for the damage analysis and monitoring techniques of rails.