Yao Tang

Yao Tang

Auto-generated profile, based on publicly available information

Yao Tang

Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
6 April 2022 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
FHFengqin Huang
Fengqin Huang
XZXiaofei Zhang
Xiaofei Zhang
GQGuojun Qin
Guojun Qin
JXJinping Xie
Jinping Xie
JPJian Peng
Jian Peng
YTYao Tang
Yao Tang
In most industrial applications, it is difficult to obtain complete demagnetization fault signals of all conditions with labels for permanent magnet synchronous motor (PMSM), and motors are not allowed to be disassembled, so non-contact diagnostic methods are essential. A non-contact fault diagnosis method using magnetic leakage signal based on wavelet scattering convolution network (WSCN) and semi-supervised deep rule-based (SSDRB) classifier is proposed. Through magnetic equivalent circuit model analysis, the magnetic leakage signal on motor surface is selected as fault signal. To avoid complex signal processing, the symmetrized dot pattern method is introduced to convert fault signals into two-dimensional images. Then, WSCN is applied to extract features from images, and SSDRB classifier is adopted to diagnose demagnetization fault. Finally, faulty motor prototypes are manufactured for experiment. By comparing with other methods, the superiority and effectiveness of the proposed method using a small number of labeled samples under different conditions are verified.

16 September 2021 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
YTYao Tang
Yao Tang
XZXiaofei Zhang
Xiaofei Zhang
GQGuojun Qin
Guojun Qin
ZLZhuo Long
Zhuo Long
SHShoudao Huang
Shoudao Huang
Haidong ShaoHaidong Shao
Haidong Shao
During the long-term operation of motors, their working conditions are changing due to the industrial demands or declining health status, and traditional diagnosis methods perform poorly in that case. This article proposes a fault diagnosis method based on graph cardinality preserved attention network (GCPAT), which can work under varying working conditions, and can be generalized to the transient state. Diagnosis results are obtained by analyzing signal-converting graphs, which are composed of nodes and edges. First, the vibration signals are converted into symmetrical snowflake images by symmetrized dot pattern (SDP) method. Second, SLIC is developed to make homogeneous super-pixels in SDP images as nodes, and form graphs according to color, texture, and distance features. Finally, the GCPAT is utilized to distinguish motor status. Compared with other state-of-art methods, the results show the out-performance of GCPAT under varying working conditions both in steady and transient state.

21 June 2021 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
YTYao Tang
Yao Tang
XZXiaofei Zhang
Xiaofei Zhang
Yujia ZhaiYujia Zhai
Yujia Zhai
GQGuojun Qin
Guojun Qin
DSDianyi Song
Dianyi Song
ZLZhuo Long
Zhuo Long
Data-driven intelligent diagnosis methods require sufficient labeled data during training, which are usually limited in practice. A semisupervised conditional random field-based graph attention network (CRF-GAT) algorithm is proposed in this article for fault diagnosis and condition monitoring. The proposed method combines the advantages of CRF and GAT, and therefore, it achieves semisupervised fault diagnosis by modeling the label dependency and learning object representations. The scheme is optimized with the variational expectation–maximization (EM) algorithm. Specially, the clustering with adaptive neighbor (CAN) method is introduced for constructing the graph. The proposed method is applied in induction motor (IM) and permanent magnet synchronous motor (PMSM), which achieves the identification of the motor status, fault severity, and working condition. The results show that the CRF-GAT can realize an accuracy of above 97% with even below 10% of labeled samples for training, which demonstrates that it is an effective method in semisupervised fault diagnosis.

23 August 2022 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
YTYao Tang
Yao Tang
XZXiaofei Zhang
Xiaofei Zhang
SHSheng Huang
Sheng Huang
GQGuojun Qin
Guojun Qin
Yunze HeYunze He
Yunze He
ZLZhuo Long
Zhuo Long
Generalization ability is a critical property for practical motor fault diagnosis (FD). By converting time-series to images, several studies have made certain achievements. However, they still have following limitations. First, multisensor information fusion is rarely considered. Second, it is time consuming. To deal with the abovementioned problems, a multisensor-driven FD method based on visual features is proposed. Specifically, a color symmetrized dot pattern method is newly designed to infuse three multisensor signals to image. Next, a coarse and refined diagnosis framework is designed. In the coarse part, the color histogram features and a support vector machine (SVM) are utilized, and a threshold is selected to decide the coarse diagnostic samples. In the refined part, the gist (GIST) descriptor and another SVM are used to diagnose remaining samples. The results on induction motor and permanent magnet synchronous motor show that the proposed method achieved reliable diagnosis with relatively efficiency, and can generalize to different working conditions and noise.

31 March 2025 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
YTYao Tang
Yao Tang
Wei Lucian LiuWei Lucian Liu
Wei Lucian Liu
KCK.T. Chau
K.T. Chau
YHYunhe Hou
Yunhe Hou
JGJian Guo
Jian Guo
Electric vehicle energy network (EVEN) enables the transmission of renewable energy from rural to urban area by the flexibility of EVs via energy exchange. In this paper, (dis)charging behavior modelling and bidirectional charging station (BCS) deployment optimization are addressed, since they are crucial in EVEN for EV accommodation, renewable energy utilization, drivers’ profitability estimation, operators’ cost assessment, and financial policy establishment. A novel stochastic Markov (dis)charging behavior model is proposed to calculate the spatiotemporal load pattern considering the realistic factors such as personal features, state of charge (SoC), electricity price, and BCS locations. Unlike most works ignoring energy trading, six scenarios are explored: (S1) no trade; (S2) trade in main battery. (S3) trade in extra battery. (S4) trade in extra ultracapacitor; (S5) trade in both main and extra battery; (S6) trade in both main battery and ultracapacitor. Also, a multi-objective BCS deployment strategy is newly designed, aiming at minimizing installation cost and driver’s electricity bill, while quality of service (QoS) and voltage stability are ensured. An improved hybrid algorithm is developed, which combines hill climbing for enhanced exploitation and particle swarm optimization for better evolvement based on genetic algorithm framework. The simulation validates the fitting ability of charging model, the effectiveness of parameter selection algorithm and the deployment approach. Comparing 6 scenarios, benefits of energy trading in EVEN is confirmed and the superiority of ultracapacitor for trading is demonstrated. The feasibility of financial policies is also studied, and certain guidance is provided for drivers to improve their cost.

1 April 2025 in IEEE Industrial Electronics Magazine
Verified
Journal Article
Closed access
XTXiaoyang Tian
Xiaoyang Tian
Wei Lucian LiuWei Lucian Liu
Wei Lucian Liu
YTYao Tang
Yao Tang
SGStefan M. Goetz
Stefan M. Goetz
For more effective decarbonization and better utilization of the finite battery storage capacity of electric vehicles (EVs), dynamic energy exchange between cars and their batteries with the stationary electrical system could be a game changer. However, all existing vehicle-to-grid concepts circle the integration of stationary cars, although the highest need for and value of energy is reached during driving, which economically generates a price spread. This price spread if accessible would allow so-called arbitrage but also reflects market inefficiencies. Furthermore, dynamic energy transfer has so far mostly been interpreted as a pure charging technology with a strong focus on technology, ignoring the economic aspects and requirements. On the other hand, dynamic energy transfer and exchange could both solve range anxiety but also increasing instability of the electricity grid driven by fluctuating sustainable energy sources and decreasing inertia in the system due to the dismantling of conventional massive generators. Based on these issues, we discuss how to utilize an energy interfacing technology to combine both semi-dynamic wired and wireless charging systems between multiple electric vehicles as well as EVs and the power grid. Typical operation modes allow vehicle-to-vehicle (V2V), vehicle-to-grid (V2G), and vehicle-for-grid (V4G) energy exchange and dynamic stabilization. Essential to such a technology, however, is a market system that is efficient, fair so that no party or operator could exploit an information advantage, and at the same time allows exploiting the existing arbitrage to finance the implementation. We present and discuss potential market concepts, which promise near-ideal market results on the one side and resilience and reliability on the other side.