YWYunda Wang

Yunda Wang

*This is an algorithmically generated author record based on publicly available information.

Yunda Wang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Vibration Signal Augmentation Method for Fault Diagnosis of Low-Voltage Circuit Breaker Based on W-CGAN

    by Jingjian Yang, Gang Zhang, Bei Chen, Yunda Wang

    Low-voltage circuit breakers (LVCBs) fault diagnosis based on artificial intelligence (AI) algorithm has always been a research hotspot and got some recent advances. However, AI algorithms usually require sufficient data to train the model, so intelligent fault diagnosis is a challenging task when lack of fault signals. To solve this problem, a fault vibration signal augmentation method based on Wasserstein distance and conditional generative adversarial networks (CGANs) is proposed in this paper. The proposed method uses Wasserstein distance to optimize the adversarial training of generator and discriminator, thus the generator can generate vibration signals under different fault conditions, which can be used to extend the training dataset. In order to verify the improvement effect of this method on the accuracy of LVCB fault diagnosis. Multiple fault classifiers are trained using generated and real fault signals, and a multi-dimensional evaluation index system is built to evaluate the classification effect. Experimental results reveal that the method can generate fault signals with high similarity and improve the accuracy of fault diagnosis.


  • Distribution Correction Model of Urban Rail Return System Considering Rail Skin Effect

    by Yunda Wang, Gang Zhang, Ruichang Qiu, Zhigang Liu, Nan Yao

    The problem of high rail potential is common in urban rail transit lines that use running rail to return train current. At present, the research of rail potential mainly adopts modeling analysis. However, the rail potential results of the traditional model are generally far less than the actual situation, and the distribution is not accurate enough. It is difficult to predict the rail overvoltage in actual operation by the traditional model. This article explains the reason for the low accuracy of the traditional model from the perspective of the rail skin effect and corrects the rail resistance parameters of the traditional model. A calculation method of rail skin effect equivalent resistance is proposed, and a distribution correction model is established to simulate the rail potential. Compared with the traditional model, the rail potential results of the correction model are obviously increased, and the value and distribution of rail potential are closer to the actual system. The accuracy of the traditional model is improved obviously after the correction of rail resistance parameters, and the problem of inaccurate analysis and prediction of OVPD by traditional models has been solved.


  • An Online Thermal Deicing Method for Urban Rail Transit Catenary

    by Yunda Wang, Gang Zhang, Zhongbei Tian, Ruichang Qiu, Zhigang Liu

    The frequent icing of catenary in cold areas has seriously affected the normal operation of urban rail transit. Among many de-icing methods for catenary, the thermal de-icing method which uses current Joule heat to melt ice has been widely adopted due to its efficiency and safety. However, most of the thermal de-icing methods are only applicable when the line is out of service, which cannot solve the icing problem of catenary during the operation period. In order to solve this problem, this paper proposes a novel online thermal de-icing method which takes the catenary of up and down lines as the de-icing current loop. Based on the Bolsdorf theory, the de-icing and anti-icing current of catenary are calculated, and the structure and control strategy of de-icing power unit (DIPU) are designed. The influence of online de-icing on the traction power supply system is quantitatively analyzed by the electric network model. The accurate dynamic simulation model of the traction power supply system including the DIPU is established to verify the analysis conclusion. The results show that the online thermal de-icing method has limited influence on the traction power supply system, but achieves good de-icing performance in the normal operation of the line.


  • Open Access

    Realization of Smooth Transition in Hybrid PWM Scheme for Induction Motor Control

    by Ting Li, Jie Chen, Yunda Wang, Ruizheng Ni, Zhigang Liu

    Hybrid pulse width modulation schemes are widely used in high-power traction converters with a limited switching frequency. During the transition between modulation modes, sudden changes in the voltage harmonics cause the induction motor to enter a transient process, and ultimately lead to torque impacts, current shocks and other adverse effects. To improve the existing solution for such effects, theoretical support is provided in this paper by using an equivalent circuit model and a dynamic model of an induction motor, and a specific implementation scheme for a smooth transition is given considering the third-harmonic frequency component that appears in the phase voltage during the transition. The feasibility and correctness of the scheme are proven by a simulation and an experiment.