Výsledky vyhledávání - "Wang Fenghua"

Akademický článek

Feature extraction and state discrimination of opening and closing coils of high-voltage circuit breakers based on corner point location

Autor: WANG Shaohe, JIANG Jiongting, JIANG Keruo, ZHANG Miaobin, WANG Fenghua, CHEN Xiaoxin

Publikováno v: Zhejiang dianli, Vol 43, Iss 6, Pp 125-132 (2024)

The extraction of current characteristics from the opening and closing coils is a crucial method for monitoring the state of high-voltage circuit breakers. Based on the waveform patterns of the opening and closing coil currents in high-voltage circui

Externí odkaz: https://doaj.org/article/7c3bec3e0cdb4d74bb2c6d5ab51c4df2

Zobrazit plný text záznamu

Akademický článek

Vibration characteristic analysis of low-frequency fast circuit breakers based on improved EWT

Autor: ZHANG Miaobin, WANG Shaohe, WANG Fenghua, CHEN Xiaoxin, ZHAO Lin

Publikováno v: Zhejiang dianli, Vol 42, Iss 12, Pp 28-35 (2023)

The violent vibrations generated during switching of low-frequency fast circuit breakers （LFFCBs） can potentially impact their mechanical performance. However， there is currently a lack of assessment methods for evaluating the effects of these

Externí odkaz: https://doaj.org/article/604ccc1faf9c4452a4e0ab955f84250a

Zobrazit plný text záznamu

Akademický článek

Intelligent diagnosis of mechanical fault of on-load tap-changer based on tensor decomposition in phase space

Autor: CHEN Wentong, SHENG Jun, QIAN Xiao, WU Xuefeng, WANG Fenghua

Publikováno v: 电力工程技术, Vol 42, Iss 4, Pp 248-255 (2023)

Vibration signals associated with on-load tap-changer (OLTC) gear switching is closely related to its mechanical state. Based on the high-dimensional phase point spatial distribution of the vibration signal of OLTC, the vibration signals at multiple

Externí odkaz: https://doaj.org/article/70cae4024f0f48f189526be85b4153f7

Zobrazit plný text záznamu

Akademický článek

Improved Convolutional Neural Network Based on Fast Exponentially Linear Unit Activation Function

Autor: Zheng Qiumei, Tan Dan, Wang Fenghua

Publikováno v: IEEE Access, Vol 7, Pp 151359-151367 (2019)

The activation functions play increasingly important roles in deep convolutional neural networks. The traditional activation functions have some problems such as gradient disappearance, neuron death and output offset, and so on. To solve these proble

Externí odkaz: https://doaj.org/article/d46d92d458064866b9368bec7e3bd29f

Zobrazit plný text záznamu