Loading...
Please wait, while we are loading the content...
Similar Documents
A Fault Warning Method for Electric Vehicle Charging Process Based on Adaptive Deep Belief Network
Content Provider | MDPI |
---|---|
Author | Gao, Dexin Wang, Yi Zheng, Xiaoyu Yang, Qing |
Copyright Year | 2021 |
Description | If an accident occurs during charging of an electric vehicle (EV), it will cause serious damage to the car, the person and the charging facility. Therefore, this paper proposes a fault warning method for an EV charging process based on an adaptive deep belief network (ADBN). The method uses Nesterov-accelerated adaptive moment estimation (NAdam) to optimize the training process of a deep belief network (DBN), and uses the historical data of EV charging to construct the ADBN of the normal charging process of an EV model. The real-time data of EV charging is obtained and input into the constructed ADBN model to predict the output, calculate the Pearson coefficient between the predicted output and the actual measured value, and judge whether there is a fault according to the size of the Pearson coefficient to realize the fault warning of the EV charging process. The experimental results show that the method is not only able to accurately warn of a fault in the EV charging process, but also has higher warning accuracy compared with the back propagation neural network (BPNN) and conventional DBN methods. |
Starting Page | 265 |
e-ISSN | 20326653 |
DOI | 10.3390/wevj12040265 |
Journal | World Electric Vehicle Journal |
Issue Number | 4 |
Volume Number | 12 |
Language | English |
Publisher | MDPI |
Publisher Date | 2021-12-17 |
Access Restriction | Open |
Subject Keyword | World Electric Vehicle Journal Industrial Engineering Transportation Science and Technology Charging Process of Ev Fault Warning Deep Belief Network Nadam Pearson Coefficient |
Content Type | Text |
Resource Type | Article |