# Insulation Monitoring of Dynamic Wireless Charging Network Based on BP Neural Network

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

_{N}system. Generally, the cable insulation monitoring in IT

_{N}system is mainly realized by injecting signal, which is divided into DC signal and AC signal [2]. The advantage of injecting DC signal is that when the ground capacitor is fully charged, the calculation results are not affected by the capacitance [3]. The disadvantage is that when the value of the ground capacitor is large, the charging time will be very long, and the current insulation status cannot be analyzed quickly. The injected AC signal is usually a low frequency signal to distinguish it from the power frequency signal. AC injection method is divided into single frequency injection and dual frequency injection. The single frequency injection method needs to obtain the phase information at the same time [4], while the dual frequency injection method needs to generate the dual frequency signal and separate the dual frequency signal [5]. The disadvantage is that when the capacitance to ground is large, the calculation result error is large due to phase error. In addition to the AC injection method, there are other methods, such as adaptive pulse injection, which uses superimposed adaptive pulse voltage signal to detect the fault circuit, and continuously measures the insulation resistance to the ground. The periodic value of the pulse is related to the capacitance to the ground. The larger the capacitance, the longer the period [6]. The disadvantage is that the calculation time is long when the capacitance is large. There are some additional methods for DC power grid, such as bridge balance method, signal tracing method and differential current detection method [7,8,9]. The disadvantage is that it is only for DC power grid and the hardware implementation is complex.

## 2. Calculation Model of Insulation Monitoring

_{f}and R

_{f}in the model. R

_{P1}and R

_{P2}are parasitic resistances on the loop, which are very small and can be ignored in the actual calculation model. R

_{1}is the current limiting resistance, R

_{0}is the sampling resistance, and S1 is the external injection signal used to detect insulation resistance. Through the external injection of a certain frequency signal, the frequency component of the sampling resistance is collected, and then the insulation resistance value of the cable can be obtained through filtering and operation.

_{DC}is selected as the injection source and the injection time is t

_{1}in a cycle t

_{0}, the injection signal Vs (t) can be expressed as:

_{0}(t) is the voltage signal at both ends of the sampling resistor:

_{f}is i

_{Cf}(t), and the injection current through the insulation resistance R

_{f}is i

_{Rf}(t). The sum of the two satisfies the following equation:

_{f}(t) at both ends of insulation resistance can be expressed as:

_{Cf}(t) and i

_{Rf}(t) can be expressed as:

_{0}at both ends of the sampling resistor is a periodic signal. There is a difference in DC component between the first half cycle and the second half cycle, and the signal component decays with time in both the first and second half cycles. Generally speaking, it is a relatively complex calculation formula. If it is realized through real-time calculation, the amount of calculation will be very large, Additionally, the expression of C

_{f}must be inversely solved, which is very difficult. Therefore, the method of BP neural network is considered. By learning the waveform of voltage V

_{0}at both ends of the actual sampling resistance, the BP neural network is used to fit the expression (17), and the corresponding relationship between insulation resistance and sampling waveform is established through a large amount of data training. Thus, for a certain V

_{0}waveform, when other variables are determined, there is a certain R

_{f}and C

_{f}corresponding to it, which greatly simplifies the calculation difficulty.

## 3. Insulation Monitoring Based on BP Neural Network

#### 3.1. Subsection

#### 3.1.1. Improvement of BP Neural Network

#### 3.1.2. Parameter Design of BP Neural Network

#### 3.2. Neural Network Training Process

## 4. Simulation and Analysis

#### 4.1. Build the Actual Experimental Circuit

#### 4.2. Recognition Results

## 5. Conclusions

## Author Contributions

## Funding

## Conflicts of Interest

## References

- Su, H.; Zhou, Z.; Liu, Z.; Zhang, L. Research review and prospect of intelligent dynamic wireless charging system for electric vehicles. Chin. J. Intell. Sci. Technol.
**2020**, 2, 1–9. [Google Scholar] - Wang, W.; Yang, T.; Shao, X.; Qiang, L.V.; Song, P. Study on insulation monitoring of low voltage it system based on injection signal. Electrotech. Electric.
**2012**, 49–55. [Google Scholar] - Li, C. Analysis on online supervision system of high voltage cable insulation condition of coal mine. Mech. Manag. Dev.
**2016**, 31, 70–86. [Google Scholar] - Yu, S.; Zeng, T.; Li, Y.; Hu, Y.; Liu, L.; Wen, J.; Liu, H.; Wang, X. Design of insulation monitoring device based on improved single frequency method. China Meas. Test.
**2020**, 46, 78–82. [Google Scholar] - Hu, Y.; Zeng, T.; Li, Y.; Yu, S.; Liu, L.; Wen, J.; Liu, H.; Wang, X. Design of insulation monitoring device based on improved dual frequency injection method. Instrum. Tech. Sens.
**2020**, 47–51. [Google Scholar] - Wang, X. Application of low voltage insulation monitoring and fault location system based on AMP measurement method. Electr. Eng.
**2020**, 49–51. [Google Scholar] [CrossRef] - Yu, H.; Jiao, S.; Yang, F. Design of insulation monitoring equipment for direct current network in ship. Chin. J. Ship Res.
**2010**, 5, 56–58. [Google Scholar] - Li, L.; Zou, J.; Sun, H. Research and realization the DC system grounding fault detector. In Proceedings of the 6th International Symposium on Test and Measurement, Dalian, China, 1–4 June 2005; p. 7444. [Google Scholar]
- Wu, Z.; Wang, L. Research on intelligent on-line insulation monitoring device for electric vehicle. Low Volt. Appar.
**2009**, 20–22. [Google Scholar] - Zhang, J.; Li, S.; Qi, K.; Wang, C.; Zhang, Q.; Huang, H. On line insulation impedance monitoring and fault location of ITN shore power system based on AC injection method. Mar. Electr. Electron. Eng.
**2020**, 40, 19–25. [Google Scholar] - Makarenko, A. Multiple-valued and branching neural networks. Eng. World
**2020**, 2, 20–28. [Google Scholar] - Al-Mawsawi, S.A.; Haider, A.; Alfaris, Q. Neural Network Model Predictive Control (NNMPC) Design for UPFC. WSEAS Trans. Comput.
**2020**, 19, 201–207. [Google Scholar] [CrossRef] - Wang, L.; Zhang, Q. Short term power load forecasting of regional distribution network based on BP neural network. Softw. Dev.
**2021**, 49–52. [Google Scholar] [CrossRef] - Wang, M.; Jing, Z.; Sun, B. Prediction of short-term market clearing price based on BP neural network. China Electr. Power Educ.
**2011**, 100–102. [Google Scholar] [CrossRef]

**Figure 1.**(

**a**) Dynamic wireless charging network model for highway. (

**b**) Calculation model of cable to ground insulation resistance in dynamic wireless charging network.

**Figure 3.**Sampling voltage values of different combinations of capacitance and insulation resistance under injection signal.

**Figure 5.**The left side is the cable insulation resistance measurement experiment, and the right side is the waveform of sampling resistance at both ends when R

_{f}= 6 MΩ and C

_{f}= 100 uF.

Parameter Name | Parameter Value |
---|---|

Number of input nodes | 1 |

Number of output nodes | 1 |

Number of hidden layers | 4 |

Number of hidden layer nodes | (50, 50, 50, 50) |

Initial learning rate | 0.001 |

Learning accuracy | 0.000001 |

Training times | 3000000 |

Analog Value of Capacitance to Ground | True Value of Insulation Resistance | Calculated Insulation Resistance Value | Error Value |
---|---|---|---|

253 μF | 2.616 kΩ | 2.791 kΩ | +6.68% |

388 μF | 12.31 kΩ | 13.402 kΩ | +8.87% |

387 μF | 85.627 kΩ | 89.737 kΩ | +4.80% |

63 μF | 599.73 kΩ | 598.83 kΩ | −0.15% |

491 μF | 174.96 kΩ | 184.92 kΩ | +5.69% |

350 μF | 732.31 kΩ | 756.22 kΩ | +3.27% |

123 μF | 1.462 MΩ | 1.496 MΩ | +2.33% |

37 μF | 8.897 MΩ | 9.041 MΩ | +1.62% |

260 μF | 5.006 MΩ | 5.103 MΩ | +1.93% |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Wen, F.; Pei, W.; Li, Q.; Chu, Z.; Zhao, W.; Wu, S.; Zhang, X.; Han, C.
Insulation Monitoring of Dynamic Wireless Charging Network Based on BP Neural Network. *World Electr. Veh. J.* **2021**, *12*, 129.
https://doi.org/10.3390/wevj12030129

**AMA Style**

Wen F, Pei W, Li Q, Chu Z, Zhao W, Wu S, Zhang X, Han C.
Insulation Monitoring of Dynamic Wireless Charging Network Based on BP Neural Network. *World Electric Vehicle Journal*. 2021; 12(3):129.
https://doi.org/10.3390/wevj12030129

**Chicago/Turabian Style**

Wen, Feng, Wenjie Pei, Qiang Li, Zhoujian Chu, Wenhan Zhao, Shuqi Wu, Xiang Zhang, and Chen Han.
2021. "Insulation Monitoring of Dynamic Wireless Charging Network Based on BP Neural Network" *World Electric Vehicle Journal* 12, no. 3: 129.
https://doi.org/10.3390/wevj12030129