Wavelet neural network-based distribution network single-phase short circuit line selection method

Abstract

The invention discloses a wavelet neural network-based distribution network single-phase short circuit line selection method, which belongs to the technical field of distribution network protection. The method comprises the following steps: 1) db4 wavelets are selected to serve as a wavelet packet basis function to decompose transient zero-sequence current in each feeder line of the distribution network, and the sampling frequency is 10KHz; 2) the modulus maximum of the transient zero-sequence current is calculated; 3) the modulus maximum obtained in the second step and the polarity of the modulus maximum are used for training the neural network; and 4) the BP neural network after the training in the third step is applied to the distribution network with single-phase short circuit, and a fault line is determined according to a different output result. The method of fault line selection by using the wavelet neural network disclosed by the invention has good reliability and practicability, a single-phase grounding fault line can be effectively eliminated, stable operation of the distribution network system is facilitated, and an important role is played in planning and applications of a distributed power supply.

Description

technical field [0001] The invention relates to a single-phase short-circuit line selection method of a distribution network, which belongs to the technical field of distribution network protection. Background technique [0002] Distributed power generation generally refers to a small power generation system connected near the user side in order to meet the specific requirements of the power system and users. Distributed power generation mostly adopts clean energy or renewable energy, which is not only inexhaustible, but also minimizes the impact on the environment, so it has been vigorously promoted. Since most distributed power sources are concentrated on the user side and directly supply power to users without passing through the upper-level transformer, the installed capacity of distributed power sources is relatively small, and the construction is also scattered. [0003] At present, the grounding mode of my country's distribution network system is mainly non-effective...

AI Technical Summary

Problems solved by technology

However, after the distributed power supply is added, the magnitude and phase angle of the current in the fault line and the normal line will change. Since the distributed power supply provides a certain fault current, the zero-sequence current of the fault line may not be the largest. At the same time, due to the arc suppression coil Therefore, the single-phase fault line selection methods such as zero-sequence current amplitude method and active component method are no longer applicable.

At the same time, due to the change of the phase angle, the first half-wave method will also be affected in practical applications. The fault occurs when the phase angle is small, and the first half-wave will not appear, and interference such as channel drift and unbalanced current will also affect Polarity of the first half wave

However, the Prony method is affected by the amplitude and phase angle, which may cause misjudgment.

[0006] For the distribution network with distributed power generation, the main direction of current research is the grid-connected regulation strategy of distributed power generation, and the impact of distributed power generation on distribution network power flow, relay protection and power quality after grid-connection. There is almost no research on single-phase short-circuit fault line selection of distribution network with distributed generation

Images