Low-current earthing line-selection method based on tabu search optimization RBF network

A RBF network, low-current grounding technology, applied in the direction of measuring electricity, measuring electrical variables, measuring devices, etc., can solve the problems that affect the convergence speed and accuracy of the network, the RBF network has many structural parameters, and the accuracy is difficult to guarantee. Fast, improving the speed and accuracy of optimization, and the effect of fast convergence

CN110221170AActive Publication Date: 2019-09-10GUIZHOU POWER GRID CO LTD
5 Cites 5 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2019-09-10

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a low-current earthing line-selection method based on tabu search optimization RBF network. A tabu algorithm is adopted, undermined RBF network structural parameters are trained so as to ensure that the RBF network structural parameters trend to optimal, and the optimized RBF network is used as a line selection model, so that low-current earthing fault comprehensive line selection is realized, automatic and quick determination of fault lines is realized, and stable operation of a power grid and safe equipment can be ensured.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the field of relay protection, and in particular relates to a small-current grounding line selection method based on tabu search to optimize an RBF network. Background technique

[0002] Since most of the 35KV and 10KV power grids use small current grounding methods (including neutral point ungrounded and neutral point grounded through arc suppression coils), the power supply system located in the southern thunderstorm humid environment has a high probability of single-phase grounding faults. After the occurrence of single-phase grounding, the safety regulations stipulate that short-term operation with faults can be performed, but there is also a hidden danger that arc grounding develops into two-phase short-circuits. Therefore, there is an urgent need for a method to automatically and quickly determine the faulty line, shorten the fault time, and ensure the stable operation of the power grid. Equipment security.

[0003] With...

Examples

Embodiment Construction

[0033] In order to further understand the content of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and examples.

[0034] The invention proposes a small current grounding line selection method based on tabu search to optimize the RBF network, such as figure 1 As shown in the figure, the tabu algorithm is used to train the structural parameters of the RBF network to be determined to make it tend to be optimal, and the optimized RBF network is used as the line selection model to realize the comprehensive line selection of the ground fault.

[0035] The network structure parameters are very important for the nonlinear approximation ability of the RBF network. If the network structure is too simple, the network's ability to learn the samples is not enough; otherwise, it will easily lead to overfitting and reduce the generalization ability of the neural network. Especially in the face of the complex and ch...