Overhead line early warning system obstacle recognition method based on time convolution neural network

Abstract

The invention discloses an overhead line early warning system obstacle recognition method based on a time convolution neural network, and the method comprises the following steps: constructing a timeconvolution module, and carrying out pre-training of the convolution network module by employing an ImageNet image data set; constructing a double-layer long-short-term memory neural network module, and inputting an output result of the time convolutional neural network module into the long-short-term memory neural network module; utilizing an Adam optimization algorithm to solve a weight value and a threshold value of the long-term and short-term memory neural network module to enable the model to achieve convergence; performing neural network hyper-parameter optimization by utilizing a gridsearch method; and inputting an obstacle picture into the trained neural network to carry out obstacle recognition. The method has the advantages that the type of an obstacle can be automatically recognized, the false alarm probability is reduced, whether the obstacle exists or not is judged, the workload of dispatching personnel and line patrol personnel is greatly reduced, and the safety and stability of a power grid are improved.

Description

technical field [0001] The invention relates to an obstacle identification method for an overhead line early warning system based on a time convolutional neural network. Background technique [0002] In recent years, my country's economy has continued to develop rapidly, the level of transmission voltage has been continuously improved, the distribution of power grids has become wider and wider, and the problem of power safety is also particularly prominent. The overhead line is erected on the ground, which is convenient for erection and maintenance, and the cost is low, but it is easily affected by weather and environment (such as strong wind, lightning strike, pollution, ice and snow, etc.) and cause failure. For some overhead lines that have been exposed to the air for a long time, passing through areas with lush vegetation, single-phase grounding and phase-to-phase short-circuits often occur due to trees, bird droppings, bird's nests, etc., causing power outages. [0003...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide an obstacle identification method for an overhead line early warning system based on a temporal convolutional...

Images