Automatic identification method and system for lightning ground flash return stroke waveform and electronic equipment

Abstract

The invention relates to the technical field of lightning signal automatic identification, in particular to an automatic identification method and system for a lightning ground flash return stroke waveform and electronic equipment. The method comprises the steps: collecting a real lightning signal; recognizing the waveform of the real lightning signal by using a pre-trained recognition model; obtaining and outputting a recognition result; wherein the identification model obtained by pre-training is obtained by performing lightning signal category labeling and feature extraction on collected lightning original waveform data, performing feature screening according to the importance degree of each feature, and training the screened features based on a machine learning algorithm. A machine learning method is adopted to establish an automatic identification model of lightning ground flash return stroke, a large number of time domain and frequency domain characteristic parameters can be extracted through self-learning and self-training of sample data, lightning waveform automatic identification is performed based on the identification model, the identification accuracy can be greatly improved, and the identification efficiency is improved. The problems of misjudgment and missed judgment caused by identification based on fixed and few time domain features are solved.

Description

technical field [0001] The invention relates to the technical field of automatic identification of lightning signals, in particular to a method, system and electronic equipment for automatic identification of lightning return stroke waveforms. Background technique [0002] Lightning disaster is one of the natural disasters that seriously endanger human activities. Ground lightning is related to ground disasters, and strikeback is one of the powerful current sources, which is seriously harmful. The return strike has a waveform that is relatively easy to identify. In the past, the lightning location system used a fixed feature identification method. [0003] For example, the Chinese patent "A Method for Recognition of All Lightning Cloud-to-Ground Lightning" with the application number of 201510047783.3 discloses a recognition method, which uses nine specific waveform parameters to extract the characteristics of the collected lightning radiation electric field waveform, and t...

AI Technical Summary

Problems solved by technology

[0005] The object of the present invention is to aim at the defects of the prior art, to provide an automatic recognition method, system and electronic equipment of lightning ground flashback waveform. Misjudgments and missed judgments caused by identification

Images