Power transmission wire wind damage early warning method and terminal based on deep learning
The invention discloses a transmission line wind damage early warning method and a terminal based on deep learning, and the method comprises the following steps: starting a camera to collect an imageif the current wind power level exceeds a first threshold value; performing instance segmentation and...
Saved in:
Main Authors | , , , , , , , , , , , , , , , , , , , , , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
07.02.2020
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses a transmission line wind damage early warning method and a terminal based on deep learning, and the method comprises the following steps: starting a camera to collect an imageif the current wind power level exceeds a first threshold value; performing instance segmentation and comparison on the acquired image and a pre-stored safe distance image through a deep learning model, and determining the offset amplitude of the power transmission wire and the ratio of the distance between every two phase sequence wires A, B and C to the safe distance; and if the deviation amplitude is not smaller than a second threshold value or any distance ratio is not larger than a third threshold value, sending out an early warning prompt. According to the power transmission wire wind damage early warning method and the terminal based on deep learning, wind damage early warning of the power transmission wire can be achieved, and losses are reduced.
本发明公开了一种基于深度学习的输电导线风害预警方法及终端,该方法包括以下步骤:若当前风力级别超过第一阈值,启动摄像头采集 |
---|---|
Bibliography: | Application Number: CN201910894102 |