Switch knife state detection method and device

Abstract

The invention discloses a switch knife switch state detection method and device, and the method comprises the steps: employing a RefineDet method with excellent performances to automatically locate the position of a knife switch in an image at a knife switch target detection stage, cutting a knife switch region image, and overcoming the impact on knife switch target detection from a complex environment; in a knife switch state detection stage, providing an optimized VGG16 network, extracting knife switch image features with rich details to identify a high-precision state of the knife switch. Meanwhile, the generalization ability of an optimized VGG16 network is stronger, and the invention can adapt to the change of a complex environment.

Description

technical field [0001] The invention belongs to the field of intelligent detection of electrical equipment, in particular to a method and device for detecting the state of a switch switch. Background technique [0002] The knife switch is a manually controlled power equipment switch, which can form a switch point between the maintenance equipment and the live equipment to ensure the personal safety of the maintenance and construction personnel of the power equipment. In the actual construction process, construction personnel need to accurately judge the "connection" or "disconnection" status of the switch knife switch to ensure safety. [0003] At present, there are mainly two methods for detecting the state of the switch. One is to add sensors or other devices to the switch switch. , a closing position detection mechanism and an opening position detection mechanism are designed. The closing position detection mechanism includes a first light emitting module and a first lig...

AI Technical Summary

Problems solved by technology

However, the target positioning of the knife gate is still affected by environmental factors. The network model for feature extraction of the knife gate is not de

Images