Visual judgment method for opening and closing of disconnecting link body of GIS equipment

Abstract

The invention belongs to the technical field of intelligent detection, and particularly relates to a GIS equipment knife switch body opening and closing visual judgment method, which comprises knife switch body static state identification and knife switch body motion state identification, and is characterized in that knife switch body static state identification is realized through a knife switch body state identification method based on improved deep learning; knife switch body motion state identification is realized through a method based on combination of a YOLOv3 deep learning target detection network and a KCF target tracking algorithm, in the knife switch body state identification method based on improved deep learning, Gaussian distribution is used to carry out random initialization on CNNs weight values, so that feature dimensions are reduced, overfitting is avoided, and the identification accuracy of the knife switch body state identification method based on improved deep learning is improved. A traditional sigmoid activation function is abandoned in an activation function in the BP algorithm, a ReLU activation function is adopted, gradient diffusion in the training process of the image set is avoided, and therefore the convergence speed of the stochastic gradient descent method is increased.

Description

technical field [0001] The invention belongs to the technical field of intelligent detection, and particularly relates to a visual judgment method for the opening and closing of a knife gate body of a GIS equipment. Background technique [0002] GIS equipment includes knife switch body, grounding switch, circuit breaker, current transformer, voltage transformer and busbar, which are enclosed in a closed space, and the space is filled with insulating gas SF6 to achieve insulation isolation. At present, only the knife gate body of GIS equipment has a tiny observation window. When the inspection personnel turn off the gate, they can observe each group of knife gate bodies with the naked eye, which depends on the physical and mental health of the person, and the result is unreliable. The camera is connected to the GIS knife switch body opening and closing status identification device, and is judged by the software video embedded in the GIS knife switch body opening and closing s...

AI Technical Summary

Problems solved by technology

[0004] The method used for the analysis of the static state of the knife switch is affected by factors such as brightness changes and complex backgrounds, and has poor stability and weak anti-interference ability.

For the method of analyzing and judging the motion state of the knife gate body, the knife gate body tracking algorithm is adversely affected by light, deformation, etc., and the discriminative KCF target tracking algorithm adopted in the industry has insufficient accuracy, robustness and adaptability.

Since KCF is a discriminative tracking method, it has deficiencies in scale transformation, feature extraction, and target loss. This method has the defects of poor stability and weak robustness.

Images