Power distribution room small animal detection method based on deep semantic feature extraction

A technology of semantic features and detection methods, applied in neural learning methods, biological neural network models, instruments, etc., can solve problems such as heavy workload, loss of residents' lives or industrial production, and difficult management, so as to reduce personnel consumption, The effect of intelligent detection process and improved detection efficiency

Pending Publication Date: 2021-11-19
佳源科技股份有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The power distribution room is an important power supply contact point in the distribution network. There are a large number of power distribution rooms, and the geographical distribution is scattered and extensive. Since the safety of the environment in the power distribution room is an important condition for safe use of electricity, the environment of the power distribution room The safety inspection will be very important. Not only the normal operation of the equipment and the normal indicators need to be paid attention to, but also the harm caused by small animals such as mice and snakes that easily enter the power distribution room to the safe operation of the power distribution room must not be ignored. They are on the high and low voltage terminals of the distribution transformer or on the knife switch of the switchboard, which will cause a short circuit or ground fault in the transformer or switchboard, which not only directly affects the normal power supply, but also causes certain losses to residents' lives or industrial production.
[0003] For the safety inspection of power distribution rooms, manual inspection is mostly used at present. Although the accuracy is generally good, due to the scattered and remote location of some of The workload is heavy, the inspection is inconvenient, and the failure cannot be found in time. Therefore, the intelligent detection of the power distribution room is very necessary. In the past, the detection method of manual inspection and the prevention of rat poison can only be used to prevent the intrusion of small animals. and other preventive methods, and the small size of small animals will also cause the negligence of the inspectors, so how to intelligentize the detection of small and medium animals in the power distribution room is also a key link to realize the intelligent operation and maintenance of the power distribution room in the future

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Power distribution room small animal detection method based on deep semantic feature extraction
  • Power distribution room small animal detection method based on deep semantic feature extraction
  • Power distribution room small animal detection method based on deep semantic feature extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0030] refer to Figure 1-2 , a method for detecting small animals in a power distribution room based on deep semantic feature extraction, including the following steps:

[0031] S1: Data collection and processing, downloading and obtaining the ISLVRC 2012 data set, and marking the data set as animals and not animals according to whether the image content is an animal;

[0032] S2: Design of deep neural network structure, the deep neural network adopts ResNet...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to the technical field of power distribution room safety, and discloses a power distribution room small animal detection method based on deep semantic feature extraction, and the method comprises the following steps: S1, data collection and processing: downloading and obtaining an ISLVRC 2012 data set, and marking the data set as an animal type or a non-animal type according to whether the image content is an animal; s2, designing a deep neural network structure, wherein the deep neural network adopts a ResNet50 network; and S3, training the deep neural network. According to the invention, the existing data set is used, and data in an extra power distribution room environment is not needed; semantic information of the approximate concept of animals is extracted from information of different animals through deep learning with a ResNet50 network as a framework; and intelligent detection of the power distribution room is carried out by using the information. Errors of manual inspection can be effectively reduced, and the whole detection process is intelligent; the personnel consumption is reduced; and the detection efficiency is remarkably improved.

Description

technical field [0001] The invention relates to the technical field of power distribution room safety, in particular to a method for detecting small animals in a power distribution room based on deep semantic feature extraction. Background technique [0002] The power distribution room is an important power supply contact point in the distribution network. There are a large number of power distribution rooms, and the geographical distribution is scattered and extensive. Since the safety of the environment in the power distribution room is an important condition for safe use of electricity, the environment of the power distribution room The safety inspection will be very important. Not only the normal operation of the equipment and the normal indicators need to be paid attention to, but also the harm caused by small animals such as mice and snakes that easily enter the power distribution room to the safe operation of the power distribution room must not be ignored. They are o...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/08G06N3/04
CPCG06N3/08G06N3/045G06F18/2431G06F18/214
Inventor 马培龙雷天悟
Owner 佳源科技股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products