Transformer substation smoke and fire intelligent identification monitoring method based on deep learning

A deep learning and intelligent recognition technology, applied in character and pattern recognition, instruments, calculations, etc., can solve problems such as tight network bandwidth resources, prone to false alarms, and heavy server loads

Active Publication Date: 2019-08-02
SHANDONG UNIV +2
View PDF10 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional sensor-based smoke detection method is easily affected by the environment, has a certain alarm delay and is not suitable for a wide range of environments such as outdoors
With the rapid development of intelligent video technology, research on smoke detection using image recognition or video recognition technology has begun. Most current applications use images alone for d

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
  • Transformer substation smoke and fire intelligent identification monitoring method based on deep learning
  • Transformer substation smoke and fire intelligent identification monitoring method based on deep learning
  • Transformer substation smoke and fire intelligent identification monitoring method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0070] Examples,

[0071] Such as figure 1 Shown.

[0072] A method for intelligent identification and monitoring of substation fireworks based on deep learning includes the following steps:

[0073] S1: Preprocess the collected smoke images and build an image model data set;

[0074] S2: Preprocess the collected smoke and non-smoke videos and construct a video model data set;

[0075] S3: Improve and optimize based on the target recognition yolov3 algorithm framework, and use image model data set training iterations to complete the construction and training of image recognition models. The recognition efficiency of the detection model can reach 0.1-0.2s / sheet;

[0076] S4: Use the video model data set to train the pseudo three-dimensional convolutional residual network, combine the time domain and frequency domain information to extract the high-dimensional feature characterization information of the smoke, complete the construction and training of the video recognition model, and the r...

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 discloses a transformer substation smoke and fire intelligent identification monitoring method based on deep learning. Improvement and optimization of a video recognition model and an image recognition model are carried out on an actual scene of a transformer substation; two improved model frameworks are fused; the disadvantages of the two improved model frameworks are avoided as much as possible, and respective advantages of the two improved model frameworks are developed, a reasonable and flexible detection method is designed, an image recognition model is used for monitoring at ordinary times, after smoke is detected, a video recognition model is automatically called for secondary rechecking, an alarm signal is sent to a monitoring platform after checking is accurate, anddetection and early warning work can be effectively completed.

Description

technical field [0001] The invention relates to a method for intelligent identification and monitoring of pyrotechnics in substations based on deep learning, and belongs to the technical field of artificial intelligence monitoring and identification for substation safety. Background technique [0002] Fire has always been one of the great threats to the safety of people's lives and properties. The suddenness, frequency and high destructive power of fires seriously threaten people's lives, properties and the natural environment. The substation is the hub of the power system. Once a fire breaks out, it may cause the collapse of the entire power grid system, seriously endangering the reliability of power supply. Therefore, doing a good job of fire prevention measures in substations is a crucial task to ensure the safe and stable operation of the power grid. The main reasons for fires in substations are as follows: electrical equipment causes fires, and substations contain a la...

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
IPC IPC(8): G06K9/00
CPCG06V20/41G06V20/52
Inventor 聂礼强宋雪萌王英龙战新刚姚一杨姚福宾
Owner SHANDONG UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap