Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Transformer substation operation site monitoring method and device based on deep learning

A job site, deep learning technology, applied in neural learning methods, instruments, data processing applications, etc., can solve the problems of high cost, low system integration, high requirements for on-site communication, and achieve low power consumption, high precision, and low equipment. Effects of cost and deployment cost

Pending Publication Date: 2019-10-11
NARI TECH CO LTD
View PDF2 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing method is based on the deployment method of the background server, which can only identify the normative operation behavior of the operators in the monitoring screen, and cannot realize the automatic evaluation function; and the inference processing calculation is implemented in the server, which requires high on-site communication. Low system integration, low flexibility, high cost

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 operation site monitoring method and device based on deep learning
  • Transformer substation operation site monitoring method and device based on deep learning
  • Transformer substation operation site monitoring method and device based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] refer to figure 1 , the substation operation site monitoring method based on deep learning in this embodiment includes the following steps:

[0030] Step 1: On-site monitoring personnel and operating personnel conduct identity verification through face recognition or fingerprint recognition respectively, and enter the substation operation site safety supervision and evaluation program;

[0031] Step 2: On-site monitoring personnel call out the operation ticket to be executed from the APP program, select and confirm the first operation step, and start the supervision and evaluation work;

[0032] Step 3: The camera collects video files of on-site operations, and converts the video files into RGB images frame by frame;

[0033] Step 4: Load the modified deep neural network YOLO-V3, which was trained using expanded image samples, and was lightweighted using model structure pruning and weight quantization methods;

[0034] Step 5: Input the RGB image into the loaded YOLO-...

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 operation field monitoring device based on deep learning. The transformer substation operation field monitoring method comprises enabling a field monitoring person and an operation person to enter a transformer substation operation field monitoring program; selecting and confirming the first operation step by the field monitoring personnel, and executing the monitoring work; enabling the camera to collect a field operation video file and convert the field operation video file into an RGB image; loading improved deep neural network YOLO-V3; inputting an image, automatically identifying the equipment and the identifier, and judging whether an operation behavior conforms to a safety specification or not; according to the recognition and judgment result, giving an alarm on site, and giving an evaluation result; visually displaying the identification and evaluation results to on-site monitoring personnel in real time; and enabling the field monitoring personnel to confirm the evaluation result and select to enter the next step or end the operation. Two deep neural network lightweight methods of model structure pruning and weight quantification are used, high-precision real-time inference of the deep neural network model in the embedded intelligent terminal is realized, and safety and efficiency are improved.

Description

technical field [0001] The present invention relates to a substation operation site monitoring method and device, in particular to a substation operation site monitoring method and device based on deep learning. Background technique [0002] Electric power safety production is a major event involving the safety of employees, and it is also the key to the safety and stable operation of the power system and the survival and development of power companies. The power production operation site is dynamic, complex, and changeable, and it is easy to cause no-ticket operation, out-of-range operation, unplanned operation, etc., resulting in frequent violations at the operation site. With the increasing complexity of power grid technology, there are more and more factors affecting power grid security, and the safety production situation is becoming increasingly severe. Although the power grid and power companies have formulated complete power safety production regulations, there are ...

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): G06K9/00G06N3/04G06N3/08G06Q50/06
CPCG06N3/08G06Q50/06G06V20/41G06N3/045
Inventor 徐弘升张琪培徐康陈天宇陆继翔杨志宏
Owner NARI TECH CO LTD
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
Eureka Blog
Learn More
PatSnap group products