Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Artificial intelligence infrared image sensing system and method

An infrared image and artificial intelligence technology, applied in the field of artificial intelligence, can solve the problems of inaccuracy, poor feature extraction ability, time-consuming and labor-consuming, etc., achieve high precision data analysis, strong intelligent recognition ability, and improve judgment accuracy and precision Effect

Active Publication Date: 2021-11-30
TERMINUSBEIJING TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method of manual judgment is inaccurate and time-consuming and labor-intensive.
Therefore, some researchers improve the judgment accuracy and processing speed by using image processing technology, such as the classic maximum inter-class variance method and maximum entropy threshold method using image segmentation methods, but these methods only improve the data processing efficiency in the early stage. Accuracy and speed, when using the processed data to identify overheating in the later stage, most of the judgments made on various indicators are based on artificial definitions
In order to overcome the above defects, some people propose to use artificial intelligence algorithm and apply it to the field of equipment overheating recognition, such as artificial neural network, rough set theory, support vector machine (SVM) and other algorithms, but there are still common problems with poor feature extraction ability. defect

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
  • Artificial intelligence infrared image sensing system and method
  • Artificial intelligence infrared image sensing system and method
  • Artificial intelligence infrared image sensing system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] This embodiment provides an artificial intelligence infrared image sensing method, which can be applied to automatically identify equipment overheating and prevent equipment failures, fires, etc., such as figure 1 shown, including the following steps:

[0057] Step 100, collect and obtain the overheated infrared image sample set under the overheated state of each device; preferably, such as figure 2 As shown, specifically:

[0058] Step 101: Conduct multiple overheating tests for each device, and collect and obtain infrared images at preset positions in real time during each test; the way of overheating tests can be set according to actual conditions, such as overloading the device and placing it in a hot environment Moderate operation, long-term operation, etc. cause the heat to exceed the normal value.

[0059] Step 102, extract the gray value of four higher temperature places of the infrared image, the four higher temperature places include the highest temperature...

Embodiment 2

[0085] This embodiment provides an artificial intelligence infrared image sensing system, such as Figure 4 shown, including:

[0086] The infrared image sensor 300 is connected with the infrared image receiving and processing unit 100, and is used to collect and output the infrared images of each device;

[0087] An infrared image receiving and processing unit 100, configured to obtain a sample set of overheated infrared images in an overheated state of each device, and obtain an infrared image of the device to be identified;

[0088] Preferably, the infrared image receiving and processing unit 100 includes:

[0089] The first receiving unit is used to obtain the infrared image at the preset position in real time during each overheating test;

[0090] The first extraction unit is used to extract the gray value of the four higher temperature places of the infrared image, and the four higher temperature places include the highest temperature place, the first higher temperatur...

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 an artificial intelligence infrared image sensing system and method, and relates to the technical field of artificial intelligence. The method includes collecting and obtaining a sample set of overheated infrared images in an overheated state of each device; using the sample set of overheated infrared images as a training sample set, The convolutional neural network method based on gray logarithmic transformation is used to extract the overheating features of the training sample set, and the convolutional neural network model is obtained. The present invention has high accuracy and precision in judging overheating phenomena in infrared images, strong feature extraction capabilities, realizes automatic identification and overheating intelligent identification of equipment displayed in infrared images, and has the advantages of high data analysis accuracy and strong intelligent identification capabilities , which can effectively prevent the occurrence of fire.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to an artificial intelligence infrared image sensing system and method. Background technique [0002] With the continuous research and breakthrough of equipment fault diagnosis technology, the equipment status live detection technology with the help of infrared image sensor has developed rapidly, and with its advantages of safety, non-contact, non-stop power supply, accurate and intuitive, it has a high degree of popularity. As an important item in the live detection of equipment status, equipment overheat detection is also often used. [0003] At present, the method of equipment overheating detection is mainly to import the original thermal infrared image taken in the inspection into the infrared image analysis software such as FLIR for the infrared thermal imager, and judge the equipment according to the different colors presented by different temperatures in the t...

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 Patents(China)
IPC IPC(8): G06N3/04G06N3/08G06K9/62G06K9/46G06K9/20
CPCG06N3/08G06V10/143G06V10/56G06N3/045G06F18/214
Inventor 王明
Owner TERMINUSBEIJING TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com