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

Deep self-learning visual analysis system

A visual analysis and self-learning technology, applied in the field of deep self-learning visual analysis system, to improve production efficiency, analyze data accurately, and reduce production costs

Pending Publication Date: 2017-07-14
江阴东民盛科技有限公司
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This standard aims to significantly reduce production costs and efficiently increase equipment production capacity. Therefore, if the working status of the assembly line can be monitored through cameras, the working conditions of equipment and personnel can be analyzed through video monitoring screens, and abnormal situations can be alarmed, the work will be effective. Invalid duration analysis

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
  • Deep self-learning visual analysis system
  • Deep self-learning visual analysis system
  • Deep self-learning visual analysis system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] Stamping shop - cold rolled steel plate:

[0028] Monitor and analyze the displacement of the steel plate in the video screen, and check whether the equipment stops during operation;

[0029] How many strokes are in the process of running;

[0030] Personnel - Personnel often wait for equipment, and equipment is down for a long time.

[0031] For better detection and analysis, it may be necessary to adjust the installation position of the monitoring equipment or add a new camera, which can fully display the movements of steel plates and personnel.

Embodiment 2

[0033] Press shop - door:

[0034] Detecting and analyzing the position of the mechanical arm in the screen, and detecting and analyzing the displacement of the stamping equipment can judge whether the equipment is working normally, stop overtime alarm, count the time of each stamping process, and count the duration of equipment shutdown.

[0035] Such as figure 2 As shown, it also includes a monitoring device unit, a video analysis server, a big data analysis server, a database server and an application platform, and the monitoring device unit includes a public output terminal, and the video analysis server, the big data analysis server, the database server and the application platform are respectively It is connected to the common output terminal of the monitoring equipment unit, the video analysis server is connected to the big data analysis server, the big data analysis server is connected to the database and the server, and the database server is connected to the applica...

Embodiment 3

[0040] Assembly workshop - glass gluing;

[0041] Action decomposition: glass gluing, placing glass, lifting glass and other actions, each action can be analyzed and identified, and the time of each action can be detected and counted, combined with the running time of the equipment, such as the running time of each action of the equipment and Duration, compared with the time point and duration of the worker's action;

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 a deep self-learning visual analysis system. The visual analysis system comprises an acquisition module, a storage module, a data analysis module, and a display module. The storage module and the data analysis module are connected with the acquisition module. The display module is connected with the acquisition module. The deep self-learning visual analysis system comprises a monitoring equipment unit, a video analysis server, a big data analysis server, a database server and an application platform. The beneficial effects are that modeling of an analysis result is conducted through industrial big data, models and parameters keep being adjusted, data is analyzed more accurately, semantic analysis of scenes and analysis of human behavior tracks are taken as directions, a significant breakthrough is achieved in terms of production line applications, the production efficiency of factories is improved, and the production cost is reduced.

Description

technical field [0001] The invention relates to the technical field of monitoring and analysis of various production lines, including generating assembly lines and generating stamping lines, and specifically relates to a deep self-learning visual analysis system. Background technique [0002] For the sake of safe production, it has become the consensus of the enterprise to install CCTV monitoring equipment in the production workshop. At present, the transformation of production methods triggered by the German Industry 4.0 standard is in the ascendant. This standard aims to significantly reduce production costs and efficiently increase equipment production capacity. Therefore, if the working status of the assembly line can be monitored through cameras, the working conditions of equipment and personnel can be analyzed through video monitoring screens, and abnormal situations can be alarmed, the work will be effective. Invalid duration analysis. At the same time access to erp...

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): G06T7/00G06K9/00G06K9/66H04N7/18G06F17/30
CPCH04N7/18G06F16/738G06T7/0004G06T2207/20081G06V20/41G06V30/194
Inventor 陈安民王颖陈鑫郝一多李林韩树明张晓东
Owner 江阴东民盛科技有限公司
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