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

Roller press roller surface abrasion detection method and device based on machine vision

A technology of machine vision and detection methods, which is applied in measuring devices, instruments, scientific instruments, etc., and can solve problems such as untimely detection.

Pending Publication Date: 2021-03-12
中材邦业(杭州)智能技术有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Based on this, it is necessary to provide a machine vision-based method and device for detecting the wear of the roller surface of the roller press to solve the problem of untimely detection of the wear of the roller surface of the roller press, change the status quo of time-delay measurement, and ensure the quality of the roller press at all times. Stability of grinding production

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
  • Roller press roller surface abrasion detection method and device based on machine vision
  • Roller press roller surface abrasion detection method and device based on machine vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described below in conjunction with accompanying drawing.

[0020] like figure 1 and 2 As shown, according to a specific embodiment of the present invention, the present invention first installs a high-resolution camera and an auxiliary light source at a suitable angle near the roller surface of the roller press, and sends the images captured by the camera to the video analysis computer after being processed by the video capture card. At the same time, a large number of images of the worn and unworn roller surfaces of the roller press are collected as input variables of the deep learning model, and the wear of the roller surface of the roller press is used as the output variable. The sample data is processed offline through the deep learning model based on the convolutional neural network. Training, in practical engineering applications, the steady-state input and output sample data can be updated at regular intervals according to ...

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 roller press roller surface abrasion detection method and device based on machine vision. The roller press roller surface abrasion detection method and device are used for detecting the roller press roller surface abrasion situation on line. According to the detection method and device, the high-resolution camera is used for collecting roller surface image data, and the roller surface image data is transmitted into the analysis computer through the video collection card. Machine vision analysis software based on a deep learning algorithm is installed in the analysis computer, model training is carried out through previously collected roller surface image data of the abraded roller press and the unabraded roller press, and an analysis model is continuously optimized. After roller surface data collected on site is input into the model, roller surface abrasion area and abrasion condition data are output through multiple times of iterative processing. The problemthat roller surface abrasion measurement of the roller press is not found in time is solved, roller surface images are collected and analyzed in time by applying a deep learning algorithm and fusing amachine vision technology, and the method has positive significance in daily production, operation and maintenance of the roller press.

Description

technical field [0001] The invention relates to the field of machine vision image recognition deep learning, in particular to a method and device for wear detection by using machine vision technology to identify the wear condition of the roller surface of a roller press. Background technique [0002] As an important grinding equipment in the cement industry, the roller press has been widely used in most cement plants. Because of its low power consumption and high production efficiency, it has been accepted by more and more cement manufacturers. However, during its use The problem of roller surface wear is also more prominent. When the roller surface is intact, the material will be fully ground and squeezed, the grinding effect is good, and the output can be maintained at a high level. When the roller surface is worn out, the distance between the rolling gaps becomes large and uneven, resulting in uneven force on the ground material, uneven size of the ground material, and p...

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): G01N21/88G06T7/00
CPCG01N21/8851G06T7/0004G01N2021/8883G01N2021/8887G01N2021/8854B02C2210/01G06T2207/10004G06T2207/20081G06T2207/20084
Inventor 冯兰洲袁亦斌魏灿黎木光赵华张亮亮王承宇赵玉薇陈紫阳蒋斌山
Owner 中材邦业(杭州)智能技术有限公司
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