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

Real-time visual inspection method and system for high-speed penicillin bottle capping production line

A technology of real-time vision and detection methods, applied in the direction of neural learning methods, measurement devices, biological neural network models, etc., can solve the algorithm operation time requirements, increase the algorithm time complexity, and it is difficult to apply real-time detection on the high-speed capping production line of vials, etc. problem, to achieve the effect of facilitating adjustment and improving reliability

Active Publication Date: 2020-09-11
DOTU TECH (FO SHAN) LTD
View PDF15 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Moreover, due to the complexity of the neural network model in deep learning, the time complexity of the algorithm has increased sharply, and it is difficult to apply it to the high-speed capping production line of vials for real-time detection, especially when the speed of the vial production line reaches more than 500 bottles per minute. There are high requirements on the operation time of the algorithm

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
  • Real-time visual inspection method and system for high-speed penicillin bottle capping production line
  • Real-time visual inspection method and system for high-speed penicillin bottle capping production line
  • Real-time visual inspection method and system for high-speed penicillin bottle capping production line

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and through specific implementation methods.

[0054] refer to Figure 1-6 , a real-time visual inspection method for a high-speed vial capping production line, including:

[0055] Obtain the real-time production video of the high-speed vial crimping and capping production line;

[0056] For each target vial in the video, a frame representative image is intercepted;

[0057] The target detection technology of deep learning is applied, and the size of the gap of the rubber stopper of the target vial is used as the detection target to detect the representative image; wherein, the target detection technology of deep learning can be a deep convolutional neural network. Object detection technology. Because the size of the gap of the vial rubber stopper is the most direct cause of whether the sealing of the vial is qualified or not, in an embodimen...

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 real-time visual inspection method and system for a high-speed penicillin bottle capping production line, and relates to the technical field of industrial visual inspection,the real-time visual inspection method for the high-speed penicillin bottle capping production line comprises the following steps: obtaining a video of real-time production of the high-speed penicillin bottle capping production line; for each target penicillin bottle in the video, intercepting a frame of representative image; detecting the representative image by applying a deep learning target detection technology; and generating a coded signal according to the detection result of the representative image, and storing the representative image of which the detection result is unqualified. Themethod is characterised in that an image region feature analysis technology is used to intercept a frame of representative image from a video, and then the representative image is detected by using adeep learning target detection technology, so that high-precision detection of abnormal conditions is completed, detection of multiple frames of images of the same target penicillin bottle is avoided,the algorithm operation amount is reduced, the detection speed is increased, and real-time target visual detection of a high-speed penicillin bottle capping production line is realized.

Description

technical field [0001] The invention relates to the technical field of industrial visual inspection, in particular to a real-time visual inspection method and system for a high-speed vial capping production line. Background technique [0002] Vials, a small bottle sealed with a rubber stopper, are available in brown and transparent types, and are generally made of glass. They are used as medicinal injection bottles, oral liquid bottles, etc. The seal is usually sealed with a rubber stopper, and finally used The capping equipment crimps the aluminum cap tightly to achieve the purpose of sealing. After the vial is filled with medicine and covered with a rubber stopper, sometimes there are gaps in the rubber stopper due to the different air pressure inside and outside the bottle. If the gap is too large, it will seriously affect its sealing performance, causing dust and bacteria in the outside air to enter the vial and contaminate the drug. Therefore, it is particularly import...

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): G06T7/00G06T7/136G06T7/187G06T5/00G06K9/62G06N3/04G06N3/08G01B11/24G01N21/84G01N21/88G01N21/892G01N21/90
CPCG06T7/0004G06T7/136G06T7/187G06N3/08G01N21/84G01N21/8851G01N21/892G01N21/90G01B11/24G01N2021/8411G06T2207/10016G06T2207/20081G06T2207/20084G06V2201/07G06N3/045G06F18/24G06T5/70
Inventor 杨雪松谢振华高竞恒方波陈思
Owner DOTU TECH (FO SHAN) 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