Intelligent visual detection method and system applied to injection molding part defective product detection
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of intelligent vision and detection system, applied in the direction of measuring devices, optical testing flaws/defects, instruments, etc., can solve the problems of poor robustness and generalization ability, and achieve the effect of high robustness and generalization ability
Pending Publication Date: 2020-08-04
苏州奥创智能科技有限公司
View PDF11 Cites 2 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0004] The disclosure provides an intelligent visual detection method and system applied to the detection of defective injection molded parts, aiming to solve the problems of poor robustness and generalization ability of traditional detection methods
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0043] refer to figure 1 , image 3 , Figure 4 and Figure 5 , the present disclosure provides an intelligent visual detection method applied to the detection of defective injection molded parts, comprising the following steps:
[0044] S101. Obtain the video stream data of the sample to be detected;
[0045] S102. Decompose the video stream data into single frame image data;
[0046] S103. Through the deep learning algorithm for defective product detection, identify the defects of defective products in the single frame image data, and calculate the pixel coordinate information (x, y) and scale information (w, h) of the center position of the defect part of the defective product in the image, ( x, y) corresponds to the horizontal and vertical coordinate information in the image, (w, h) corresponds to the length and width information of the defective part in the image, and uses the camera matrix to convert the coordinate information of the coordinate system into the coordi...
Embodiment 2
[0054] refer to figure 2 , the present disclosure also provides an intelligent visual detection system applied to the detection of defective injection molded parts, which is characterized in that it includes: a data acquisition module, an intelligent control module and a display module, the intelligent control module includes a data stream decomposition module, not Good product detection module, defective product classification module, target tracking module and statistics module;
[0055] A data acquisition module for obtaining video stream data of samples to be detected;
[0056] The data stream decomposition module decomposes the video stream data into single frame image data;
[0057] The defective product detection module, through the defective product detection deep learning algorithm, identifies the defects of defective products in a single frame of image data, and calculates the pixel coordinate information (x, y) and scale information (w, h) of the center position o...
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
Login to view more
Abstract
The invention provides an intelligent visual detection method and system applied to injection molding part defective product detection, and aims at solving the problems that a traditional detection method is poor in robustness and generalization ability. The detection method comprises the following steps: acquiring video stream data of a to-be-detected sample; decomposing the video stream data into single-frame image data; detecting defects of defective products through a defective product detection deep learning algorithm; classifying defective products through a defective product classification algorithm; and counting the number of detection samples and the number of defective products through an injection molding part tracking detection algorithm, and displaying a detection result. Thedetection system is characterized by comprising a data acquisition module, an intelligent control module and a display module, and the intelligent control module comprises a data flow decomposition module, a defective product detection module, a defective product classification module, a target tracking module and a statistics module. According to the method, rapid, real-time and high-accuracy detection can be carried out on various defective products of different degrees, and the method has higher robustness and generalization ability in comparison with the traditional detection method.
Description
technical field [0001] The disclosure belongs to the technical field of intelligent detection of defective injection molded parts, and in particular relates to an intelligent visual detection method and system applied to the detection of defective injection molded parts. Background technique [0002] In the production and processing of injection molded parts, due to the uneven surface of the cavity, small demoulding slope, inconsistent demoulding direction and processing lines, insufficient cooling time, unreasonable distribution of mold ejection, operator errors and other reasons, there are some common products Defects such as flash, deformation, burns, cracks, cold material, etc. occur. Once these defective products flow into the next production chain, it will lead to certain safety hazards in the final product. Therefore, the quality inspection after the processing and production of injection molded parts is very important. [0003] In the traditional inspection process ...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more