Method and system for judging molding abnormalities based on image recognition
A technology of abnormality judgment and image recognition, applied in character and pattern recognition, instruments, calculations, etc., can solve the problems of low bellows forming precision, abnormal bellows hydroforming, low-precision bellows, etc.
Active Publication Date: 2021-12-17
JIANGSU NEW HENGJI SPECIAL EQUIP
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] At present, during the hydroforming process, there may be small deformations between the constituent parts of the bellows hydroforming device, that is, there are slight displacements between the constituent parts; in this case, although the bellows hydroforming device can still continue work, but the bellows produced by it will also have the defect of low forming accuracy; the existing patent application number is CN202110365387.0, and the patent name is a device and method for hydroforming of super-large-diameter corrugated pipes, which can greatly reduce the oversized When the caliber corrugated pipe is hydraulically formed, the thrust demanded by the equipment is required, and the overall one-time hydroforming of the super-large caliber corrugated pipe is realized with a small pressure to ensure the smooth progress of the work.
However, there is still a risk of abnormal bellows hydroforming, and the relevant staff do not know that the bellows hydroforming device has broken down, resulting in continuous production of low-precision bellows, causing a lot of losses
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0049] Such as figure 1 As shown, a method for judging molding abnormalities based on image recognition is proposed, including the following steps:
[0050] S1: Obtain a period of historical time series information, which is recorded as standard time series information;
[0051] S2: Obtain a press position image data set and a bellows image data set respectively corresponding to the standard time series information, and the press position image data set and the bellows image data set are respectively a complete set of bellows hydroforming actions The standard press position image data set and the standard bellows image data set in the process;
[0052] S3: When the whole action process of bellows hydroforming starts, real-time press position image data and real-time bellows image data are obtained;
[0053] S4: comparing and judging the real-time press position image data and the real-time bellows image data with the standard press position image data set and the standard bell...
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 relates to a method for judging molding abnormalities based on image recognition, which belongs to the technical field of image data processing, and acquires a period of historical time series information, which is recorded as standard time series information; and obtains press position images corresponding to the standard time series information respectively. The data set and the bellows image data set, the press position image data set and the bellows image data set are respectively the standard press position image data set and the bellows image data set in the complete action process of the bellows hydroforming. In the present invention, an abnormal alarm can be issued in time to let the relevant staff know that the hydroforming of the corrugated pipe has failed, and they can respond in time so that the low-precision corrugated pipe will not continue to be produced. The three elements of tube image and time series information are bound and judged, which greatly improves the accuracy of abnormal judgment, reduces the rate of misjudgment, and minimizes the labor cost of staff.
Description
technical field [0001] The invention belongs to the technical field of image data processing, and in particular relates to a method and system for judging molding abnormalities based on image recognition. Background technique [0002] At present, during the hydroforming process, there may be small deformations between the constituent parts of the bellows hydroforming device, that is, there are slight displacements between the constituent parts; in this case, although the bellows hydroforming device can still continue work, but the bellows produced by it will also have the defect of low forming accuracy; the existing patent application number is CN202110365387.0, and the patent name is a device and method for hydroforming of super-large-diameter corrugated pipes, which can greatly reduce the oversized When the caliber corrugated pipe is hydroforming, there is a demand for the thrust exerted by the equipment, and a small pressure is used to realize the overall hydroforming of ...
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
Login to View More IPC IPC(8): G06K9/00G06K9/20G06K9/62
CPCG06F18/22
Inventor 陈敬一王槐春鲍艳东
Owner JIANGSU NEW HENGJI SPECIAL EQUIP