A detection method for pre-filled nest boxes

Abstract

The present invention relates to the technical field of detection methods for pre-filled and sealed nest boxes, and provides a detection method for pre-filled and sealed nest boxes, comprising the following steps: S1, using a CCD detection camera to collect the edge lines of the Tyvek paper and the inner side of the nest box; S2, using a CCD detection camera to photograph the weld effect of the outer layer paper of the nest box that has passed the preliminary inspection to obtain a weld image; S3, calculating the weld width performance influence factor W; S4, calculating the weld uniformity performance influence factor U0; S5, calculating the weld area performance influence factor; S6, calculating the weld quality factor; S7, comparing the calculated weld quality factor with a preset weld quality factor. The beneficial effects of the present invention are as follows: By adopting optical imaging combined with an image processing algorithm, the welding quality can be accurately detected, the contradiction between airtightness and easy tearability can be balanced, and detection can be achieved without damaging the packaging.

Description

Technical Field

[0001] The present invention relates to the technical field of detection methods for pre-filled nest boxes, and specifically relates to a detection method for pre-filled nest boxes. Background Art

[0002] As an important packaging form in the modern medical field, pre-filled syringes are widely used in scenarios such as vaccines, biological agents, and emergency drugs due to their convenience, sterility, and high-precision drug delivery characteristics. As the core protective structure of pre-filled syringes, nest box packaging needs to have sealing performance, easy-opening performance, and physical protection functions, and its quality directly affects drug safety and use efficiency. However, the current production process of pre-filled nest box packaging still faces technical bottlenecks:

[0003] For example, the welding process between the outer layer paper and the nest box has problems with insufficient stability. Fluctuations in welding temperature, pressure, or time parameters are likely to result in uneven weld strength, manifested as poor sealing effects (such as air leakage or liquid leakage) or over-welding (such as excessive tearing force). The former may cause the drug to become ineffective during transportation or storage, and the latter affects the rapid access by medical staff, especially in emergency scenarios, which may delay the treatment opportunity.

[0004] In addition, traditional quality inspection methods mostly rely on manual visual inspection and sampling destructive testing, with low efficiency and insufficient coverage, making it difficult to achieve real-time monitoring of the entire production process. Existing automated detection systems have limited recognition accuracy for micron-level offsets and lack the ability to quantitatively evaluate welding strength and tearing performance, resulting in a relatively high risk of defective products flowing into downstream processes.

[0005] With the continuous improvement of the medical industry's requirements for packaging safety and compliance, developing a high-precision, non-destructive online detection method to monitor the welding parameters of Tyvek paper has become a key technical requirement for improving the quality of pre-filled nest box packaging. Summary of the Invention

[0006] The present invention aims at problems such as poor welding firmness, poor sealing effect, or difficulty in tearing after welding of the pre-filled nest box paper;

[0007] The present invention provides a detection method for pre-filled nest boxes, including the following steps:

[0008] S1. When the light source of the corresponding weld seam lights up after the nest box reaches the detection position, use a CCD detection camera to collect the edge lines of the Tyvek paper and the inner side of the nest box. The directional analysis module converts the image information into digital information, compares the distance L between the edge line of the Tyvek paper and the inner side edge line of the nest box and the included angle α formed between the corresponding edge lines, and compares them with a preset distance threshold L' and a preset included angle threshold α'. If the values of the distance L and the included angle α are less than the preset thresholds, it indicates that the placement position of the inner layer Tyvek paper is qualified; otherwise, it is unqualified.

[0009] S2. Use a CCD detection camera to photograph the weld effect of the outer layer paper of the nest box that has passed the preliminary inspection to obtain a weld image. Perform semantic segmentation processing on the obtained weld image to obtain an image of the welding surface area of the nest box and background information. Mark the contours of the inner layer paper, the edges of the nest box, and the weld image of the outer layer paper, and record the weld brightness. Determine the welding area based on the change in the gray value of the image area formed by continuous edge points.

[0010] S3. Calculate the weld width performance impact factor W;

[0011] ;

[0012] where β - γ represents the angular difference between adjacent pixel points on the weld edge in the image, and d represents the width variance of the weld corresponding to the edge image pixel points;

[0013] S4. Calculate the weld uniformity performance impact factor ;

[0014] ;

[0015] where represents the minimum brightness of the weld, represents the average brightness of the weld;

[0016] S5. Calculate the weld area performance impact factor ;

[0017] ;

[0018] where F(x) represents the corresponding fitting relationship curve between the gray value and the exposure amount, a and b are the pixel points at the initial and end points of the weld, represents the preset maximum area threshold;

[0019] S6. Calculate the weld quality factor ;

[0020] ;

[0021] S7. Compare the calculated weld quality factor with the preset minimum weld quality factor and maximum weld quality factor. If the weld quality factor falls between the minimum weld quality factor and the maximum weld quality factor , the weld quality is qualified; otherwise, it is unqualified.

[0022] As a preferred solution, the semantic segmentation processing in S2 is to segment the image into independent image individuals and strengthen the edge processing, and perform brightness testing on the obtained detection image.

[0023] As a preferred solution, the number of CCD detection cameras in S1 is 4, corresponding to the four sides of the nest box respectively.

[0024] As a preferred solution, the CCD detection camera captures the edge lines of the Tyvek paper and the inner edge of the nest box. The orientation analysis module converts the image information into digital information, compares the distance L between the four edge lines of the Tyvek paper and the inner edge line of the nest box, and the angle α formed between the corresponding edge lines, and compares the distance L with a preset distance threshold L' and a preset angle threshold α'. If the values of the distance L and the angle α are less than the preset thresholds, it indicates that the placement of the inner layer of Tyvek paper is qualified; otherwise, it is unqualified.

[0025] The beneficial effects of the present invention are:

[0026] This system utilizes optical imaging or laser sensing technology, combined with image processing algorithms, to accurately detect weld quality, balancing the trade-off between sealing and tearability without damaging the packaging. This system replaces traditional manual destructive sampling testing. Through high-speed data acquisition and processing, the system outputs test results in real time and automatically removes defective products from the production line, significantly improving detection efficiency and defect interception rates, preventing defective packaging from entering the market. DETAILED DESCRIPTION

[0027] To illustrate the characteristics of the present invention, the present invention will be further described below with reference to the embodiments.

[0028] Example:

[0029] An embodiment of the present invention provides a method for detecting a pre-filled nest box, comprising the following steps:

[0030] S1. When the nest box reaches the inspection position, the corresponding weld light source is illuminated. A CCD camera is used to capture the edge lines of the Tyvek paper and the inner edge line of the nest box. The directional analysis module converts the image information into digital information, compares the distance L between the edge line of the Tyvek paper and the inner edge line of the nest box, and the angle α formed between the corresponding edge lines, and compares the distance L with the preset distance threshold L' and the preset angle threshold α'. If the values of the distance L and the angle α are less than the preset thresholds, it indicates that the inner layer Tyvek paper placement position is qualified; otherwise, it is unqualified.

[0031] S2. Use a CCD detection camera to photograph the welding seam effect of the outer layer paper of the nest box that has passed the preliminary inspection to obtain a welding seam image. Perform semantic segmentation processing on the obtained welding seam image to obtain the nest box welding surface area image and background information. Segment the image into independent image individuals through instance segmentation and perform enhanced edge processing. Combine the obtained detection images for brightness testing, record the contours of the inner layer paper, the edges of the nest box, and the welding seam image of the outer layer paper, and the brightness of the welding seam. Determine the welding area based on the change in the gray value of the image area formed by continuous edge points;

[0032] S3. Calculate the influence factor W of the welding seam width performance;

[0033] ;

[0034] where, β - γ represents the angle difference between adjacent pixel points on the welding seam edge in the image, and d represents the width variance of the welding seam corresponding to the edge image pixel points;

[0035] S4. Calculate the influence factor of the welding seam uniformity performance ;

[0036] ;

[0037] where, represents the minimum brightness of the welding seam, represents the average brightness of the welding seam;

[0038] S5. Calculate the influence factor of the welding seam area performance ;

[0039] ;

[0040] where, F(x) represents the corresponding fitting relationship curve between the gray value and the exposure amount, a and b are the pixel points at the initial and end points of the welding seam, represents the preset maximum area threshold;

[0041] S6. Calculate the welding seam quality factor ;

[0042] ;

[0043] S7. Compare the calculated welding seam quality factor with the preset minimum welding seam quality factor and maximum welding seam quality factor;

[0044] where δ represents the welding seam quality factor, δmin represents the preset minimum welding seam quality factor, and δmax represents the preset maximum welding seam quality factor.

[0045] Welding seam quality factor If it falls between the minimum weld quality factor and the maximum weld quality factor, the weld quality is qualified.

[0046] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. The present invention has been described in detail with reference to the preferred embodiments. Those of ordinary skill in the art should understand that any changes, modifications, additions or substitutions made by those of ordinary skill in the art within the scope of the essence of the present invention do not depart from the purpose of the present invention and should also fall within the scope of protection of the claims of the present invention. Other related technical structures not exhaustively disclosed in the present invention are the prior art in the art.

Claims

1. A detection method for a pre-filled nest box, characterized in that, It includes the following steps: S1. When the light source of the corresponding weld seam lights up after the nest box reaches the detection position, use a CCD detection camera to collect the edge lines of the Tyvek paper and the inner side of the nest box. The orientation analysis module converts the image information into digital information, compares the distance L between the edge line of the Tyvek paper and the inner edge line of the nest box and the included angle α formed between the corresponding edge lines, and compares them with the preset distance threshold L' and the preset included angle threshold α'. If the values of the distance L and the included angle α are less than the preset thresholds, it means that the placement position of the inner-layer Tyvek paper is qualified; otherwise, it is unqualified. S2. Use a CCD detection camera to take pictures of the weld seam effect of the outer layer paper of the nest box that has passed the preliminary inspection to obtain a weld seam image. Perform semantic segmentation processing on the obtained weld seam image to obtain an image of the welding surface area of the nest box and background information. Mark the contours of the edges of the inner layer paper and the nest box and the weld seam image of the outer layer paper and record the weld seam brightness. Determine the welding area according to the change in the gray value of the image area formed by the continuous edge points. S3. Calculate the influence factor W of the weld width performance. ； Among them, β - γ represents the angle difference between adjacent pixel points on the weld seam edge in the image, and d represents the variance of the weld width at the corresponding positions of the pixel points on the weld seam image edge. S4. Calculate the influence factor U0 of the weld seam uniformity performance. ； Among them, E min represents the minimum brightness of the weld seam, and E av represents the average brightness of the weld seam; S5. Calculate the influence factor S of the weld seam area performance. ； Among them, F(x) represents the corresponding fitting relationship curve between the gray value and the exposure amount, a and b are respectively the pixel point values corresponding to the initial point and the end point of the weld seam in the two-dimensional coordinate system, and A max represents a preset maximum area threshold value; S6. Calculate the weld quality factor ; ； S7. Compare the calculated weld quality factor with the preset minimum weld quality factor and maximum weld quality factor. If the weld quality factor falls between the minimum weld quality factor δmin and the maximum weld quality factor δmax, the weld quality is qualified; otherwise, it is unqualified.

2. The detection method of the pre-filled nest box according to claim 1, characterized in that: The semantic segmentation processing in S2 is to perform instance segmentation on the image into independent image individuals and enhanced edge processing, and combine the obtained detection images for brightness testing.

3. The detection method of the pre-filled nest box according to claim 1, wherein: The number of CCD detection cameras in S1 is 4, corresponding to the four sides of the nest box respectively.

Images