CN117735462A - Control system for cosmetic packaging quality detection equipment - Google Patents
Control system for cosmetic packaging quality detection equipment Download PDFInfo
- Publication number
- CN117735462A CN117735462A CN202410184536.7A CN202410184536A CN117735462A CN 117735462 A CN117735462 A CN 117735462A CN 202410184536 A CN202410184536 A CN 202410184536A CN 117735462 A CN117735462 A CN 117735462A
- Authority
- CN
- China
- Prior art keywords
- packaging bottle
- before filling
- detection
- pose
- assembly
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004806 packaging method and process Methods 0.000 title claims abstract description 288
- 238000001514 detection method Methods 0.000 title claims abstract description 236
- 239000002537 cosmetic Substances 0.000 title claims abstract description 33
- 238000011049 filling Methods 0.000 claims abstract description 182
- 238000007789 sealing Methods 0.000 claims abstract description 31
- 238000007689 inspection Methods 0.000 claims description 29
- 238000000034 method Methods 0.000 claims description 29
- 238000012015 optical character recognition Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 9
- 238000000354 decomposition reaction Methods 0.000 claims description 7
- 239000000463 material Substances 0.000 claims description 6
- 238000005303 weighing Methods 0.000 claims description 6
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 239000003086 colorant Substances 0.000 claims description 2
- 238000012856 packing Methods 0.000 claims description 2
- 238000012372 quality testing Methods 0.000 claims description 2
- 238000013528 artificial neural network Methods 0.000 description 20
- 238000013527 convolutional neural network Methods 0.000 description 10
- 238000009826 distribution Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 6
- 238000012986 modification Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 6
- 230000003042 antagnostic effect Effects 0.000 description 4
- 125000004122 cyclic group Chemical group 0.000 description 4
- 230000006872 improvement Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000009517 secondary packaging Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention provides a control system for cosmetic packaging quality detection equipment, which relates to the field of equipment control, wherein the detection equipment comprises a detection module before filling and a detection module after sealing, the detection module before filling comprises an ultrasonic detection assembly, an image acquisition assembly and a point cloud acquisition assembly, and the detection module after sealing comprises a weight detection assembly and a tightness detection assembly; the control system for the cosmetic packaging quality detection equipment comprises a control module before filling and a control module after sealing, wherein the control module before filling is used for controlling an ultrasonic detection assembly, an image acquisition assembly and a point cloud acquisition assembly to detect the quality of a packaging bottle before filling, and the control module after sealing is used for controlling a weight detection assembly and a tightness detection assembly to detect the quality of the packaging bottle after sealing, so that the control system has the advantages of improving the efficiency and accuracy of cosmetic packaging quality detection.
Description
Technical Field
The invention relates to the field of equipment control, in particular to a control system for cosmetic packaging quality detection equipment.
Background
The cosmetic package refers to the general names of containers, materials, auxiliary materials and the like used according to a certain technical method for protecting products in the circulation process, facilitating storage and transportation and promoting sales. The manufacturing process of cosmetics comprises a series of production line processes of preparation, storage, filling, sealing, secondary packaging, trademark pasting, coding, wrapping, bundling and the like, and the packaging is increasingly valued by cosmetic manufacturers and consumers as an important process of cosmetic production and processing.
In the packaging quality detection process, products with unqualified packages and empty packages generally need to be removed, and in the prior art, the work is mainly carried out manually, so that huge labor cost and management cost are added to a factory, and meanwhile, the inspection qualification rate can not be guaranteed.
Accordingly, it is desirable to provide a control system for a cosmetic product packaging quality inspection device for improving the efficiency and accuracy of cosmetic product packaging quality inspection.
Disclosure of Invention
One of the embodiments of the present disclosure provides a control system for a cosmetic packaging quality detection device, where the detection device includes a pre-filling detection module and a post-sealing detection module, the pre-filling detection module includes an ultrasonic detection assembly, an image acquisition assembly, and a point cloud acquisition assembly, and the post-sealing detection module includes a weight detection assembly and a tightness detection assembly; the control system for the cosmetic packaging quality detection equipment comprises a control module before filling and a control module after sealing, wherein the control module before filling is used for controlling the ultrasonic detection assembly, the image acquisition assembly and the point cloud acquisition assembly to detect the quality of packaging bottles before filling, and the control module after sealing is used for controlling the weight detection assembly and the tightness detection assembly to detect the quality of the packaging bottles after sealing.
In some embodiments, the pre-filling detection module further comprises a first frame, a first conveying component, a first pose adjusting component, a second pose adjusting component, a third pose adjusting component and a first sensing component are arranged on the first frame, the ultrasonic detection component is arranged on the first pose adjusting component, the image acquisition component is arranged on the second pose adjusting component, the point cloud acquisition component is arranged on the third pose adjusting component, and the first pose adjusting component, the second pose adjusting component, the third pose adjusting component and the first sensing component are all arranged above the first conveying component; the control module control before the filling ultrasonic detection subassembly the image acquisition subassembly reaches the point cloud obtains the subassembly and carries out quality testing to the packing bottle before the filling, includes: braking the first transfer assembly when the first sensing assembly senses an object; controlling the second pose adjusting component to adjust the image acquisition component to an initial pose of image acquisition; the image acquisition component acquires an initial image of the packaging bottle under the initial image acquisition pose; based on the initial image of the packaging bottle, the first pose adjusting component is controlled to adjust the pose of the ultrasonic detection component, the third pose adjusting component is controlled to adjust the pose of the point cloud acquisition component, the second pose adjusting component is controlled to adjust the pose of the image acquisition component, and quality detection is carried out on the packaging bottle before filling.
In some embodiments, the pre-filling control module controls the first pose adjustment assembly to adjust the pose of the ultrasonic detection assembly, controls the third pose adjustment assembly to adjust the pose of the point cloud acquisition assembly, and controls the second pose adjustment assembly to adjust the pose of the image acquisition assembly based on the initial image of the packaging bottle, and performs quality detection on the packaging bottle before filling, including: based on the initial image of the packaging bottle, determining the position information and the form information of the packaging bottle before filling: generating a plurality of image acquisition target positions based on the position information and the form information of the packaging bottles before filling, and controlling the second pose adjusting assembly to adjust the pose of the image acquisition assembly based on the plurality of image acquisition target positions to acquire a plurality of packaging bottle images acquired at the plurality of image acquisition target positions; performing optical character recognition and color detection on the packaging bottles before filling based on the plurality of packaging bottle images; when the optical character recognition result and the color detection result of the packaging bottle before filling are qualified, generating an ultrasonic detection track based on the position information and the form information of the packaging bottle before filling through a first track generation model, wherein the ultrasonic detection track comprises a plurality of ultrasonic detection poses, controlling the first pose adjusting component to adjust the pose of the ultrasonic detection component based on the ultrasonic detection track, and acquiring an ultrasonic detection signal set, wherein the ultrasonic detection signal set comprises ultrasonic detection signals acquired under each ultrasonic detection pose; performing crack detection on the packaging bottle before filling based on the ultrasonic detection signal set; when the crack detection result of the packaging bottle before filling is qualified, generating a scanning track based on the position information and the form information of the packaging bottle before filling through a second track generation model, wherein the scanning track comprises a plurality of scanning pose, and controlling the third pose adjusting component to adjust the pose of the point cloud acquiring component based on the scanning track to acquire the point cloud information of the packaging bottle before filling; and carrying out three-dimensional detection on the packaging bottle before filling based on the point cloud information of the packaging bottle before filling.
In some embodiments, the crack detection of the packaging bottle before filling based on the ultrasonic detection signal set comprises: generating an ultrasonic comparison signal set based on related information of the packaging bottle before filling and the ultrasonic detection track through a signal generation model, wherein the ultrasonic comparison signal set comprises ultrasonic standard signals corresponding to ultrasonic detection signals acquired under each ultrasonic detection pose, and the related information of the packaging bottle before filling at least comprises material information of the packaging bottle before filling and form information of the packaging bottle before filling; for each ultrasonic detection signal, performing empirical mode decomposition on the ultrasonic detection signal, generating a plurality of content modal components and residual errors corresponding to the ultrasonic detection signal, performing denoising processing, and obtaining a plurality of denoised content modal components and residual errors corresponding to the ultrasonic detection signal; performing empirical mode decomposition on an ultrasonic standard signal corresponding to the ultrasonic detection signal to generate a plurality of connotation mode components and residual errors corresponding to the ultrasonic standard signal; and determining the crack condition of the packaging bottle before filling based on the plurality of denoised content modal components and residual errors corresponding to the ultrasonic detection signals and the plurality of content modal components and residual errors corresponding to the ultrasonic standard signals.
In some embodiments, the optical character recognition and color detection of the packaging bottles prior to filling based on the plurality of packaging bottle images comprises: determining a plurality of text areas based on the plurality of packaging bottle images; for each text region, determining the position information, text features and background region color features of the text region, wherein the text features comprise text color features, text size features, text integrity features and text arrangement features; calculating the area similarity between the text area and the standard text area based on the position information, text feature and background area color feature of the text area and the standard position information, standard text feature and standard background area color feature corresponding to the standard text area corresponding to the text area, wherein the standard text area is a text area of a standard packaging bottle with qualified quality corresponding to a packaging bottle, the standard position information of the standard text area comprises the position of each character of the standard text area, the standard text feature of the standard text area comprises the size and color of each character of the standard text area, and the standard background area color feature comprises the color of the area except the characters in the standard text area; and when the region similarity is larger than a preset region similarity threshold, performing optical character recognition on the character region to generate a character recognition result.
In some embodiments, the three-dimensional detection of the packaging bottle before filling based on the point cloud information of the packaging bottle before filling includes: determining at least one target area corresponding to the packaging bottle before filling based on relevant historical detection information of the packaging bottle before filling, wherein the relevant historical detection information of the packaging bottle before filling comprises detection results of the packaging bottles which are detected in the packaging bottles to which the packaging bottle before filling belongs; determining a three-dimensional characteristic information set of the packaging bottle before filling based on the point cloud information of the packaging bottle before filling and at least one target area corresponding to the packaging bottle before filling; and determining the form quality of the packaging bottle before filling based on the three-dimensional characteristic information set of the packaging bottle before filling.
In some embodiments, the post-sealing detection module comprises a second rack, a second induction component and a detection table are arranged on the second rack, and the weight detection component and the tightness detection component are both arranged on the detection table; the weight detection assembly comprises a clamping seat and at least one weighing sensor arranged between the detection table and the clamping seat, wherein the clamping seat is used for accommodating the sealed packaging bottle; the tightness detection assembly comprises a vibration device and a sound collection device, wherein the sound collection device is arranged on the clamping seat.
In some embodiments, the post-closure control module is configured to control the weight detection assembly and the tightness detection assembly to perform quality detection on the sealed packaging bottle, and includes: when the second sensing component senses an object, the weighing sensor is started to acquire the weight information of the sealed packaging bottle; determining filling quality based on the obtained weight information of the sealed packaging bottle; when the filling quality is qualified, starting the vibration device and the sound collecting device, wherein the sound collecting device is used for collecting sound information of the sealed packaging bottle in the running process of the vibration device; and determining the tightness of the sealed packaging bottle based on the collected sound information of the sealed packaging bottle in the running process of the vibration device.
In some embodiments, the post-closure control module determines tightness of the closed packaging bottle based on collected sound information of the closed packaging bottle during operation of the vibration device, including: denoising the collected sound information of the sealed packaging bottle in the running process of the vibrating device to obtain denoised sound information; performing feature extraction processing on the denoised sound information to determine the features of the denoised sound information; and determining the tightness of the sealed packaging bottle based on the characteristics of the denoised sound information.
In some embodiments, the characteristics of the denoised sound information at least include time domain characteristics and frequency domain characteristics of the denoised sound information; the post-sealing control module determines the tightness of the sealed packaging bottle based on the characteristics of the denoised sound information, and comprises the following steps: and determining the tightness of the sealed packaging bottle based on the time domain characteristics and the frequency domain characteristics of the denoised sound information through an anomaly identification model.
Compared with the prior art, the control system for the cosmetic packaging quality detection equipment provided by the specification has the following beneficial effects:
1. the control module controls the ultrasonic detection assembly, the image acquisition assembly and the point cloud acquisition assembly to acquire related information of the packaging bottle before filling, automatically performs data processing to finish quality detection of the packaging bottle before filling, controls the weight detection assembly and the tightness detection assembly to acquire related information of the packaging bottle after sealing through the control module after sealing, and automatically performs data processing to finish quality detection of the packaging bottle after sealing;
2. setting a detection sequence, firstly performing detection work with lower cost and lower complexity, such as optical character recognition and color detection, and sequentially performing subsequent detection work, such as crack detection and three-dimensional detection when the detection with lower cost and lower complexity passes, wherein the detection work has higher efficiency and lower cost compared with simultaneous detection of multiple items;
3. The ultrasonic detection track of the packaging bottle which is more suitable for the detection is generated based on the position information and the form information of the packaging bottle before filling through the first track generation model, the scanning track of the packaging bottle which is more suitable for the detection is generated based on the position information and the form information of the packaging bottle before filling through the second track generation model, compared with the ultrasonic detection and scanning through the fixed track, the ultrasonic detection signal and the point cloud information which are acquired later are more effective, and the processing work of invalid data is reduced.
Drawings
The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:
FIG. 1 is a block schematic diagram of a control system for a cosmetic product packaging quality inspection device according to some embodiments of the present disclosure;
FIG. 2 is a schematic flow diagram of quality detection according to some embodiments of the present disclosure;
FIG. 3 is a schematic flow chart of quality inspection of packaging bottles prior to filling according to an adjusted pose according to some embodiments of the present disclosure;
FIG. 4 is a schematic flow diagram of crack detection according to some embodiments of the present disclosure;
FIG. 5 is a schematic flow chart of optical character recognition and color detection of a packaging bottle prior to filling according to some embodiments of the present disclosure;
FIG. 6 is a schematic flow chart of quality inspection of sealed packaging bottles according to some embodiments of the present disclosure;
FIG. 7 is a schematic diagram of a pre-filled detection module according to some embodiments of the present disclosure;
fig. 8 is a flow chart of a control method for a detection device according to some embodiments of the present disclosure.
In the figure, 710, a first rack; 720. a first transfer assembly; 730. a first pose adjustment assembly; 740. a second pose adjustment assembly; 750. and a third pose adjustment assembly.
Detailed Description
In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present specification, and it is possible for those of ordinary skill in the art to apply the present specification to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.
A flowchart is used in this specification to describe the operations performed by the system according to embodiments of the present specification. It should be appreciated that the preceding or following operations are not necessarily performed in order precisely. Rather, the steps may be processed in reverse order or simultaneously. Also, other operations may be added to or removed from these processes.
Fig. 1 is a block diagram of a control system for a cosmetic product packaging quality inspection device according to some embodiments of the present disclosure. The cosmetic packaging quality detection equipment comprises a detection module before filling and a detection module after sealing, wherein the detection module before filling comprises an ultrasonic detection assembly, an image acquisition assembly and a point cloud acquisition assembly, and the detection module after sealing comprises a weight detection assembly and a tightness detection assembly. As shown in fig. 1, the control system for the cosmetic packaging quality detection device comprises a control module before filling and a control module after sealing, wherein the control module before filling is used for controlling the ultrasonic detection assembly, the image acquisition assembly and the point cloud acquisition assembly to detect the quality of the packaging bottle before filling, and the control module after sealing is used for controlling the weight detection assembly and the tightness detection assembly to detect the quality of the packaging bottle after sealing.
Fig. 7 is a schematic structural diagram of a detection module before filling according to some embodiments of the present disclosure, as shown in fig. 7, the detection module before filling further includes a first rack 710, a first transmission component 720, a first pose adjustment component 730, a second pose adjustment component 740, a third pose adjustment component 750, and a first sensing component are disposed on the first rack 710, an ultrasonic detection component is disposed on the first pose adjustment component 730, an image acquisition component is disposed on the second pose adjustment component 740, a point cloud acquisition component is disposed on the third pose adjustment component 750, and the first pose adjustment component 730, the second pose adjustment component 740, the third pose adjustment component 750, and the first sensing component are all disposed above the first transmission component 720. The first pose adjustment assembly 730, the second pose adjustment assembly 740, and the third pose adjustment assembly 750 may be mechanical arms.
In some embodiments, the first sensing assembly may include a plurality of infrared pairs of tubes, it being understood that when a packaging bottle prior to filling passes the first sensing assembly, at least a portion of the infrared pairs of tubes included in the first sensing assembly emit infrared light that is blocked.
Fig. 2 is a schematic flow chart of quality detection according to some embodiments of the present disclosure, as shown in fig. 2, in some embodiments, a control module before filling controls an ultrasonic detection assembly, an image acquisition assembly, and a point cloud acquisition assembly to perform quality detection on a packaging bottle before filling, including:
when the first sensing component senses an object, the first transfer component 720 is braked;
controlling the second pose adjustment component 740 to adjust the image acquisition component to an initial pose of image acquisition;
the image acquisition component acquires an initial image of the packaging bottle under an initial image acquisition pose;
based on the initial image of the packaging bottle, the first pose adjusting component 730 is controlled to adjust the pose of the ultrasonic detecting component, the third pose adjusting component 750 is controlled to adjust the pose of the point cloud acquiring component, and the second pose adjusting component 740 is controlled to adjust the pose of the image acquiring component, so that quality detection is carried out on the packaging bottle before filling.
Specifically, when the number of infrared transmitting tubes in the first sensing assembly, in which infrared rays are blocked, is greater than a preset number threshold (for example, 5), the first sensing assembly senses an object. The preset number threshold value can be determined based on the installation mode of the infrared geminate transistors.
The initial pose of image acquisition may be a calibrated pose. The initial image of the packaging bottle is the image acquired by the image acquisition assembly under the initial pose of image acquisition.
Fig. 3 is a schematic flow chart of quality detection of a packaging bottle before filling according to an embodiment of the present disclosure, as shown in fig. 3, in some embodiments, a control module before filling controls a first pose adjustment component 730 to adjust a pose of an ultrasonic detection component, controls a third pose adjustment component 750 to adjust a pose of a point cloud acquisition component, and controls a second pose adjustment component 740 to adjust a pose of an image acquisition component based on an initial image of the packaging bottle, and performs quality detection of the packaging bottle before filling, including:
based on the initial image of the packaging bottle, determining the position information and the form information of the packaging bottle before filling:
generating a plurality of image acquisition target positions based on the position information and the form information of the packaging bottles before filling, and controlling the second pose adjustment assembly 740 to adjust the pose of the image acquisition assembly based on the plurality of image acquisition target positions to acquire a plurality of packaging bottle images acquired under the plurality of image acquisition target positions;
based on a plurality of packaging bottle images, carrying out optical character recognition and color detection on the packaging bottles before filling;
When the optical character recognition result and the color detection result of the packaging bottle before filling are qualified, generating an ultrasonic detection track based on the position information and the form information of the packaging bottle before filling through a first track generation model, wherein the ultrasonic detection track comprises a plurality of ultrasonic detection poses, controlling a first pose adjusting component 730 to adjust the pose of the ultrasonic detection component based on the ultrasonic detection track, and acquiring an ultrasonic detection signal set, wherein the ultrasonic detection signal set comprises ultrasonic detection signals acquired under each ultrasonic detection pose;
performing crack detection on the packaging bottle before filling based on the ultrasonic detection signal set;
when the crack detection result of the packaging bottle before filling is qualified, generating a scanning track based on the position information and the form information of the packaging bottle before filling through a second track generation model, wherein the scanning track comprises a plurality of scanning positions, and controlling a third position adjusting component 750 to adjust the position of a point cloud obtaining component based on the scanning track so as to obtain the point cloud information of the packaging bottle before filling;
and carrying out three-dimensional detection on the packaging bottle before filling based on the point cloud information of the packaging bottle before filling.
Specifically, the position information of the packaging bottle before filling may be coordinates of the packaging bottle before filling under a world coordinate system, and the form information of the packaging bottle before filling may include information such as height and diameter of the packaging bottle before filling.
The first trajectory generation model and the second trajectory generation model may each be one of a Convolutional Neural Network (CNN), a Deep Neural Network (DNN), a Recurrent Neural Network (RNN), a multi-layer neural network (MLP), a generation antagonistic neural network (GAN), or any combination thereof.
In some embodiments, the location information and the form information of the packaging bottle prior to filling may be determined by:
acquiring an area-of-interest image from the initial image of the packaging bottle, wherein the area-of-interest image is an image of an area of the packaging bottle before filling in the initial image of the packaging bottle;
acquiring a plurality of template images, wherein the template images can be pre-acquired standard images of packaging bottles before filling, and one template image corresponds to one packaging bottle before filling;
for each template image, determining the image RGB value distribution similarity based on a pixel RGB value distribution matrix corresponding to the region of interest image and a pixel RGB value distribution matrix corresponding to the template image, wherein row vectors of the pixel RGB value distribution matrix represent RGB values of one row of pixels, and column vectors of the pixel RGB value distribution matrix represent RGB values of one column of pixels;
Determining the similarity of the outline shape of the packaging bottle based on the outline shape of the packaging bottle corresponding to the region of interest image and the outline shape of the packaging bottle corresponding to the template image;
calculating the similarity of the packaging bottle between the region of interest image and the template image based on the distribution similarity of the RGB values of the images and the shape similarity of the outline of the packaging bottle, and determining a target template image;
acquiring information such as the height, the diameter and the like of a packaging bottle corresponding to a pre-stored target template image based on the target template image;
acquiring an image of the packaging bottle before filling, which is shot in advance, at a calibration position based on a target template image, wherein the calibration coordinates are calibrated under a world coordinate system and an image acquisition initial pose coordinate system;
and determining the position information of the packaging bottle before filling based on the size of the packaging bottle in the initial image of the packaging bottle, the position information of a plurality of characteristic points and the size of the packaging bottle in the image of the packaging bottle before filling, which is shot in advance, under the calibration position.
Specifically, the packaging bottle similarity between the region of interest image and the template image may be calculated based on the following formula:
wherein,for the similarity of the packaging bottle between the region of interest image and the jth template image, For image RGB value distribution similarity between the region of interest image and the jth template image,for the similarity of the contour shape of the packaging bottle between the region of interest image and the jth template image,、all are preset weights.
The template image with the highest similarity of the packaging bottles can be used as the target template image.
The coordinates of the packaging bottle before filling in the world coordinate system can be calculated based on the following formula:
wherein, the method comprises the following steps of) For the coordinates of the j-th point of the packaging bottle before filling in the world coordinate system,for determining an offset matrix based on the size of the packaging bottle in the initial image of the packaging bottle and the position information of a plurality of characteristic points and the size of the packaging bottle in the image of the packaging bottle before being filled in a calibration position, which is shot in advance,the method is characterized in that a conversion matrix between an initial pose coordinate system and a world coordinate system is acquired for an image，) The coordinate of the j-th point of the packaging bottle before filling in the calibration position is in the initial pose coordinate system of image acquisition.
Fig. 5 is a schematic flow chart of optical character recognition and color detection for a packaging bottle before filling according to some embodiments of the present disclosure, as shown in fig. 5, in some embodiments, based on a plurality of packaging bottle images, the optical character recognition and color detection for the packaging bottle before filling includes:
Determining a plurality of text areas based on the plurality of packaging bottle images;
for each text region, determining the position information, text features and background region color features of the text region, wherein the text features comprise text color features, text size features, text integrity features and text arrangement features;
calculating the area similarity between the text area and the standard text area based on the position information of the text area, the text feature and background area color feature and the standard position information of the standard text area, the standard text feature and the standard background area color feature corresponding to the text area, wherein the standard text area is the text area of the standard packaging bottle with qualified quality corresponding to the packaging bottle, the standard position information of the standard text area comprises the position of each character of the standard text area, the standard text feature of the standard text area comprises the size and the color of each character of the standard text area, and the standard background area color feature comprises the colors of areas except the characters in the standard text area;
when the region similarity is larger than a preset region similarity threshold, performing optical character recognition on the character region to generate a character recognition result.
Specifically, for each packaging bottle image, the text area in the packaging bottle image can be identified through the target identification model. For each text region, the position information, the text features and the background region color features of the text region can be identified by a feature identification model based on the image of the text region, wherein the target identification model and the feature identification model can be one or any combination of a Convolutional Neural Network (CNN), a Deep Neural Network (DNN), a cyclic neural network (RNN), a multi-layer neural network (MLP), a generation antagonistic neural network (GAN) and the like.
For example, the region similarity between the text region and the standard text region may be calculated based on the following formula:
wherein,for the region similarity between the mth text region and the corresponding standard text region,for the similarity of the position information between the mth text region and the corresponding standard text region,for the word feature similarity between the mth word region and the corresponding standard word region,for the background area color feature similarity between the mth text area and the corresponding standard text area,、andAll are preset weights.
Specifically, the cosine similarity between the character information obtained after the optical character recognition is performed on the character area and the standard character information corresponding to the character area can be calculated, and when the cosine similarity is greater than a preset cosine similarity threshold value, the optical character recognition result and the color detection result of the packaging bottle before filling are judged to be qualified.
FIG. 4 is a schematic flow chart of crack detection according to some embodiments of the present disclosure, as shown in FIG. 4, in some embodiments, crack detection of a packaging bottle prior to filling based on a set of ultrasonic detection signals, including:
generating an ultrasonic comparison signal set based on related information of the packaging bottle before filling and an ultrasonic detection track through a signal generation model, wherein the ultrasonic comparison signal set comprises ultrasonic standard signals corresponding to ultrasonic detection signals acquired under each ultrasonic detection pose;
for each ultrasonic detection signal, performing empirical mode (Empirical Mode Decomposition) decomposition on the ultrasonic detection signal, generating a plurality of connotation mode components and residual errors corresponding to the ultrasonic detection signal, performing denoising treatment, and obtaining a plurality of denoised connotation mode components and residual errors corresponding to the ultrasonic detection signal;
performing empirical mode decomposition on an ultrasonic standard signal corresponding to the ultrasonic detection signal to generate a plurality of connotation mode components and residual errors corresponding to the ultrasonic standard signal;
and determining the crack condition of the packaging bottle before filling based on the plurality of content modal components and residual errors after denoising corresponding to the ultrasonic detection signals and the plurality of content modal components and residual errors corresponding to the ultrasonic standard signals.
Specifically, the related information of the packaging bottle before filling may include material information of the packaging bottle before filling, form information of the packaging bottle before filling, and the like. The ultrasonic standard signal may be an ultrasonic detection signal obtained by the predicted ultrasonic detection unit at a certain ultrasonic detection pose. The signal generation model may generate an impedance network (Generative Adversarial Nets, GAN) model.
In some embodiments, the related information of the packaging bottle before filling may further include ultrasonic parameter information corresponding to the packaging bottle before filling. Specifically, the ultrasonic parameter information corresponding to the packaging bottle before filling can be determined by the parameter determination model based on the material information of the packaging bottle before filling, the form information of the packaging bottle before filling and the like. The parameter determination model may be one of Convolutional Neural Network (CNN), deep Neural Network (DNN), cyclic neural network (RNN), multi-layer neural network (MLP), generation antagonistic neural network (GAN), or any combination thereof.
The denoising process may be performed on the plurality of content modal components and residuals corresponding to the ultrasonic detection signal in any manner. For example, the denoising model may be used to denoise a plurality of content modal components and residuals corresponding to the ultrasonic detection signal. The denoising model may be one of Convolutional Neural Network (CNN), deep Neural Network (DNN), cyclic neural network (RNN), multi-layer neural network (MLP), generation antagonistic neural network (GAN), or any combination thereof.
In some embodiments, the crack condition of the packaging bottle before filling can be determined by the crack determination model based on the plurality of content modal components and residual errors after denoising corresponding to the ultrasonic detection signal and the plurality of content modal components and residual errors corresponding to the ultrasonic standard signal. The crack condition of the packaging bottle before filling can comprise information such as crack position, crack size and the like. And when the crack determination model determines that no crack exists, judging that the crack detection result of the packaging bottle before filling is qualified.
In some embodiments, three-dimensional inspection of a pre-filled packaging bottle based on point cloud information of the pre-filled packaging bottle includes:
determining at least one target area corresponding to the packaging bottle before filling based on relevant historical detection information of the packaging bottle before filling;
determining a three-dimensional characteristic information set of the packaging bottle before filling based on point cloud information of the packaging bottle before filling and at least one target area corresponding to the packaging bottle before filling;
and determining the form quality of the packaging bottle before filling based on the three-dimensional characteristic information set of the packaging bottle before filling.
The target area may be a location where such a package to which the package prior to filling belongs is susceptible to deformation. The relevant history detection information of the packaging bottles before filling may include detection results of the packaging bottles which have been detected in the packaging bottles to which the packaging bottles before filling belong, for example, deformed parts and the like.
Specifically, the at least one target area corresponding to the packaging bottle before filling can be determined by:
in the point cloud information of the packaging bottles before filling and the packaging bottles before filling, the detection result is the deformation part corresponding to each packaging bottle which is deformed, and then the deformation frequency of each deformation part is determined, for example, the deformation frequency of each deformation part can be determined based on the following formula:
wherein,is the deformation frequency of the nth deformation part,the number of times that the nth deformation part is deformed in the relevant historical detection information of the packaging bottle before filling,the total number of deformation of the packaging bottles before filling in the relevant historical detection information of the packaging bottles before filling;
taking a deformation part with deformation frequency larger than a first preset deformation frequency threshold value as a first target area;
the deformation part with the deformation frequency smaller than or equal to a first preset deformation frequency threshold and larger than a second preset deformation frequency threshold is used as a candidate area, wherein the second preset deformation frequency threshold is smaller than the first preset deformation frequency threshold;
for each first target region, an associated region of the first target region is determined, i.e. the association coefficient between the candidate region and the first target region is determined first, e.g. the association coefficient between the other regions and the first target region may be calculated based on the following formula:
Wherein,for the association coefficient between the kth first target region and the ith candidate region,for the number of simultaneous deformations of the kth first target area and the first candidate area in the relevant history of packaging bottles before filling,the number of times that the kth first target area is deformed in the relevant historical detection information of the packaging bottle before filling;
and taking the candidate region with the association coefficient larger than the preset association coefficient threshold value as an association region of the first target region and also as a second target region, wherein at least one target region comprises all first target regions and all second target regions.
The three-dimensional model of the packaging bottle before filling can be generated based on the point cloud information of the packaging bottle before filling, and then the three-dimensional characteristics corresponding to each target area are determined, and whether the packaging bottle before filling is deformed or not is judged.
In some embodiments, the post-sealing detection module comprises a second frame, a second sensing assembly and a detection table are arranged on the second frame, and the weight detection assembly and the tightness detection assembly are arranged on the detection table. The weight detection assembly comprises a clamping seat and at least one weighing sensor arranged between the detection table and the clamping seat, wherein the clamping seat is used for accommodating the sealed packaging bottle. The tightness detection assembly comprises a vibration device and a sound collection device, and the sound collection device is arranged on the clamping seat.
Fig. 6 is a schematic flow chart of quality detection of a sealed packaging bottle according to some embodiments of the present disclosure, as shown in fig. 6, in some embodiments, the quality detection of the sealed packaging bottle by the weight detection component and the tightness detection component is controlled by the control module after sealing, including:
when the second sensing component senses an object, a weighing sensor is started to acquire the weight information of the sealed packaging bottle;
determining filling quality based on the obtained weight information of the sealed packaging bottles;
when the filling quality is qualified, starting a vibration device and a sound collecting device, wherein the sound collecting device is used for collecting sound information of the sealed packaging bottle in the running process of the vibration device;
and determining the tightness of the sealed packaging bottle based on the collected sound information of the sealed packaging bottle in the running process of the vibration device.
Specifically, when the weight information of the sealed packaging bottle is smaller than a preset weight threshold, empty bottles or insufficient filling can be judged, and the packaging bottle needs to be reprocessed, namely the quality of filling is judged to be unqualified.
In some embodiments, determining the tightness of the sealed packaging bottle based on the collected sound information of the sealed packaging bottle during the operation of the vibration device comprises:
The method comprises the steps of performing characteristic extraction processing on collected sound information of the sealed packaging bottle in the running process of a vibrating device, and obtaining denoised sound information;
denoising the denoised sound information, and determining the time domain characteristics and the frequency domain characteristics of the denoised sound information;
and determining the tightness of the sealed packaging bottle based on the time domain characteristics and the frequency domain characteristics of the denoised sound information.
It will be appreciated that when the seal is less tight, the sealed bottle may experience abnormal sounds during operation of the vibrating device. The tightness of the sealed packaging bottle can be determined based on the time domain features and the frequency domain features of the denoised sound information through an anomaly identification model, wherein the anomaly identification model can be one or any combination of a Convolutional Neural Network (CNN), a Deep Neural Network (DNN), a cyclic neural network (RNN), a multi-layer neural network (MLP), a generation countermeasure neural network (GAN) and the like.
Fig. 8 is a flow chart of a control method for a detecting device according to some embodiments of the present specification, as shown in fig. 8, in some embodiments, the control method for a cosmetic package quality detecting device includes:
Step 810, before filling, controlling an image acquisition component to acquire an initial image of a packaging bottle before filling under an initial image acquisition pose, and adjusting the pose of an ultrasonic detection component, the pose of a point cloud acquisition component and the pose of the image acquisition component based on the initial image of the packaging bottle to perform quality detection on the packaging bottle before filling;
step 820, after sealing, obtaining weight information of the sealed packaging bottle, determining filling quality based on the obtained weight information of the sealed packaging bottle, and starting a vibration device and a sound collection device when the filling quality is qualified, wherein the sound collection device is used for collecting sound information of the sealed packaging bottle in the operation process of the vibration device, and determining tightness of the sealed packaging bottle based on the collected sound information of the sealed packaging bottle in the operation process of the vibration device.
In some embodiments, the control method for the cosmetic product packaging quality detection apparatus may be performed by a control system for the cosmetic product packaging quality detection apparatus. For more description of the control method for the detection device, reference may be made to fig. 1-7 and their related description, which are not repeated here.
While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations to the present disclosure may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this specification, and therefore, such modifications, improvements, and modifications are intended to be included within the spirit and scope of the exemplary embodiments of the present invention.
Furthermore, the order in which the elements and sequences are processed, the use of numerical letters, or other designations in the description are not intended to limit the order in which the processes and methods of the description are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present disclosure. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.
Likewise, it should be noted that in order to simplify the presentation disclosed in this specification and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the present description. Indeed, less than all of the features of a single embodiment disclosed above.
Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.
Claims (10)
1. The control system for the cosmetic packaging quality detection equipment is characterized by comprising a pre-filling detection module and a post-sealing detection module, wherein the pre-filling detection module comprises an ultrasonic detection assembly, an image acquisition assembly and a point cloud acquisition assembly, and the post-sealing detection module comprises a weight detection assembly and a tightness detection assembly;
The control system for the cosmetic packaging quality detection equipment comprises a control module before filling and a control module after sealing, wherein the control module before filling is used for controlling the ultrasonic detection assembly, the image acquisition assembly and the point cloud acquisition assembly to detect the quality of packaging bottles before filling, and the control module after sealing is used for controlling the weight detection assembly and the tightness detection assembly to detect the quality of the packaging bottles after sealing.
2. The control system for cosmetic product packaging quality detection equipment according to claim 1, wherein the pre-filling detection module further comprises a first rack, a first conveying component, a first pose adjustment component, a second pose adjustment component, a third pose adjustment component and a first sensing component are arranged on the first rack, the ultrasonic detection component is arranged on the first pose adjustment component, the image acquisition component is arranged on the second pose adjustment component, the point cloud acquisition component is arranged on the third pose adjustment component, and the first pose adjustment component, the second pose adjustment component, the third pose adjustment component and the first sensing component are all arranged above the first conveying component;
The control module control before the filling ultrasonic detection subassembly the image acquisition subassembly reaches the point cloud obtains the subassembly and carries out quality testing to the packing bottle before the filling, includes:
braking the first transfer assembly when the first sensing assembly senses an object;
controlling the second pose adjusting component to adjust the image acquisition component to an initial pose of image acquisition;
the image acquisition component acquires an initial image of the packaging bottle under the initial image acquisition pose;
based on the initial image of the packaging bottle, the first pose adjusting component is controlled to adjust the pose of the ultrasonic detection component, the third pose adjusting component is controlled to adjust the pose of the point cloud acquisition component, the second pose adjusting component is controlled to adjust the pose of the image acquisition component, and quality detection is carried out on the packaging bottle before filling.
3. The control system for a cosmetic product packaging quality inspection apparatus according to claim 2, wherein the pre-filling control module controls the first pose adjustment assembly to adjust the pose of the ultrasonic inspection assembly, controls the third pose adjustment assembly to adjust the pose of the point cloud acquisition assembly, and controls the second pose adjustment assembly to adjust the pose of the image acquisition assembly based on the initial image of the packaging bottle, and performs quality inspection of the packaging bottle before filling, comprising:
Based on the initial image of the packaging bottle, determining the position information and the form information of the packaging bottle before filling:
generating a plurality of image acquisition target positions based on the position information and the form information of the packaging bottles before filling, and controlling the second pose adjusting assembly to adjust the pose of the image acquisition assembly based on the plurality of image acquisition target positions to acquire a plurality of packaging bottle images acquired at the plurality of image acquisition target positions;
performing optical character recognition and color detection on the packaging bottles before filling based on the plurality of packaging bottle images;
when the optical character recognition result and the color detection result of the packaging bottle before filling are qualified, generating an ultrasonic detection track based on the position information and the form information of the packaging bottle before filling through a first track generation model, wherein the ultrasonic detection track comprises a plurality of ultrasonic detection poses, controlling the first pose adjusting component to adjust the pose of the ultrasonic detection component based on the ultrasonic detection track, and acquiring an ultrasonic detection signal set, wherein the ultrasonic detection signal set comprises ultrasonic detection signals acquired under each ultrasonic detection pose;
Performing crack detection on the packaging bottle before filling based on the ultrasonic detection signal set;
when the crack detection result of the packaging bottle before filling is qualified, generating a scanning track based on the position information and the form information of the packaging bottle before filling through a second track generation model, wherein the scanning track comprises a plurality of scanning pose, and controlling the third pose adjusting component to adjust the pose of the point cloud acquiring component based on the scanning track to acquire the point cloud information of the packaging bottle before filling;
and carrying out three-dimensional detection on the packaging bottle before filling based on the point cloud information of the packaging bottle before filling.
4. A control system for a cosmetic product packaging quality inspection apparatus according to claim 3, wherein the crack inspection of the packaging bottle prior to filling based on the ultrasonic inspection signal set comprises:
generating an ultrasonic comparison signal set based on related information of the packaging bottle before filling and the ultrasonic detection track through a signal generation model, wherein the ultrasonic comparison signal set comprises ultrasonic standard signals corresponding to ultrasonic detection signals acquired under each ultrasonic detection pose, and the related information of the packaging bottle before filling at least comprises material information of the packaging bottle before filling and form information of the packaging bottle before filling;
For each ultrasonic detection signal, performing empirical mode decomposition on the ultrasonic detection signal, generating a plurality of content modal components and residual errors corresponding to the ultrasonic detection signal, performing denoising processing, and obtaining a plurality of denoised content modal components and residual errors corresponding to the ultrasonic detection signal;
performing empirical mode decomposition on an ultrasonic standard signal corresponding to the ultrasonic detection signal to generate a plurality of connotation mode components and residual errors corresponding to the ultrasonic standard signal;
and determining the crack condition of the packaging bottle before filling based on the plurality of denoised content modal components and residual errors corresponding to the ultrasonic detection signals and the plurality of content modal components and residual errors corresponding to the ultrasonic standard signals.
5. The control system for a cosmetic product packaging quality inspection apparatus according to claim 4, wherein the optical character recognition and color inspection of the packaging bottles before filling based on the plurality of packaging bottle images comprises:
determining a plurality of text areas based on the plurality of packaging bottle images;
for each text region, determining the position information, text features and background region color features of the text region, wherein the text features comprise text color features, text size features, text integrity features and text arrangement features;
Calculating the area similarity between the character area and the standard character area based on the position information, character characteristics and background area color characteristics of the character area and the standard position information, standard character characteristics and standard background area color characteristics of the standard character area corresponding to the character area, wherein the standard character area is the character area of the standard packaging bottle with qualified quality corresponding to the packaging bottle, the standard position information of the standard character area comprises the position of each character of the standard character area, the standard character characteristics of the standard character area comprise the size and color of each character of the standard character area, and the standard background area color characteristics comprise the colors of areas except the characters in the standard character area;
and when the region similarity is larger than a preset region similarity threshold, performing optical character recognition on the text region to generate a text recognition result.
6. The control system for a cosmetic product packaging quality inspection apparatus according to claim 5, wherein the three-dimensional inspection of the packaging bottle before filling based on the point cloud information of the packaging bottle before filling comprises:
Determining at least one target area corresponding to the packaging bottle before filling based on relevant historical detection information of the packaging bottle before filling, wherein the relevant historical detection information of the packaging bottle before filling comprises detection results of the packaging bottles which are detected in the packaging bottles to which the packaging bottle before filling belongs;
determining a three-dimensional characteristic information set of the packaging bottle before filling based on the point cloud information of the packaging bottle before filling and at least one target area corresponding to the packaging bottle before filling;
and determining the form quality of the packaging bottle before filling based on the three-dimensional characteristic information set of the packaging bottle before filling.
7. The control system for a cosmetic product packaging quality inspection device of any one of claims 1-6, wherein the post-sealing inspection module comprises a second frame, a second sensing assembly and an inspection station are disposed on the second frame, and the weight inspection assembly and the tightness inspection assembly are both disposed on the inspection station;
the weight detection assembly comprises a clamping seat and at least one weighing sensor arranged between the detection table and the clamping seat, wherein the clamping seat is used for accommodating the sealed packaging bottle;
The tightness detection assembly comprises a vibration device and a sound collection device, wherein the sound collection device is arranged on the clamping seat.
8. The control system for a cosmetic product packaging quality inspection apparatus of claim 7, wherein the post-closure control module controls the weight inspection assembly and the tightness inspection assembly to inspect the quality of the sealed packaging bottle, comprising:
when the second sensing component senses an object, the weighing sensor is started to acquire the weight information of the sealed packaging bottle;
determining filling quality based on the obtained weight information of the sealed packaging bottle;
when the filling quality is qualified, starting the vibration device and the sound collecting device, wherein the sound collecting device is used for collecting sound information of the sealed packaging bottle in the running process of the vibration device;
and determining the tightness of the sealed packaging bottle based on the collected sound information of the sealed packaging bottle in the running process of the vibration device.
9. The control system for a cosmetic product packaging quality inspection apparatus of claim 8, wherein the post-closure control module determines tightness of the closed packaging bottle based on collected sound information of the closed packaging bottle during operation of the vibration device, comprising:
Denoising the collected sound information of the sealed packaging bottle in the running process of the vibrating device to obtain denoised sound information;
performing feature extraction processing on the denoised sound information to determine the features of the denoised sound information;
and determining the tightness of the sealed packaging bottle based on the characteristics of the denoised sound information.
10. The control system for a cosmetic product packaging quality inspection device of claim 9, wherein the characteristics of the denoised sound information include at least time domain characteristics and frequency domain characteristics of the denoised sound information;
the post-sealing control module determines the tightness of the sealed packaging bottle based on the characteristics of the denoised sound information, and comprises the following steps:
and determining the tightness of the sealed packaging bottle based on the time domain characteristics and the frequency domain characteristics of the denoised sound information through an anomaly identification model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410184536.7A CN117735462B (en) | 2024-02-19 | Control system for cosmetic packaging quality detection equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410184536.7A CN117735462B (en) | 2024-02-19 | Control system for cosmetic packaging quality detection equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117735462A true CN117735462A (en) | 2024-03-22 |
| CN117735462B CN117735462B (en) | 2024-04-26 |
Family
ID=
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006242820A (en) * | 2005-03-04 | 2006-09-14 | Dainippon Printing Co Ltd | Foreign matter inspection device in paper container, filling-sealing device using it, and filling-sealing method |
| US20100013500A1 (en) * | 2006-08-28 | 2010-01-21 | Detection Systems (Marketing) Pty Ltd | Production line detection apparatus and method |
| CN104890950A (en) * | 2015-04-27 | 2015-09-09 | 四川制药制剂有限公司 | Injection cefoxitin sodium preparation technology for automatically examining products |
| CN107478722A (en) * | 2017-05-18 | 2017-12-15 | 中北大学 | A kind of new resonance acoustics the cannot-harm-detection device |
| US9937100B1 (en) * | 2015-10-20 | 2018-04-10 | Express Scripts Strategic Development, Inc. | Methods and systems for labeling and loading pharmaceutical containers |
| WO2020001801A1 (en) * | 2018-06-27 | 2020-01-02 | Krones Aktiengesellschaft | Handling and/or unpacking device and method for unpacking articles |
| KR20220106478A (en) * | 2021-01-22 | 2022-07-29 | 피피에스 주식회사 | A system and method for identifying defective products under capacity connected to CPS(CYBER PHYSICAL SYSTEM) |
| CN218180210U (en) * | 2022-07-26 | 2022-12-30 | 广州诗妃生物科技有限公司 | Liquid leakage detection device of liquid packaging bag |
| WO2023094948A1 (en) * | 2021-11-26 | 2023-06-01 | G.D S.P.A | Machine for filling and closing containers |
| US20230271734A1 (en) * | 2020-08-07 | 2023-08-31 | G.D S.P.A. | Coupling device for coupling a component to an article |
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006242820A (en) * | 2005-03-04 | 2006-09-14 | Dainippon Printing Co Ltd | Foreign matter inspection device in paper container, filling-sealing device using it, and filling-sealing method |
| US20100013500A1 (en) * | 2006-08-28 | 2010-01-21 | Detection Systems (Marketing) Pty Ltd | Production line detection apparatus and method |
| CN104890950A (en) * | 2015-04-27 | 2015-09-09 | 四川制药制剂有限公司 | Injection cefoxitin sodium preparation technology for automatically examining products |
| US9937100B1 (en) * | 2015-10-20 | 2018-04-10 | Express Scripts Strategic Development, Inc. | Methods and systems for labeling and loading pharmaceutical containers |
| CN107478722A (en) * | 2017-05-18 | 2017-12-15 | 中北大学 | A kind of new resonance acoustics the cannot-harm-detection device |
| WO2020001801A1 (en) * | 2018-06-27 | 2020-01-02 | Krones Aktiengesellschaft | Handling and/or unpacking device and method for unpacking articles |
| US20230271734A1 (en) * | 2020-08-07 | 2023-08-31 | G.D S.P.A. | Coupling device for coupling a component to an article |
| KR20220106478A (en) * | 2021-01-22 | 2022-07-29 | 피피에스 주식회사 | A system and method for identifying defective products under capacity connected to CPS(CYBER PHYSICAL SYSTEM) |
| WO2023094948A1 (en) * | 2021-11-26 | 2023-06-01 | G.D S.P.A | Machine for filling and closing containers |
| CN218180210U (en) * | 2022-07-26 | 2022-12-30 | 广州诗妃生物科技有限公司 | Liquid leakage detection device of liquid packaging bag |
Non-Patent Citations (2)
| Title |
|---|
| 李桂玲;张坤;: "瓶装啤酒密封性的检测与控制", 啤酒科技, no. 07, 10 July 2009 (2009-07-10) * |
| 熊路;蔡健荣;孙力;涂佳;: "基于机器视觉的黄酒灌装品质检测", 食品工业, no. 08, 20 August 2013 (2013-08-20) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220051391A1 (en) | Method of automatic tire inspection and system thereof | |
| CN111597857B (en) | Logistics package detection method, device, equipment and readable storage medium | |
| CN112132796A (en) | Visual detection method and system for improving detection precision by means of feedback data autonomous learning | |
| CN113470005B (en) | Welding spot detection device and welding spot detection method for cylindrical battery cap | |
| CN114693661A (en) | Rapid sorting method based on deep learning | |
| CN117735462B (en) | Control system for cosmetic packaging quality detection equipment | |
| Zhang et al. | Robust pattern recognition for measurement of three dimensional weld pool surface in GTAW | |
| CN114742818A (en) | Visual defect detection system based on industrial area array camera and detection method thereof | |
| EP3833951A1 (en) | Inspection of vacuum packaged product for detection of gas inside package | |
| CN117735462A (en) | Control system for cosmetic packaging quality detection equipment | |
| CN112304964A (en) | Fuse box vision detection system | |
| CN108830833B (en) | Online evaluation method of workpiece identification project, server and terminal | |
| CN113392747A (en) | Goods packing box identification method and system for stereoscopic warehouse | |
| CN112069841B (en) | X-ray contraband parcel tracking method and device | |
| CN111307798B (en) | Article checking method adopting multiple acquisition technologies | |
| JP6912367B2 (en) | Cap float inspection method and cap float inspection device | |
| CN114359023B (en) | Method, equipment and system for dispatching picture shunt to center based on complexity | |
| JPH06307812A (en) | Method and device for measuring three-dimensional position on curved surface | |
| JP7442672B2 (en) | Method for inspecting the side walls of objects | |
| US20240046659A1 (en) | Method for detecting an environment by means of images from at least two image sensors | |
| CN117011293A (en) | Product packaging quality detection method and system | |
| CN116843645A (en) | Method and device for detecting defects of polypropylene film on product outer package | |
| CN117840065A (en) | Sorting method, sorting system and processor for recyclable materials | |
| CN117350968A (en) | Product surface micro defect detection method based on machine vision | |
| CN117649375A (en) | Automobile assembly line hub quality detection method and system based on machine vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240407 Address after: No. 118 Guangchen Road, Baiyun District, Guangzhou City, Guangdong Province, 510000 Applicant after: Guangdong Shifei Cosmetics Co.,Ltd. Country or region after: China Address before: No. A10, 2nd Floor, No. 8 Jinxiu Street, Wuhou District, Chengdu, Sichuan Province, 610000 Applicant before: Sichuan Danjingchen Technology Co.,Ltd. Country or region before: China |
|
| GR01 | Patent grant |