Non-woven fabric bag detection method and system

Through detection methods and systems, the molding process of the non-woven bag is controlled, the characteristics and combinations are identified, and the molding coefficients are matched, which solves the problem of insufficient control of the forming node of the non-woven bag, and improves the molding effect and quality.

CN119048978AActive Publication Date: 2024-11-29WENZHOU MILES PACKING CO LTD
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202411080916.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-08
Publication Date
2024-11-29
Estimated Expiration
2044-08-08

AI Technical Summary

Technical Problem

The lack of effective molding node control during the molding process of existing non-woven bags has affected the molding effect.

Method used

Through detection methods and systems, the shaping information and detection images of the non-woven bag are collected, the areas are divided to identify features, the correlation numbers and feature combinations are defined, the molding coefficients are matched, and the molding level is determined, and the overall grade is defined in combination with the material grade to control molding. Logic and nodes.

Benefits of technology

Accurate control of the molding effect of non-woven bags is achieved, ensuring the improvement of molding quality and overall grade.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119048978A_ABST
    Figure CN119048978A_ABST
Patent Text Reader

Abstract

The invention discloses a non-woven fabric bag detection method and system, and the method comprises the steps: matching the forming logic of a non-woven fabric bag according to the shape type of the non-woven fabric bag, thereby facilitating the introduction of the forming logic of the non-woven fabric bag, controlling the forming of the non-woven fabric based on the forming logic of the non-woven fabric bag, outputting the non-woven fabric bag, collecting a detection image of the non-woven fabric bag, and carrying out the detection of the non-woven fabric bag. Dividing a plurality of regions based on the detection image; the method comprises the following steps: determining corresponding features according to recognition of a plurality of regions, so as to define a correlation coefficient based on correlation of the plurality of features, triggering a combination of the plurality of features according to the correlation coefficient, and controlling a feature combination, so as to match a forming coefficient based on the feature combination and define a forming grade according to the forming coefficient; the overall grade of the non-woven fabric bag is defined according to the multiple forming grades and the material grade of the non-woven fabric bag, so that the forming effect of the non-woven fabric bag is guaranteed, and meanwhile, all forming nodes of the forming logic of the non-woven fabric bag can be conveniently controlled.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of non-woven bags, and in particular to a detection method and system for non-woven bags. Background Art

[0002] With the development of science and technology, non-woven bags are formed by non-woven fabrics through multiple forming nodes and are used to hold objects. At this time, the non-woven bags are formed at multiple forming process nodes, and the shaping of each side and the holding groove is completed in turn. However, there is no control on the forming level of the non-woven bags, nor is there any control based on each forming node, which affects the forming effect of the non-woven bags. Summary of the invention

[0003] The purpose of the present invention is to overcome the shortcomings of the prior art. The present invention provides a non-woven bag detection method and system, which matches the molding logic of the non-woven bag according to the shape type of the non-woven bag, so as to introduce the molding logic of the non-woven bag, thereby controlling the molding of the non-woven fabric based on the molding logic of the non-woven bag, and outputting the non-woven bag. At the same time, the detection image of the non-woven bag is collected, and a plurality of regions are divided based on the detection image; corresponding features are determined according to the identification of multiple regions, so as to define a correlation coefficient based on the association of multiple features, and a combination of multiple features is triggered according to the correlation coefficient, so as to control the feature combination, so as to match the molding coefficient based on the feature combination, and define the molding grade according to the molding coefficient, and define the overall grade of the non-woven bag according to the plurality of molding grades and the material grade of the non-woven bag, thereby ensuring the molding effect of the non-woven bag, and at the same time, it is convenient to control each molding node of the molding logic of the non-woven bag.

[0004] In order to solve the above technical problems, an embodiment of the present invention provides a non-woven bag detection method, which is applied to the detection scenario of non-woven bags;

[0005] The detection method of the non-woven bag comprises:

[0006] Collecting the shaping information of the non-woven bag, and defining the shape type of the non-woven bag according to the shaping information of the non-woven bag;

[0007] Matching the forming logic of the non-woven bag based on the shape type of the non-woven bag, and triggering the forming of the non-woven fabric according to the forming logic of the non-woven bag to output the non-woven bag;

[0008] Collecting a detection image of the non-woven bag, and dividing the detection image into multiple areas;

[0009] Determining corresponding features based on the identification of the multiple regions, and associating the multiple features;

[0010] A correlation coefficient is defined based on the correlation of multiple features, and a combination of multiple features is triggered according to the correlation coefficient to construct multiple feature combinations;

[0011] The forming coefficient is matched based on each feature combination, and the forming grade is defined according to the forming coefficient. The overall grade of the non-woven bag is defined according to multiple forming grades and the material grade of the non-woven bag.

[0012] Optionally, the collecting of the shaping information of the non-woven bag and defining the shape type of the non-woven bag according to the shaping information of the non-woven bag include:

[0013] Acquiring a communication signal input by a user via remote communication;

[0014] Outputting a plurality of information according to the analysis of the communication signal, the plurality of information including user information, non-woven bag order information and non-woven bag shaping information;

[0015] Screening the shaping information of the non-woven bag based on multiple information to complete the collection of the shaping information of the non-woven bag;

[0016] Traverse the shaping information of non-woven bags, and filter shaping keywords based on the shaping information of non-woven bags;

[0017] The shape type of the non-woven bag is defined according to the stereotyped keywords and the shape type learning model. At this time, the shape type learning model is trained based on the stereotyped keywords and shape types in the past.

[0018] Optionally, matching the forming logic of the non-woven bag based on the shape type of the non-woven bag, and triggering the forming of the non-woven fabric according to the forming logic of the non-woven bag to output the non-woven bag, includes:

[0019] The shape type of the fixed non-woven bag;

[0020] Associate the shape type and forming logic table of non-woven bags;

[0021] Matching the forming logic of the non-woven bag based on the shape type of the non-woven bag and the forming logic table. At this time, matching is performed according to the mapping relationship between the shape type of the non-woven bag and the forming logic table;

[0022] The forming logic is collected, and a forming process table of the non-woven bag is constructed according to the forming logic. At this time, each forming node of the non-woven bag is presented in the forming process table.

[0023] Optionally, the method of matching the forming logic of the non-woven bag based on the shape type of the non-woven bag, and triggering the forming of the non-woven fabric according to the forming logic of the non-woven bag to output the non-woven bag, further includes:

[0024] Trigger the forming monitoring of non-woven bags based on each forming node;

[0025] Trigger the forming process of non-woven fabric to non-woven bag according to each forming node of the non-woven bag to complete the forming of the non-woven bag;

[0026] According to the forming monitoring of non-woven bags, images of each stage of the forming process of non-woven bags are collected, and abnormal parts are defined according to the image recognition of each stage image;

[0027] The repair of the next forming node is triggered based on the abnormal part until the non-woven bag is output.

[0028] Optionally, collecting a detection image of the non-woven bag and dividing the detection image into multiple areas includes:

[0029] After the non-woven bag is formed, locate the position of the non-woven bag;

[0030] Based on the location of the non-woven bag, the surrounding cameras are triggered, and a camera combination is constructed, which takes the location of the non-woven bag as the location center;

[0031] The non-woven bag is photographed in multiple directions according to the camera combination to obtain images in multiple directions;

[0032] Constructing a detection image of the non-woven bag according to the images in multiple different directions, and the detection image of the non-woven bag is used as a panoramic image;

[0033] The closed-loop contour line is highlighted based on the detection image, and multiple areas are divided according to the closed-loop contour line.

[0034] Optionally, determining corresponding features according to the identification of multiple regions and associating multiple features includes:

[0035] Collect multiple areas and locate the spatial relationship between multiple areas;

[0036] Defining recognition priorities among the multiple areas according to the spatial relationship between the multiple areas and the outer contour of the non-woven bag;

[0037] Triggering sequential identification of multiple areas based on identification priority;

[0038] In the sequential recognition of multiple regions, multiple regions are sequentially input into the feature learning model, and the corresponding features are sequentially output. At this time, the feature learning model is trained based on previous regions and features;

[0039] Associate multiple features.

[0040] Optionally, defining a correlation coefficient based on the correlation of multiple features, and triggering a combination of multiple features according to the correlation coefficient to construct multiple feature combinations, includes:

[0041] Define core features among multiple features, and associate them with the remaining features based on the core features;

[0042] Define the corresponding correlation coefficient based on the correlation between the core feature and the remaining features;

[0043] Collect multiple correlation coefficients, and build a combination relationship based on the multiple correlation coefficients and recognition priorities. At this time, mark the multiple correlation coefficients in the preset range, and combine the features corresponding to the marked multiple correlation relationships to form a feature combination. At the same time, match the recognition priority to the feature combination;

[0044] Based on multiple feature combinations, they are listed and an integration mechanism is constructed for the multiple feature combinations. In the integration mechanism, the similarity of the multiple feature combinations is defined, and the similarity is compared with a preset similarity threshold. The similarities of the multiple feature combinations are integrated to improve the multiple feature combinations.

[0045] Optionally, matching the forming coefficients based on the combination of each feature, defining the forming grade according to the forming coefficient, and defining the overall grade of the non-woven bag according to the multiple forming grades and the material grade of the non-woven bag include:

[0046] Freeze each feature combination;

[0047] According to each feature combination and the molding table, the corresponding molding coefficient is matched. At this time, the molding mapping relationship in the molding table is associated with the feature combination and the molding coefficient;

[0048] The forming level is defined based on the forming coefficient and the number of feature combinations, and each feature combination matches the corresponding forming level;

[0049] Collect multiple molding levels, and define the molding priority of each feature combination according to the molding process of non-woven bags and multiple molding levels;

[0050] The molding sequence of each feature combination is triggered according to the molding priority, and at the same time, the material grade of the non-woven bag is collected.

[0051] Optionally, matching the forming coefficients based on the combination of each feature, defining the forming grade according to the forming coefficient, and defining the overall grade of the non-woven bag according to the multiple forming grades and the material grade of the non-woven bag, further includes:

[0052] Correlate multiple molding grades and material grades for non-woven bags;

[0053] The overall grade of the non-woven bag is defined according to a plurality of molding grades and the material grade of the non-woven bag, and the shaping grade in the final shaping process is matched based on the overall grade of the non-woven bag.

[0054] In addition, an embodiment of the present invention further provides a non-woven bag detection system, the non-woven bag detection system comprising:

[0055] The shape area module is used to collect the shaping information of the non-woven bag and define the shape type of the non-woven bag according to the shaping information of the non-woven bag;

[0056] A forming module, used for matching the forming logic of the non-woven bag based on the shape type of the non-woven bag, and triggering the forming of the non-woven fabric according to the forming logic of the non-woven bag to output the non-woven bag;

[0057] A region module, used to collect detection images of non-woven bags and divide them into multiple regions based on the detection images;

[0058] A feature module, used to determine corresponding features according to the identification of multiple regions, and associate multiple features;

[0059] A feature combination module, used for defining a correlation coefficient based on the correlation of multiple features, and triggering the combination of multiple features according to the correlation coefficient to construct multiple feature combinations;

[0060] The grade module is used to match the forming coefficient based on each feature combination, and define the forming grade according to the forming coefficient, and define the overall grade of the non-woven bag according to multiple forming grades and the material grade of the non-woven bag.

[0061] In an embodiment of the present invention, through the method in the embodiment of the present invention, the molding logic of the non-woven bag is matched according to the shape type of the non-woven bag, so as to introduce the molding logic of the non-woven bag, thereby controlling the molding of the non-woven fabric based on the molding logic of the non-woven bag, and outputting the non-woven bag. At the same time, the detection image of the non-woven bag is collected, and a plurality of regions are divided based on the detection image; the corresponding features are determined according to the identification of the plurality of regions, so as to define the correlation coefficient based on the association of the plurality of features, and trigger the combination of the plurality of features according to the correlation coefficient, so as to control the feature combination, so as to match the molding coefficient based on the feature combination, and define the molding grade according to the molding coefficient, and define the overall grade of the non-woven bag according to the plurality of molding grades and the material grade of the non-woven bag, so as to ensure the molding effect of the non-woven bag, and at the same time, perform dynamic detection during the molding process of the non-woven bag, so as to control each molding node of the molding logic of the non-woven bag. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0063] Figure 1 1 is a schematic flow chart of a method for detecting a non-woven bag in an embodiment of the present invention;

[0064] Figure 2 is a flow chart of S11 in the method for detecting a non-woven bag in an embodiment of the present invention;

[0065] Figure 3 is a schematic flow chart of S12 in the method for detecting a non-woven bag in an embodiment of the present invention;

[0066] Figure 4 is a schematic flow chart of S13 in the method for detecting a non-woven bag in an embodiment of the present invention;

[0067] Figure 5 is a schematic flow chart of S14 in the method for detecting a non-woven bag in an embodiment of the present invention;

[0068] Figure 6 is a schematic flow chart of S15 in the method for detecting a non-woven bag in an embodiment of the present invention;

[0069] Figure 7 is a schematic flow chart of S16 in the method for detecting a non-woven bag in an embodiment of the present invention;

[0070] Figure 8 Schematic diagram of the structure of the non-woven bag detection system in the embodiment of the present invention;

[0071] Fig. 9 The figure is a hardware diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0072] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0073] Example

[0074] See also Figures 1 to 9 , a non-woven bag detection method is applied to the detection scene of non-woven bags; the non-woven bag detection method includes:

[0075] Step S11: collecting the shaping information of the non-woven bag, and defining the shape type of the non-woven bag according to the shaping information of the non-woven bag;

[0076] Step S12: matching the forming logic of the non-woven bag based on the shape type of the non-woven bag, and triggering the forming of the non-woven fabric according to the forming logic of the non-woven bag to output the non-woven bag;

[0077] Step S13: collecting a detection image of the non-woven bag, and dividing the detection image into multiple areas;

[0078] Step S14: determining corresponding features according to the identification of the multiple regions, and associating the multiple features;

[0079] Step S15: defining a correlation coefficient based on the correlation of the multiple features, and triggering a combination of the multiple features according to the correlation coefficient to construct a plurality of feature combinations;

[0080] Step S16: matching the forming coefficients based on the feature combinations, defining the forming grades according to the forming coefficients, and defining the overall grade of the non-woven bag according to the multiple forming grades and the material grade of the non-woven bag.

[0081] In an embodiment of the present invention, through the method in the embodiment of the present invention, the molding logic of the non-woven bag is matched according to the shape type of the non-woven bag, so as to introduce the molding logic of the non-woven bag, thereby controlling the molding of the non-woven fabric based on the molding logic of the non-woven bag, and outputting the non-woven bag. At the same time, the detection image of the non-woven bag is collected, and a plurality of regions are divided based on the detection image; the corresponding features are determined according to the identification of the plurality of regions, so as to define the correlation coefficient based on the association of the plurality of features, and trigger the combination of the plurality of features according to the correlation coefficient, so as to control the feature combination, so as to match the molding coefficient based on the feature combination, and define the molding grade according to the molding coefficient, and define the overall grade of the non-woven bag according to the plurality of molding grades and the material grade of the non-woven bag, so as to ensure the molding effect of the non-woven bag, and at the same time, perform dynamic detection during the molding process of the non-woven bag, so as to control each molding node of the molding logic of the non-woven bag.

[0082] refer to Figure 2 In step S11, the shaping information of the non-woven bag is collected, and the shape type of the non-woven bag is defined according to the shaping information of the non-woven bag;

[0083] In the specific implementation process of the present invention, the specific steps may be:

[0084] S111: Acquiring a communication signal input by a user via remote communication;

[0085] S112: Outputting a plurality of information according to the analysis of the communication signal, the plurality of information including user information, non-woven bag order information and non-woven bag shaping information;

[0086] S113: Screening the shaping information of the non-woven bag based on the multiple information to complete the collection of the shaping information of the non-woven bag;

[0087] S114: traversing the shaping information of the non-woven bag, and filtering shaping keywords based on the shaping information of the non-woven bag;

[0088] S115: defining the shape type of the non-woven bag according to the stereotyped keywords and the shape type learning model. At this time, the shape type learning model is trained based on the stereotyped keywords and shape types in the past.

[0089] In an embodiment of the present application, a communication signal input by a user via remote communication is obtained, and signal analysis is performed on the communication signal so as to output multiple information based on the analysis of the communication signal. Optionally, the multiple information includes user information, non-woven bag order information, and non-woven bag shaping information.

[0090] At this time, the stereotyped information of the non-woven bag is filtered based on multiple information to complete the collection of the stereotyped information of the non-woven bag; the stereotyped information of the non-woven bag is traversed to facilitate further processing of the stereotyped information of the non-woven bag, thereby filtering stereotyped keywords based on the stereotyped information of the non-woven bag, and then realizing keyword matching of the stereotyped information of the non-woven bag, so as to define the shape type of the non-woven bag according to the stereotyped keywords and the shape type learning model, thereby ensuring the accuracy of the shape type of the non-woven bag. At this time, the shape type learning model is trained based on previous stereotyped keywords and shape types.

[0091] refer to Figure 3 , in step S12, matching the forming logic of the non-woven bag based on the shape type of the non-woven bag, and triggering the forming of the non-woven fabric according to the forming logic of the non-woven bag to output the non-woven bag;

[0092] In the specific implementation process of the present invention, the specific steps may be:

[0093] S121: The appearance type of the fixed non-woven bag;

[0094] S122: associating the shape type of the non-woven bag and the forming logic table;

[0095] S123: matching the forming logic of the non-woven bag based on the shape type of the non-woven bag and the forming logic table. At this time, matching is performed according to the mapping relationship between the shape type of the non-woven bag and the forming logic table;

[0096] S124: collecting the forming logic, and constructing a forming process table of the non-woven bag according to the forming logic. At this time, the forming process table presents various forming nodes of the non-woven bag;

[0097] S125: Triggering the forming monitoring of the non-woven bag based on each forming node;

[0098] S126: triggering a forming process of the non-woven fabric to the non-woven bag according to each forming node of the non-woven bag to complete the forming of the non-woven bag;

[0099] S127: collecting images of each stage of the non-woven bag during the forming process according to the forming monitoring of the non-woven bag, and defining abnormal parts according to image recognition of each stage image;

[0100] S128: Triggering the repair of the next forming node based on the abnormal part until the non-woven bag is output.

[0101] In an embodiment of the present application, the shape type of the non-woven bag is fixed to facilitate associating the shape type of the non-woven bag and the molding logic table, so as to match the molding logic of the non-woven bag based on the shape type of the non-woven bag and the molding logic table, and then introduce the molding logic of the non-woven bag, so as to perform corresponding shaping for the non-woven fabric molding to the non-woven bag, and perform targeted shaping for the non-woven bag. At this time, matching is performed according to the mapping relationship between the shape type of the non-woven bag and the molding logic table, so as to intelligently select the corresponding molding logic according to the shape type of the non-woven bag, so as to control the molding logic of the non-woven bag.

[0102] Furthermore, the forming logic is collected, and a forming process table for the non-woven bag is constructed according to the forming logic. At this time, the forming process table presents various forming nodes of the non-woven bag, so as to facilitate the management and control of each forming node of the non-woven bag, thereby triggering the forming monitoring of the non-woven bag based on each forming node, realizing the monitoring and adjustment of the non-woven bag during the forming process, and dynamically following up the forming process of the non-woven bag.

[0103] At this time, the forming process of non-woven fabric to non-woven bag is triggered according to each forming node of the non-woven bag to complete the forming of the non-woven bag, thereby realizing the forming of the non-woven bag. At the same time, various stage images of the non-woven bag in the forming process are collected according to the forming monitoring of the non-woven bag, and the abnormal part is defined according to the image recognition of each stage image; the repair of the next forming node is triggered based on the abnormal part until the non-woven bag is output, so as to make real-time adjustments to each forming node in the forming of the non-woven bag, and timely repair the next forming node for the abnormal part.

[0104] At the same time, the forming logic of the non-woven bag is matched according to the shape type of the non-woven bag, so as to introduce the forming logic of the non-woven bag, so as to control the forming of the non-woven fabric based on the forming logic of the non-woven bag and output the non-woven bag.

[0105] refer to Figure 4 , in step S13, a detection image of the non-woven bag is collected, and a plurality of regions are divided based on the detection image;

[0106] In the specific implementation process of the present invention, the specific steps may be:

[0107] S131: After the non-woven bag is formed, the position of the non-woven bag is located;

[0108] S132: triggering the surrounding cameras based on the location of the non-woven bag, and constructing a camera combination, wherein the camera combination takes the location of the non-woven bag as the location center;

[0109] S133: photographing the non-woven bag in multiple directions according to the camera combination to obtain images in multiple directions;

[0110] S134: constructing a detection image of the non-woven bag according to the multiple images in different directions, and the detection image of the non-woven bag is used as a panoramic image;

[0111] S135: highlighting a closed-loop contour line based on the detection image, and dividing the closed-loop contour line into a plurality of regions.

[0112] In an embodiment of the present application, after the non-woven bag is formed, the position of the non-woven bag is located so that the position of the non-woven bag can be used to respond to the camera, thereby triggering the surrounding cameras based on the position of the non-woven bag, and constructing a camera combination, which takes the position of the non-woven bag as the position center; the non-woven bag is photographed in multiple directions according to the camera combination to obtain images in multiple directions, so as to present different sides of the non-woven bag based on multiple images, and then the different sides of the non-woven bag are detected in real time.

[0113] At this time, a detection image of the non-woven bag is constructed based on images in multiple directions, and the detection image of the non-woven bag is used as a panoramic image. The closed-loop contour line is highlighted based on the detection image, and multiple areas are divided according to the closed-loop contour line to facilitate definition of multiple areas, thereby managing and controlling the multiple areas, and then completing image analysis of the detection image, thereby defining the actual situation of the non-woven bag and realizing intelligent recognition of the non-woven bag.

[0114] refer to Figure 5 , S14: determining corresponding features according to the identification of the multiple regions, and associating the multiple features;

[0115] In the specific implementation process of the present invention, the specific steps may be:

[0116] S141: collecting multiple regions and locating the spatial relationship between the multiple regions;

[0117] S142: defining recognition priorities among the multiple regions according to the spatial relationship between the multiple regions and the outer contour of the non-woven bag;

[0118] S143: triggering orderly identification of multiple areas based on identification priorities;

[0119] S144: In the sequential identification of the multiple regions, the multiple regions are sequentially input into the feature learning model, and the corresponding features are sequentially output. At this time, the feature learning model is trained based on the previous regions and features;

[0120] S145: Associating multiple features.

[0121] In an embodiment of the present application, multiple areas are collected and the spatial relationship between the multiple areas is located; the recognition priority between the multiple areas is defined according to the spatial relationship between the multiple areas and the outer contour of the non-woven bag; the orderly recognition of the multiple areas is triggered based on the recognition priority, and then the recognition of the multiple areas is completed, so as to output multiple features based on the recognition of the multiple areas.

[0122] At this time, in the orderly identification of multiple areas, the multiple areas are input into the feature learning model in sequence, and the corresponding features are output in sequence. At this time, the feature learning model is trained based on previous areas and features; multiple features are associated, and a feature set is constructed for the associated multiple features, so as to facilitate the overall control of the feature set and realize the detection of non-woven bags.

[0123] refer to Figure 6 , S15: defining a correlation coefficient based on the correlation of multiple features, and triggering a combination of multiple features according to the correlation coefficient to construct multiple feature combinations;

[0124] In the specific implementation process of the present invention, the specific steps may be:

[0125] S151: defining a core feature among the multiple features, and associating the core feature with the remaining features;

[0126] S152: defining a corresponding correlation coefficient based on the correlation between the core feature and the remaining features;

[0127] S153: collecting multiple correlation coefficients, and constructing a combination relationship according to the multiple correlation coefficients and the recognition priority. At this time, marking multiple correlation coefficients in a preset range, and combining the features corresponding to the marked multiple correlation relationships to form a feature combination. At the same time, matching the recognition priority to the feature combination;

[0128] S154: Listing based on multiple feature combinations, and constructing an integration mechanism for the multiple feature combinations. In the integration mechanism, the similarity of the multiple feature combinations is defined, and the similarity is compared with a preset similarity threshold, and the similarity of the multiple feature combinations is integrated to improve the multiple feature combinations.

[0129] In an embodiment of the present application, a core feature is defined among multiple features, and the core feature is associated with the remaining features, thereby comparing the core feature with the remaining features, so as to define a corresponding correlation coefficient based on the association between the core feature and the remaining features, thereby introducing the correlation coefficient, and then controlling the core feature and the remaining features based on the correlation coefficient.

[0130] At the same time, multiple correlation coefficients are collected, and a combination relationship is constructed based on the multiple correlation coefficients and recognition priorities. At this time, multiple correlation coefficients in a preset range are marked, and the features corresponding to the marked multiple correlation relationships are combined to form a feature combination. At the same time, the recognition priority is matched to the feature combination, so as to introduce recognition priority for the feature combination and be compatible with the influence of recognition order, so as to integrate multiple feature combinations.

[0131] In addition, multiple feature combinations are listed and an integration mechanism is constructed for the multiple feature combinations. In the integration mechanism, the similarity of the multiple feature combinations is defined, and the similarity is compared with a preset similarity threshold. The similarities of the multiple feature combinations are integrated to improve the multiple feature combinations and ensure the accuracy of the multiple feature combinations.

[0132] refer to Figure 7 , S16: matching the forming coefficients based on the combination of each feature, defining the forming grade according to the forming coefficient, and defining the overall grade of the non-woven bag according to the multiple forming grades and the material grade of the non-woven bag;

[0133] In the specific implementation process of the present invention, the specific steps may be:

[0134] S161: freeze each feature combination;

[0135] S162: Matching corresponding forming coefficients according to each feature combination and the forming table. At this time, the forming mapping relationship in the forming table is associated with the feature combination and the forming coefficient;

[0136] S163: defining a forming level based on a forming coefficient and the number of feature combinations, wherein each feature combination matches a corresponding forming level;

[0137] S164: Collect multiple molding levels, and define the molding priority of each feature combination according to the molding process of the non-woven bag and the multiple molding levels;

[0138] S165: triggering the molding sequence of each feature combination according to the molding priority, and at the same time, collecting the material grade of the non-woven bag;

[0139] S166: Associate multiple molding grades and material grades of non-woven bags;

[0140] S167: defining an overall grade of the non-woven bag according to the plurality of molding grades and the material grade of the non-woven bag, and matching the shaping grade in the final shaping process based on the overall grade of the non-woven bag.

[0141] In an embodiment of the present application, a detection image of a non-woven bag is collected, and a plurality of regions are divided based on the detection image; corresponding features are determined based on the identification of the plurality of regions, so that a correlation coefficient is defined based on the correlation of the plurality of features, and a combination of the plurality of features is triggered based on the correlation coefficient, so that the feature combination is controlled, so that a molding coefficient is matched based on the feature combination, and a molding grade is defined based on the molding coefficient, and an overall grade of the non-woven bag is defined based on the plurality of molding grades and the material grade of the non-woven bag, so as to ensure the molding effect of the non-woven bag, and at the same time, dynamic detection is performed during the molding process of the non-woven bag, so as to control each molding node of the molding logic of the non-woven bag.

[0142] At this time, freeze each feature combination; match the corresponding molding coefficient according to each feature combination and the molding table. At this time, the molding mapping relationship in the molding table associates the feature combination and the molding coefficient, so as to define the molding level based on the molding coefficient and the number of feature combinations. At this time, each feature combination matches the corresponding molding level, so as to present the difficulty of molding through the molding level, and then carry out the molding of the non-woven bag in different processes, so as to control the molding of each process.

[0143] At the same time, multiple molding levels are collected, and the molding priority of each feature combination is defined according to the molding process of the non-woven bag and multiple molding levels; the molding order of each feature combination is triggered according to the molding priority, and at the same time, the material grade of the non-woven bag is collected; multiple molding levels and the material grade of the non-woven bag are associated; the overall grade of the non-woven bag is defined according to the multiple molding levels and the material grade of the non-woven bag, and the molding grade in the final molding process is matched based on the overall grade of the non-woven bag, so as to strictly limit the final molding process and control it with the overall grade of the non-woven bag, so as to ensure the molding accuracy of the output non-woven bag.

[0144] Therefore, the forming logic of the non-woven bag is matched according to the shape type of the non-woven bag, so as to introduce the forming logic of the non-woven bag, so as to control the forming of the non-woven fabric based on the forming logic of the non-woven bag, and output the non-woven bag. At the same time, the detection image of the non-woven bag is collected, and a plurality of regions are divided based on the detection image; the corresponding features are determined according to the identification of a plurality of regions, so as to define the correlation coefficient based on the association of a plurality of features, and the combination of a plurality of features is triggered according to the correlation coefficient, so as to control the feature combination, so as to match the forming coefficient based on the feature combination, and define the forming grade according to the forming coefficient, and define the overall grade of the non-woven bag according to the plurality of forming grades and the material grade of the non-woven bag, so as to ensure the forming effect of the non-woven bag, and at the same time, perform dynamic detection during the forming process of the non-woven bag, so as to control each forming node of the forming logic of the non-woven bag.

[0145] Example

[0146] See also Figure 8 , Figure 8 It is a schematic diagram of the structural composition of the non-woven bag detection system in an embodiment of the present invention.

[0147] like Figure 8 As shown, a non-woven bag detection system, the non-woven bag detection system comprises:

[0148] The shape area module 21 is used to collect the shaping information of the non-woven bag and define the shape type of the non-woven bag according to the shaping information of the non-woven bag;

[0149] A forming module 22, used to match the forming logic of the non-woven bag based on the shape type of the non-woven bag, and trigger the forming of the non-woven fabric according to the forming logic of the non-woven bag to output the non-woven bag;

[0150] The area module 23 is used to collect the detection image of the non-woven bag and divide it into multiple areas based on the detection image;

[0151] A shaping module 24, for determining corresponding features according to the identification of the plurality of regions, and associating the plurality of features;

[0152] A feature combination module 25, used to define a correlation coefficient based on the correlation of multiple features, and trigger the combination of multiple features according to the correlation coefficient to construct multiple feature combinations;

[0153] The grade module 26 is used to match the forming coefficients based on the characteristic combinations, define the forming grades according to the forming coefficients, and define the overall grade of the non-woven bag according to the multiple forming grades and the material grade of the non-woven bag.

[0154] Example

[0155] See also Fig. 9, refer to the following Fig. 9 The electronic device 40 according to this embodiment of the present invention will be described. Fig. 9 The electronic device 40 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0156] like Fig. 9 As shown, the electronic device 40 is in the form of a general computing device. The components of the electronic device 40 may include but are not limited to: at least one processing unit 41, at least one storage unit 42, and a bus 43 connecting different system components (including the storage unit 42 and the processing unit 41).

[0157] The storage unit stores program codes, which can be executed by the processing unit 41, so that the processing unit 41 executes the steps according to various exemplary embodiments of the present invention described in the above “Embodiment Method” section of this specification.

[0158] The storage unit 42 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 421 and / or a cache memory unit 422 , and may further include a read-only memory unit (ROM) 423 .

[0159] The storage unit 42 may also include a program / utility 424 having a set (at least one) of program modules 425, such program modules 425 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0160] Bus 43 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0161] The electronic device 40 may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 40, and / or any device that enables the electronic device 40 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 44. Furthermore, the electronic device 40 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 45. Fig. 9 As shown, the network adapter 45 communicates with other modules of the electronic device 40 via the bus 43. It should be understood that although Fig. 9Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 40, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup planning systems.

[0162] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0163] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium can include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. In addition, it stores computer program instructions, and when the computer program instructions are executed by a computer, the computer executes the above method.

[0164] In addition, the above is a detailed introduction to the detection method and system for non-woven bags provided in the embodiments of the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for detecting non-woven bags, It is characterized in that Applied to the detection scenario of non-woven bags; The detection method of the non-woven bag comprises: Collecting the shaping information of the non-woven bag, and defining the shape type of the non-woven bag according to the shaping information of the non-woven bag; Matching the forming logic of the non-woven bag based on the shape type of the non-woven bag, and triggering the forming of the non-woven fabric according to the forming logic of the non-woven bag to output the non-woven bag; Collecting a detection image of the non-woven bag, and dividing the detection image into multiple areas; Determining corresponding features based on the identification of the multiple regions, and associating the multiple features; A correlation coefficient is defined based on the correlation of multiple features, and a combination of multiple features is triggered according to the correlation coefficient to construct multiple feature combinations; The forming coefficient is matched based on each feature combination, and the forming grade is defined according to the forming coefficient. The overall grade of the non-woven bag is defined according to multiple forming grades and the material grade of the non-woven bag.

2. The method for detecting a non-woven bag according to claim 1, It is characterized in that The collecting of the shaping information of the non-woven bag and defining the shape type of the non-woven bag according to the shaping information of the non-woven bag include: Acquiring a communication signal input by a user via remote communication; Outputting a plurality of information according to the analysis of the communication signal, the plurality of information including user information, non-woven bag order information and non-woven bag shaping information; Screening the shaping information of the non-woven bag based on multiple information to complete the collection of the shaping information of the non-woven bag; Traverse the shaping information of non-woven bags, and filter shaping keywords based on the shaping information of non-woven bags; The shape type of the non-woven bag is defined according to the stereotyped keywords and the shape type learning model. At this time, the shape type learning model is trained based on the stereotyped keywords and shape types in the past.

3. The detection method for non-woven bags according to claim 2, It is characterized in that The method of matching the forming logic of the non-woven bag based on the shape type of the non-woven bag and triggering the forming of the non-woven fabric according to the forming logic of the non-woven bag to output the non-woven bag includes: The shape type of the fixed non-woven bag; Associate the shape type and forming logic table of non-woven bags; Matching the forming logic of the non-woven bag based on the shape type of the non-woven bag and the forming logic table. At this time, matching is performed according to the mapping relationship between the shape type of the non-woven bag and the forming logic table; The forming logic is collected, and a forming process table of the non-woven bag is constructed according to the forming logic. At this time, each forming node of the non-woven bag is presented in the forming process table.

4. The method for detecting a non-woven bag according to claim 1, It is characterized in that The method of matching the forming logic of the non-woven bag based on the shape type of the non-woven bag and triggering the forming of the non-woven fabric according to the forming logic of the non-woven bag to output the non-woven bag also includes: Trigger the forming monitoring of non-woven bags based on each forming node; Trigger the forming process of non-woven fabric to non-woven bag according to each forming node of the non-woven bag to complete the forming of the non-woven bag; According to the forming monitoring of non-woven bags, images of each stage of the forming process of non-woven bags are collected, and abnormal parts are defined according to the image recognition of each stage image; The repair of the next forming node is triggered based on the abnormal part until the non-woven bag is output.

5. The method for detecting a non-woven bag according to claim 1, It is characterized in that The collecting of the detection image of the non-woven bag and dividing the detection image into multiple areas include: After the non-woven bag is formed, locate the position of the non-woven bag; Based on the location of the non-woven bag, the surrounding cameras are triggered, and a camera combination is constructed, which takes the location of the non-woven bag as the location center; The non-woven bag is photographed in multiple directions according to the camera combination to obtain images in multiple directions; Constructing a detection image of the non-woven bag according to the images in multiple different directions, and the detection image of the non-woven bag is used as a panoramic image; The closed-loop contour line is highlighted based on the detection image, and multiple areas are divided according to the closed-loop contour line.

6. The method for detecting a non-woven bag according to claim 5, It is characterized in that The determining corresponding features according to the identification of the multiple regions and associating the multiple features includes: Collect multiple areas and locate the spatial relationship between multiple areas; Defining recognition priorities among the multiple areas according to the spatial relationship between the multiple areas and the outer contour of the non-woven bag; Triggering sequential identification of multiple areas based on identification priority; In the sequential recognition of multiple regions, multiple regions are sequentially input into the feature learning model, and the corresponding features are sequentially output. At this time, the feature learning model is trained based on previous regions and features; Associate multiple features.

7. The method for detecting a non-woven bag according to claim 6, It is characterized in that The step of defining a correlation coefficient based on the correlation of multiple features and triggering a combination of multiple features according to the correlation coefficient to construct multiple feature combinations includes: Define core features among multiple features, and associate them with the remaining features based on the core features; Define the corresponding correlation coefficient based on the correlation between the core feature and the remaining features; Collect multiple correlation coefficients, and build a combination relationship based on the multiple correlation coefficients and recognition priorities. At this time, mark the multiple correlation coefficients in the preset range, and combine the features corresponding to the marked multiple correlation relationships to form a feature combination. At the same time, match the recognition priority to the feature combination; Based on multiple feature combinations, they are listed and an integration mechanism is constructed for the multiple feature combinations. In the integration mechanism, the similarity of the multiple feature combinations is defined, and the similarity is compared with a preset similarity threshold. The similarities of the multiple feature combinations are integrated to improve the multiple feature combinations.

8. The method for detecting a non-woven bag according to claim 7, It is characterized in that The forming coefficients are matched based on the combination of each feature, and the forming grade is defined according to the forming coefficients, and the overall grade of the non-woven bag is defined according to the multiple forming grades and the material grade of the non-woven bag, including: Freeze each feature combination; According to each feature combination and the molding table, the corresponding molding coefficient is matched. At this time, the molding mapping relationship in the molding table is associated with the feature combination and the molding coefficient; The forming level is defined based on the forming coefficient and the number of feature combinations, and each feature combination matches the corresponding forming level; Collect multiple molding levels, and define the molding priority of each feature combination according to the molding process of non-woven bags and multiple molding levels; The molding sequence of each feature combination is triggered according to the molding priority, and at the same time, the material grade of the non-woven bag is collected.

9. The method for detecting a non-woven bag according to claim 8, It is characterized in that The method of matching the forming coefficients based on the combination of each feature, defining the forming grade according to the forming coefficient, and defining the overall grade of the non-woven bag according to the multiple forming grades and the material grade of the non-woven bag, further includes: Correlate multiple molding grades and material grades for non-woven bags; The overall grade of the non-woven bag is defined according to a plurality of molding grades and the material grade of the non-woven bag, and the shaping grade in the final shaping process is matched based on the overall grade of the non-woven bag.

10. A non-woven bag detection system, It is characterized in that The non-woven bag detection system is applied to the non-woven bag detection method as claimed in any one of claims 1 to 9, and the non-woven bag detection system comprises: The shape area module is used to collect the shaping information of the non-woven bag and define the shape type of the non-woven bag according to the shaping information of the non-woven bag; A forming module, used for matching the forming logic of the non-woven bag based on the shape type of the non-woven bag, and triggering the forming of the non-woven fabric according to the forming logic of the non-woven bag to output the non-woven bag; A region module, used to collect detection images of non-woven bags and divide them into multiple regions based on the detection images; A feature module, used to determine corresponding features according to the identification of multiple regions, and associate multiple features; A feature combination module, used for defining a correlation coefficient based on the correlation of multiple features, and triggering the combination of multiple features according to the correlation coefficient to construct multiple feature combinations; The grade module is used to match the forming coefficient based on each feature combination, and define the forming grade according to the forming coefficient, and define the overall grade of the non-woven bag according to multiple forming grades and the material grade of the non-woven bag.

Citation Information

Patent Citations

  • Polypropylene infusion bag quality monitoring and analyzing system based on production full-cycle tracking

    CN113673915A

  • Acquired data processing method and system for injection molding production of injector

    CN116238124A

  • Aluminum profile production quality intelligent management system based on machine vision

    CN117094609A

  • Image-based injection molding product quality detection system and method thereof

    CN117132600A

  • Deviation early warning method and system for non-woven fabric production line

    CN117775825A