Glass gluing planning method and system based on artificial intelligence

Abstract

The present invention discloses a glass gluing planning method and system based on artificial intelligence, which belongs to the technical field of gluing planning; it is used to solve the technical problems of poor autonomous supervision of glass gluing and poor autonomous control of glass gluing planning in existing solutions; it monitors and processes data from the internal dimension of gluing; further processes and analyzes the abnormal influence sequence obtained from the early processing, and determines the external overall abnormal influence corresponding to the gluing range, which can not only realize the periodic digital processing and analysis of the external state of gluing from the external dimension of gluing, but also provide reliable external dimension supervision data support for the subsequent evaluation and dynamic control of the overall state of gluing; by integrating the gluing monitoring and analysis data of different dimensions, the local supervision state of glass gluing in the supervision cycle is evaluated as a whole, and the subsequent glass gluing is adaptively and dynamically controlled according to the overall evaluation result.

Description

Technical Field

[0001] The present invention relates to the technical field of gluing planning, and in particular to a glass gluing planning method and system based on artificial intelligence. Background Art

[0002] Glass gluing refers to the process of applying a layer of glue on the surface or edge of the glass in order to achieve specific functions or aesthetic requirements during the processing of glass products.

[0003] The existing glass gluing planning scheme has certain defects in its implementation. It cannot implement periodic gluing quality supervision and analysis of the automatic glass gluing process, and cannot adaptively and dynamically control the subsequent gluing planning based on the supervision and analysis results to avoid unqualified glass gluing schemes from having greater negative impacts. There are technical problems such as poor autonomous supervision of glass gluing and poor autonomous control of glass gluing planning. Summary of the Invention

[0004] The purpose of the present invention is to provide a glass gluing planning method and system based on artificial intelligence, which is used to solve the technical problems of poor autonomous supervision of glass gluing and poor autonomous control of glass gluing planning in existing solutions.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] The glass gluing planning method based on artificial intelligence includes:

[0007] Acquire a colloid image corresponding to the coated glass colloid according to a preset supervision distance;

[0008] Preprocessing and feature extraction of colloid images to obtain corresponding colloid features, and then feature processing of the colloid features and implementation of multi-dimensional colloid coating quality monitoring and analysis to obtain a quality monitoring and analysis set; the quality monitoring and analysis set consists of internal monitoring and analysis data of the coating and external monitoring and analysis data of the coating;

[0009] The local supervision status of the glass gluing corresponding to the supervision distance is determined based on the monitoring and analysis data of different dimensions in the quality monitoring and analysis center, and the subsequent glass gluing is adaptively and dynamically controlled based on the local supervision status of the glass gluing.

[0010] Preferably, when monitoring and analyzing the internal dimensions of the colloid features, pixel recognition is performed on the colloid features, and the total number of recognized pixel types and the corresponding pixel proportions are counted;

[0011] Perform data analysis on the total number of pixel types. If the total number of pixel types is 1, generate a normal instruction for the first gluing process.

[0012] If the total number of pixel types is not 1, an internal verification instruction is generated and the internal abnormality degree is obtained through calculation using a formula.

[0013] Preferably, when determining the internal states of the glue coating corresponding to the plurality of pixel types according to the internal abnormality degree, if the internal abnormality degree is 0, a second internal normal glue coating instruction is generated;

[0014] Otherwise, a glue internal exception instruction is generated;

[0015] The first normal instruction inside the glue coating, the second normal instruction inside the glue coating or the abnormal instruction inside the glue coating constitute the internal monitoring and analysis data of the glue coating.

[0016] Preferably, the calculation formula of the internal abnormality degree NY is: ; In the formula, Fj is the pixel ratio corresponding to different pixel types; j is different pixel types, j=1, 2, 3, ..., m; m is a positive integer; U is the standard pixel ratio range; M is the total number that meets the corresponding conditions.

[0017] Preferably, when monitoring and analyzing the external dimension of the colloid feature, four vertices corresponding to the colloid feature are obtained, and adjacent vertices are connected to obtain a colloid feature contour map;

[0018] Identify the fit between all vertex lines and the colloid in the colloid feature contour map. If there is a gap between the colloid and the line in the colloid feature contour map, generate a first abnormal instruction. According to the first abnormal instruction, obtain the area of ​​the gap and mark it as a first abnormal value.

[0019] If the colloid in the colloid characteristic contour diagram exceeds the connecting line, a second abnormal instruction is generated, and the area corresponding to the part exceeding the connecting line is obtained according to the second abnormal instruction and marked as a second abnormal value;

[0020] If the colloid in the colloid feature contour map fits the connecting line, a normal instruction is generated.

[0021] Preferably, the abnormal influence degree corresponding to the colloid feature is obtained by calculating the abnormal influence formula according to the first abnormal instruction or the second abnormal instruction;

[0022] Among them, the expression of the abnormal impact formula is ; Wherein, k=1, 2; YYk is YY1 and YY2, which are the first abnormal influence and the second abnormal influence respectively; Sk is S1 and S2, which are the first abnormal value and the second abnormal value respectively; Ski is a different first abnormal value or second abnormal value; i=1, 2, 3, ..., N; N is a positive integer; Nk is N1 and N2, which are the total number of first abnormal values ​​and the total number of second abnormal values ​​respectively; A is the standard abnormal influence value;

[0023] The first abnormality impact degree and the second abnormality impact degree obtained by calculation are sorted and combined to obtain an abnormality impact sequence.

[0024] Preferably, when determining the overall abnormal impact of the glue coating range according to the abnormal impact sequence, the abnormal impact sequence is traversed and analyzed. If the values ​​in the abnormal impact sequence are all 0, a verification instruction is generated, and the verification instruction is verified according to the formula Calculate and obtain the abnormal impact integration degree YZ; if the abnormal impact integration degree is 0, generate the external normal instruction of gluing;

[0025] If the abnormal impact integration degree is not 0, the first glue external abnormal instruction is generated;

[0026] If the value in the abnormal impact sequence is not 0, the second glue external exception instruction or the third glue external exception instruction is generated according to the abnormal type corresponding to the element whose value is not 0;

[0027] The gluing external normal instruction, the first gluing external abnormal instruction, the second gluing external abnormal instruction or the third gluing external abnormal instruction constitute the gluing external monitoring and analysis data.

[0028] Preferably, the internal monitoring and analysis data of the gluing and the external monitoring and analysis data of the gluing in the quality monitoring and analysis set are traversed to determine the local monitoring state of the glass gluing corresponding to the corresponding monitoring distance;

[0029] If all the traversed results are normal instructions, then a normal instruction for gluing is generated and the subsequent glass gluing is controlled to continue with the preset parameters.

[0030] Preferably, if there is an abnormal instruction in the traversal result, an overall abnormal instruction for gluing is generated and the subsequent glass gluing is controlled to be suspended, and the abnormal data of the corresponding dimension is optimized and managed according to the abnormal instruction.

[0031] Artificial intelligence-based glass gluing planning system, including:

[0032] The feature extraction, processing and analysis module is used to pre-process the colloid image and extract features to obtain the corresponding colloid features, perform feature processing on the colloid features and implement multi-dimensional colloid coating quality monitoring and analysis to obtain a quality monitoring and analysis set; the quality monitoring and analysis set is composed of internal monitoring and analysis data of the coating and external monitoring and analysis data of the coating;

[0033] The multi-dimensional analysis result control module is used to determine the local supervision status of the glass glue coating corresponding to the supervision distance based on the monitoring and analysis data of different dimensions in the quality monitoring and analysis center, and to adaptively and dynamically control the subsequent glass glue coating based on the local supervision status of the glass glue coating.

[0034] Compared with the existing solutions, the present invention achieves the following beneficial effects:

[0035] The present invention performs monitoring and data analysis from the internal dimension of the glue coating, which can not only realize the periodic digital processing and analysis of the internal state of the glue coating from the internal dimension of the glue coating, but also provide reliable internal dimension supervision data support for the subsequent evaluation of the overall state of the glue coating and dynamic control.

[0036] The present invention further processes and analyzes the abnormal impact sequence obtained in the early stage of processing to determine the external overall abnormal impact corresponding to the gluing range. It can not only realize the periodic digital processing and analysis of the external state of the gluing from the external dimension of the gluing, but also provide reliable external dimension supervision data support for the subsequent evaluation of the overall state of the gluing and dynamic control; it improves the diversity of the periodic supervision analysis of glass gluing and the reliability and comprehensiveness of the subsequent expansion and utilization.

[0037] The present invention integrates glue monitoring and analysis data of different dimensions to conduct an overall assessment of the local supervision status of glass glue coating in the corresponding supervision cycle, and adaptively and dynamically controls subsequent glass glue coating based on the overall assessment results, thereby improving the autonomous supervision effect of glass glue coating and the autonomous control effect of glass glue coating planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The present invention will be further described below with reference to the accompanying drawings.

[0039] Figure 1 This is a flowchart of the glass gluing planning method based on artificial intelligence of the present invention.

[0040] Figure 2 This is a module block diagram of the glass gluing planning system based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0041] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0042] Example 1: Figure 1 As shown, the present invention is a glass gluing planning method based on artificial intelligence, comprising:

[0043] Obtain the planned path and the corresponding planned gluing data corresponding to the glass gluing;

[0044] Among them, the planning path is determined according to the shape of the glued glass and the glue design corresponding to the glued glass;

[0045] The planned gluing data includes the gluing coordinates at different locations, as well as the unit gluing speed and unit gluing amount corresponding to different gluing coordinates. The unit gluing speed and unit gluing amount can be determined based on the specific glass and the actual gluing design requirements. The gluing coordinates can be determined based on the center point of the glass to be glued, the preset coordinate axis direction, and the coordinate spacing.

[0046] When the glass glue coating starts, the colloid image corresponding to the glued glass colloid is obtained according to the preset supervision distance;

[0047] The supervision distance is determined based on the total length of the planned path and the actual glue coating supervision requirements, and the unit is centimeters;

[0048] Colloid images can be acquired using high-resolution industrial cameras or machine vision systems;

[0049] Preprocessing and feature extraction of colloid images to obtain corresponding colloid features, and then feature processing of the colloid features and implementation of multi-dimensional colloid coating quality monitoring and analysis to obtain a quality monitoring analysis set;

[0050] Among them, the preprocessing and feature extraction of the colloid image are both existing conventional technical solutions, and the specific steps are not repeated here; the colloid feature is the colloid after coating;

[0051] In addition, the feature processing of the colloid features includes the processing of the inner dimension of the glue coating and the outer dimension of the glue coating;

[0052] Specifically, when monitoring and analyzing the internal dimensions of the colloid features, pixel recognition is performed on the colloid features, and the total number of recognized pixel types and the corresponding pixel ratios are counted; pixel types correspond to different colors; and the pixel ratio is the ratio between the corresponding pixel value and the overall pixel value of the colloid;

[0053] Perform data analysis on the total number of pixel types. If the total number of pixel types is 1, generate a normal instruction for the first glue coating. The corresponding scenario may be that there is no noise or bubbles in the colloid feature.

[0054] If the total number of pixel types is not 1, an internal verification instruction is generated and the internal abnormality degree NY is calculated by the formula; the calculation formula of the internal abnormality degree NY is Where, Fj is the pixel ratio corresponding to different pixel types; j is different pixel types, j=1, 2, 3, ..., m; m is a positive integer; U is the standard pixel ratio range, which is determined based on the colloid color data corresponding to the glass coating and the noise pixel data of the previous image processing; M is the total number of pixels that meet the corresponding conditions;

[0055] It should be noted that the internal abnormality is used to integrate and calculate the pixel identification data obtained from the monitoring from the internal dimension of the glue coating to digitally represent the internal state of the glue coating of its colloid characteristics;

[0056] When determining the internal states of the glue coating corresponding to several pixel types according to the internal abnormality degree, if the internal abnormality degree is 0, a second internal normal instruction of the glue coating is generated;

[0057] Otherwise, a glue internal exception instruction is generated;

[0058] The first normal instruction inside the gluing coating, the second normal instruction inside the gluing coating or the abnormal instruction inside the gluing coating constitute the gluing coating internal monitoring and analysis data;

[0059] In the embodiment of the present invention, by performing monitoring processing and data analysis from the internal dimension of the gluing, it is possible to achieve periodic digital processing and analysis of the internal state of the gluing from the internal dimension of the gluing, and at the same time provide reliable internal dimension supervision data support for the subsequent evaluation of the overall state of the gluing and dynamic control;

[0060] When monitoring and analyzing the external dimensions of the colloid feature, the four vertices corresponding to the colloid feature are obtained, and the adjacent vertices are connected to obtain the colloid feature contour map; the shape corresponding to the colloid feature is a rectangle;

[0061] Identify the fit between all vertex lines and the colloid in the colloid feature contour map. If there is a gap between the colloid and the line in the colloid feature contour map, generate a first abnormal instruction. According to the first abnormal instruction, obtain the area of ​​the gap and mark it as a first abnormal value.

[0062] If the colloid in the colloid characteristic contour diagram exceeds the connecting line, a second abnormal instruction is generated, and the area corresponding to the part exceeding the connecting line is obtained according to the second abnormal instruction and marked as a second abnormal value;

[0063] If the colloid in the colloid feature contour map fits the connecting line, a normal instruction is generated;

[0064] Among them, the gaps, protrusions or fits between the colloid and the connecting lines in the colloid feature contour map, as well as the corresponding areas, can all be obtained through feature detection using existing convolutional neural networks (CNNs). The specific implementation steps are not detailed here.

[0065] Obtaining the abnormal influence degree corresponding to the colloid feature by calculating the abnormal influence formula according to the first abnormal instruction or the second abnormal instruction;

[0066] Among them, the expression of the abnormal impact formula is Wherein, k=1, 2; YYk is YY1 and YY2, which are the first abnormal influence degree and the second abnormal influence degree respectively; Sk is S1 and S2, which are the first abnormal value and the second abnormal value respectively; Ski is a different first abnormal value or second abnormal value; i=1, 2, 3, ..., N; N is a positive integer; Nk is N1 and N2, which are the total number of first abnormal values ​​and the total number of second abnormal values ​​respectively; A is the standard abnormal influence value, which can be determined based on the previous glass glue test data;

[0067] Sorting and combining the first abnormality impact degree and the second abnormality impact degree obtained by calculation to obtain an abnormality impact sequence;

[0068] In the embodiment of the present invention, by monitoring and analyzing the external dimensions of the glue coating on the colloid characteristics, the adhesion state between the colloid and the connecting line in the colloid characteristic contour diagram is monitored, digitally processed and combined to obtain an abnormal impact sequence. This can not only perform various external monitoring data processing on the colloid characteristics, but also provide reliable digital data support for subsequent state analysis of the external dimensions of the glue coating.

[0069] When determining the overall abnormal impact of the gluing range according to the abnormal impact sequence, the abnormal impact sequence is traversed and analyzed. If the values ​​in the abnormal impact sequence are all 0, a verification instruction is generated, and the verification instruction is verified according to the formula Calculate and obtain the abnormal impact integration degree YZ; if the abnormal impact integration degree is 0, generate the external normal instruction of gluing;

[0070] If the abnormal impact integration degree is not 0, the first glue external abnormal instruction is generated;

[0071] If the value in the abnormal impact sequence is not 0, the second glue external exception instruction or the third glue external exception instruction is generated according to the abnormal type corresponding to the element whose value is not 0;

[0072] The gluing external normal instruction, the first gluing external abnormal instruction, the second gluing external abnormal instruction or the third gluing external abnormal instruction constitutes the gluing external monitoring and analysis data;

[0073] In the embodiment of the present invention, by further processing and analyzing the abnormal impact sequence obtained in the early stage, the external overall abnormal impact corresponding to the gluing range is determined, which can not only realize the periodic digital processing and analysis of the external state of the gluing from the external dimension of the gluing, but also provide reliable external dimension supervision data support for the subsequent evaluation of the overall state of the gluing and dynamic management and control; it improves the diversity of the periodic supervision analysis of glass gluing and the reliability and comprehensiveness of subsequent expansion and utilization;

[0074] The internal monitoring and analysis data of gluing and the external monitoring and analysis data of gluing constitute the quality monitoring and analysis set;

[0075] Determine the local supervision status of the glass glue coating corresponding to the supervision distance based on the monitoring and analysis data of different dimensions in the quality monitoring and analysis center, and dynamically control the subsequent glass glue coating based on the local supervision status of the glass glue coating;

[0076] Traverse the gluing internal monitoring and analysis data and the gluing external monitoring and analysis data in the quality monitoring and analysis set to determine the local supervision status of the glass gluing corresponding to the supervision distance;

[0077] If all the traversed results are normal instructions, then generate the overall normal glue coating instruction and control the subsequent glass glue coating to continue with the preset parameters;

[0078] It should be noted that, in the embodiment of the present invention, only when the monitoring and analysis data of different aspects of gluing are normal, will the subsequent glass gluing of the planned gluing data be continued; if they are not present at the same time, targeted optimization management will be implemented for the planned gluing data;

[0079] If there are abnormal instructions in the traversal results, an overall abnormal instruction for gluing is generated and the subsequent glass gluing is controlled to be suspended, and the abnormal data of the corresponding dimension is optimized and managed according to the abnormal instruction;

[0080] Among them, when performing optimization management, targeted management can be implemented for the anomalies in the dimension to which the abnormal instructions belong, such as optimizing the planned gluing data from the inside of the gluing according to the internal abnormal instructions of the gluing, and optimizing the planned gluing data from the outside of the gluing according to the first external abnormal instructions of the gluing, the second external abnormal instructions of the gluing or the third external abnormal instructions of the gluing.

[0081] In an embodiment of the present invention, the local supervision status of glass gluing in the supervision cycle is comprehensively evaluated by integrating the glue monitoring and analysis data of different dimensions, and the subsequent glass gluing is adaptively and dynamically controlled based on the overall evaluation results, thereby improving the autonomous supervision effect of glass gluing and the autonomous control effect of glass gluing planning.

[0082] Example 2: Figure 2 As shown, the present invention is a glass gluing planning system based on artificial intelligence, comprising:

[0083] The feature extraction, processing and analysis module is used to pre-process the colloid image and extract features to obtain the corresponding colloid features, perform feature processing on the colloid features and implement multi-dimensional colloid coating quality monitoring and analysis to obtain a quality monitoring and analysis set; the quality monitoring and analysis set is composed of internal monitoring and analysis data of the coating and external monitoring and analysis data of the coating;

[0084] The multi-dimensional analysis result control module is used to determine the local supervision status of the glass glue coating corresponding to the supervision distance based on the monitoring and analysis data of different dimensions in the quality monitoring and analysis center, and to adaptively and dynamically control the subsequent glass glue coating based on the local supervision status of the glass glue coating.

[0085] In addition, the formulas involved in the above are all calculated by removing dimensions and taking their numerical values. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and simulating it through simulation software.

[0086] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments of the invention described above are merely illustrative. For example, the division of modules is only a logical function division, and other division methods may be used in actual implementation.

[0087] Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, and may be located in one place or distributed across multiple network modules. Some or all of these modules may be selected to achieve the objectives of this embodiment based on actual needs.

[0088] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing module, each module may exist physically separately, or two or more modules may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or hardware plus software functional modules.

[0089] It is obvious to a person skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, but that the present invention can be implemented in other specific forms without departing from the essential characteristics of the present invention.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. The glass gluing planning method based on artificial intelligence is characterized by: include: Acquire a colloid image corresponding to the coated glass colloid according to a preset supervision distance; Preprocessing and feature extraction of colloid images to obtain corresponding colloid features, and then feature processing of the colloid features and implementation of multi-dimensional colloid coating quality monitoring and analysis to obtain a quality monitoring and analysis set; the quality monitoring and analysis set consists of internal monitoring and analysis data of the coating and external monitoring and analysis data of the coating; Among them, the abnormal influence degree corresponding to the colloid feature is calculated by the abnormal influence formula according to the first abnormal instruction or the second abnormal instruction; the abnormal influence formula is expressed as ; Wherein, k=1, 2; YYk is YY1 and YY2, which are the first abnormal influence and the second abnormal influence respectively; Sk is S1 and S2, which are the first abnormal value and the second abnormal value respectively; Ski is a different first abnormal value or second abnormal value; i=1, 2, 3, ..., N; N is a positive integer; Nk is N1 and N2, which are the total number of first abnormal values ​​and the total number of second abnormal values ​​respectively; A is the standard abnormal influence value; Sorting and combining the first abnormality impact degree and the second abnormality impact degree obtained by calculation to obtain an abnormality impact sequence; When determining the overall abnormal impact of the gluing range according to the abnormal impact sequence, the abnormal impact sequence is traversed and analyzed. If the values ​​in the abnormal impact sequence are all 0, a verification instruction is generated, and the verification instruction is verified according to the formula Calculate and obtain the abnormal impact integration degree YZ; if the abnormal impact integration degree is 0, generate the external normal instruction of gluing; If the abnormal impact integration degree is not 0, the first glue external abnormal instruction is generated; If the value in the abnormal impact sequence is not 0, the second glue external exception instruction or the third glue external exception instruction is generated according to the abnormal type corresponding to the element whose value is not 0; The gluing external normal instruction, the first gluing external abnormal instruction, the second gluing external abnormal instruction or the third gluing external abnormal instruction constitutes the gluing external monitoring and analysis data; The local supervision status of the glass gluing corresponding to the supervision distance is determined based on the monitoring and analysis data of different dimensions in the quality monitoring and analysis center, and the subsequent glass gluing is adaptively and dynamically controlled based on the local supervision status of the glass gluing.

2. The glass gluing planning method based on artificial intelligence according to claim 1 is characterized in that: When monitoring and analyzing the internal dimensions of the colloid features, the colloid features are pixel-recognized, and the total number of identified pixel types and the corresponding pixel proportions are counted; Perform data analysis on the total number of pixel types. If the total number of pixel types is 1, generate a normal instruction for the first gluing process. If the total number of pixel types is not 1, an internal verification instruction is generated and the internal abnormality degree is obtained through calculation using a formula.

3. The glass gluing planning method based on artificial intelligence according to claim 2, characterized in that: When determining the internal states of the glue coating corresponding to several pixel types according to the internal abnormality degree, if the internal abnormality degree is 0, a second internal normal instruction of the glue coating is generated; Otherwise, a glue internal exception instruction is generated; The first normal instruction inside the glue coating, the second normal instruction inside the glue coating or the abnormal instruction inside the glue coating constitute the internal monitoring and analysis data of the glue coating.

4. The glass gluing planning method based on artificial intelligence according to claim 2, characterized in that: The calculation formula of internal abnormality NY is: ; Where Fj is the pixel ratio corresponding to different pixel types; j is different pixel types, j=1, 2, 3, ..., m; m is a positive integer; U is the standard pixel ratio range; M is the total number of pixels that meet the corresponding conditions.

5. The glass gluing planning method based on artificial intelligence according to claim 1, characterized in that: When monitoring and analyzing the external dimension of the colloid feature, the four vertices corresponding to the colloid feature are obtained, and the adjacent two vertices are connected to obtain the colloid feature contour map; Identify the fit between all vertex lines and the colloid in the colloid feature contour map. If there is a gap between the colloid and the line in the colloid feature contour map, generate a first abnormal instruction. According to the first abnormal instruction, obtain the area of ​​the gap and mark it as a first abnormal value. If the colloid in the colloid characteristic contour diagram exceeds the connecting line, a second abnormal instruction is generated, and the area corresponding to the part exceeding the connecting line is obtained according to the second abnormal instruction and marked as a second abnormal value; If the colloid in the colloid feature contour map fits the connecting line, a normal instruction is generated.

6. The glass gluing planning method based on artificial intelligence according to claim 3 is characterized in that: Traverse the gluing internal monitoring and analysis data and the gluing external monitoring and analysis data in the quality monitoring and analysis set to determine the local supervision status of the glass gluing corresponding to the supervision distance; If all the traversed results are normal instructions, then a normal instruction for gluing is generated and the subsequent glass gluing is controlled to continue with the preset parameters.

7. The artificial intelligence-based glass gluing planning method according to claim 6, characterized in that: If there are abnormal instructions in the traversal results, an overall abnormal instruction for gluing is generated and the subsequent glass gluing is controlled to be suspended, and the abnormal data of the corresponding dimension is optimized and managed according to the abnormal instruction.

8. An artificial intelligence-based glass gluing planning system, applying the artificial intelligence-based glass gluing planning method according to any one of claims 1 to 7, characterized in that: include: The feature extraction, processing and analysis module is used to pre-process the colloid image and extract features to obtain the corresponding colloid features, perform feature processing on the colloid features and implement multi-dimensional colloid coating quality monitoring and analysis to obtain a quality monitoring and analysis set; the quality monitoring and analysis set is composed of internal monitoring and analysis data of the coating and external monitoring and analysis data of the coating; The multi-dimensional analysis result control module is used to determine the local supervision status of the glass glue coating corresponding to the supervision distance based on the monitoring and analysis data of different dimensions in the quality monitoring and analysis center, and to adaptively and dynamically control the subsequent glass glue coating based on the local supervision status of the glass glue coating.

Images