Coating effect visual detection method, system and medium of coating recycling machine
By acquiring and analyzing the operating parameters and image characteristics of the coating and recycling machine, and dynamically adjusting the coating parameters, the problem of difficult adjustment of coating effect detection in the prior art is solved, and efficient coating effect and defect analysis is achieved.
Patent Information
- Application Number
- CN202410143212.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-02-01
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-02-01
AI Technical Summary
The existing coating and recycling machines are difficult to dynamically adjust operating parameters according to the detection results of the coating effect, resulting in waste of coating and poor effect.
By obtaining the operating parameter information of the coating and recycling machine, the coating status information is generated, and whether the program is completed is identified, and when completed, the coating image is obtained for preprocessing and feature extraction, input the network model for detection, and generate the detection result; if not After completion, the adjustment information is generated and the operation parameters are optimized, and the coating status is dynamically adjusted.
Accurate coating effect detection and dynamic parameter adjustment are achieved, the coating effect is improved, the coating waste is reduced, and image defects can be analyzed after the coating is completed and the coating effect is accurately analyzed.
Smart Images

Figure CN118122579B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of visual inspection, and more specifically, to a method, system and medium for visual inspection of coating effects of a coating and recycling integrated machine. Background Art
[0002] The coating and recycling machine is mainly used for the surface coating process production of base film, paper, etc. and for simultaneous coating and recycling. The rolled substrate is coated with a layer of glue, coating or ink with specific functions, etc., and then rolled up after drying. It uses a special multi-functional coating head, which can realize various forms of surface coating. The winding and unwinding of the coating and recycling machine are equipped with a full-speed automatic film splicing mechanism, and the PLC program tension closed-loop automatic control. After coating, the coating effect needs to be detected to analyze the operating effect of the coating and recycling machine. The existing coating effect detection method is difficult to dynamically adjust the operating parameter information of the coating and recycling machine according to the coating effect detection results, resulting in more coating waste; in response to the above problems, effective technical solutions are urgently needed. Summary of the invention
[0003] The purpose of the embodiments of the present application is to provide a method, system and medium for visually detecting the coating effect of a coating and recycling machine, dynamically adjust the coating state through different operating parameter information, so as to accurately complete the coating and improve the coating effect as much as possible during coating. After the coating is completed, the coating image is analyzed to detect image defects and accurately analyze the coating effect.
[0004] The embodiment of the present application also provides a method for visually detecting the coating effect of a coating and recycling integrated machine, comprising:
[0005] Obtaining the operating parameter information of the coating and recycling machine, generating coating status information according to the operating parameter information, and identifying whether the coating procedure is completed according to the coating status information;
[0006] If completed, the coating image is obtained, and the coating image is preprocessed to obtain an enhanced image;
[0007] Extract enhanced image features to obtain a feature data set, input the feature data set into a set network model for detection, and obtain a detection result;
[0008] Transmit the test results to the terminal for storage according to the transmission requirements;
[0009] If not completed, the adjustment information is generated, and the operating parameter information of the coating and recycling machine is optimized according to the adjustment information.
[0010] Optionally, in the coating effect visual detection method of the coating and recycling machine described in the embodiment of the present application, the operating parameter information of the coating and recycling machine is obtained, the coating status information is generated according to the operating parameter information, and whether the coating procedure is completed is identified according to the coating status information, specifically including:
[0011] Obtaining the operating parameter information of the coating and recycling machine, including the operating time, operating power, operating current and operating program switching mode;
[0012] Calculate the current coating state information of the coating and recycling machine according to the operating parameter information, compare the current coating state information with the set coating state information, and obtain the state deviation rate;
[0013] Determining whether the state deviation rate is greater than or equal to a set state deviation rate threshold;
[0014] If it is greater than or equal to, a switching program is generated, and the current coating program of the coating and recycling integrated machine is switched to the next coating program according to the switching program;
[0015] If it is less than, a reciprocating mode is generated for reciprocating coating.
[0016] Optionally, in the coating effect visual detection method of the coating recycling machine described in the embodiment of the present application, if completed, the coating image is obtained, and the coating image is preprocessed to obtain an enhanced image, specifically including:
[0017] Acquire a coating image and extract coating image features;
[0018] Analyze and screen out coating features, noise features and background features in the coating image according to the coating image features;
[0019] Remove the noise features in the coating image features and retain the coating features and background features;
[0020] The coating features are enhanced and the background features are blurred to obtain an enhanced image.
[0021] Optionally, in the coating effect visual detection method of the coating recycling machine described in the embodiment of the present application, the coating features and background features are analyzed and screened out according to the coating image features, specifically including:
[0022] Acquire a coating image, extract coating image features, compare the coating image features with set features, and obtain a feature deviation rate;
[0023] Determining whether the characteristic deviation rate is greater than a set characteristic deviation rate threshold;
[0024] If it is greater than, the corresponding feature is determined to be a background feature;
[0025] If it is less than, the corresponding feature is determined to be a coating feature.
[0026] Optionally, in the coating effect visual detection method of the coating recycling machine described in the embodiment of the present application, the enhanced image features are extracted to obtain a feature data set, and the feature data set is input into a set network model for detection to obtain a detection result, which specifically includes:
[0027] Obtain an image feature data set, and classify the image feature data set into a training set and a validation set;
[0028] Input the training set into the network model for iterative training to obtain the training results;
[0029] Determine whether the training result converges, and if so, output the detection result according to the network model;
[0030] If it does not converge, increase the number of iterations by one until the training results converge.
[0031] Optionally, in the coating effect visual detection method of the coating recycling machine described in the embodiment of the present application, if it does not converge, the number of iterations is increased by one until the training result converges, and further includes:
[0032] Obtain the model parameters of the network model, input the verification set into the trained network model for parameter verification, and obtain the verification results;
[0033] Determine whether the verification results meet the requirements;
[0034] If the requirements are met, the optimal model parameters are obtained;
[0035] If it does not meet the requirements, continue to iteratively train the network model.
[0036] In a second aspect, an embodiment of the present application provides a coating effect visual detection system of a coating and recycling machine, the system comprising: a memory and a processor, the memory comprising a program of a coating effect visual detection method of the coating and recycling machine, and the program of the coating effect visual detection method of the coating and recycling machine is executed by the processor to implement the following steps:
[0037] Obtaining the operating parameter information of the coating and recycling machine, generating coating status information according to the operating parameter information, and identifying whether the coating procedure is completed according to the coating status information;
[0038] If completed, the coating image is obtained, and the coating image is preprocessed to obtain an enhanced image;
[0039] Extract enhanced image features to obtain a feature data set, input the feature data set into a set network model for detection, and obtain a detection result;
[0040] Transmit the test results to the terminal for storage according to the transmission requirements;
[0041] If not completed, the adjustment information is generated, and the operating parameter information of the coating and recycling machine is optimized according to the adjustment information.
[0042] Optionally, in the coating effect visual inspection system of the coating and recycling machine described in the embodiment of the present application, the operating parameter information of the coating and recycling machine is obtained, the coating status information is generated according to the operating parameter information, and whether the coating procedure is completed is identified according to the coating status information, specifically including:
[0043] Obtaining the operating parameter information of the coating and recycling machine, including the operating time, operating power, operating current and operating program switching mode;
[0044] Calculate the current coating state information of the coating and recycling machine according to the operating parameter information, compare the current coating state information with the set coating state information, and obtain the state deviation rate;
[0045] Determining whether the state deviation rate is greater than or equal to a set state deviation rate threshold;
[0046] If it is greater than or equal to, a switching program is generated, and the current coating program of the coating and recycling integrated machine is switched to the next coating program according to the switching program;
[0047] If it is less than, a reciprocating mode is generated for reciprocating coating.
[0048] Optionally, in the coating effect visual inspection system of the coating recycling machine described in the embodiment of the present application, if completed, the coating image is obtained, and the coating image is preprocessed to obtain an enhanced image, specifically including:
[0049] Acquire a coating image and extract coating image features;
[0050] Analyze and screen out coating features, noise features and background features in the coating image according to the coating image features;
[0051] Remove the noise features in the coating image features and retain the coating features and background features;
[0052] The coating features are enhanced and the background features are blurred to obtain an enhanced image.
[0053] In the third aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium includes a method program for visually detecting coating effects of a coating and recycling machine. When the method program for visually detecting coating effects of a coating and recycling machine is executed by a processor, the steps of the method for visually detecting coating effects of a coating and recycling machine as described in any one of the above items are implemented.
[0054] As can be seen from the above, the embodiment of the present application provides a method, system and medium for visually detecting the coating effect of a coating and recycling machine. By acquiring the operating parameter information of the coating and recycling machine, coating status information is generated according to the operating parameter information, and whether the coating procedure is completed is identified according to the coating status information; if completed, a coating image is acquired, and the coating image is preprocessed to obtain an enhanced image; the enhanced image features are extracted to obtain a feature data set, and the feature data set is input into a set network model for detection to obtain a detection result; the detection result is transmitted to the terminal for storage according to the transmission requirements; if not completed, adjustment information is generated, and the operating parameter information of the coating and recycling machine is optimized according to the adjustment information; the coating status is dynamically adjusted through different operating parameter information, so as to accurately complete the coating and improve the coating effect as much as possible during coating. After coating is completed, the coating image is analyzed to detect image defects and accurately analyze the coating effect. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0056] Figure 1 A flow chart of a method for visually detecting coating effects of a coating and recycling integrated machine provided in an embodiment of the present application;
[0057] Figure 2 A flow chart of a coating program switching method of a coating effect visual detection method of a coating and recycling integrated machine provided in an embodiment of the present application;
[0058] Figure 3 An enhanced image acquisition flow chart of the coating effect visual detection method of the coating and recycling integrated machine provided in an embodiment of the present application. DETAILED DESCRIPTION
[0059] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.
[0060] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0061] Please refer to Figure 1 , Figure 1 The present invention is a flowchart of a coating effect visual detection method of a coating and recycling machine in some embodiments of the present invention. The coating effect visual detection method of the coating and recycling machine is used in a terminal device, and the coating effect visual detection method of the coating and recycling machine includes the following steps:
[0062] S101, obtaining operating parameter information of the coating and recycling machine, generating coating status information according to the operating parameter information, and identifying whether the coating procedure is completed according to the coating status information;
[0063] S102, if completed, obtaining a coating image, preprocessing the coating image, and obtaining an enhanced image;
[0064] S103, extracting enhanced image features to obtain a feature data set, inputting the feature data set into a set network model for detection, and obtaining a detection result;
[0065] S104, transmitting the detection results to the terminal for storage according to the transmission requirements;
[0066] S105: If not completed, generate adjustment information, and optimize the operating parameter information of the coating and recycling machine according to the adjustment information.
[0067] It should be noted that the coating image is enhanced so that it can be automatically detected according to the network model, so as to accurately analyze whether the coating effect meets the requirements, and the operating parameters of the coating and recycling machine can be reversely corrected according to the detection results.
[0068] Please refer to Figure 2, Figure 2 The present invention is a flow chart of a coating program switching method of a coating effect visual detection method of a coating recycling machine in some embodiments of the present invention. According to an embodiment of the present invention, the operation parameter information of the coating recycling machine is obtained, the coating status information is generated according to the operation parameter information, and the coating program is identified according to the coating status information. Specifically, it includes:
[0069] S201, obtaining operating parameter information of the coating and recycling machine, the operating parameter information including operating time, operating power, operating current and operating program switching mode;
[0070] S202, calculating the current coating state information of the coating and recycling integrated machine according to the operation parameter information, comparing the current coating state information with the set coating state information, and obtaining the state deviation rate;
[0071] S203, determining whether the state deviation rate is greater than or equal to a set state deviation rate threshold;
[0072] S204, if it is greater than or equal to, generating a switching program, and switching the current coating program of the coating and recycling machine to the next coating program according to the switching program;
[0073] S205: If it is less than, a reciprocating mode is generated to perform reciprocating coating.
[0074] It should be noted that by analyzing the current coating status information of the coating and recycling machine, the coating program can be flexibly switched to ensure that the coating and recycling machine can fully execute a complete set of coating programs, and before detection and analysis, it is ensured that the coating produced has the best effect of equipment processing.
[0075] Please refer to Figure 3 , Figure 3 It is a flowchart of an enhanced image acquisition method of a coating effect visual detection method of a coating recycling machine in some embodiments of the present application. According to an embodiment of the present invention, if completed, a coating image is acquired, and the coating image is preprocessed to obtain an enhanced image, specifically including:
[0076] S301, acquiring a coating image and extracting coating image features;
[0077] S302, analyzing and screening out coating features, noise features and background features in the coating image according to the coating image features;
[0078] S303, removing noise features from the coating image features, and retaining coating features and background features;
[0079] S304, enhancing the coating features and blurring the background features to obtain an enhanced image.
[0080] It should be noted that the coating image is processed to remove image noise, while retaining the coating features and background features in the coating image, which will not cause misdetection. In addition, the coating features and background features are processed separately, and the background features are blurred to reduce the interference of background features.
[0081] According to an embodiment of the present invention, the coating features and background features are analyzed and screened out according to the coating image features, specifically including:
[0082] Acquire a coating image, extract coating image features, compare the coating image features with set features, and obtain a feature deviation rate;
[0083] Determine whether the feature deviation rate is greater than a set feature deviation rate threshold;
[0084] If it is greater than, the corresponding feature is determined to be a background feature;
[0085] If it is less than, the corresponding feature is determined to be a coating feature.
[0086] It should be noted that the coating image is feature extracted to screen out background features and coating features according to the set image features, so that the coating features can be analyzed and compared separately, the defect features in the coating features can be accurately analyzed, and the defect analysis in the coating process can be improved.
[0087] According to an embodiment of the present invention, the enhanced image features are extracted to obtain a feature data set, and the feature data set is input into a set network model for detection to obtain a detection result, which specifically includes:
[0088] Obtain an image feature data set, and classify the image feature data set into a training set and a validation set;
[0089] Input the training set into the network model for iterative training to obtain the training results;
[0090] Determine whether the training results converge. If converged, output the test results according to the network model;
[0091] If it does not converge, increase the number of iterations by one until the training results converge.
[0092] It should be noted that the image feature data set is classified to obtain a training set and a validation set. The network model is continuously iterated through the training set to make the output results of the network model closer to the actual value, thereby improving the detection accuracy of the coating effect.
[0093] According to an embodiment of the present invention, if it does not converge, the number of iterations is increased by one until the training result converges, and further includes:
[0094] Obtain the model parameters of the network model, input the verification set into the trained network model for parameter verification, and obtain the verification results;
[0095] Determine whether the verification results meet the requirements;
[0096] If the requirements are met, the optimal model parameters are obtained;
[0097] If it does not meet the requirements, continue to iteratively train the network model.
[0098] It should be noted that the validation set is used to verify the parameters of the trained network model, so as to analyze and obtain the optimal model parameters and improve the output accuracy of the network model.
[0099] According to an embodiment of the present invention, if it is not completed, then the adjustment information is generated, and the operating parameter information of the coating and recycling machine is optimized according to the adjustment information, specifically including:
[0100] Identify whether the coating procedure is completed according to the coating status information;
[0101] If not completed, the progress of the current coating procedure in the complete coating procedure is analyzed to obtain the degree of completion;
[0102] If the degree of completion is greater than the first threshold and less than the second threshold, first adjustment information is generated, and the operating parameter information is optimized according to the first adjustment method based on the first adjustment information;
[0103] If the degree of completion is greater than a second threshold, second adjustment information is generated, and the operating parameter information is optimized according to a second adjustment method based on the second adjustment information.
[0104] It should be noted that by analyzing the degree of completion of the current coating program, the operating parameter information is adjusted in different ways according to different degrees of completion, thereby improving the adjustment accuracy of the operating parameter information and enabling the coating and recycling integrated machine to dynamically adapt to the coating program.
[0105] In a second aspect, an embodiment of the present application provides a coating effect visual detection system for a coating and recycling machine, the system comprising: a memory and a processor, the memory comprising a program of a coating effect visual detection method for the coating and recycling machine, and when the program of the coating effect visual detection method for the coating and recycling machine is executed by the processor, the following steps are implemented:
[0106] Obtaining the operating parameter information of the coating and recycling machine, generating coating status information according to the operating parameter information, and identifying whether the coating procedure is completed according to the coating status information;
[0107] If completed, the coating image is obtained, and the coating image is preprocessed to obtain an enhanced image;
[0108] Extract enhanced image features to obtain a feature data set, input the feature data set into a set network model for detection, and obtain a detection result;
[0109] Transmit the test results to the terminal for storage according to the transmission requirements;
[0110] If not completed, the adjustment information is generated, and the operating parameter information of the coating and recycling machine is optimized according to the adjustment information.
[0111] It should be noted that the coating image is enhanced so that it can be automatically detected according to the network model, so as to accurately analyze whether the coating effect meets the requirements, and the operating parameters of the coating and recycling machine can be reversely corrected according to the detection results.
[0112] According to an embodiment of the present invention, the operation parameter information of the coating and recycling machine is obtained, the coating status information is generated according to the operation parameter information, and the coating program is identified according to the coating status information. Specifically, it includes:
[0113] Obtaining the operating parameter information of the coating and recycling machine, including the operating time, operating power, operating current and operating program switching mode;
[0114] Calculate the current coating state information of the coating and recycling machine according to the operating parameter information, compare the current coating state information with the set coating state information, and obtain the state deviation rate;
[0115] Determine whether the state deviation rate is greater than or equal to a set state deviation rate threshold;
[0116] If it is greater than or equal to, a switching program is generated, and the current coating program of the coating and recycling integrated machine is switched to the next coating program according to the switching program;
[0117] If it is less than, a reciprocating mode is generated for reciprocating coating.
[0118] It should be noted that by analyzing the current coating status information of the coating and recycling machine, the coating program can be flexibly switched to ensure that the coating and recycling machine can fully execute a complete set of coating programs, and before detection and analysis, it is ensured that the coating produced has the best effect of equipment processing.
[0119] According to an embodiment of the present invention, if completed, a coating image is obtained, and the coating image is preprocessed to obtain an enhanced image, specifically including:
[0120] Acquire a coating image and extract coating image features;
[0121] Analyze and screen out coating features, noise features and background features in the coating image according to the coating image features;
[0122] Remove the noise features in the coating image features and retain the coating features and background features;
[0123] The coating features are enhanced and the background features are blurred to obtain an enhanced image.
[0124] It should be noted that the coating image is processed to remove image noise, while retaining the coating features and background features in the coating image, which will not cause misdetection. In addition, the coating features and background features are processed separately, and the background features are blurred to reduce the interference of background features.
[0125] According to an embodiment of the present invention, the coating features and background features are analyzed and screened out according to the coating image features, specifically including:
[0126] Acquire a coating image, extract coating image features, compare the coating image features with set features, and obtain a feature deviation rate;
[0127] Determine whether the feature deviation rate is greater than a set feature deviation rate threshold;
[0128] If it is greater than, the corresponding feature is determined to be a background feature;
[0129] If it is less than, the corresponding feature is determined to be a coating feature.
[0130] It should be noted that the coating image is feature extracted to screen out background features and coating features according to the set image features, so that the coating features can be analyzed and compared separately, the defect features in the coating features can be accurately analyzed, and the defect analysis in the coating process can be improved.
[0131] According to an embodiment of the present invention, the enhanced image features are extracted to obtain a feature data set, and the feature data set is input into a set network model for detection to obtain a detection result, which specifically includes:
[0132] Obtain an image feature data set, and classify the image feature data set into a training set and a validation set;
[0133] Input the training set into the network model for iterative training to obtain the training results;
[0134] Determine whether the training results converge. If converged, output the test results according to the network model;
[0135] If it does not converge, increase the number of iterations by one until the training results converge.
[0136] It should be noted that the image feature data set is classified to obtain a training set and a validation set. The network model is continuously iterated through the training set to make the output results of the network model closer to the actual value, thereby improving the detection accuracy of the coating effect.
[0137] According to an embodiment of the present invention, if it does not converge, the number of iterations is increased by one until the training result converges, and further includes:
[0138] Obtain the model parameters of the network model, input the verification set into the trained network model for parameter verification, and obtain the verification results;
[0139] Determine whether the verification results meet the requirements;
[0140] If the requirements are met, the optimal model parameters are obtained;
[0141] If it does not meet the requirements, continue to iteratively train the network model.
[0142] It should be noted that the validation set is used to verify the parameters of the trained network model, so as to analyze and obtain the optimal model parameters and improve the output accuracy of the network model.
[0143] According to an embodiment of the present invention, if it is not completed, then the adjustment information is generated, and the operating parameter information of the coating and recycling machine is optimized according to the adjustment information, specifically including:
[0144] Identify whether the coating procedure is completed according to the coating status information;
[0145] If not completed, the progress of the current coating procedure in the complete coating procedure is analyzed to obtain the degree of completion;
[0146] If the degree of completion is greater than the first threshold and less than the second threshold, first adjustment information is generated, and the operating parameter information is optimized according to the first adjustment method based on the first adjustment information;
[0147] If the degree of completion is greater than a second threshold, second adjustment information is generated, and the operating parameter information is optimized according to a second adjustment method based on the second adjustment information.
[0148] It should be noted that by analyzing the degree of completion of the current coating program, the operating parameter information is adjusted in different ways according to different degrees of completion, thereby improving the adjustment accuracy of the operating parameter information and enabling the coating and recycling integrated machine to dynamically adapt to the coating program.
[0149] The third aspect of the present invention provides a computer-readable storage medium, which includes a program for a method for visually detecting coating effects of a coating and recycling machine. When the program for the method for visually detecting coating effects of a coating and recycling machine is executed by a processor, the steps of the method for visually detecting coating effects of a coating and recycling machine as described in any of the above items are implemented.
[0150] The present invention discloses a coating effect visual detection method, system and medium of a coating and recycling integrated machine. The method obtains operating parameter information of the coating and recycling integrated machine, generates coating status information according to the operating parameter information, and identifies whether the coating procedure is completed according to the coating status information; if completed, obtains a coating image, pre-processes the coating image to obtain an enhanced image; extracts enhanced image features to obtain a feature data set, inputs the feature data set into a set network model for detection, and obtains a detection result; transmits the detection result to a terminal for storage according to transmission requirements; if not completed, generates adjustment information, and optimizes the operating parameter information of the coating and recycling integrated machine according to the adjustment information; dynamically adjusts the coating status through different operating parameter information, thereby accurately completing the coating and improving the coating effect as much as possible during coating, and after coating is completed, analyzes the coating image to detect image defects and accurately analyzes the coating effect.
[0151] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.
[0152] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0153] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0154] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, the aforementioned program can be stored in a readable storage medium, and when the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.
[0155] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.
Claims
1. A method for visually detecting coating effects of a coating and recycling machine, characterized in that: include: Obtaining the operating parameter information of the coating and recycling machine, generating coating status information according to the operating parameter information, and identifying whether the coating procedure is completed according to the coating status information; If completed, the coating image is obtained, and the coating image is preprocessed to obtain an enhanced image; Extract enhanced image features and obtain features Data set, input the feature data set into the set network model for detection to obtain the detection result; Transmit the test results to the terminal for storage according to the transmission requirements; If not completed, generate adjustment information, and optimize the operating parameter information of the coating and recycling machine according to the adjustment information; Obtaining the operating parameter information of the coating and recycling machine, generating coating status information according to the operating parameter information, and identifying whether the coating procedure is completed according to the coating status information, specifically including: Obtaining the operating parameter information of the coating and recycling machine, including the operating time, operating power, operating current and operating program switching mode; Calculate the current coating state information of the coating and recycling machine according to the operating parameter information, compare the current coating state information with the set coating state information, and obtain the state deviation rate; Determining whether the state deviation rate is greater than or equal to a set state deviation rate threshold; If it is greater than or equal to, a switching program is generated, and the current coating program of the coating and recycling integrated machine is switched to the next coating program according to the switching program; If it is less than, a reciprocating mode is generated for reciprocating coating; If completed, the coating image is obtained, and the coating image is preprocessed to obtain an enhanced image, specifically including: Acquire a coating image and extract coating image features; Analyze and screen out coating features, noise features and background features in the coating image according to the coating image features; Remove the noise features in the coating image features and retain the coating features and background features; Enhance the coating features and blur the background features to obtain an enhanced image; If not completed, generate adjustment information, and optimize the operating parameter information of the coating and recycling machine according to the adjustment information, including: Identify whether the coating procedure is completed according to the coating status information; If not completed, the progress of the current coating procedure in the complete coating procedure is analyzed to obtain the degree of completion; If the degree of completion is greater than the first threshold and less than the second threshold, first adjustment information is generated, and the operating parameter information is optimized according to the first adjustment method based on the first adjustment information; If the degree of completion is greater than a second threshold, second adjustment information is generated, and the operating parameter information is optimized according to a second adjustment method based on the second adjustment information.
2. The coating effect visual detection method of the coating and recycling integrated machine according to claim 1 is characterized in that: According to the coating image features, the coating features and background features are analyzed and screened out, including: Acquire a coating image, extract coating image features, compare the coating image features with set features, and obtain a feature deviation rate; Determining whether the characteristic deviation rate is greater than a set characteristic deviation rate threshold; If it is greater than, the corresponding feature is determined to be a background feature; If it is less than, the corresponding feature is determined to be a coating feature.
3. The coating effect visual detection method of the coating and recycling integrated machine according to claim 2 is characterized in that: Extract enhanced image features to obtain feature data sets, input the feature data sets into the set network model for detection, and obtain the detection results, which specifically include: Obtain an image feature data set, and classify the image feature data set into a training set and a validation set; Input the training set into the network model for iterative training to obtain the training results; Determine whether the training result converges, and if so, output the detection result according to the network model; If it does not converge, increase the number of iterations by one until the training results converge.
4. The coating effect visual detection method of the coating and recycling integrated machine according to claim 3 is characterized in that: If it does not converge, the number of iterations is increased by one until the training results converge, including: Obtain the model parameters of the network model, input the verification set into the trained network model for parameter verification, and obtain the verification results; Determine whether the verification results meet the requirements; If the requirements are met, the optimal model parameters are obtained; If it does not meet the requirements, continue to iterate the network model.
5. A coating effect visual inspection system for a coating and recycling machine, characterized in that: The system includes: a memory and a processor, wherein the memory includes a program of a coating effect visual detection method of a coating recycling machine, and when the program of the coating effect visual detection method of the coating recycling machine is executed by the processor, the following steps are implemented: Obtaining the operating parameter information of the coating and recycling machine, generating coating status information according to the operating parameter information, and identifying whether the coating procedure is completed according to the coating status information; If completed, the coating image is obtained, and the coating image is preprocessed to obtain an enhanced image; Extract enhanced image features to obtain a feature data set, input the feature data set into a set network model for detection, and obtain a detection result; Transmit the test results to the terminal for storage according to the transmission requirements; If not completed, generate adjustment information, and optimize the operating parameter information of the coating and recycling machine according to the adjustment information; Obtaining the operating parameter information of the coating and recycling machine, generating coating status information according to the operating parameter information, and identifying whether the coating procedure is completed according to the coating status information, specifically including: Obtaining the operating parameter information of the coating and recycling machine, including the operating time, operating power, operating current and operating program switching mode; Calculate the current coating state information of the coating and recycling machine according to the operating parameter information, compare the current coating state information with the set coating state information, and obtain the state deviation rate; Determining whether the state deviation rate is greater than or equal to a set state deviation rate threshold; If it is greater than or equal to, a switching program is generated, and the current coating program of the coating and recycling integrated machine is switched to the next coating program according to the switching program; If it is less than, a reciprocating mode is generated for reciprocating coating; If completed, the coating image is obtained, and the coating image is preprocessed to obtain an enhanced image, specifically including: Acquire a coating image and extract coating image features; Analyze and screen out coating features, noise features and background features in the coating image according to the coating image features; Remove the noise features in the coating image features and retain the coating features and background features; Enhance the coating features and blur the background features to obtain an enhanced image; If not completed, generate adjustment information, and optimize the operating parameter information of the coating and recycling machine according to the adjustment information, including: Identify whether the coating procedure is completed according to the coating status information; If not completed, the progress of the current coating procedure in the complete coating procedure is analyzed to obtain the degree of completion; If the degree of completion is greater than the first threshold and less than the second threshold, first adjustment information is generated, and the operating parameter information is optimized according to the first adjustment method based on the first adjustment information; If the degree of completion is greater than a second threshold, second adjustment information is generated, and the operating parameter information is optimized according to a second adjustment method based on the second adjustment information.
6. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a coating effect visual detection method program of the coating and recycling machine. When the coating and recycling machine visual detection method program is executed by the processor, the steps of the coating effect visual detection method of the coating and recycling machine as described in any one of claims 1 to 4 are implemented.
