Intelligent maintenance device based on cigarette case appearance defect detection and high-speed packaging machine

Abstract

The invention provides an intelligent maintenance device based on cigarette case appearance defect detection and a high-speed packaging machine. The intelligent maintenance device comprises a main control unit and a plurality of detection units. Each subsystem is provided with at least one detection unit; the detection units are used for shooting operation images of the corresponding subsystems; the main control unit is used for executing the following steps: determining defect information in each operation image according to the operation image of each subsystem; determining association information of each piece of defect information according to the defect information in each operation image and operation association among the subsystems; and determining a maintenance strategy of the high-speed packaging machine according to the defect information and the associated information in each operation image. Defects in a produced cigarette case are identified by utilizing an image identification technology, and then potential faults of the high-speed packaging machine are analyzed in combination with association among subsystems, so that a corresponding maintenance strategy is formulated, non-planned shutdown is avoided, and the production efficiency is effectively improved.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent detection technology, and in particular relates to an intelligent maintenance device and a high-speed packaging machine based on cigarette box appearance defect detection. Background Art

[0002] Packed cigarette inspection is a necessary step in cigarette quality control, and packaging defect detection is a key link in quality control. Common cigarette box defects include dirty seals, damage, scratches, wrinkles, peeling, glue spitting, overlapping corners, missing, small boxes are wrinkled, broken, and irregular shapes. Due to long-term and high-intensity work, cigarette equipment may have various faults, such as wear, heat, abnormal pressure, etc. If these faults are not discovered and handled in time, they may cause irreversible damage to the equipment and cause unplanned downtime.

[0003] Currently, in the production process, unplanned downtime, the time, labor and maintenance costs required for regular maintenance of packaging machines are the main factors hindering factory production efficiency. When unplanned downtime occurs, the need to solve hardware failures will lead to delayed product supply, which in turn leads to low production efficiency. Summary of the invention

[0004] In view of this, the present invention provides an intelligent maintenance device and a high-speed packaging machine based on cigarette box appearance defect detection, aiming to solve the problem of low production efficiency caused by unplanned downtime in the prior art.

[0005] A first aspect of an embodiment of the present invention provides an intelligent maintenance device based on cigarette box appearance defect detection, wherein a high-speed cigarette box packaging machine includes multiple subsystems; the intelligent maintenance device includes: a main control unit and multiple detection units; each subsystem is provided with at least one detection unit; the detection unit is used to capture an operation image of the corresponding subsystem; and the main control unit is used to perform the following steps:

[0006] According to the operation images of each subsystem, determine the defect information in each operation image;

[0007] Determine the correlation information of each defect information according to the defect information in each operation image and the operation correlation between each subsystem;

[0008] The maintenance strategy of the high-speed packaging machine is determined based on the defect information and associated information in each operating image.

[0009] In a possible implementation, the main control unit is used to:

[0010] The operation images of each subsystem are input into the image recognition model corresponding to the subsystem to determine the defect information in each operation image.

[0011] In a possible implementation, the main control unit is used to:

[0012] Extract the region of interest corresponding to the subsystem in the running image;

[0013] The region of interest is input into the image recognition model corresponding to the subsystem to determine the defect information corresponding to the subsystem.

[0014] In a possible implementation, the main control unit is used to:

[0015] According to the operation associations and areas of interest between each subsystem, a fault knowledge graph of each subsystem is constructed;

[0016] According to the defect information in each operation image and the fault knowledge graph of each subsystem, the associated information of each defect information is determined.

[0017] In a possible implementation, the main control unit is further configured to:

[0018] According to the operational association between each subsystem, the preceding subsystem of each subsystem is determined, and the recognition loss of the image recognition model of each subsystem is transmitted to the preceding subsystem of the subsystem.

[0019] In a possible implementation, for any subsystem, the main control unit is used to:

[0020] Determine a plurality of previous-level-relationship-current-level defect triplets according to defect information identified by the region of interest corresponding to the previous-level subsystem of the subsystem and defect information identified by the corresponding region of interest;

[0021] Based on multiple previous-level-relationship-current-level defect triplets, a fault knowledge graph for each subsystem is constructed.

[0022] In a possible implementation, the main control unit is used to:

[0023] Input the defect information and associated information in each operation image into the fault identification model to determine the fault information;

[0024] Determine the maintenance strategy for the high-speed packaging machine based on the fault information.

[0025] In a possible implementation, the main control unit is used to:

[0026] Get the operation plan of high-speed packaging machine;

[0027] Input the defect information and associated information in each operation image into the fault identification model to determine the fault information;

[0028] Predict the remaining life information of each subsystem based on fault information, operation plan and life prediction model;

[0029] Determine the maintenance strategy for the high-speed packaging machine based on the operation plan, fault information and remaining life information.

[0030] A second aspect of an embodiment of the present invention provides a high-speed packaging machine, comprising a plurality of subsystems and the intelligent maintenance device based on cigarette box appearance defect detection as described in the first aspect above.

[0031] In a possible implementation, the high-speed packaging machine includes: a material supply system, a conveying system, a packaging forming system, and a drying and heat shrinking system.

[0032] The embodiment of the present invention provides an intelligent maintenance device and a high-speed packaging machine based on cigarette box appearance defect detection. The intelligent maintenance device includes: a main control unit and multiple detection units; each subsystem is provided with at least one detection unit; the detection unit is used to shoot the operation image of the corresponding subsystem; the main control unit is used to perform the following steps: according to the operation image of each subsystem, determine the defect information in each operation image; according to the defect information in each operation image and the operation association between each subsystem, determine the association information of each defect information; according to the defect information and the association information in each operation image, determine the maintenance strategy of the high-speed packaging machine. By using image recognition technology to identify defects in the produced cigarette boxes, and then combining the association between the subsystems, analyze the potential faults of the high-speed packaging machine, so as to formulate corresponding maintenance strategies, avoid unplanned downtime, and effectively improve production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, 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 labor.

[0034] Figure 1 It is a structural schematic diagram of an intelligent maintenance device based on cigarette box appearance defect detection provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0035] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0036] Figure 1FIG. 1 is a schematic diagram of the structure of an intelligent maintenance device based on cigarette box appearance defect detection provided by an embodiment of the present invention. Figure 1 As shown, in some embodiments, an intelligent maintenance device based on cigarette box appearance defect detection, a high-speed cigarette box packaging machine includes multiple subsystems; specifically, a material supply system, a conveying system, a packaging forming system, and a drying and heat shrinking system. The intelligent maintenance device includes: a main control unit 11 and multiple detection units 12; each subsystem is provided with at least one detection unit 12;

[0037] In the embodiment of the present invention, the material supply system is the starting point of the entire packaging process. It provides the necessary packaging materials, such as paper boxes, films, etc., for the packaging forming system. The system is responsible for storing, conveying and positioning packaging materials to ensure that the materials are delivered to the packaging line in the correct form at the right time. It must match the packaging speed to ensure production efficiency. The conveying system connects the material supply system and the packaging forming system, and also supports the delivery of the packaged products to the drying and heat shrinking system. The conveying system is responsible for accurately and smoothly conveying empty cigarette boxes or semi-finished cigarette boxes from one station to the next station. It ensures that the product maintains the correct position and direction during the entire packaging process to avoid damage. The packaging forming system receives the material from the material supply system and completes the packaging forming of the cigarette box with the cooperation of the conveying system. The system is responsible for folding and sealing the packaging materials (such as paper boxes) to form a complete cigarette box. In this process, the cigarettes are accurately placed in the box and sealed by heat sealing or other means. The drying and heat shrinking system is the last stage of the packaging process. It receives the cigarette boxes that have been packaged and dried and heat-shrunk. The main function of the drying heat shrink system is to make the heat shrink film on the cigarette box close to the surface of the cigarette box, which plays a role in protecting the cigarette box and increasing its aesthetics. The drying process can remove moisture from the packaging material to ensure the firmness and appearance of the packaging.

[0038] In the embodiment of the present invention, the main control unit 11 may be a single chip microcomputer, an MCU, etc., which is not limited here. The detection unit may be a CCD industrial camera, a point cloud data extraction device, etc., which is not limited here.

[0039] The detection unit 12 is used to capture the operation image of the corresponding subsystem;

[0040] The main control unit 11 is used to perform the following steps:

[0041] According to the operation images of each subsystem, determine the defect information in each operation image;

[0042] Determine the correlation information of each defect information according to the defect information in each operation image and the operation correlation between each subsystem;

[0043] The maintenance strategy of the high-speed packaging machine is determined based on the defect information and associated information in each operating image.

[0044] In the embodiment of the present invention, the operation images of each subsystem are images related to cigarette boxes, for example, the image of the material supply system can be an image of the supplied paper box, film, etc. The operation image of the conveying system is an image of an empty cigarette box or a semi-finished cigarette box.

[0045] In some embodiments, the main control unit is used to: input the operation images of each subsystem into the image recognition model corresponding to the subsystem, and determine the defect information in each operation image.

[0046] In the embodiments of the present invention, unstable supply speed may cause the speed of the main conveyor system to be mismatched, causing cigarette boxes to pile up or the conveyor belt to slip. Material breakage or inaccurate cutting may affect the operation of the packaging forming system, resulting in incomplete cigarette box packaging. Coil deviation may cause improper handling of the drying and heat shrinking system, affecting the appearance and quality of the cigarette boxes.

[0047] Conveyor failure can cause the packaging material supply system and package forming system to not work properly because the material cannot be conveyed correctly. Improper speed control will affect the efficiency of the finished product output system and may cause finished products to pile up. The posture of the cigarette box on the conveyor has a direct impact on the packaging effect of the packaging machine. Here are a few key points to explain how the posture of the cigarette box affects the packaging effect: Positioning accuracy: The posture of the cigarette box on the conveyor must be accurate to ensure that the clamp or mechanical arm of the packaging machine can correctly grasp and place the cigarette box. If the cigarette box is tilted or offset, it may cause poor packaging or failure. Sealing quality: Incorrect posture of the cigarette box may cause the sealing part of the packaging machine to fail to close correctly, thus affecting the sealing of the package. For example, if one side of the cigarette box is higher than the other side, the seal may be uneven, causing leakage or damage. Packaging speed: Correct cigarette box posture can ensure that the packaging machine operates at the highest efficiency. If the cigarette box posture is incorrect, the packaging machine may need to slow down for adjustment, which will reduce production efficiency. Reduce downtime: Incorrect cigarette box posture may cause the packaging machine to stop frequently to clear the jam or failure caused by improper posture. This increases maintenance time and cost.

[0048] In the embodiments of the present invention, inaccurate folding or poor lamination may affect the effect of the drying and heat shrinking system, resulting in problems with the appearance and quality of the cigarette box. A loose seal may result in poor sealing of the cigarette box output by the finished product output system. Uneven heating may affect the final effect of the packaging forming system, resulting in an uneven appearance of the cigarette box. Poor heat shrinking effect may affect the efficiency of the finished product output system and the overall quality of the cigarette box.

[0049] Some of the above defects can be detected directly through image analysis, while others require specific analysis of the relationship between the various subsystems (for example, the defect of the previous processing step will affect the next processing step). Therefore, according to the defect information and related information in each running image, the corresponding high-speed packaging machine maintenance strategy is formulated to reduce unplanned downtime.

[0050] In some embodiments, for the operation image of any subsystem, the main control unit is used to: extract the region of interest corresponding to the subsystem in the operation image; input the region of interest into the image recognition model corresponding to the subsystem to determine the defect information corresponding to the subsystem.

[0051] In the embodiment of the present invention, first, the running image needs to be preprocessed. Image preprocessing can filter out interference and optimize its visual effect, and can also reduce the data content of subsequent processing and improve the accuracy of the measurement system. Then, the border of the preprocessed image is determined; then, the region of interest (ROI) is determined, and a preliminary judgment is made based on the image features of a good packaging box, and each ROI is judged; finally, when the ROI is judged to be defective, the defect will be further classified to determine the defect type. Specifically, neural networks, support vector machines, etc. can be used as image recognition models for recognition and classification.

[0052] For each subsystem, the running images pre-labeled with defects can be input into the model for training, so that each subsystem obtains a corresponding image recognition model.

[0053] In some embodiments, the main control unit is used to: construct a fault knowledge graph for each subsystem based on the operation associations and areas of interest between the subsystems; and determine the association information of each defect information based on the defect information in each operation image and the fault knowledge graph of each subsystem.

[0054] In the embodiment of the present invention, an empty or blocked hopper may affect the continuity of the package forming system, resulting in package interruption.

[0055] In some embodiments, the main control unit is further used to: determine the preceding subsystem of each subsystem according to the operational association between the subsystems, and transmit the recognition loss of the image recognition model of each subsystem to the preceding subsystem of the subsystem.

[0056] In the embodiment of the present invention, the image recognition model set in each subsystem is not isolated. Since the subsystems cooperate with each other in production, the defects of the previous processing step will affect the next processing step. That is, the defects of the product in the current process are probably not caused by the current process, but by the wrong operation of the previous process, and the error was not detected in the previous process. Therefore, the present invention sets up a loss feedback mechanism, which transmits the recognition loss of the image recognition model of the subsystem to the previous subsystem of the subsystem. The image recognition model of the previous subsystem multiplies its own loss and the received loss by the preset weight to calculate the total loss, thereby improving the accuracy of defect recognition and avoiding defects caused by the failure of the previous subsystem. Due to the failure to recognize the defect, the subsequent subsystem recognizes the defect and causes a misjudgment of the fault.

[0057] In some embodiments, for any subsystem, the main control unit is used to: determine multiple previous-level-relationship-current-level defect triplets based on defect information identified in the area of ​​interest corresponding to the previous subsystem of the subsystem and defect information identified in the area of ​​interest corresponding to the subsystem; and construct a fault knowledge graph for each subsystem based on the multiple previous-level-relationship-current-level defect triplets.

[0058] In an embodiment of the present invention, the relationship value between a defect detected by a subsystem and a defect of its previous subsystem is given by an expert, thereby establishing multiple previous-level-relationship-current-level defect triplets to form a knowledge graph. Subsequently, when a defect is detected, by querying the knowledge graph, it can be determined whether there are undetected defects in the previous subsystem, that is, the above-mentioned association information.

[0059] In some embodiments, the main control unit is used to: input defect information and associated information in each operating image into a fault identification model to determine fault information; and determine a maintenance strategy for the high-speed packaging machine based on the fault information.

[0060] In an embodiment of the present invention, after detecting product defects in each subsystem, they are input into a trained fault identification model to obtain fault information. The fault information can be a fault of any one or more subsystems, such as wear, heat, abnormal pressure, etc., which is not limited here. High-speed packaging machines usually shut down for maintenance regularly, and the training set and test set of the fault identification model are obtained from the maintenance data. In addition to the type of defect, the defect information and related information can also include the number of defects of each type, the frequency and number of consecutive occurrences of defects of the same type, etc., which are not limited here.

[0061] In the embodiment of the present invention, it is determined whether to immediately shut down for maintenance or to perform maintenance at the next or subsequent planned shutdown according to the fault. The maintenance strategies corresponding to the specific types of faults can be queried through a preset table.

[0062] In some embodiments, the main control unit is used to: obtain an operation plan for the high-speed packaging machine; input defect information and related information in each operation image into a fault identification model to determine fault information; predict the remaining life information of each subsystem based on the fault information, operation plan and life prediction model; determine the maintenance strategy of the high-speed packaging machine based on the operation plan, fault information and remaining life information.

[0063] In the embodiment of the present invention, after the fault information is identified, the life of each subsystem can also be predicted. Specifically, a life prediction model can be constructed through a neural network. The input of the neural network is the fault information and the operation plan, and the output is the reliability / failure rate. The lower the reliability and the higher the failure rate, the shorter the remaining life. The operation plan can include the operation time, downtime, operation mode, etc. of each subsystem, which are not limited here.

[0064] In the embodiment of the present invention, it is determined whether to shut down for maintenance immediately or to perform maintenance at the next or subsequent planned shutdown according to the fault and the remaining life. The maintenance strategy corresponding to each type of fault can be queried through a preset table.

[0065] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0066] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0067] In the embodiments provided by the present invention, it should be understood that the disclosed devices / controllers and methods can be implemented in other ways. For example, the device / controller embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0068] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, 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 solution of this embodiment.

[0069] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0070] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0071] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. An intelligent maintenance device based on cigarette box appearance defect detection, characterized in that: The high-speed cigarette packaging machine includes multiple subsystems; the intelligent maintenance device includes: a main control unit and multiple detection units; each subsystem is provided with at least one detection unit; The detection unit is used to capture the operation image of the corresponding subsystem; The main control unit is used to perform the following steps: According to the operation images of each subsystem, determine the defect information in each operation image; Determine the correlation information of each defect information according to the defect information in each operation image and the operation correlation between each subsystem; A maintenance strategy for the high-speed packaging machine is determined according to the defect information in each operation image and the associated information.

2. The intelligent maintenance device based on cigarette box appearance defect detection according to claim 1 is characterized in that: The main control unit is used for: The operation images of each subsystem are input into the image recognition model corresponding to the subsystem to determine the defect information in each operation image.

3. The intelligent maintenance device based on cigarette box appearance defect detection according to claim 2 is characterized in that: For the running image of any subsystem, the main control unit is used to: Extracting a region of interest corresponding to the subsystem in the running image; The region of interest is input into an image recognition model corresponding to the subsystem to determine defect information corresponding to the subsystem.

4. The intelligent maintenance device based on cigarette box appearance defect detection according to claim 3 is characterized in that: The main control unit is used for: According to the operation associations and areas of interest between each subsystem, a fault knowledge graph of each subsystem is constructed; According to the defect information in each operation image and the fault knowledge graph of each subsystem, the associated information of each defect information is determined.

5. The intelligent maintenance device based on cigarette box appearance defect detection according to claim 4 is characterized in that: The main control unit is also used for: According to the operational association between each subsystem, the preceding subsystem of each subsystem is determined, and the recognition loss of the image recognition model of each subsystem is transmitted to the preceding subsystem of the subsystem.

6. The intelligent maintenance device based on cigarette box appearance defect detection according to claim 5 is characterized in that: For any subsystem, the main control unit is used to: Determine a plurality of previous-level-relationship-current-level defect triplets according to defect information identified by the region of interest corresponding to the previous-level subsystem of the subsystem and defect information identified by the region of interest corresponding to the subsystem; Based on multiple previous-level-relationship-current-level defect triplets, a fault knowledge graph for each subsystem is constructed.

7. The intelligent maintenance device based on cigarette box appearance defect detection according to claim 1 is characterized in that: The main control unit is used for: Inputting the defect information and the associated information in each operation image into a fault identification model to determine the fault information; A maintenance strategy for the high-speed packaging machine is determined based on the fault information.

8. The intelligent maintenance device based on cigarette box appearance defect detection according to claim 1 is characterized in that: The main control unit is used for: Obtaining an operation plan of the high-speed packaging machine; Inputting the defect information and the associated information in each operation image into a fault identification model to determine the fault information; Predicting the remaining life information of each subsystem according to the fault information, the operation plan and the life prediction model; A maintenance strategy for the high-speed packaging machine is determined according to the operation plan, the fault information and the remaining life information.

9. A high-speed packaging machine, characterized in that: The invention comprises a plurality of subsystems and an intelligent maintenance device based on cigarette box appearance defect detection as claimed in any one of claims 1 to 9.

10. The high-speed packaging machine according to claim 9, characterized in that: The high-speed packaging machine comprises: a material supply system, a conveying system, a packaging forming system, and a drying and heat shrinking system.

Images