A process management method based on digital twin technology

Through digital twin technology, a digital twin model matching the assembly line equipment is generated, and the actual and simulated operation data is compared, which solves the problem that manual inspections are difficult to accurately obtain the equipment status, and realizes real-time and accurate production process management of assembly line equipment.

CN115617000BActive Publication Date: 2024-11-22HUIZHIAN INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202211277573.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-10-19
Publication Date
2024-11-22
Estimated Expiration
2042-10-19

AI Technical Summary

Technical Problem

The huge scale of assembly line equipment leads to missed inspections, missed inspections and delays in manual inspections, and the difference between the actual working state and the expected state of the equipment cannot be accurately obtained, reducing the real-time and accuracy of production process management.

Method used

Using a process management method based on digital twin technology, by collecting and analyzing the operating dynamic images of the target equipment, generating a digital twin model that matches the equipment, comparing the production action process data of actual operation and simulated operation, determining whether the equipment has a fault and performing status Adjustment.

Benefits of technology

Real-time and accurate production process management of assembly line equipment, timely discover and handle faults, and improve the accuracy and management efficiency of equipment status.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115617000B_ABST
    Figure CN115617000B_ABST
Patent Text Reader

Abstract

The present invention provides a process management method based on digital twin technology, which utilizes digital twin technology to generate a digital twin model that matches the target device. By using the digital twin model as a reference benchmark, the difference between the actual working state and the expected working state of the target device is obtained promptly and quickly, thereby improving the real-time and accuracy of production process management of the target device.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of equipment management and control, and in particular to a process management method based on digital twin technology. Background Art

[0002] As a necessary device for standardized industrial production, assembly line equipment sets different production equipment on the assembly line according to certain rules, so that the production materials can be processed through different production links in sequence to become the required products. In order to ensure the normal production operation of assembly line equipment, it is necessary to arrange special staff to conduct continuous inspections of assembly line equipment. Due to the large scale of assembly line equipment, staff will inevitably miss inspections or make false inspections during the inspection process. At the same time, manual inspection methods will inevitably have delays and lags, and it is impossible to accurately obtain the difference between the actual working state and the expected working state of the assembly line equipment, thereby reducing the real-time and accuracy of production process management of assembly line equipment. Summary of the invention

[0003] In view of the defects of the prior art, the present invention provides a process management method based on digital twin technology, which collects and analyzes the dynamic operation image of the target device to obtain the action-related data of all the action components of the target device; then, according to the action-related data, the digital twin model corresponding to the target device is driven to operate, so as to obtain the production action process data of the action components of the digital twin model in a stable operation state; then, the actual operation process of the target device and the simulated operation process of the digital twin model, respectively corresponding to the production action process data of the same component are compared, so as to determine the difference information of the operation status of the target device relative to the digital twin model, and then determine whether there is a production action process failure in the target device, so as to adjust the working status of the target device; the above method uses digital twin technology to generate a digital twin model matching the target device, and uses the digital twin model as a reference benchmark to promptly and quickly obtain the difference between the actual working status and the expected working status of the target device, so as to ensure the real-time and accuracy of the production process management of the target device.

[0004] The present invention provides a process management method based on digital twin technology, which comprises the following steps:

[0005] Step S1, when the target device is started, the target device is detected by camera, and the running dynamic image of the target device is collected; the running dynamic image is analyzed and processed to obtain the action-related data of all action parts of the target device;

[0006] Step S2, after marking the action-related data, driving the digital twin model corresponding to the target device to operate according to the action-related data; when the operation of the digital twin model reaches a stable operation state, obtaining the production action process data of the action components corresponding to the digital twin model during the simulation operation process;

[0007] Step S3, after time synchronization calibration of the actual operation process of the target device and the simulated operation process of the digital twin model, the production action process data of the same component corresponding to the actual operation process and the simulated operation process are compared to determine the difference information of the operation status of the target device relative to the digital twin model;

[0008] Step S4, judging whether the target device has a production action process failure according to the operation status difference information; and adjusting the working status of the target device according to the above judgment result.

[0009] Furthermore, in step S1, when the target device is started, the target device is detected by camera, and the acquisition of the running dynamic image of the target device specifically includes:

[0010] When the target device is started, binocular camera detection is performed on the target device to collect binocular operation dynamic images of the target device.

[0011] Furthermore, in step S1, the motion dynamic image is analyzed and processed to obtain the motion-related data of all motion components of the target device, specifically including:

[0012] Determining binocular disparity information of the binocular running dynamic image, and generating a three-dimensional motion state image of the target device according to the binocular disparity information;

[0013] The component contours of all the moving parts of the target device are extracted from the three-dimensional motion state image; and based on each component contour, the motion posture data, motion amplitude data and motion speed data corresponding to each moving part in a time period corresponding to a complete production process are obtained from the three-dimensional motion state image, as the motion-related data of each moving part.

[0014] Further, in the step S2, after the action-related data is identified, driving the digital twin model corresponding to the target device to operate according to the action-related data specifically includes:

[0015] Adding component names of corresponding action components to the action posture data, the action amplitude data and the action speed data as data identifiers;

[0016] A driver program for the action components corresponding to the operation of the digital twin model is generated according to the action posture data, the action amplitude data and the action speed data; and the driver program is used to drive the action components corresponding to the operation of the digital twin model to operate.

[0017] Further, in step S2, when the operation of the digital twin model reaches a stable operation state, obtaining the production action process data of the action components corresponding to the digital twin model during the simulation operation specifically includes:

[0018] After all the action components of the digital twin model are operated under the driving action of their respective corresponding drivers, the analog working current and the analog working voltage corresponding to the digital twin model are collected; if the change rate of the analog working current is lower than the preset current change rate threshold and the change rate of the analog working voltage is lower than the preset voltage change rate threshold, it is determined that the digital twin model has reached a stable operating state;

[0019] Then obtain the production action process data corresponding to all action components in a complete production process during the simulation operation of the digital twin model; wherein, the production action process data refers to the time axis relationship data corresponding to the time axis relationship data of all action components completing their respective actions in a complete production process.

[0020] Further, in step S3, time synchronization calibration of the actual operation process of the target device and the simulated operation process of the digital twin model specifically includes:

[0021] The start time of a complete production process of the actual operation process of the target device and the start time of a complete production process of the simulated operation process of the digital twin model are synchronously calibrated.

[0022] Further, in step S3, the production action process data of the same component corresponding to the actual operation process and the simulated operation process are compared to determine the operation status difference information of the target device relative to the digital twin model, which specifically includes:

[0023] The production action flow data of the same component corresponding to the actual operation process and the simulated operation process are compared to determine the action phase difference between the target device and the digital twin model on the same action component, which is used as the operation status difference information.

[0024] Further, in the step S4, judging whether the target device has a production action process failure according to the operation status difference information; and adjusting the working status of the target device according to the above judgment result specifically includes:

[0025] If the action phase difference corresponding to any action component is greater than or equal to the preset phase difference threshold, it is determined that the target device has a production action process failure; otherwise, it is determined that the target device does not have a production action process failure;

[0026] When a production action flow failure occurs in the target device, a work restart adjustment process is performed on all action components in the target device whose action phase difference is greater than or equal to a preset phase difference threshold.

[0027] Compared with the existing technology, the process management method based on digital twin technology collects and analyzes the dynamic operation image of the target equipment to obtain the action-related data of all the action parts of the target equipment; then, according to the action-related data, the digital twin model corresponding to the target equipment is driven to operate, so as to obtain the production action process data of the action parts of the digital twin model in a stable operation state; then, the actual operation process of the target equipment and the simulated operation process of the digital twin model, respectively corresponding to the production action process data of the same component are compared, so as to determine the difference information of the operation status of the target equipment relative to the digital twin model, and then determine whether there is a production action process failure in the target equipment, so as to adjust the working status of the target equipment; the above method uses digital twin technology to generate a digital twin model matching the target equipment, and uses the digital twin model as a reference benchmark to promptly and quickly obtain the difference between the actual working status and the expected working status of the target equipment, so as to improve the real-time and accuracy of the production process management of the target equipment.

[0028] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0029] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0031] Figure 1 A flowchart of a process management method based on digital twin technology provided by the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] See also Figure 1 , is a flow chart of a process management method based on digital twin technology provided by an embodiment of the present invention. The process management method based on digital twin technology includes the following steps:

[0034] Step S1, when the target device is started, the target device is detected by camera, and the running dynamic image of the target device is collected; the running dynamic image is analyzed and processed to obtain the action-related data of all action parts of the target device;

[0035] Step S2, after marking the action-related data, drive the digital twin model corresponding to the target device to operate according to the action-related data; when the operation of the digital twin model reaches a stable operation state, obtain the production action process data of the action component corresponding to the digital twin model during the simulation operation process;

[0036] Step S3, after time synchronization calibration of the actual operation process of the target device and the simulated operation process of the digital twin model, the production action flow data of the same component corresponding to the actual operation process and the simulated operation process are compared to determine the difference information of the operation status of the target device relative to the digital twin model;

[0037] Step S4, judging whether the target device has a production action process failure according to the operation status difference information; and adjusting the working status of the target device according to the above judgment result.

[0038] The beneficial effects of the above technical solution are as follows: the process management method based on digital twin technology collects and analyzes the dynamic operation image of the target device to obtain the action-related data of all the action components of the target device; then, according to the action-related data, the digital twin model corresponding to the target device is driven to operate, so as to obtain the production action process data of the action components of the digital twin model in a stable operation state; then, the actual operation process of the target device and the simulated operation process of the digital twin model are compared with the production action process data of the same component corresponding to each other, so as to determine the difference information of the operation status of the target device relative to the digital twin model, and then determine whether there is a production action process failure in the target device, so as to adjust the working status of the target device; the above method uses digital twin technology to generate a digital twin model that matches the target device, and uses the digital twin model as a reference benchmark to promptly and quickly obtain the difference between the actual working status and the expected working status of the target device, so as to achieve real-time and accurate production process management of the target device.

[0039] Preferably, in step S1, when the target device is started, performing camera detection on the target device, and acquiring the running dynamic image of the target device specifically includes:

[0040] When the target device is started, binocular camera detection is performed on the target device to collect binocular operation dynamic images of the target device.

[0041] The beneficial effect of the above technical solution is: through the above method, the dynamic running state of the target device after startup is captured by binocular, so that the running process of the target device can be captured in all directions, which is convenient for subsequent accurate identification of the action state information of each action component of the target device.

[0042] Preferably, in step S1, analyzing and processing the motion dynamic image to obtain the motion-related data of all motion components of the target device specifically includes:

[0043] Determine binocular disparity information of the binocular running dynamic image, and generate a three-dimensional motion state image of the target device according to the binocular disparity information;

[0044] The component contours of all the moving parts of the target device are extracted from the three-dimensional motion state image; and based on each component contour, the motion posture data, motion amplitude data and motion speed data corresponding to each moving part in the time period corresponding to a complete production process are obtained from the three-dimensional motion state image, as the motion-related data of each moving part.

[0045] The beneficial effect of the above technical solution is: through the above method, a three-dimensional motion state image is generated based on the binocular operation dynamic image, and then the corresponding image contour information is extracted from the three-dimensional motion state image, and each action component of the target device is independently analyzed based on the contour of each action component, so as to obtain the action-related data of each action component of the target device in the time period corresponding to a completed production process.

[0046] Preferably, in step S2, after the action-related data is identified, driving the digital twin model corresponding to the target device to operate according to the action-related data specifically includes:

[0047] Add the component names of the corresponding action components to the action posture data, the action amplitude data and the action speed data as data identifiers;

[0048] According to the motion posture data, the motion amplitude data and the motion speed data, a driver program for the motion components corresponding to the operation of the digital twin model is generated; and the driver program is used to drive the motion components corresponding to the operation of the digital twin model to operate.

[0049] The beneficial effect of the above technical solution is: by adding the corresponding component name to the action posture data, action amplitude data and action speed data of each action component in the above manner, the recognition of the action-related data can be improved to avoid confusion with the action-related data of other action components. In addition, the digital twin model is a simulation model formed with the target device as a reference benchmark. There is a one-to-one mapping relationship between the action components of the digital twin model and the action components of the target device. According to the action posture data, action amplitude data and action speed data, a driver program for the action components corresponding to the operation of the digital twin model is generated, which can ensure that each action component of the digital twin model has the same drive input as the action component of the target device, thereby realizing the normal drive of the digital twin model.

[0050] Preferably, in step S2, when the operation of the digital twin model reaches a stable operation state, obtaining the production action process data of the action components corresponding to the digital twin model during the simulation operation specifically includes:

[0051] After all the action components of the digital twin model are operated under the driving action of their respective corresponding drivers, the analog working current and the analog working voltage corresponding to the digital twin model are collected; if the change rate of the analog working current is lower than the preset current change rate threshold and the change rate of the analog working voltage is lower than the preset voltage change rate threshold, it is determined that the digital twin model has reached a stable operating state;

[0052] Then obtain the production action process data corresponding to all action components in a complete production process during the simulation operation of the digital twin model; wherein the production action process data refers to the time axis relationship data corresponding to the time axis relationship data of all action components completing their respective actions in a complete production process.

[0053] The beneficial effect of the above technical solution is: through the above method, the operational stability state of the digital twin model after it is activated can be quantitatively evaluated, and at the same time, the production action process data corresponding to all action components of the digital twin model in a complete production process during the simulation operation is used as a benchmark, which facilitates the subsequent comparison and judgment of the actual production process status of the target equipment.

[0054] Preferably, in step S3, time synchronization calibration of the actual operation process of the target device and the simulated operation process of the digital twin model specifically includes:

[0055] The start time of a complete production process of the actual operation process of the target device and the start time of a complete production process of the simulated operation process of the digital twin model are synchronously calibrated.

[0056] The beneficial effect of the above technical solution is: through the above method, the start time of a complete production process of the actual operation process of the target equipment and the start time of a complete production process of the simulated operation process of the digital twin model are synchronously calibrated, so that a comprehensive comparison of the target equipment and the digital twin model can be achieved in the same complete production process.

[0057] Preferably, in step S3, the production action flow data of the same component corresponding to the actual operation process and the simulated operation process are compared to determine the operation state difference information of the target device relative to the digital twin model, specifically including:

[0058] The production action flow data of the same component corresponding to the actual operation process and the simulated operation process are compared to determine the action phase difference between the target device and the digital twin model on the same action component, which is used as the operation status difference information.

[0059] The beneficial effect of the above technical solution is: through the above method, taking the production action process data of each action component of the digital twin model as a reference benchmark, if the target device fails, the action of at least one action component of the target device will be out of sync with the action of the action component in the digital twin model. This asynchrony actually corresponds to the above action phase difference. In this way, based on the above action phase difference, it is possible to quantitatively judge whether the target device is in a faulty state.

[0060] Preferably, in step S4, judging whether the target device has a production action process failure according to the operation status difference information; and adjusting the working status of the target device according to the above judgment result specifically includes:

[0061] If the action phase difference corresponding to any action component is greater than or equal to the preset phase difference threshold, it is determined that the target device has a production action process failure; otherwise, it is determined that the target device does not have a production action process failure;

[0062] When a production action flow failure occurs in the target device, a restart adjustment process is performed on all action components in the target device whose action phase difference is greater than or equal to a preset phase difference threshold.

[0063] The beneficial effect of the above technical solution is: through the above method, taking the action phase difference corresponding to the action component as a reference, it is possible to quickly determine whether the target device has a production action process failure, thereby making targeted work start-up adjustments to the action components of the target device to restore the working state of the target device to normal.

[0064] From the content of the above embodiment, it can be seen that the process management method based on digital twin technology collects and analyzes the running dynamic image of the target device to obtain the action-related data of all the action components of the target device; then, according to the action-related data, the digital twin model corresponding to the target device is driven to operate, so as to obtain the production action process data of the action components of the digital twin model in a stable operating state; then, the actual operation process of the target device and the simulated operation process of the digital twin model are compared with the production action process data of the same component corresponding to each other, so as to determine the difference information of the running state of the target device relative to the digital twin model, and then determine whether there is a production action process failure in the target device, so as to adjust the working state of the target device; the above method uses digital twin technology to generate a digital twin model that matches the target device, and uses the digital twin model as a reference benchmark to promptly and quickly obtain the difference between the actual working state and the expected working state of the target device, so as to achieve real-time and accuracy in the production process management of the target device.

[0065] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A process management method based on digital twin technology, characterized in that: It includes the following steps: Step S1, when the target device is started, the target device is detected by camera, and the running dynamic image of the target device is collected; the running dynamic image is analyzed and processed to obtain the action-related data of all action parts of the target device; Step S2, after marking the action-related data, driving the digital twin model corresponding to the target device to operate according to the action-related data; when the operation of the digital twin model reaches a stable operation state, obtaining the production action process data of the action components corresponding to the digital twin model during the simulation operation process; Step S3, after time synchronization calibration of the actual operation process of the target device and the simulated operation process of the digital twin model, the production action process data of the same component corresponding to the actual operation process and the simulated operation process are compared to determine the difference information of the operation status of the target device relative to the digital twin model; Step S4, judging whether the target device has a production action process failure according to the operation status difference information; and adjusting the working status of the target device according to the above judgment result; Among them, in the step S1, when the target device is started, the target device is detected by camera, and the acquisition of the running dynamic image of the target device specifically includes: When the target device is started, binocular camera detection is performed on the target device to collect binocular operation dynamic images of the target device; Among them, in the step S1, the operation dynamic image is analyzed and processed to obtain the action-related data of all action components of the target device, which specifically includes: Determining binocular disparity information of the binocular running dynamic image, and generating a three-dimensional motion state image of the target device according to the binocular disparity information; Extracting the component outlines of all the action components of the target device from the three-dimensional motion state image; and taking each component outline as a reference, obtaining the action posture data, action amplitude data and action speed data corresponding to each action component in a time period corresponding to a complete production process from the three-dimensional motion state image, and using this as the action-related data of each action component; Among them, in the step S2, after the action-related data is identified, driving the digital twin model corresponding to the target device to operate according to the action-related data specifically includes: Adding component names of corresponding action components to the action posture data, the action amplitude data and the action speed data as data identifiers; A driver program for the action components corresponding to the operation of the digital twin model is generated according to the action posture data, the action amplitude data and the action speed data; and the driver program is used to drive the action components corresponding to the operation of the digital twin model to operate.

2. The process management method based on digital twin technology according to claim 1, characterized in that: In step S2, when the operation of the digital twin model reaches a stable operation state, obtaining the production action process data of the action components corresponding to the digital twin model during the simulation operation specifically includes: After all the action components of the digital twin model are operated under the driving action of their respective corresponding drivers, the analog working current and the analog working voltage corresponding to the digital twin model are collected; if the change rate of the analog working current is lower than the preset current change rate threshold and the change rate of the analog working voltage is lower than the preset voltage change rate threshold, it is determined that the digital twin model has reached a stable operating state; Then obtain the production action process data corresponding to all action components in a complete production process during the simulation operation of the digital twin model; wherein, the production action process data refers to the time axis relationship data corresponding to the time axis relationship data of all action components completing their respective actions in a complete production process.

3. The process management method based on digital twin technology according to claim 2, characterized in that: In step S3, time synchronization calibration of the actual operation process of the target device and the simulated operation process of the digital twin model specifically includes: The start time of a complete production process of the actual operation process of the target device and the start time of a complete production process of the simulated operation process of the digital twin model are synchronously calibrated.

4. The process management method based on digital twin technology according to claim 3, characterized in that: In step S3, the production action process data of the same component corresponding to the actual operation process and the simulated operation process are compared to determine the difference information of the operation state of the target device relative to the digital twin model, which specifically includes: The production action flow data of the same component corresponding to the actual operation process and the simulated operation process are compared to determine the action phase difference between the target device and the digital twin model on the same action component, which is used as the operation status difference information.

5. The process management method based on digital twin technology according to claim 4, characterized in that: In the step S4, judging whether the target device has a production action process failure according to the operation status difference information; and adjusting the working status of the target device according to the above judgment result specifically includes: If the action phase difference corresponding to any action component is greater than or equal to the preset phase difference threshold, it is determined that the target device has a production action process failure; otherwise, it is determined that the target device does not have a production action process failure; When a production action flow failure occurs in the target device, a work restart adjustment process is performed on all action components in the target device whose action phase difference is greater than or equal to a preset phase difference threshold.