Digital twinborn model automatic optimization method

Abstract

The invention discloses an automatic optimization method for a digital twin model, and the method specifically comprises the following steps: S1, a data collection module is used for collecting the related construction data of each scene, and a model construction module is used for constructing the digital twin model according to the collected scene data; and S2, parameters in an actual application system are collected through a target parameter collection module, and a classification module is used for classifying the collected target parameters. According to the automatic optimization method for the digital twinborn model, data of actual system application parameters are stored in a database, the actual parameters are drawn into a data table diagram and stored, and a test unit substitutes test data into the digital twinborn model for running test. Various data in a test state and various data in practical application are compared and analyzed, and then parameters of the digital twin model are optimized and corrected according to comparison errors, so that the accuracy of the digital twin model is continuously improved.

Description

Technical Field

[0001] The present invention relates to the field of data technology, and in particular to a method for automatic optimization of a digital twin model. Background Art

[0002] Digital twins make full use of physical models, sensor updates, operation history and other data, integrate multi-disciplinary, multi-physical quantity, multi-scale, and multi-probability simulation processes, complete mapping in virtual space, and thus reflect the entire life cycle of the corresponding physical equipment. Digital twins are a concept that transcends reality and can be regarded as a digital mapping system of one or more important and interdependent equipment systems. Digital twins are a universally adaptable theoretical and technical system that can be applied in many fields. They are widely used in product design, product manufacturing, medical analysis, engineering construction and other fields. The most in-depth application in China is in the field of engineering construction, and the field of intelligent manufacturing has received the highest attention and the hottest research.

[0003] Currently, after the digital twin model is built, its initial data is the target parameter value in the existing actual system. Since the target parameters in the actual system are constantly changing, the accuracy of the digital twin model is affected. The current method of manually changing parameters for optimization has poor real-time performance, cumbersome operation, and requires a lot of time. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the shortcomings of the prior art, the present invention provides an automatic optimization method for a digital twin model, which solves the problem that the accuracy of the digital twin model is affected by the constant changes in the target parameters in the actual system, and the current method of manually changing parameters for optimization has poor real-time performance and cumbersome operation.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for automatic optimization of a digital twin model, specifically comprising the following steps:

[0008] S1. The data acquisition module is used to collect relevant construction data of each scene, and the model construction module is used to build a digital twin model based on the collected scene data;

[0009] S2. The parameters in the actual application system are collected by the target parameter collection module, the classification module is used to classify the collected target parameters, the chart drawing module is used to draw the classified target parameters in a data table, the storage module is used to store the target parameters in the form of a data table, and the real-time update module is used to update the data in the data table according to the target parameters collected in real time;

[0010] S3, the parameter substitution module is used to substitute the test data into the constructed digital twin model, the model operation module is used to perform scenario operation calculations according to the substituted data, and the result output module is used to output the test data and upload it to the data processing unit;

[0011] S4, the statistical module is used to perform detailed statistics on the test data in step S3, the calculation module is used to convert and analyze the test data, the data table establishment module is used to establish a data table chart according to the test data, and the comparison analysis module is used to compare and analyze the data in the test state with the data in the actual application, and upload the comparison results to the central processing system;

[0012] S5. The automatic verification module in the monitoring unit is used to monitor the comparison and analysis process and the operating status of the twin model in real time. The alarm module is used to alarm when errors occur in the comparison and operating status failures. When errors occur in the comparison, the automatic optimization unit is triggered;

[0013] S6. The extraction module is used to extract the parameters of the actual system of relevant errors from the database. The parameter optimization module is used to optimize the parameters of the digital twin model according to the extracted actual parameters. The log is used to record the optimization times and data of the twin model.

[0014] The present invention also discloses a system for the automatic optimization method of a digital twin model, including a central processing system, wherein the input end of the central processing system is electrically connected to the output end of a model construction module, the input end of the model construction module is electrically connected to the output end of a data acquisition module, the central processing system is bidirectionally connected to a database via wireless, the central processing system is bidirectionally connected to a test unit via wireless, the output end of the test unit is electrically connected to the input end of a data processing unit, the input end of the data processing unit is electrically connected to the output end of a comparison and analysis module, the output end of the database is electrically connected to the input end of the comparison and analysis module, the central processing system is bidirectionally connected to an automatic optimization unit via wireless, and the central processing system is bidirectionally connected to a monitoring unit via wireless.

[0015] Preferably, the output end of the comparison and analysis module is electrically connected to the input end of the central processing system, and the monitoring unit is bidirectionally connected to the test unit via wireless.

[0016] Preferably, the database includes a target parameter acquisition module, a classification module, a chart drawing module, a storage module and a real-time update module.

[0017] Preferably, the test unit includes a parameter substitution module, a model running module and a result output module.

[0018] Preferably, the data processing unit includes a statistical module, a calculation module and a data table creation module.

[0019] Preferably, the automatic optimization unit includes an extraction module, a parameter optimization module and a log.

[0020] Preferably, the monitoring unit includes an automatic verification module and an alarm module.

[0021] (III) Beneficial effects

[0022] The present invention provides a method for automatic optimization of a digital twin model, which has the following beneficial effects:

[0023] (1) The digital twin model automatic optimization method saves the data of actual system application parameters in the database, plots the actual parameters into a data table and stores them. The test unit substitutes the test data into the digital twin model for running test, compares and analyzes the various data under the test state with the various data in actual application, and then optimizes and corrects the parameters of the digital twin model according to the comparison error, thereby continuously improving the accuracy of the digital twin model.

[0024] (2) The digital twin model automatic optimization method uses a monitoring unit to monitor the comparative analysis process and operating status problems of the digital twin model in real time. The alarm module is used to alarm when errors and operating status failures occur, which is convenient for automatically triggering the optimization system and has better real-time performance.

[0025] (3) The automatic optimization method of the digital twin model draws data tables for all data under the test state and all data in actual application, which facilitates intuitive and clear understanding of the data in subsequent comparisons, shortens the comparison time, and improves data processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a structural principle block diagram of the system of the present invention;

[0027] Figure 2 It is a structural principle block diagram of the database of the present invention;

[0028] Figure 3 It is a structural principle block diagram of the test unit of the present invention;

[0029] Figure 4 It is a structural principle block diagram of the data processing unit of the present invention;

[0030] Figure 5 This is a structural principle block diagram of the automatic optimization unit of the present invention;

[0031] Figure 6 This is a block diagram of the structural principle of the monitoring unit of the present invention.

[0032] In the figure: 1 central processing system, 2 model building module, 3 data acquisition module, 4 database, 41 target parameter acquisition module, 42 classification module, 43 chart drawing module, 44 storage module, 45 real-time update module, 5 test unit, 51 parameter substitution module, 52 model operation module, 53 result output module, 6 data processing unit, 61 statistics module, 62 calculation module, 63 data table establishment module, 7 comparison and analysis module, 8 automatic optimization unit, 81 extraction module, 82 parameter optimization module, 83 log, 9 monitoring unit, 91 automatic verification module, 92 alarm module. DETAILED DESCRIPTION

[0033] 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.

[0034] See also Figure 1-6 The embodiment of the present invention provides a technical solution: a method for automatic optimization of a digital twin model, which specifically includes the following steps:

[0035] S1, data acquisition module 3 is used to collect relevant construction data of each scene, and model construction module 2 is used to build a digital twin model based on the collected scene data;

[0036] S2. The parameters in the actual application system are collected through the target parameter collection module 41. The classification module 42 is used to classify the collected target parameters. The classified data is easy to extract and find. The chart drawing module 43 is used to draw the classified target parameters in the form of a data table. The storage module 44 is used to store the target parameters in the form of a data table. The real-time update module 45 is used to update the data table data according to the real-time collected target parameters, so that the actual parameters in the storage module 44 are always referenceable, thereby improving the accuracy of the subsequent digital twin model.

[0037] S3, the parameter substitution module 51 is used to substitute the test data into the constructed digital twin model, the model operation module 52 is used to perform scenario operation calculation according to the substituted data, and the result output module 53 is used to output the test data and upload it to the data processing unit 6;

[0038] S4, the statistical module 61 is used to perform detailed statistics on the test data in step S3, the calculation module 62 is used to convert and analyze the test data and normalize the data, the data table establishment module 63 is used to establish a data table chart according to the test data, and the comparison analysis module 7 is used to compare and analyze the data in the test state with the data in the actual application to determine whether the data has errors, and upload the comparison results to the central processing system 1;

[0039] S5, the automatic verification module 91 in the monitoring unit 9 is used to monitor the comparison analysis process and the operating status of the twin model in real time, and the alarm module 92 is used to alarm when an error occurs in the comparison and an operating status failure occurs. When an error occurs in the comparison, the automatic optimization unit 8 is triggered;

[0040] S6, the extraction module 81 is used to extract the parameters of the actual system of relevant errors from the database 4, the parameter optimization module 82 is used to optimize and correct the parameters of the digital twin model according to the extracted actual parameters, and the log 83 is used to record the optimization times and data of the twin model for subsequent tracing.

[0041] The present invention also discloses a system for the automatic optimization method of a digital twin model, including a central processing system 1, the input end of the central processing system 1 is electrically connected to the output end of a model construction module 2, the input end of the model construction module 2 is electrically connected to the output end of a data acquisition module 3, the central processing system 1 is bidirectionally connected to a database 4 via wireless, the central processing system 1 is bidirectionally connected to a test unit 5 via wireless, the output end of the test unit 5 is electrically connected to the input end of a data processing unit 6, the input end of the data processing unit 6 is electrically connected to the output end of a comparison and analysis module 7, the output end of the database 4 is electrically connected to the input end of the comparison and analysis module 7, the central processing system 1 is bidirectionally connected to an automatic optimization unit 8 via wireless, and the central processing system 1 is bidirectionally connected to a monitoring unit 9 via wireless.

[0042] In the embodiment of the present invention, the output end of the comparison and analysis module 7 is electrically connected to the input end of the central processing system 1 , and the monitoring unit 9 is bidirectionally connected to the test unit 5 via wireless.

[0043] In the embodiment of the present invention, the database 4 includes a target parameter acquisition module 41 , a classification module 42 , a chart drawing module 43 , a storage module 44 and a real-time update module 45 .

[0044] In the embodiment of the present invention, the testing unit 5 includes a parameter substitution module 51 , a model operation module 52 and a result output module 53 .

[0045] In the embodiment of the present invention, the data processing unit 6 includes a statistical module 61 , a calculation module 62 and a data table creation module 63 .

[0046] In the embodiment of the present invention, the automatic optimization unit 8 includes an extraction module 81 , a parameter optimization module 82 and a log 83 .

[0047] In the embodiment of the present invention, the monitoring unit 9 includes an automatic verification module 91 and an alarm module 92. The alarm module 92 triggers the automatic optimization unit 8 to work after an error occurs in the comparison.

[0048] Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0049] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0050] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A digital twin model automatic optimization method, characterized by: The specific steps include: S1. The data acquisition module is used to collect relevant construction data of each scene, and the model construction module is used to build a digital twin model based on the collected scene data; S2. The parameters in the actual application system are collected by the target parameter collection module, the classification module is used to classify the collected target parameters, the chart drawing module is used to draw the classified target parameters in a data table, the storage module is used to store the target parameters in the form of a data table, and the real-time update module is used to update the data in the data table according to the target parameters collected in real time; S3, the parameter substitution module is used to substitute the test data into the constructed digital twin model, the model operation module is used to perform scenario operation calculations according to the substituted data, and the result output module is used to output the test data and upload it to the data processing unit; S4, the statistical module is used to perform detailed statistics on the test data in step S3, the calculation module is used to convert and analyze the test data, the data table establishment module is used to establish a data table chart according to the test data, and the comparison analysis module is used to compare and analyze the data in the test state with the data in the actual application, and upload the comparison results to the central processing system; S5. The automatic verification module in the monitoring unit is used to monitor the comparison and analysis process and the operating status of the twin model in real time. The alarm module is used to alarm when errors occur in the comparison and operating status failures. When errors occur in the comparison, the automatic optimization unit is triggered; S6. The extraction module is used to extract the parameters of the actual system of relevant errors from the database. The parameter optimization module is used to optimize the parameters of the digital twin model according to the extracted actual parameters. The log is used to record the optimization times and data of the twin model.

2. A system for automatic optimization of digital twin models according to claim 1, comprising a central processing system, characterized in that: The input end of the central processing system is electrically connected to the output end of the model construction module, the input end of the model construction module is electrically connected to the output end of the data acquisition module, the central processing system is bidirectionally connected to the database via wireless, the central processing system is bidirectionally connected to the test unit via wireless, the output end of the test unit is electrically connected to the input end of the data processing unit, the input end of the data processing unit is electrically connected to the output end of the comparison and analysis module, the output end of the database is electrically connected to the input end of the comparison and analysis module, the central processing system is bidirectionally connected to the automatic optimization unit via wireless, and the central processing system is bidirectionally connected to the monitoring unit via wireless.

3. A system for automatic optimization of digital twin models according to claim 2, characterized in that: The output end of the comparison and analysis module is electrically connected to the input end of the central processing system, and the monitoring unit is bidirectionally connected to the test unit via wireless.

4. A system for automatic optimization of digital twin models according to claim 2, characterized in that: The database includes a target parameter acquisition module, a classification module, a chart drawing module, a storage module and a real-time update module.

5. The system for automatic optimization of digital twin models according to claim 2, characterized in that: The test unit includes a parameter substitution module, a model running module and a result output module.

6. A system for automatic optimization of digital twin models according to claim 2, characterized in that: The data processing unit includes a statistical module, a calculation module and a data table creation module.

7. The system for automatic optimization of digital twin models according to claim 2, characterized in that: The automatic optimization unit includes an extraction module, a parameter optimization module and a log.

8. The system for automatic optimization of digital twin models according to claim 2, characterized in that: The monitoring unit includes an automatic verification module and an alarm module.

Images