A joint simulation method for multiple types of models of embedded computer digital twins

Abstract

The present invention relates to the field of multi-type model joint simulation, and in particular to a joint simulation method for multi-type models of an embedded computer digital twin. The present invention obtains configuration information for a simulation object; obtains several types of models required for the simulation, encapsulates each type of model, builds a simulation model library to be run, and synchronously parses each type of model; starts the simulation model library, performs synchronous simulation, and determines resource synchronization competition characterization parameters for a synchronous simulation process based on complexity differences and load competition rates of each type of model, so as to divide the resource synchronization competition categories for the synchronous simulation process; in the synchronous simulation process, adaptively controls simulation parameters based on the resource synchronization competition categories; and monitors and displays each simulation data in real time. The present invention can alleviate system resource competition in the multi-type model joint simulation process, ensure balanced resource allocation and the stability of the simulation process, and improve the simulation effect and efficiency.

Description

Technical Field

[0001] The present invention relates to the field of multi-type model joint simulation, and in particular to a joint simulation method for multi-type models of embedded computer digital twins. Background Art

[0002] With the rapid advancement of computer technology, especially the integrated application of technologies such as big data, cloud computing, artificial intelligence and the Internet of Things, modern systems are becoming increasingly complex, even crossing the traditional disciplinary boundaries, forming a development trend of multidisciplinary cross-integration, integrating models from different disciplines into a unified framework, such as mechanics, electronics, and control, to achieve a comprehensive evaluation and optimization of the overall performance of the system. Through joint simulation, the behavior of the system under different working conditions is simulated to predict system performance, discover potential problems and optimize the system design. At the same time, digital twins, as digital mappings of physical entities in virtual space, can simulate system responses under several hypothetical conditions, thereby improving the flexibility and efficiency of embedded system design. At the same time, the development of digital twin technology has also promoted the need for high-precision and high-real-time simulation of embedded systems.

[0003] Chinese Patent Publication No.: CN117555251A, discloses a digital twin simulation device and a digital twin simulation system, including a sensor module, a data acquisition module, a modeling and simulation module and an analysis and optimization module. The sensor module is connected to the data acquisition module, the data acquisition module is connected to the modeling and simulation module, and the modeling and simulation module is connected to the analysis and optimization module; the sensor module is used to collect data in the physical world in real time.

[0004] However, there are still the following problems in the prior art:

[0005] When several physical entities are dynamized in a short period of time and the digital twin models mapped by the physical entities are relatively complex, the simultaneous simulation of multiple related and interacting digital twins in the virtual space may lead to excessive competition for system resources, frequent freezes in the simulation process, and increased difficulty of simulation, affecting the simulation effect and efficiency. Summary of the invention

[0006] To this end, the present invention provides a joint simulation method for multiple types of models of digital twins of embedded computers, so as to overcome the problems in the prior art that several physical entities are concentrated and dynamic in a short period of time, and the digital twin models mapped by the physical entities are relatively complex. When multiple related and interacting digital twins are simulated simultaneously in the virtual space, it may lead to excessive competition for system resources, frequent freezes may occur during the simulation process, increase the difficulty of simulation, and affect the simulation effect and efficiency.

[0007] To achieve the above object, the present invention provides a joint simulation method of multiple types of models of embedded computer digital twins, which includes:

[0008] Step S1, obtaining configuration information for a simulation object, including the structural composition and internal structural relationship of the simulation object;

[0009] Step S2, based on the configuration information of the simulation object, obtain several types of models required for the simulation, encapsulate each type of model, build a simulation model library to be run, and synchronously parse each type of model, including preloading each type of model, recording the load of each type of model when it is run in the time domain segment, and determining the load competition rate based on the corresponding load rising trend of each type of model in different time domain segments;

[0010] Step S3, starting the simulation model library, performing synchronous simulation, and determining resource synchronization competition characterization parameters for the synchronous simulation process based on the complexity differences of various types of models and the load competition rate, so as to classify the resource synchronization competition categories for the synchronous simulation process;

[0011] Step S4, during the synchronous simulation process, controlling simulation parameters based on the resource synchronization competition category, including:

[0012] Adjust the time step in the synchronous simulation process based on the resource synchronization competition characterization parameter, obtain the update time when updating the simulation model in the synchronous simulation process, and determine whether the simulation process meets the resource balancing standard based on the difference in update time, so as to adjust the number of grids for the simulation model;

[0013] Or, maintain the reference time step during the synchronous simulation;

[0014] Step S5: During the synchronous simulation process, each simulation data is monitored and displayed in real time.

[0015] Furthermore, in the step S2, several types of models required for simulation are acquired based on the configuration information of the simulation object, including a functional model, a performance model and a geometric model.

[0016] Furthermore, in step S2, the process of determining the load contention rate based on the corresponding load rising trend of each type of model in different time domain segments includes:

[0017] Determine the load change trend of each type of model when it is operated in each time domain segment;

[0018] Determine a time domain segment that meets a predetermined trend change condition as a characteristic time domain segment;

[0019] The ratio of the characteristic time domain segment to the total number of time domain segments is determined as the load contention ratio;

[0020] The predetermined trend change condition is that each type of model has a load increase trend when being operated within the time domain segment.

[0021] Furthermore, in step S3, the process of determining the resource synchronization competition characterization parameters for the synchronous simulation process based on the complexity difference of each type of model and the load competition rate includes:

[0022] Get the complexity of each type of model;

[0023] solving for the standard deviation of the complexity;

[0024] Calculating the ratio of the standard deviation to the standard deviation threshold and assigning a corresponding weight coefficient as the first resource feature;

[0025] Calculating a ratio of the load contention rate to the load contention rate threshold and assigning a corresponding weight coefficient as a second resource feature;

[0026] The sum of the first resource characteristic and the second resource characteristic is determined as a resource synchronization contention characterization parameter.

[0027] Furthermore, in step S3, resource synchronization competition categories for the synchronous simulation process are divided into:

[0028] If the resource synchronization contention characterization parameter is greater than or equal to the resource synchronization contention characterization parameter threshold, the resource synchronization of the synchronous simulation process is determined to be a strong contention category;

[0029] If the resource synchronization contention characterization parameter is less than the resource synchronization contention characterization parameter threshold, it is determined that the resource synchronization of the synchronous simulation process is a weak contention category.

[0030] Furthermore, in step S4, the simulation parameters are controlled based on the resource synchronization competition category, including:

[0031] If the resource synchronization of the synchronous simulation process is of the strong contention category, the time step in the synchronous simulation process is adjusted based on the resource synchronization competition characterization parameter, the update duration when the simulation model is updated in the synchronous simulation process is obtained, and whether the simulation process meets the resource balancing standard is determined based on the difference in the update duration, so as to adjust the number of grids for the simulation model;

[0032] If the resource synchronization of the synchronous simulation process is of weak contention type, the reference time step is maintained during the synchronous simulation process.

[0033] Furthermore, in step S4, the simulation parameters are controlled based on the resource synchronization competition category, including:

[0034] The time step is increased, and the increase value of the time step is positively correlated with the resource synchronization competition characterization parameter.

[0035] Furthermore, in step S4, the process of obtaining the update duration when updating the simulation model during the synchronous simulation process and determining whether the simulation process meets the resource balancing standard based on the difference in the update duration includes:

[0036] Get the update duration when updating the simulation model for a predetermined number of times;

[0037] Solve the variance of update duration;

[0038] Comparing the variance with a predetermined variance threshold to determine whether the simulation process meets the resource balancing standard;

[0039] If the variance is greater than a predetermined variance threshold, it is determined that the simulation process does not meet the resource balancing standard.

[0040] Furthermore, in step S4, adjusting the number of grids for the simulation model includes:

[0041] The number of grids is reduced, and the amount of reduction in the number of grids is positively correlated with the variance of the update duration.

[0042] Furthermore, in step S1, the configuration information of the simulation object also includes module parameters and reference relationships between models.

[0043] Compared with the prior art, the present invention obtains configuration information for a simulation object; based on the configuration information of the simulation object, obtains several types of models required for the simulation, encapsulates each type of model, builds a simulation model library to be run, and synchronously parses each type of model; starts the simulation model library, performs synchronous simulation, and determines resource synchronization competition characterization parameters for the synchronous simulation process based on complexity differences and load competition rates of each type of model, so as to classify resource synchronization competition categories for the synchronous simulation process; in the synchronous simulation process, adaptively controls simulation parameters based on resource synchronization competition categories; and monitors and displays each simulation data in real time. The present invention can alleviate system resource competition in the joint simulation process of multiple types of models, ensure balanced resource allocation and the stability of the simulation process, and improve the simulation effect and efficiency.

[0044] In particular, the present invention determines the resource synchronization competition characterization parameters through the complexity differences and load competition rates of various models. When multiple models of different types are synchronously simulated at the same time, each model requires resources provided by the system to support the operation of the simulation. Since the complexity of the digital twin models mapped by different model entities is different, and the system performs unified resource allocation, during the synchronous simulation process, relatively complex models will occupy too many system resources in order to maintain the smoothness of the simulation, resulting in resource competition. The present application calculates the resource synchronization competition characterization parameters to characterize the degree of demand for system resources and the degree of competition for system resources of each type of model, provides data support for the subsequent classification of resource synchronization competition categories for the synchronous simulation process, and adaptively controls the simulation parameters to ensure balanced resource allocation and the stability of the simulation process.

[0045] In particular, the present invention adjusts the time step in advance when the resource synchronization of the synchronous simulation process is a strong competition category to control the speed and progress of the simulation and alleviate system resource competition. Furthermore, the smoothness and stability of the adjusted simulation process are determined according to the update duration of the simulation model. If there is a large difference in the update duration of any simulation model, it can be reflected that the simulation model may have other abnormal situations such as freezes and resource competition during the simulation process, resulting in an extension of the update duration. Therefore, the present application determines whether resource balance is achieved based on the update duration of the adjusted simulation model, and timely adjusts the number of grids of the simulation model to ensure the smoothness and progress of the current multi-category models, thereby alleviating system resource competition in the joint simulation process of multiple models, ensuring balanced resource allocation and the stability of the simulation process, and improving the simulation effect and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic diagram of the steps of a joint simulation method for multiple types of models of an embedded computer digital twin according to an embodiment of the invention;

[0047] Figure 2 A logic decision diagram for classifying resource synchronization contention categories for a synchronous simulation process for an embodiment of the invention;

[0048] Figure 3 A logic decision diagram for controlling simulation parameters for an embodiment of the invention;

[0049] Figure 4 A logical decision diagram for determining whether a simulation process meets resource balancing standards according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0051] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0052] See also Figures 1 to 4 As shown, Figure 1 Schematic diagram of the steps of the joint simulation method of multiple types of models of embedded computer digital twins according to an embodiment of the present invention, Figure 2 A logical decision diagram for classifying resource synchronization competition categories for a synchronous simulation process according to an embodiment of the present invention, Figure 3 is a logic decision diagram for controlling simulation parameters in an embodiment of the present invention, Figure 4 The embodiment of the present invention is a logical decision diagram for determining whether the simulation process meets the resource balancing standard. The joint simulation method of multiple types of models of embedded computer digital twins in the embodiment of the present invention includes:

[0053] Step S1, obtaining configuration information for a simulation object, including the structural composition and internal structural relationship of the simulation object;

[0054] Step S2, based on the configuration information of the simulation object, obtain several types of models required for the simulation, encapsulate each type of model, build a simulation model library to be run, and synchronously parse each type of model, including preloading each type of model, recording the load of each type of model when it is run in the time domain segment, and determining the load competition rate based on the corresponding load rising trend of each type of model in different time domain segments;

[0055] Step S3, starting the simulation model library, performing synchronous simulation, and determining resource synchronization competition characterization parameters for the synchronous simulation process based on the complexity differences of various types of models and the load competition rate, so as to classify the resource synchronization competition categories for the synchronous simulation process;

[0056] Step S4, during the synchronous simulation process, controlling simulation parameters based on the resource synchronization competition category, including:

[0057] Adjust the time step in the synchronous simulation process based on the resource synchronization competition characterization parameter, obtain the update time when updating the simulation model in the synchronous simulation process, and determine whether the simulation process meets the resource balancing standard based on the difference in update time, so as to adjust the number of grids for the simulation model;

[0058] Or, maintain the reference time step during the synchronous simulation;

[0059] Step S5: During the synchronous simulation process, each simulation data is monitored and displayed in real time.

[0060] In this embodiment, the configuration information of the simulation object is obtained through the SysML model. This is a prior art and will not be described in detail.

[0061] Specifically, in step S2, several types of models required for simulation are obtained based on the configuration information of the simulation object, including a functional model, a performance model and a geometric model.

[0062] It is understandable that the packaging model may include FPGA models, schematic models, instruction set simulators, embedded simulation software, etc. This is the existing technology of modeling and simulation and will not be elaborated on.

[0063] It is understandable that those skilled in the art can configure the schematic model required for simulation according to the schematic model during design, and configure the simulation device library required for simulation according to the device library during design, which will not be elaborated herein.

[0064] Specifically, after determining the type of model that needs to be simulated, it is necessary to allocate corresponding memory for each type of model to ensure the simulation process and the storage of the simulation model.

[0065] Specifically, in step S2, the process of determining the load contention rate based on the corresponding load rising trend of each type of model in different time domain segments includes:

[0066] Determine the load change trend of each type of model when it is operated in each time domain segment;

[0067] Determine a time domain segment that meets a predetermined trend change condition as a characteristic time domain segment;

[0068] The ratio of the characteristic time domain segment to the total number of time domain segments is determined as the load contention ratio;

[0069] The predetermined trend change condition is that each type of model has a load increase trend when being operated within the time domain segment.

[0070] Specifically, in step S3, the process of determining the resource synchronization competition characterization parameters for the synchronous simulation process based on the complexity difference of each type of model and the load competition rate includes:

[0071] Get the complexity of each type of model;

[0072] solving for the standard deviation of the complexity;

[0073] Calculating the ratio of the standard deviation to the standard deviation threshold and assigning a corresponding weight coefficient as the first resource feature;

[0074] Calculating a ratio of the load contention rate to the load contention rate threshold and assigning a corresponding weight coefficient as a second resource feature;

[0075] The sum of the first resource characteristic and the second resource characteristic is determined as a resource synchronization contention characterization parameter.

[0076] In this embodiment, when assigning weights, the weight of the first resource feature is set to 0.4, and the weight of the second resource feature is set to 0.6;

[0077] The complexity standard deviation threshold C0 and the load contention rate threshold J0 are obtained in advance by obtaining relevant data of several multi-type model synchronous simulations, calling the complexity standard deviation and load contention rate data, solving the complexity standard deviation mean and the load contention rate mean, and setting the complexity standard deviation threshold to between 1.07 and 1.18 times the complexity standard deviation mean, and the load contention rate threshold to between 1.12 and 1.23 times the load contention rate mean.

[0078] The complexity of a model is the average load of the model when it is loaded by the server over a number of cycles.

[0079] The present invention determines the resource synchronization competition characterization parameters through the complexity differences and load competition rates of various models. When multiple models of different types are synchronously simulated at the same time, each model requires resources provided by the system to support the operation of the simulation. Since the complexity of the digital twin models mapped by different model entities is different, and the system performs unified resource allocation, during the synchronous simulation process, relatively complex models will occupy too many system resources in order to maintain the smoothness of the simulation, resulting in resource competition. The present application calculates the resource synchronization competition characterization parameters to characterize the degree of demand for system resources and the degree of competition for system resources of each type of model, provides data support for the subsequent classification of resource synchronization competition categories for the synchronous simulation process, and adaptively controls the simulation parameters to ensure balanced resource allocation and the stability of the simulation process.

[0080] Specifically, in step S3, resource synchronization competition categories for the synchronous simulation process are divided into:

[0081] If the resource synchronization contention characterization parameter is greater than or equal to the resource synchronization contention characterization parameter threshold, the resource synchronization of the synchronous simulation process is determined to be a strong contention category;

[0082] If the resource synchronization contention characterization parameter is less than the resource synchronization contention characterization parameter threshold, it is determined that the resource synchronization of the synchronous simulation process is a weak contention category.

[0083] The resource synchronization contention characterization parameter threshold Z0 is selected in the interval [1.21, 1.34].

[0084] Specifically, in step S4, the simulation parameters are controlled based on the resource synchronization competition category, including:

[0085] If the resource synchronization of the synchronous simulation process is of the strong contention category, the time step in the synchronous simulation process is adjusted based on the resource synchronization competition characterization parameter, the update duration when the simulation model is updated in the synchronous simulation process is obtained, and whether the simulation process meets the resource balancing standard is determined based on the difference in the update duration, so as to adjust the number of grids for the simulation model;

[0086] If the resource synchronization of the synchronous simulation process is of weak contention type, the reference time step is maintained during the synchronous simulation process.

[0087] Specifically, in step S4, the simulation parameters are controlled based on the resource synchronization competition category, including:

[0088] The time step is increased, and the increase value of the time step is positively correlated with the resource synchronization competition characterization parameter.

[0089] In this embodiment, optionally,

[0090] The resource synchronization contention characterization parameter Z is compared with the first resource synchronization contention characterization parameter comparison threshold Z1 and the second resource synchronization contention characterization parameter comparison threshold Z2.

[0091] When the resource synchronization competition characterization parameter is greater than the second resource synchronization competition characterization parameter comparison threshold, the time step increase value is determined to be the first time step increase value b1, and the first time step increase value b1 is set to be 0.45 times the reference time step b0;

[0092] When the resource synchronization competition characterization parameter is within a closed interval formed by the first resource synchronization competition characterization parameter comparison threshold and the second resource synchronization competition characterization parameter comparison threshold, the time step increase value is determined to be the second time step increase value b2, and the second time step increase value b2 is set to be 0.37 times the reference time step b0;

[0093] When the resource synchronization competition characterization parameter is less than the first resource synchronization competition characterization parameter comparison threshold, the time step increase value is determined to be the third time step increase value b3, and the third time step increase value b3 is set to be 0.28 times the reference time step b0;

[0094] Among them, the first resource synchronization competition characterization parameter comparison threshold Z1 is 1.1 times the resource synchronization competition characterization parameter threshold Z0, the second resource synchronization competition characterization parameter comparison threshold Z2 is 1.3 times the resource synchronization competition characterization parameter threshold Z0, and the reference time step b0 is selected in the interval [1ps, 10ps].

[0095] Specifically, in step S4, the update duration of updating the simulation model during the synchronous simulation process is obtained, and the process of determining whether the simulation process meets the resource balancing standard based on the difference in the update duration includes:

[0096] Get the update duration when updating the simulation model for a predetermined number of times;

[0097] Solve the variance of update duration;

[0098] Comparing the variance with a predetermined variance threshold to determine whether the simulation process meets the resource balancing standard;

[0099] Wherein, if the variance is greater than a predetermined variance threshold, it is determined that the simulation process does not meet the resource balancing standard;

[0100] If the variance is less than or equal to a predetermined variance threshold, it is determined that the simulation process meets the resource balancing standard.

[0101] The predetermined variance threshold F0 is selected in the interval [1.3, 1.6].

[0102] Specifically, in step S4, adjusting the number of grids for the simulation model includes:

[0103] The number of grids is reduced, and the amount of reduction in the number of grids is positively correlated with the variance of the update duration.

[0104] In this embodiment, optionally,

[0105] The variance F of the update duration is compared with the variance comparison threshold F1 of the first update duration and the variance comparison threshold F2 of the second update duration.

[0106] When the variance of the update time is greater than the variance comparison threshold of the second update time, the reduction amount of the number of grids is determined to be the first reduction amount of the number of grids h1, and the first reduction amount of the number of grids h1 is set to be 0.36 integer multiples of the initial number of grids h0;

[0107] When the variance of the update duration is within a closed interval formed by the variance comparison threshold of the first update duration and the variance comparison threshold of the second update duration, the reduction amount of the number of grids is determined to be the second reduction amount of the number of grids h2, and the second reduction amount of the number of grids h2 is set to be 0.27 integer multiples of the initial number of grids h0;

[0108] When the variance of the update duration is less than the variance comparison threshold of the first update duration, the reduction amount of the number of grids is determined to be the third reduction amount of the number of grids h3, and the third reduction amount of the number of grids h3 is set to be 0.19 integer multiples of the initial number of grids h0;

[0109] The variance comparison threshold F1 of the first update duration is 1.2 times the variance comparison threshold F0 of the update duration, and the variance comparison threshold F2 of the second update duration is 1.3 times the variance comparison threshold F0 of the update duration.

[0110] The present invention adjusts the time step in advance when the resource synchronization of the synchronous simulation process is a strong competition category to control the speed and progress of the simulation and alleviate system resource competition. Furthermore, the smoothness and stability of the adjusted simulation process are determined according to the update duration of the simulation model. If there is a large difference in the update duration of any simulation model, it can be reflected that the simulation model may have other abnormal situations such as freezes and resource competition during the simulation process, resulting in an extension of the update duration. Therefore, the present application determines whether resource balance is achieved based on the update duration of the adjusted simulation model, and timely adjusts the number of grids of the simulation model to ensure the smoothness and progress of the current multi-category model, thereby alleviating system resource competition in the joint simulation process of multiple models, ensuring balanced resource allocation and the stability of the simulation process, and improving the simulation effect and efficiency.

[0111] Specifically, in step S1, the configuration information of the simulation object also includes module parameters and reference relationships between models.

[0112] Block parameters include configuration settings for each block in a simulation model, which define the behavior and characteristics of the block.

[0113] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A joint simulation method for multiple types of models of embedded computer digital twins, characterized in that: include: Step S1, obtaining configuration information for a simulation object, including the structural composition and internal structural relationship of the simulation object; Step S2, based on the configuration information of the simulation object, obtain several types of models required for the simulation, encapsulate each type of model, build a simulation model library to be run, and synchronously parse each type of model, including preloading each type of model, recording the load of each type of model when it is run in the time domain segment, and determining the load competition rate based on the corresponding load rising trend of each type of model in different time domain segments; Step S3, starting the simulation model library, performing synchronous simulation, and determining resource synchronization competition characterization parameters for the synchronous simulation process based on the complexity differences of various types of models and the load competition rate, so as to classify the resource synchronization competition categories for the synchronous simulation process; Step S4, during the synchronous simulation process, controlling simulation parameters based on the resource synchronization competition category, including: Adjust the time step in the synchronous simulation process based on the resource synchronization competition characterization parameter, obtain the update time when updating the simulation model in the synchronous simulation process, and determine whether the simulation process meets the resource balancing standard based on the difference in update time, so as to adjust the number of grids for the simulation model; Or, maintain the reference time step during the synchronous simulation; Step S5: During the synchronous simulation process, each simulation data is monitored and displayed in real time.

2. The method for joint simulation of multiple types of models of embedded computer digital twins according to claim 1, characterized in that: In the step S2, several types of models required for simulation are acquired based on the configuration information of the simulation object, including a functional model, a performance model and a geometric model.

3. The method for joint simulation of multiple types of models of embedded computer digital twins according to claim 1, characterized in that: In step S2, the process of determining the load contention rate based on the corresponding load rising trend of each type of model in different time domain segments includes: Determine the load change trend of each type of model when it is operated in each time domain segment; Determine a time domain segment that meets a predetermined trend change condition as a characteristic time domain segment; The ratio of the characteristic time domain segment to the total number of time domain segments is determined as the load contention ratio; The predetermined trend change condition is that each type of model has a load increase trend when being operated within the time domain segment.

4. The method for joint simulation of multiple types of models of embedded computer digital twins according to claim 1, characterized in that: In step S3, the process of determining the resource synchronization competition characterization parameters for the synchronous simulation process based on the complexity difference of each type of model and the load competition rate includes: Get the complexity of each type of model; solving for the standard deviation of the complexity; Calculating the ratio of the standard deviation to the standard deviation threshold and assigning a corresponding weight coefficient as the first resource feature; Calculating a ratio of the load contention rate to the load contention rate threshold and assigning a corresponding weight coefficient as a second resource feature; The sum of the first resource characteristic and the second resource characteristic is determined as a resource synchronization contention characterization parameter.

5. The method for joint simulation of multiple types of models of embedded computer digital twins according to claim 1, characterized in that: In step S3, resource synchronization competition categories for the synchronous simulation process are divided into: If the resource synchronization contention characterization parameter is greater than or equal to the resource synchronization contention characterization parameter threshold, the resource synchronization of the synchronous simulation process is determined to be a strong contention category; If the resource synchronization contention characterization parameter is less than the resource synchronization contention characterization parameter threshold, it is determined that the resource synchronization of the synchronous simulation process is a weak contention category.

6. The method for joint simulation of multiple types of models of embedded computer digital twins according to claim 1, characterized in that: In step S4, controlling simulation parameters based on resource synchronization competition categories includes: If the resource synchronization of the synchronous simulation process is of the strong contention category, the time step in the synchronous simulation process is adjusted based on the resource synchronization competition characterization parameter, the update duration when the simulation model is updated in the synchronous simulation process is obtained, and whether the simulation process meets the resource balancing standard is determined based on the difference in the update duration, so as to adjust the number of grids for the simulation model; If the resource synchronization of the synchronous simulation process is of weak contention type, the reference time step is maintained during the synchronous simulation process.

7. The method for joint simulation of multiple types of models of embedded computer digital twins according to claim 1, characterized in that: In step S4, controlling simulation parameters based on resource synchronization competition categories includes: The time step is increased, and the increase value of the time step is positively correlated with the resource synchronization competition characterization parameter.

8. The method for co-simulating multiple types of models of embedded computer digital twins according to claim 1, characterized in that: In step S4, the update duration of updating the simulation model during the synchronous simulation process is obtained, and the process of determining whether the simulation process meets the resource balancing standard based on the difference in the update duration includes: Get the update duration when updating the simulation model for a predetermined number of times; Solve the variance of update duration; Comparing the variance with a predetermined variance threshold to determine whether the simulation process meets the resource balancing standard; If the variance is greater than a predetermined variance threshold, it is determined that the simulation process does not meet the resource balancing standard.

9. The method for joint simulation of multiple types of models of embedded computer digital twins according to claim 1, characterized in that: In step S4, adjusting the number of grids for the simulation model includes: The number of grids is reduced, and the amount of reduction in the number of grids is positively correlated with the variance of the update duration.

10. The method for joint simulation of multiple types of models of embedded computer digital twins according to claim 1, characterized in that: In step S1, the configuration information of the simulation object also includes module parameters and reference relationships between models.

Images