A distributed real-time simulation platform

Through the design of the distributed real-time simulation platform, the problems of unreasonable allocation of simulation tasks and complex data interaction are solved, resource utilization and processing speed are improved, interaction complexity is reduced, and efficient simulation task processing and scalability are achieved.

CN113867889BInactive Publication Date: 2024-11-013RD GENERAL DESIGN DEPT CHINA AEROSPACE SCI & IND CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111122435.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-09-24
Publication Date
2024-11-01
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing simulation platform architecture is not reasonable enough in the allocation and configuration of simulation tasks, resulting in wasted resources or inability to meet the needs of simulation tasks with high computing volume, and the simulation data interaction process is complex.

Method used

Design a distributed real-time simulation platform, including simulation master control system, simulation management bus, real-time simulation bus and computing nodes, optimize resource utilization and interaction process by generating simulation task lists, deploying subtasks, control command transmission and data interaction .

Benefits of technology

It improves the resource utilization rate of computing nodes and the processing speed of simulation sub-tasks, reduces the complexity of simulation data interaction, realizes high-speed and stable network communication, and enhances the reusability and scalability of the platform.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113867889B_ABST
    Figure CN113867889B_ABST
Patent Text Reader

Abstract

The invention discloses a distributed real-time simulation platform, which belongs to the field of simulation technology and is used to solve the problems of unreasonable simulation task allocation in existing simulation platforms. The platform includes: a simulation main control system, a simulation management bus, a real-time simulation bus and a computing node; the simulation main control system generates a simulation task list according to the simulation task and the computing node list; the simulation task list includes multiple simulation subtasks and computing nodes for deploying each simulation subtask; the simulation task list is sent to the simulation management bus, and the simulation management bus sends the simulation subtask to the corresponding computing node; the simulation control instruction is also sent to the corresponding computing node through the real-time simulation bus to control the progress of the computing node in executing the simulation processing process; the computing node is used to execute the simulation processing process based on the received simulation subtask and simulation control instruction, and interact with the simulation main control system and other computing nodes through the real-time simulation bus to exchange the data generated in the simulation processing process.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of simulation technology, and in particular to a distributed real-time simulation platform. Background Art

[0002] In the process of simulating simulation objects using a simulation platform, there are many interactive objects involved, the interactive data is diverse, and the interactive process is complex. At the same time, the computing resources required for different simulation tasks are not the same. If too many computing resources are pre-set in the simulation platform, it is easy to cause a waste of resources. If too few computing resources are pre-set, it will not be able to meet the simulation requirements of simulation tasks with large amounts of computation.

[0003] In summary, how to optimize the architecture of the simulation platform based on the above-mentioned problems existing in the existing simulation platform architecture, realize the reasonable allocation of simulation tasks, optimize the simulation configuration and the data interaction process during simulation, is an urgent problem to be solved. Summary of the invention

[0004] In view of the above analysis, an embodiment of the present invention aims to provide a distributed real-time simulation platform to solve the problems existing in the existing simulation platform architecture, such as unreasonable simulation task allocation, high complexity of simulation configuration and simulation data interaction process.

[0005] The present invention discloses a distributed real-time simulation platform, which comprises: a simulation main control system, a simulation management bus, a real-time simulation bus and a plurality of computing nodes; wherein:

[0006] The simulation main control system,

[0007] Used to generate a simulation task list according to the simulation task and the computing node list; the simulation task list includes multiple simulation subtasks and the computing node for deploying each simulation subtask;

[0008] It is also used to send the simulation task list to the simulation management bus, and the simulation management bus sends each simulation subtask to the computing node where the simulation subtask is deployed;

[0009] It is also used to send simulation control instructions to the computing nodes that deploy simulation subtasks through the real-time simulation bus to control the progress of the simulation processing process performed by the computing nodes;

[0010] The computing node for deploying simulation subtasks is used to execute the simulation processing process based on the received simulation subtasks and the simulation control instructions, and to exchange the data generated during the simulation processing process with the simulation main control system and other computing nodes through the real-time simulation bus.

[0011] On the basis of the above scheme, the present invention also makes the following improvements:

[0012] Furthermore, the platform also includes a simulation monitoring system.

[0013] The simulation monitoring system is connected to the simulation management bus and the real-time simulation bus to monitor the simulation process.

[0014] Furthermore, the platform also includes a clock synchronization system and a clock synchronization bus; wherein,

[0015] The simulation master control system, computing nodes and simulation monitoring system are all connected to the clock synchronization bus;

[0016] The time synchronization signal generated by the clock synchronization system is sent to the simulation main control system, all computing nodes and the simulation monitoring system through the clock synchronization bus to achieve time synchronization among the simulation main control system, all computing nodes and the simulation monitoring system.

[0017] Furthermore, the simulation task includes a plurality of simulation models and simulation configuration parameters, wherein the simulation configuration parameters include simulation initial parameters, simulation step length, and interface communication cycle of each simulation model;

[0018] The computing node list includes node attribute configuration information and node status of each computing node;

[0019] The node attribute configuration information includes:

[0020] Node ID, used to describe the unique identification of the computing node in the system;

[0021] Performance attributes, used to describe the performance attribute information of computing nodes;

[0022] Communication port number, used to describe the port number of the computing node;

[0023] The IP address of the node server, which is used to describe the IP address of the node server in the computing node;

[0024] Node status is divided into idle, occupied and abnormal status.

[0025] Further, the simulation main control system generates a simulation task list by performing the following operations:

[0026] Based on each simulation model and simulation configuration parameters, a simulation subtask matching the simulation model is determined; the simulation subtask includes simulation initial parameters, a dynamic link library of the simulation model, and simulation resource data;

[0027] Predict the computational amount of each simulation subtask, determine the computing node to deploy each simulation subtask based on the computational amount of each simulation subtask and the performance attributes of the computing nodes in the idle state in the computing node list, and update the node state of the computing node in the computing node list where the simulation subtask is deployed to a busy state;

[0028] Summarize all simulation subtasks and deploy the computing nodes of each simulation subtask to form a simulation task list.

[0029] Furthermore, the simulation task list also includes a data interaction list; the data interaction list maintains the ID of the simulation master control system, the task number of each simulation subtask, the node ID of the computing node deploying each simulation subtask, and the simulation data storage module of each simulation subtask; wherein,

[0030] The simulation data storage module is used to store the data generated during the simulation processing of the simulation subtask; the simulation data storage module of each simulation subtask corresponds to the task number of the simulation subtask one by one;

[0031] The simulation master control system and computing nodes connected to the same real-time simulation bus share the same data interaction list.

[0032] Further, the simulation control instructions include initialization instructions, run instructions, pause instructions, stop instructions and restart instructions;

[0033] The simulation master control system controls the progress of the simulation process executed by the computing nodes by performing the following operations:

[0034] After obtaining all simulation model startup success instructions, generate initialization instructions;

[0035] After obtaining the initialization success instructions generated by all simulation models in response to the initialization instructions, generating a running instruction;

[0036] After obtaining the start running instruction generated by some or all simulation models in response to the running instruction, a pause instruction for controlling the corresponding simulation model to pause, a stop instruction for controlling the corresponding simulation model to stop, and / or a restart instruction for controlling the corresponding simulation model to restart is generated according to the simulation progress, so that the corresponding simulation model temporarily runs the current simulation model based on the pause instruction, stops running the current simulation model based on the stop instruction, and / or restarts the current simulation model based on the restart instruction;

[0037] When the computing node where the simulation subtask is deployed is in an abnormal state, the simulation main control system migrates the simulation subtask on the computing node to a computing node in an idle state.

[0038] Further, each computing node performs a simulation process based on the received corresponding simulation subtask and simulation control instruction, including:

[0039] Based on the simulation model in the simulation subtask, load the dynamic link library and simulation resource data associated with the current simulation subtask, and generate a successful start instruction;

[0040] Initialize the current simulation model based on the initialization instruction generated by the simulation main control system in response to the startup success instruction and the simulation initial parameters associated with the current simulation subtask, and generate an initialization success instruction;

[0041] Run the corresponding simulation model based on the running instructions generated by the simulation main control system in response to the initialization success instruction, and update and store the data generated during the simulation running process to the simulation data storage module of the current simulation subtask, so that other computing nodes and the simulation main control system can access and obtain the data generated during the simulation running process stored in each simulation data storage module through the data interaction list;

[0042] If a pause instruction is received, the current simulation model is temporarily run based on the pause instruction;

[0043] If a stop instruction is received, the current simulation model is stopped based on the stop instruction;

[0044] If a restart instruction is received, the current simulation model is restarted based on the restart instruction.

[0045] Furthermore, the computing node also regularly feeds back the subtask execution status to the simulation main control system, so that the simulation main control system dynamically updates the simulation progress of the simulation subtask in the simulation task list according to the subtask execution status;

[0046] When the computing node completes the deployed simulation subtask, it feeds back the subtask execution completion status to the simulation main control system so that the simulation main control system dynamically updates the simulation progress of the simulation subtask in the simulation task list to completed according to the simulation subtask execution completion status, and controls the simulation management bus to update the node status of the current computing node to idle status.

[0047] Furthermore, the simulation management bus controls the joining and exiting of computing nodes by managing the node attribute information of computing nodes:

[0048] When a computing node dynamically accesses the simulation management bus:

[0049] The computing node sends node attribute configuration information to the simulation management bus, and periodically sends heartbeat information to the simulation management bus;

[0050] The simulation management bus dynamically maintains the computing node list based on the node attribute configuration information and periodic heartbeat information;

[0051] When the computing node actively or passively disconnects from the simulation management bus, the simulation management bus cannot receive the heartbeat information sent by the computing node; if the simulation management bus cannot receive the heartbeat information sent by the computing node within a first preset time, the node status of the computing node is updated to an abnormal state; if the heartbeat information sent by the computing node is still not received within a second preset time that is longer than the first preset time, the node attribute configuration information and node status of the computing node are deleted from the computing list.

[0052] Compared with the prior art, the present invention can achieve at least one of the following beneficial effects:

[0053] The distributed real-time simulation platform provided by the present invention has the following advantages:

[0054] First, the distributed real-time simulation platform provided by the present invention effectively improves the resource utilization of computing nodes and the processing speed of simulation subtasks by decomposing the simulation task into multiple simulation subtasks and deploying the multiple simulation subtasks on corresponding computing nodes respectively; optimizes the simulation configuration and simulation task allocation process, and reduces the complexity of the simulation data interaction process.

[0055] Second, the present invention also uses a simulation management bus to transmit simulation task lists with lower real-time requirements and manage computing node lists, and uses a real-time simulation bus to transmit control instructions with higher real-time requirements and data generated during the simulation process, providing high-speed and stable network communication from a hardware perspective, eliminating the impact of different transmission delays on information interaction.

[0056] Third, since the real-time simulation platform in the present invention is implemented in a distributed manner, the functions of the various systems, buses, and computing nodes involved in the platform are relatively independent, following the principle of loose coupling, and can achieve distributed operation and centralized management of the simulation process. In addition, the platform involves data interaction between multiple systems, multiple buses, and computing nodes, and has strong reusability, interoperability, and composability, which is convenient for users to choose according to actual simulation requirements, effectively expanding the use scenarios of distributed real-time simulation platforms.

[0057] In the present invention, the above-mentioned technical solutions can also be combined with each other to achieve more preferred combination solutions. Other features and advantages of the present invention will be described in the subsequent description, and some advantages can become obvious from the description, or can be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained through the contents particularly pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The drawings are only for the purpose of illustrating particular embodiments and are not to be considered limiting of the present invention. Like reference symbols denote like components throughout the drawings.

[0059] Figure 1 This is a schematic diagram of the structure of a distributed real-time simulation platform in Example 1 of the present invention;

[0060] Figure 2 This is a schematic diagram of the structure of a distributed real-time simulation platform suitable for simulation models and process models in Example 2 of the present invention. DETAILED DESCRIPTION

[0061] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0062] Example 1

[0063] Specific embodiment 1 of the present invention discloses a distributed real-time simulation platform, the structural diagram of which is shown in FIG. Figure 1 The platform comprises a simulation main control system (1), a simulation management bus (2), a real-time simulation bus (3) and a plurality of computing nodes (4); wherein,

[0064] A simulation main control system (1) is used to generate a simulation task list according to a simulation task and a computing node list; the simulation task list includes a plurality of simulation subtasks and a computing node (4) for deploying each simulation subtask; the simulation control system (1) is used to send the simulation task list to a simulation management bus (2), and the simulation management bus (2) sends each simulation subtask to the computing node for deploying the simulation subtask; the simulation control system (1) is used to send a simulation control instruction to the computing node (4) for deploying the simulation subtask through a real-time simulation bus (3) to control the progress of the simulation processing process executed by the computing node.

[0065] The computing node (4) for deploying simulation subtasks is used to execute the simulation processing process based on the received simulation subtasks and simulation control instructions, and to exchange data generated during the simulation processing process with the simulation main control system (1) and other computing nodes (4) through the real-time simulation bus (3).

[0066] Compared with the prior art, in this embodiment, by decomposing the simulation task into multiple simulation subtasks and deploying the multiple simulation subtasks on corresponding computing nodes, the resource utilization rate of the computing nodes and the processing speed of the simulation subtasks are effectively improved; this embodiment also uses a simulation management bus (2) to transmit a simulation task list with low real-time requirements, and uses a real-time simulation bus (3) to transmit control instructions with high real-time requirements and data generated during the simulation processing, thereby providing high-speed and stable network communication from the hardware perspective and eliminating the impact of different transmission delays on information interaction; in actual application, considering that the simulation management bus (2) has low real-time requirements, an Ethernet network can be used for communication; while the real-time simulation bus (3) has high real-time requirements and needs to complete data interaction in a timely manner, a real-time optical fiber reflection memory network can be used.

[0067] Preferably, the distributed real-time simulation platform in this embodiment may also include a simulation monitoring system (5), which is connected to the simulation management bus (2) and the real-time simulation bus (3) to monitor the simulation process; in the actual working process, the simulation monitoring system (5) can be opened or closed according to user needs, thereby effectively enhancing the flexibility of the simulation platform.

[0068] Preferably, the distributed real-time simulation platform may also include a clock synchronization system (6) and a clock synchronization bus (7); wherein the simulation main control system (1), the computing nodes (4) and the simulation monitoring system (5) are all connected to the clock synchronization bus (7), and the time synchronization signal generated by the clock synchronization system (6) is sent to the simulation main control system (1), all computing nodes (4) and the simulation monitoring system (5) through the clock synchronization bus (7) to achieve time synchronization between the simulation main control system (1), all computing nodes (4) and the simulation monitoring system (5), thereby providing an effective time management mechanism, ensuring the time consistency of each system and computing node, and meeting the platform's real-time requirements.

[0069] Preferably, the simulation task includes multiple simulation models and simulation configuration parameters; it should be noted that the simulation models described in this embodiment are all simulation models obtained based on mathematical modeling tools; the simulation configuration parameters include information such as the initial simulation parameters, the simulation step size, and the interface communication cycle of each simulation model. Simulation subtasks correspond one-to-one to simulation models. The computing node list includes the node attribute configuration information and node status of each computing node; wherein the node attribute configuration information is the inherent information of the computing node and does not change with the simulation process; the node status is the variable information of the computing node, which will change with the simulation process and the node's own status, such as CPU occupancy, core occupancy, memory occupancy, and hard disk occupancy, etc.; preferably, the node attribute configuration information includes:

[0070] Node ID, used to describe the unique identification of the computing node in the system;

[0071] Performance attributes, which are used to describe the performance attribute information of computing nodes, such as memory size, CPU main frequency, number of CPU cores, hard disk size, and real-time operating system type;

[0072] Communication port number, used to describe the port number of the computing node;

[0073] The IP address of the node is used to describe the IP address of the node in the computing node. The simulation processing process is completed on the node server.

[0074] Preferably, the node status is divided into idle, occupied and abnormal status; wherein, the idle status indicates that the computing node itself is in a normal status and is not assigned a simulation subtask; the occupied status indicates that the computing node itself is in a normal status and is assigned a simulation subtask; the abnormal status indicates that the computing node itself is in an abnormal status.

[0075] Based on the above simulation tasks and computing node list, the simulation main control system (1) generates a simulation task list by performing the following operations:

[0076] 1) Based on each simulation model and simulation configuration parameters, determine a simulation subtask matching the simulation model; the simulation subtask includes information such as simulation initial parameters, a dynamic link library of the simulation model, and simulation resource data;

[0077] 2) predicting the computational amount of each simulation subtask, determining the computing node to deploy each simulation subtask based on the computational amount of each simulation subtask and the performance attributes of the computing nodes in the idle state in the computing node list, and updating the node state of the computing node in the computing node list where the simulation subtask is deployed to the busy state;

[0078] In this process, according to the actual situation, a simulation subtask can be deployed on a computing node. If the performance attributes of the computing node are good, several simulation subtasks can also be deployed on the same computing node. At this time, in order to ensure that the simulation subtasks do not affect each other, each simulation subtask is generally deployed separately on a CPU core of the computing node. The corresponding deployment method can be determined based on the computing amount of each simulation subtask and the performance attributes of the computing node.

[0079] 3) Summarize all simulation subtasks and deploy the computing nodes of each simulation subtask to form a simulation task list.

[0080] Preferably, in order to improve data interaction efficiency and positioning accuracy, the simulation task list may also include a data interaction list, in which the ID of the simulation main control system (1), the task number of each simulation subtask, the node ID of the computing node (4) deploying each simulation subtask, and the simulation data storage module of each simulation subtask are maintained; wherein the simulation data storage module is used to store data generated during the simulation processing of the simulation subtask; the simulation data storage module of each simulation subtask corresponds one-to-one with the task number of the simulation subtask; the simulation main control system and the computing node connected to the same real-time simulation bus share the same data interaction list; the data interaction list includes the simulation progress of the simulation subtask, and in addition, the simulation task list may also include the simulation progress of the simulation subtask, so that the user can understand the simulation progress at any time. Exemplarily, the simulation main control system (1) generates the data interaction list in the simulation task list by performing the following operations:

[0081] 4) Assign a unique task number to each simulation subtask, and summarize the simulation task number, the node ID of the computing node where the simulation subtask is deployed, the ID of the simulation main control system (1), the simulation data storage module and the simulation progress of each simulation subtask to form a data interaction list.

[0082] In addition, it should be noted that, considering that the simulation main control system (1) may receive multiple simulation tasks at the same time, in order to facilitate the priority processing of urgent tasks, the simulation task may also include a task priority, which is used to describe the urgency of the current simulation task. The higher the task priority, the higher the urgency of the simulation task. If there are multiple simulation tasks at the same time, the simulation main control system (1) determines the execution order of the multiple simulation tasks based on the task priority of each simulation task in the multiple simulation tasks.

[0083] Preferably, the simulation control instructions are generated by the simulation main control system, including initialization instructions, operation instructions, pause instructions, stop instructions and restart instructions; illustratively, the simulation main control system (1) controls the progress of the simulation processing process executed by the computing node by performing the following operations:

[0084] 1) After obtaining all simulation model startup success instructions, generate initialization instructions;

[0085] 2) after obtaining the initialization success instructions generated by all simulation models in response to the initialization instructions, generating a running instruction;

[0086] 3) after obtaining the start running instruction generated by some or all simulation models in response to the running instruction, generating a pause instruction for controlling the corresponding simulation model to pause, a stop instruction for controlling the corresponding simulation model to stop, and / or a restart instruction for controlling the corresponding simulation model to restart according to the simulation progress, so that the corresponding simulation model temporarily runs the current simulation model based on the pause instruction, stops running the current simulation model based on the stop instruction, and / or restarts the current simulation model based on the restart instruction;

[0087] 4) When the computing node (4) where the simulation subtask is deployed is in an abnormal state, the simulation subtask on the computing node is migrated to a computing node in an idle state.

[0088] Preferably, each computing node (4) performs a simulation processing process based on the received corresponding simulation subtask and simulation control instruction, including:

[0089] 1) Based on the simulation model corresponding to the simulation subtask, load the dynamic link library and simulation resource data associated with the current simulation subtask, and generate a successful start instruction;

[0090] 2) initializing the current simulation model based on the initialization instruction generated by the simulation main control system (1) in response to the startup success instruction and the simulation initial parameters associated with the current simulation subtask, and generating an initialization success instruction;

[0091] 3) running the corresponding simulation model based on the running instruction generated by the simulation main control system (1) in response to the initialization success instruction, and updating and storing the data generated during the simulation running process in the simulation data storage module of the current simulation subtask, so that other computing nodes (4) and the simulation main control system (1) can access and obtain the data generated during the simulation running process stored in each simulation data storage module through the data interaction list;

[0092] 4) If a pause instruction is received, temporarily running the current simulation model based on the pause instruction;

[0093] If a stop instruction is received, the current simulation model is stopped based on the stop instruction;

[0094] If a restart instruction is received, the current simulation model is restarted based on the restart instruction.

[0095] The instructions and data involved in the above-mentioned simulation processing are updated and stored in the simulation data storage module corresponding to each simulation subtask. The computing node (4) that deploys the simulation subtask shares the simulation data storage module with the simulation main control system (1) so as to obtain the latest data generated in the simulation processing process related to itself.

[0096] In addition, the computing node also regularly feeds back the subtask execution status to the simulation main control system (1), so that the simulation main control system (1) dynamically updates the simulation progress of the simulation subtask in the simulation task list according to the subtask execution status. When the computing node completes the deployed simulation subtask, the subtask execution completion status is fed back to the simulation main control system (1), so that the simulation main control system (1) dynamically updates the simulation progress of the simulation subtask in the simulation task list to completed according to the simulation subtask execution completion status, and controls the simulation management bus (2) to update the node status of the current computing node (4) to an idle state.

[0097] It should be noted that the computing resources of the real-time simulation platform are composed of computing nodes (4), and computing nodes (4) can dynamically join and exit the simulation platform. In this embodiment, the simulation management bus (2) manages the node attribute information of the computing nodes (4) to control the joining and exit of the computing nodes (4). Specifically,

[0098] When the computing node (4) dynamically accesses the simulation management bus (2):

[0099] The computing node (4) sends node attribute configuration information to the simulation management bus (2), and periodically sends heartbeat information to the simulation management bus (2);

[0100] The simulation management bus (2) dynamically maintains the computing node list based on the node attribute configuration information and periodic heartbeat information.

[0101] When the computing node actively or passively disconnects from the simulation management bus (21), the simulation management bus (21) cannot receive the heartbeat information sent by the computing node; if the simulation management bus (21) cannot receive the heartbeat information sent by the computing node within a first preset time, the node state of the computing node is updated to an abnormal state; if the heartbeat information sent by the computing node is still not received within a second preset time longer than the first preset time, the node attribute configuration information and the node state of the computing node are deleted from the computing list.

[0102] Preferably, according to the simulation calculation amount of the real-time simulation platform, a variety of computing nodes (4) can be designed to meet the diverse needs of the simulation process. For example, computing nodes based on X86 or embedded architecture, wherein computing nodes based on X86 architecture have the advantages of high performance, easy performance expansion and strong compatibility, but have the disadvantage of high power consumption; computing nodes based on embedded architecture have the advantage of low power consumption. In addition, computing nodes with a variety of different performance attributes can be set, so that the appropriate computing nodes can be selected according to different simulation models, so as to achieve the effect of taking into account both simulation processing speed and performance.

[0103] Example 2

[0104] Considering that in the actual hardware-in-the-loop simulation process, in addition to the simulation model for the functional algorithm of the simulation object obtained based on the mathematical modeling tool, it is also necessary to simulate the communication format and process of the physical interface of the simulation object. The model that simulates the communication format and process of the physical interface of the simulation object is called a process model. In the process of simulating the process model, it is necessary to connect the physical object or physical effect equipment, and the physical object or physical effect equipment cooperates to complete the simulation task. Therefore, in order to adapt to the simulation of this type of process model and enhance the adaptability of the distributed real-time simulation platform, Example 2 of the present invention is improved on the basis of Example 1, forming a distributed real-time simulation platform in this Example 2 that can simultaneously meet the simulation process of the simulation model and the process model, that is, a distributed real-time simulation platform suitable for the simulation model and the process model. The structural diagram is shown as follows Figure 2 The improvement method is:

[0105] An I / O interface adapter (8) is added on the basis of the scheme of Example 1. The I / O interface adapter (8) is used to connect to a physical object or physical effect device according to the simulation task, and cooperate with the computing node (4) to complete the I / O simulation data interaction between the physical object or physical effect device during the simulation process. The I / O interface adapter is also connected to the clock synchronization bus (7); the time synchronization signal generated by the clock synchronization system (6) is also sent to the I / O interface adapter through the clock synchronization bus (7) to achieve time synchronization between the simulation main control system (1), all computing nodes (4), the simulation monitoring system (5) and the I / O interface adapter (8).

[0106] Preferably, the distributed real-time simulation platform also includes an I / O interface bus (9), and the I / O interface adapter (8) is also connected to the simulation management bus (2) and the I / O interface bus (9); the access or exit of the I / O interface adapter (8) and the physical or physical effect device is managed through the simulation management bus (2), and the I / O simulation data interaction between the computing node (4) and the physical or physical effect device connected to the I / O interface adapter (8) during the simulation process is realized through the I / O interface bus (9).

[0107] Before executing the simulation task related to the process model, it is necessary to connect the I / O interface adapter (8) to the simulation management bus (2), and then connect the required physical or physical effect device to the corresponding interface of the I / O interface adapter (8). In this embodiment, the simulation management bus (2) manages the access or exit of the I / O interface adapter and the physical or physical effect device by dynamically maintaining the interface adapter list; so as to ensure the reliable connection between the I / O interface adapter (8), the simulation management bus (2) and the physical or physical effect device.

[0108] Preferably, the interface adapter list is composed of several pieces of interface adapter configuration information, each of which includes:

[0109] The I / O interface adapter ID is used to describe the unique address of the I / O interface adapter; one piece of interface adapter configuration information corresponds to a unique I / O interface adapter ID, and the I / O interface adapter ID is uniquely allocated by the simulation management bus;

[0110] The interface allocation list includes an interface number, an interface type, and an interface performance parameter of each interface in the I / O interface adapter; the interface number is used to describe the unique address of the interface in the I / O interface adapter (8); the interface type is used to describe the type of data transmitted by the interface; illustratively, the interface type may be a switch quantity, an analog quantity, etc.; the interface performance parameter is used to describe the performance parameter information of the interface, such as a baud rate, etc.;

[0111] The interface status list is used to describe the interface status of each interface in the I / O interface adapter. When a physical object or physical effect device is connected to the interface, the interface status of the interface is connected. Otherwise, the interface status of the interface is not connected.

[0112] The I / O interface adapter status is used to describe whether the status of the I / O interface adapter is normal or abnormal.

[0113] Specifically, the simulation management bus (2) manages the access or exit of the I / O interface adapter (8) and the physical or physical effect device by dynamically maintaining the interface adapter list, including:

[0114] When the I / O interface adapter (8) dynamically accesses the simulation management bus (2), the I / O interface adapter (8) sends an interface allocation list to the simulation management bus (2), and after receiving the interface allocation list, the simulation management bus (2) allocates an I / O interface adapter ID to the I / O interface adapter (8) and updates the state of the I / O interface adapter to normal;

[0115] When a physical object or physical effect device is connected to or exits the interface of the I / O interface adapter (8), the I / O interface adapter (8) updates the interface status list and sends the updated interface status list to the simulation management bus (2), and the simulation management bus (2) updates the interface status list;

[0116] The I / O interface adapter (8) also periodically sends heartbeat information to the simulation management bus (2); when the I / O interface adapter (8) actively or passively disconnects from the simulation management bus (21), the simulation management bus (21) will be unable to receive the heartbeat information sent by the I / O interface adapter (8); if the simulation management bus (21) cannot receive the heartbeat information sent by the I / O interface adapter (8) within a first preset time, the ID state of the I / O interface adapter (8) is updated to an abnormal state, and all interfaces of the I / O interface adapter (8) are disabled; if the heartbeat information sent by the I / O interface adapter (8) is still not received within a second preset time longer than the first preset time, the interface adapter configuration information corresponding to the current I / O interface adapter ID is deleted from the interface adapter list.

[0117] After the I / O interface adapter (8), the simulation management bus (2) and the physical object or physical effect device are reliably connected, the simulation main control system (1) can generate a task list, specifically:

[0118] A simulation main control system (1) is used to generate a simulation task list according to a simulation task, a computing node list and an interface adapter list; the simulation task includes a plurality of process models, a plurality of simulation models or a combination of a plurality of process models and a plurality of simulation models; the simulation task list includes: a plurality of simulation subtasks and a computing node (4) for deploying each simulation subtask; each simulation subtask is associated with a simulation model or a process model; the simulation subtask associated with the process model also includes the interface number of the interface of the I / O interface adapter (8) associated with the process model; the simulation task list is also used to send the simulation task list to a simulation management bus (2), and the simulation management bus (2) sends each simulation subtask to the computing node (4) for deploying the simulation subtask; the simulation control instruction is also used to send the simulation control instruction to the computing node (4) for deploying the simulation subtask through a real-time simulation bus (3) to control the progress of the simulation processing process executed by the computing node;

[0119] The computing node (4) deploying the simulation subtask is used to execute the simulation processing process based on the simulation subtask and the simulation control instruction, and to interact with the simulation main control system (1) and other computing nodes (4) through the real-time simulation bus (3) to exchange the data generated during the simulation processing; when the simulation subtask deployed on the computing node (4) is associated with a process model, the simulation I / O data is also interacted with the physical object or physical effect device connected to the interface of the I / O interface adapter (8) associated with the process model through the I / O interface bus (9) and the I / O interface adapter (8).

[0120] Preferably, the simulation task of the second embodiment also includes simulation configuration parameters and interface configuration information of each process model; the simulation configuration parameters include information such as simulation initial parameters, simulation step length, interface communication cycle of each simulation model and each process model; the interface configuration information includes interface type and interface configuration parameters, which are used to determine the interface of the I / O interface adapter (8) associated with the process model. The computing node list is the same as that of the first embodiment.

[0121] Preferably, in this embodiment, the simulation main control system (1) generates a simulation task list by performing the following operations:

[0122] 1) For each simulation model, a simulation subtask matching the simulation model is determined based on the simulation model and the simulation configuration parameters; at this time, the simulation subtask includes information such as the simulation initial parameters, the dynamic link library of the corresponding simulation model, and the simulation resource data;

[0123] For each process model, a simulation subtask matching the process model is determined based on the process model, simulation configuration parameters, interface configuration information, and interface adapter list: specifically,

[0124] If the interface in the interface adapter list satisfies: the interface state is connected, the interface type is the same as the interface type in the interface configuration information, and the interface performance parameter matches the interface configuration parameter, then the interface is used as the interface of the I / O interface adapter (8) associated with the process model; at this time, the simulation subtask also includes information such as the simulation initial parameters, dynamic link library, simulation resource data and interface configuration parameters of the process model;

[0125] 2) This step is the same as step 2) of generating a simulation task list by the simulation main control system (1) in Example 1;

[0126] 3) Summarizing all simulation subtasks and the computing nodes for deploying each simulation subtask. When the simulation subtasks deployed on the computing nodes (4) are associated with process models, the interface numbers of the interfaces of the I / O interface adapters (8) associated with the process models are also summarized to form a simulation task list.

[0127] 4) This step is the same as step 4) of generating a simulation task list by the simulation main control system (1) in Example 1;

[0128] In addition, the simulation task list may also include an interface address interaction list, which maintains the task number of the simulation subtask corresponding to each process model, the node ID of the computing node (4) deploying the simulation subtask corresponding to each process model, the interface number of the interface of the I / O interface adapter (8) associated with the process model, and the corresponding I / O interface adapter ID;

[0129] Exemplarily, the simulation main control system (1) generates the interface address interaction list in the simulation task list by performing the following operations:

[0130] 5) Obtain the interface number of the interface of the I / O interface adapter (8) associated with the process model from the interface adapter list, and the corresponding I / O interface adapter ID (i.e., the I / O interface adapter ID of the I / O interface adapter (8) to which the physical object or physical effect device is connected), and form an interface address interaction list together with the task number of the simulation subtask corresponding to each process model and the node ID of the computing node (4) that deploys the simulation subtask corresponding to each process model. The computing nodes (4) and I / O interface adapters (8) connected to the same I / O interface bus share the same interface address interaction list.

[0131] Preferably, when processing the simulation subtask corresponding to the simulation model, the simulation processing process of the computing node (4) is the same as the computing node (4) in Embodiment 1 performing the simulation processing process based on the received corresponding simulation subtask and simulation control instruction;

[0132] When processing the simulation subtask corresponding to the process model, the computing node (4) performs the simulation processing process based on the received corresponding simulation subtask and simulation control instruction, including:

[0133] 1) Based on the process model in the simulation subtask, load the corresponding dynamic link library and simulation resource data, and generate a successful startup instruction;

[0134] 2) Based on the initialization instruction generated by the simulation main control system (1) in response to the startup success instruction, the initialization instruction includes:

[0135] Initialize the process model based on the initial simulation parameters of the current process model;

[0136] Based on the interface configuration parameters of the current process model, configure the interface of the associated I / O interface adapter (8);

[0137] Then, generate an initialization success instruction;

[0138] 3) running the corresponding process model and the physical object or physical effect device connected to the interface of the I / O interface adapter (8) associated with the current process model based on the running instruction generated by the simulation main control system (1) in response to the initialization success instruction, and updating and storing the data generated during the simulation running process into the corresponding data storage space in the simulation data storage module, so that other computing nodes (4) and the simulation main control system (1) can access and obtain the data generated during the simulation running process stored in each simulation data storage module through the data interaction list;

[0139] At the same time, in the process of executing the simulation task, the computing node (4) also interacts with the physical object or physical effect device connected to the interface of the I / O interface adapter (8) associated with the current process model through the interface address interaction list to generate simulation I / O data during the interactive simulation process, including: obtaining interface control data output by the process model, or feeding back interface input data to the process model.

[0140] 4) If a pause instruction is received, the current process model is temporarily run based on the pause instruction;

[0141] If a stop instruction is received, the current process model is stopped based on the stop instruction;

[0142] If a restart instruction is received, the current process model is restarted based on the restart instruction.

[0143] For other contents not described, please refer to the relevant contents in Example 1.

[0144] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0145] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A distributed real-time simulation platform, It is characterized in that The platform includes: a simulation main control system, a simulation management bus, a real-time simulation bus and several computing nodes; wherein, The simulation main control system, Used to generate a simulation task list according to the simulation task and the computing node list; the simulation task list includes multiple simulation subtasks and the computing node for deploying each simulation subtask; It is also used to send the simulation task list to the simulation management bus, and the simulation management bus sends each simulation subtask to the computing node where the simulation subtask is deployed; It is also used to send simulation control instructions to the computing nodes that deploy simulation subtasks through the real-time simulation bus to control the progress of the simulation processing process performed by the computing nodes; The computing node for deploying simulation subtasks is used to execute the simulation processing process based on the received simulation subtasks and the simulation control instructions, and to exchange the data generated during the simulation processing process with the simulation main control system and other computing nodes through the real-time simulation bus.

2. The distributed real-time simulation platform according to claim 1, It is characterized in that The platform also includes a simulation monitoring system, The simulation monitoring system is connected to the simulation management bus and the real-time simulation bus to monitor the simulation process.

3. The distributed real-time simulation platform according to claim 2, It is characterized in that The platform also includes a clock synchronization system and a clock synchronization bus; wherein, The simulation master control system, computing nodes and simulation monitoring system are all connected to the clock synchronization bus; The time synchronization signal generated by the clock synchronization system is sent to the simulation main control system, all computing nodes and the simulation monitoring system through the clock synchronization bus to achieve time synchronization among the simulation main control system, all computing nodes and the simulation monitoring system.

4. A distributed real-time simulation platform according to any one of claims 1 to 3, It is characterized in that The simulation task includes multiple simulation models and simulation configuration parameters, and the simulation configuration parameters include simulation initial parameters, simulation step length and interface communication cycle of each simulation model; The computing node list includes node attribute configuration information and node status of each computing node; The node attribute configuration information includes: Node ID, used to describe the unique identification of the computing node in the system; Performance attributes, used to describe the performance attribute information of computing nodes; Communication port number, used to describe the port number of the computing node; The IP address of the node server, which is used to describe the IP address of the node server in the computing node; Node status is divided into idle, occupied and abnormal status.

5. The distributed real-time simulation platform according to claim 4, It is characterized in that The simulation master control system generates a simulation task list by performing the following operations: Based on each simulation model and simulation configuration parameters, a simulation subtask matching the simulation model is determined; the simulation subtask includes simulation initial parameters, a dynamic link library of the simulation model, and simulation resource data; Predict the computational amount of each simulation subtask, determine the computing node to deploy each simulation subtask based on the computational amount of each simulation subtask and the performance attributes of the computing nodes in the idle state in the computing node list, and update the node state of the computing node in the computing node list where the simulation subtask is deployed to a busy state; Summarize all simulation subtasks and deploy the computing nodes of each simulation subtask to form a simulation task list.

6. The distributed real-time simulation platform according to claim 5, It is characterized in that The simulation task list also includes a data interaction list; the data interaction list maintains the ID of the simulation master control system, the task number of each simulation subtask, the node ID of the computing node deploying each simulation subtask, and the simulation data storage module of each simulation subtask; wherein, The simulation data storage module is used to store the data generated during the simulation processing of the simulation subtask; the simulation data storage module of each simulation subtask corresponds to the task number of the simulation subtask one by one; The simulation master control system and computing nodes connected to the same real-time simulation bus share the same data interaction list.

7. The distributed real-time simulation platform according to claim 5 or 6, It is characterized in that The simulation control instructions include initialization instructions, operation instructions, pause instructions, stop instructions and restart instructions; The simulation master control system controls the progress of the simulation process executed by the computing nodes by performing the following operations: After obtaining all simulation model startup success instructions, generate initialization instructions; After obtaining the initialization success instructions generated by all simulation models in response to the initialization instructions, generating a running instruction; After obtaining the start running instruction generated by some or all simulation models in response to the running instruction, a pause instruction for controlling the corresponding simulation model to pause, a stop instruction for controlling the corresponding simulation model to stop, and / or a restart instruction for controlling the corresponding simulation model to restart is generated according to the simulation progress, so that the corresponding simulation model temporarily runs the current simulation model based on the pause instruction, stops running the current simulation model based on the stop instruction, and / or restarts the current simulation model based on the restart instruction; When the computing node where the simulation subtask is deployed is in an abnormal state, the simulation main control system migrates the simulation subtask on the computing node to a computing node in an idle state.

8. The distributed real-time simulation platform according to claim 7, It is characterized in that Each computing node performs a simulation process based on the received corresponding simulation subtask and simulation control instruction, including: Based on the simulation model in the simulation subtask, load the dynamic link library and simulation resource data associated with the current simulation subtask, and generate a successful start instruction; Initialize the current simulation model based on the initialization instruction generated by the simulation main control system in response to the startup success instruction and the simulation initial parameters associated with the current simulation subtask, and generate an initialization success instruction; Run the corresponding simulation model based on the running instructions generated by the simulation main control system in response to the initialization success instruction, and update and store the data generated during the simulation running process to the simulation data storage module of the current simulation subtask, so that other computing nodes and the simulation main control system can access and obtain the data generated during the simulation running process stored in each simulation data storage module through the data interaction list; If a pause instruction is received, the current simulation model is temporarily run based on the pause instruction; If a stop instruction is received, the current simulation model is stopped based on the stop instruction; If a restart instruction is received, the current simulation model is restarted based on the restart instruction.

9. The distributed real-time simulation platform according to claim 8, It is characterized in that The computing node also regularly feeds back the subtask execution status to the simulation main control system, so that the simulation main control system dynamically updates the simulation progress of the simulation subtask in the simulation task list according to the subtask execution status; When the computing node completes the deployed simulation subtask, it feeds back the subtask execution completion status to the simulation main control system so that the simulation main control system dynamically updates the simulation progress of the simulation subtask in the simulation task list to completed according to the simulation subtask execution completion status, and controls the simulation management bus to update the node status of the current computing node to idle status.

10. The distributed real-time simulation platform according to claim 4, It is characterized in that The simulation management bus controls the joining and exiting of computing nodes by managing the node attribute information of computing nodes: When a computing node dynamically accesses the simulation management bus: The computing node sends node attribute configuration information to the simulation management bus, and periodically sends heartbeat information to the simulation management bus; The simulation management bus dynamically maintains the computing node list based on the node attribute configuration information and periodic heartbeat information; When a computing node actively or passively disconnects from the simulation management bus, the simulation management bus cannot receive the heartbeat information sent by the computing node; If the simulation management bus fails to receive the heartbeat information sent by the computing node within the first preset time, the node state of the computing node is updated to an abnormal state; If the heartbeat information sent by the computing node is still not received within a second preset time that is longer than the first preset time, the node attribute configuration information and the node status of the computing node are deleted from the computing list.