Simulation method and device of aero-engine, computer equipment, medium and product

Abstract

The invention relates to a simulation method and device of an aero-engine, computer equipment, a medium and a product. The method comprises the steps of determining initial simulation parameters according to simulation requirements of the aero-engine; the initial simulation parameters comprise sub-models of multiple dimensions, a complete machine performance model of the aero-engine in a preset dimension, an initial coupling relation, an initial field file and initial data; calling the initial simulation parameters to execute a current matching task corresponding to the current simulation step length of the aero-engine, and obtaining a current matching result of the current matching task in a preset dimension; obtaining an initial field file of a new dimension corresponding to the current matching result, and calling the initial field file of the new dimension to execute a new matching task corresponding to the next simulation step size of the current simulation step size, so as to obtain a new matching result of the new matching task in the new dimension; and determining a target simulation result of the aero-engine according to the current matching result and the new matching result. Therefore, the self-adaptive joint simulation efficiency of the aero-engine can be improved.

Description

Technical Field

[0001] The present application relates to the field of aero-engine technology, and in particular to a simulation method, device, computer equipment, medium and product for an aero-engine. Background Art

[0002] With the development of aero-engines, the design and simulation of aero-engine components can be carried out in parallel by various teams, and then the design results of multiple teams can be integrated to develop the best aero-engine. In order to achieve the best balance between accuracy and solution efficiency in different simulation tasks, sub-models of different dimensions and different accuracies in the simulation task can be called at different times, which leads to changes in the initial field files, initial data and coupling relationships between various aero-engine components with different sub-models.

[0003] Based on this, how to adaptively adjust the initial field files, initial data and coupling relationships between various components of aero-engines during the joint simulation of aero-engines is crucial for the research and development simulation field of aero-engines. Summary of the invention

[0004] Based on this, it is necessary to provide an aircraft engine simulation method, device, computer equipment, medium and product that can adaptively adjust the coupling relationship between the various components of the aircraft engine during the joint simulation of the aircraft engine in order to address the above technical problems.

[0005] In a first aspect, the present application provides a simulation method for an aircraft engine, comprising:

[0006] Determine initial simulation parameters according to the simulation requirements of the aircraft engine; the initial simulation parameters include sub-models of multiple dimensions, the whole machine performance model of the aircraft engine in preset dimensions, initial coupling relationship, initial field file and initial data;

[0007] Calling the initial simulation parameters to execute the current matching task corresponding to the current simulation step of the aircraft engine, and obtaining the current matching result of the current matching task in the preset dimension;

[0008] Obtaining an initial field file of a new dimension corresponding to the current matching result, and calling the initial field file of the new dimension to execute a new matching task corresponding to the next simulation step of the current simulation step, to obtain a new matching result of the new matching task in the new dimension;

[0009] A target simulation result of the aircraft engine is determined according to the current matching result and the new matching result.

[0010] In one embodiment, determining the initial simulation parameters according to the simulation requirements of the aircraft engine includes:

[0011] Determining whether the overall performance model of the aircraft engine includes candidate simulation parameters that meet the simulation requirements;

[0012] If the overall performance model includes the candidate simulation parameters, determining the initial simulation parameters from the candidate simulation parameters;

[0013] If the overall performance model does not include the candidate simulation parameters, the target computing resources are used to determine the initial simulation parameters.

[0014] In one embodiment, calling the initial simulation parameters to execute the current matching task corresponding to the current simulation step of the aircraft engine to obtain the current matching result of the current matching task in the preset dimension includes:

[0015] A solver is used to execute a current matching task corresponding to a current simulation step of the aircraft engine according to the initial simulation parameters to obtain a current matching result of the current matching task in the preset dimension; the solver is independently set up from the overall performance model.

[0016] In one embodiment, the obtaining of the initial field file of the new dimension corresponding to the current matching result includes:

[0017] The current matching result is input into a preset initial value prediction network for prediction, and an initial field file of the next simulation step of the current simulation step in a new dimension is obtained.

[0018] In one embodiment, the method further comprises:

[0019] When the simulation requirement or the current matching result or the new matching result satisfies a preset simulation condition, adjusting the initial simulation parameter to obtain an adjusted initial simulation parameter; the preset simulation condition includes monitoring a discrete signal corresponding to the simulation requirement, and / or an error of the current matching result is greater than a preset error threshold;

[0020] The adjusted initial simulation parameters are used as new initial simulation parameters, and the initial simulation parameters are returned to execute the current matching task corresponding to the current simulation step of the aircraft engine, so as to obtain the current matching result of the current matching task in the preset dimension.

[0021] In one embodiment, the training method of the initial value prediction network includes:

[0022] Obtain a historical data set; the historical data set includes historical matching results and labels corresponding to historical initial field files;

[0023] Training an initial value prediction network according to the historical data set to obtain the initial value prediction network;

[0024] The initial value prediction network is updated according to the simulation requirements of the next simulation step, the initial simulation parameters of the next simulation step and the new matching result corresponding to the next simulation step.

[0025] In a second aspect, the present application also provides a simulation device for an aircraft engine, comprising:

[0026] A determination module is used to determine initial simulation parameters according to the simulation requirements of the aircraft engine; the initial simulation parameters include sub-models of multiple dimensions, the whole machine performance model of the aircraft engine in the preset dimensions, initial coupling relationship, initial field file and initial data;

[0027] A first execution module is used to call the initial simulation parameters to execute the current matching task corresponding to the current simulation step of the aircraft engine, and obtain the current matching result of the current matching task in the preset dimension;

[0028] The second execution module obtains the initial field file of the new dimension corresponding to the current matching result, and calls the initial field file of the new dimension to execute the new matching task corresponding to the next simulation step of the current simulation step, to obtain the new matching result of the new matching task in the new dimension;

[0029] The simulation module is used to determine the target simulation result of the aircraft engine according to the current matching result and the new matching result.

[0030] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method in any one of the embodiments of the first aspect are implemented.

[0031] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method in any one of the embodiments of the first aspect are implemented.

[0032] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the method in any one of the embodiments of the first aspect are implemented.

[0033] The above-mentioned aircraft engine simulation method, device, computer equipment, medium and product determine the initial simulation parameters according to the simulation requirements of the aircraft engine; the initial simulation parameters include sub-models of multiple dimensions, the whole machine performance model of the aircraft engine in preset dimensions, initial coupling relationship, initial field file and initial data; call the initial simulation parameters to execute the current matching task corresponding to the current simulation step of the aircraft engine, and obtain the current matching result of the current matching task in the preset dimension; obtain the initial field file of the new dimension corresponding to the current matching result, and call the initial field file of the new dimension to execute the new matching task corresponding to the next simulation step of the current simulation step, and obtain the new matching result of the new matching task in the new dimension; determine the target simulation result of the aircraft engine according to the current matching result and the new matching result. Since the initial simulation parameters include the initial coupling relationship, the initial field file and the initial data, and the embodiment of the present application can call the initial simulation parameters to determine the current matching results of the preset dimension, and use the current matching results of the preset dimension to determine the initial field file of the new dimension, the embodiment of the present application can adaptively determine the initial simulation parameters of another dimension according to the matching results of one dimension during the joint simulation of the aircraft engine, so as to quickly determine more accurate initial simulation parameters without having to search for the initial simulation parameters multiple times from a large number of simulation parameters, thereby improving the efficiency of the adaptive multi-disciplinary and multi-fidelity joint simulation of the aircraft engine. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 A schematic diagram of the structure of a simulation system for an aircraft engine in one embodiment;

[0036] Figure 2 is a schematic structural diagram of a simulation system for an aircraft engine in an exemplary embodiment;

[0037] Figure 3 It is a structural schematic diagram of a simulation system of an aircraft engine in a specific embodiment;

[0038] Figure 4 A schematic diagram of a flow chart of a simulation method for an aircraft engine in one embodiment;

[0039] Figure 5 A schematic diagram of a process for determining initial simulation parameters in one embodiment;

[0040] Figure 6 A schematic diagram of a flow chart of a simulation method for an aircraft engine in another embodiment;

[0041] Figure 7 A schematic diagram of a flow chart of a simulation method for an aircraft engine in an optional embodiment;

[0042] Figure 8 A structural block diagram of a simulation device for an aircraft engine in one embodiment;

[0043] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0045] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0046] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0047] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0048] With the development of aircraft engines, the design and simulation of aircraft engine components can be carried out in parallel by various teams, and then the design results of multiple teams can be integrated to develop the best aircraft engine. Since the development of aircraft engines is a complex system engineering, there is a strong coupling relationship between the various aircraft engine components. Therefore, it is difficult to obtain the optimal solution by carrying out the system integration process after completing the component design. That is, the later the integration process is carried out, the smaller the space for optimization. Based on this, it is usually combined with different simulation units in the early stage of design to achieve global coupling simulation of the entire system. For example, the coupling simulation method in the relevant technology can include but is not limited to any of the methods such as weak coupling method, decoupling method, iterative coupling method and full coupling method.

[0049] In order to achieve the optimal balance between accuracy and solution efficiency in different simulation tasks, sub-models of different dimensions and different accuracy in the simulation task can be called at different times, which will cause the initial field files, initial data and coupling relationships between the various components of the aircraft engine to change with the different sub-models called. Generally, first, the related technology needs to search multiple times from a large number of simulation parameters to determine the relatively accurate initial field files and initial data across dimensions, so the method of determining the initial field files and initial data in the related technology is less efficient. Second, the coupling simulation method in the related technology is to determine the coupling relationship first and then perform the simulation calculation after the overall performance model is built. After that, when facing discrete events, the iterative initial data of the simulation calculation may be unreasonable, convergence is difficult, and due to changes in the sub-model dimension and accuracy requirements, nonlinear equations and algebraic loops may appear. At this time, the related technology can only terminate the calculation and re-establish the coupling relationship. It is impossible to give full play to the advantages of sub-models of different dimensions and accuracy and different coupling methods, and it is impossible to adaptively switch different sub-models according to different simulation requirements, so it is impossible to achieve a balance between model solution accuracy and solution resources, and it is impossible to achieve adaptive whole-machine multi-disciplinary multi-fidelity joint simulation. Based on this, how to adaptively adjust the initial field files, initial data and coupling relationships between the various components of the aero-engine in the process of joint simulation of the aero-engine is crucial for the research and development simulation of the aero-engine.

[0050] After introducing the background technology of the aircraft engine simulation method provided by the embodiment of the present application, the implementation environment involved in the aircraft engine simulation method provided by the embodiment of the present application will be briefly described below. The aircraft engine simulation method provided by the embodiment of the present application can be applied to Figure 1 The simulation system of the aircraft engine is shown.

[0051] The present application provides a simulation system for an aircraft engine, such as Figure 1As shown, the simulation system of the aircraft engine includes an overall performance model 11 and a main model 12 which are communicatively connected, the overall performance model 11 includes a plurality of simulation parameters, and the main model 12 includes a parameter determination module 121, a solver 122 and a control module 123;

[0052] The parameter determination module 121 is used to determine initial simulation parameters according to the simulation requirements of the aircraft engine and multiple simulation parameters in the overall performance model; the initial simulation parameters include sub-models of multiple dimensions, the overall performance model of the aircraft engine in preset dimensions, initial coupling relationships, initial field files and initial data;

[0053] A solver 122, used to call the initial simulation parameters to execute the current matching task corresponding to the current simulation step of the aircraft engine, and obtain the current matching result of the current matching task in a preset dimension;

[0054] The control module 123 is used to obtain the initial field file of the new dimension corresponding to the current matching result;

[0055] The solver 122 is further used to call the initial field file of the new dimension to execute a new matching task corresponding to the next simulation step of the current simulation step, and obtain a new matching result of the new matching task in the new dimension;

[0056] The control module 123 is further used to determine the target simulation result of the aircraft engine according to the current matching result and the new matching result.

[0057] In the embodiment of the present application, the simulation system of the aircraft engine includes a communication-connected overall performance model 11 and a main model 12, that is, the overall performance model 11 and the main model 12 are independently designed in the simulation system of the aircraft engine, and the overall performance model 11 includes multiple simulation parameters, which may include but are not limited to characteristic diagrams, ports, nonlinear equations required for the overall performance model, algorithms and empirical data, etc. The nonlinear equations required for the overall performance model refer to the nonlinear equations formed when the overall performance model of the aircraft engine is coupled with each model for simulation, and each model may include but is not limited to system models and component models, etc. The main model 12 includes a communication-connected parameter determination module 121, a solver 122 and a control module 123, and the parameter determination module 121 can determine the initial simulation parameters according to the simulation requirements of the aircraft engine and the multiple simulation parameters in the overall performance model; the initial simulation parameters include sub-models of multiple dimensions, the whole machine performance model of the aircraft engine in the preset dimensions, the initial coupling relationship, the initial field file and the initial data.

[0058] For example, Figure 2 As shown, Figure 2The schematic diagram of the structure of the simulation system of an aircraft engine in an exemplary embodiment is as follows. The simulation system of the aircraft engine includes an overall performance model 11, a main model 12 and a plurality of subordinate models which are communicatively connected. The main model 12 also includes a dynamic event monitoring module 124, a coupling relationship module 125 and a plurality of ports. The subordinate models may include but are not limited to at least one of a time-continuous model, a discrete event model and the like. The time-continuous model may include but are not limited to models, ports and the like. The discrete event model may include but are not limited to models, ports, solvers and the like.

[0059] In the above-mentioned simulation system of the aircraft engine, the simulation system of the aircraft engine includes a communication-connected overall performance model and a main model. The overall performance model includes multiple simulation parameters, and the main model includes a parameter determination module, a solver, and a control module. In the embodiment of the present application, the overall performance model and the main model are independently designed in the simulation system of the aircraft engine, that is, the multiple simulation parameters in the overall performance model of the aircraft engine can be separated from the main model, and the overall performance model is downgraded to a subordinate model at the same level as the subsystem and the component, so that the overall performance model itself no longer has a solver, and only needs to provide corresponding multiple simulation parameters according to the simulation task requirements, which can avoid the problem that the overall performance model is required to be used as the main model to pull all subsystems and component models to perform simulation calculations during the whole machine coupling simulation in the related technology. Moreover, the embodiment of the present application can adaptively adjust the initial simulation parameters through the parameter determination module, the solver, and the control module in the main model when the current matching result meets the preset simulation conditions, so that the coupling relationship between the various components of the aircraft engine can be adaptively adjusted in the process of joint simulation of the aircraft engine, thereby realizing adaptive whole machine multi-disciplinary multi-fidelity joint simulation.

[0060] In one embodiment, the control module includes a monitoring module and an adjustment module in communication connection;

[0061] A monitoring module is used to monitor whether the simulation requirement or the current matching result or the new matching result meets the preset simulation condition; the preset simulation condition includes that the simulation system monitors a discrete signal corresponding to the simulation requirement, and / or that the error of the current matching result is greater than a preset error threshold;

[0062] The adjustment module is used to adjust the initial simulation parameters when it is monitored that the simulation requirements or the current matching results or the new matching results meet the preset simulation conditions, and simulate the aircraft engine according to the adjusted initial simulation parameters to obtain the simulation results.

[0063] In one of the embodiments, the main model further includes a prediction module, which is connected to the parameter determination module, the solver and the control module respectively;

[0064] The prediction module is used to input the current matching result into a preset initial value prediction network for prediction, and obtain the initial field file of the next simulation step of the current simulation step in the new dimension; and update the initial value prediction network according to the simulation requirements of the next simulation step, the initial simulation parameters of the next simulation step and the new matching result corresponding to the next simulation step.

[0065] Among them, the specific explanation of the above embodiment can be found in the embodiment corresponding to the simulation method of the following aircraft engine, which will not be elaborated here.

[0066] In one of the embodiments, the simulation system includes a database, a model library, and a standard specification library.

[0067] In one of the embodiments, the simulation system further includes a resource scheduling module, and the resource scheduling module is connected to the main model;

[0068] The resource scheduling module is used to schedule resources according to the current matching tasks and initial simulation parameters.

[0069] In one of the embodiments, the simulation system further includes a platform operation interface, and the platform operation interface is connected to the main model;

[0070] The platform operation interface is used to input the simulation requirements of the aircraft engine into the main model.

[0071] In one of the embodiments, the simulation system further includes an integrated simulation module, the integrated simulation module being connected to the main model;

[0072] The integrated simulation module is used to integrate multiple target simulation results to obtain an integrated engine model.

[0073] In one of the embodiments, the simulation system further includes an external interface module, the external interface module being connected to the main model;

[0074] The external interface module is used to interact with external systems through interfaces according to the simulation requirements of aircraft engines.

[0075] In one of the embodiments, the simulation system also includes a cloud simulation module, which is connected to the main model, and the cloud simulation module is used to support computer devices in multiple network environments to realize joint simulation of aircraft engines.

[0076] In one of the embodiments, the simulation system further includes a security policy module, and the security policy module is connected to the main model.

[0077] In the present application embodiment, Figure 3 As shown, Figure 3This is a structural diagram of a simulation system of an aircraft engine in a specific embodiment. The simulation system of an aircraft engine includes a designer operation module 101 with communication connection, a platform operation interface 102, a database 103, a model library 104, an algorithm library 105, a standard specification module 106, a data bus module 107, a display module 108, an integrated simulation module 109, an external interface module 110, a cloud simulation module 111, a resource scheduling module 112, and a security policy module 113. Among them, the designer operation module 101 is used to determine the joint simulation task through each designer, so that each designer can call relevant modeling data from the database 103 to complete the modeling, uploading and calibration work according to the simulation task corresponding to the designer himself in the joint simulation task on the platform operation interface 102 corresponding to his own operating computer, and can build the model according to the overall requirements of the joint simulation task, and import the built model into the model library 104 and the algorithm library 105 according to the joint simulation interface standards and specifications. In addition, each designer can also select the corresponding national standard, military standard, enterprise standard and calling standards and specifications of other modules of the platform from the standard specification module 106 according to his own modeling and simulation task needs, so as to comprehensively complete the joint simulation task.

[0078] The data bus module 107 includes an overall performance model 11, a main model 12 and multiple subordinate models. The main model 12 includes a communication-connected parameter determination module 121, a solver 122, a control module 123, a dynamic event monitoring module 124 (i.e., the above-mentioned monitoring module), a coupling relationship module 125, an intelligent decision module 126 (i.e., the above-mentioned adjustment module), an initial value prediction module 127 (i.e., the above-mentioned prediction module) and multiple ports. The coupling relationship module 125 stores multiple coupling relationship equation groups. The data bus module 107 can integrate the data, models, algorithms, etc. determined in the platform operation interface 102, the database 103, the model library 104, the algorithm library 105, and the standard specification module 106 through the data transmission process, standards and specifications formulated in the data bus to meet the call of different resources by different simulation tasks in the joint simulation.

[0079] The display module 108 is used to display the joint simulation results of the aircraft engine. The integrated simulation module 109 is used to integrate the models of different languages, different tools and different disciplines according to the interface standards and specifications according to the joint simulation task determined by the designer, and determine the solver, solution algorithm, simulation duration, simulation step length and other instructions required in the joint simulation task. The external interface module 110 is used to interact with the external platform according to the simulation task requirements. The cloud simulation module 111 is used to distribute the models integrated by the integrated simulation module to different computing resources according to the joint simulation task, and also supports designers in different network environments to upload models for joint simulation. The resource scheduling module 112 is used to set the selection of task type, execution order and batch processing according to the joint simulation task, and set the computing resources required for the joint simulation task according to the simulation task. The security policy module 113 is used to ensure information security in the joint simulation by formulating security policies.

[0080] The present application also provides a method for developing a simulation system for an aircraft engine, the development method comprising the following steps: a first step is to develop a 0-dimensional component model 104 required for building an overall performance model of the aircraft engine, so that designers can select components for combination according to modeling requirements to build an overall performance model of the aircraft engine. For example, the 0-dimensional component model may include but is not limited to the basic structure, aerodynamic performance, design parameters, calculation formulas, logical relationships, input and output ports, and component characteristic diagrams and empirical data of each component of the aircraft engine.

[0081] The second step is to determine the ports, nonlinear equations, algebraic loops and iterative parameters required for coupling different models, and develop a coupling method for the overall performance model of the aircraft engine with different system models and component models of different fidelity based on the above parameters.

[0082] The third step is to develop a database by studying the data source identification and calling methods for the joint simulation of multi-system and multi-fidelity models of aircraft engines, and combining the relationship between the test data of various design disciplines and model simulation in the system-level simulation of aircraft engines to formulate standards and specifications for data calling, model calibration and analysis, and to realize the integrated calling of different model data sources by developing an integrated simulation module. Among them, the data source identification and calling methods may include but are not limited to those based on the FMI communication protocol, based on encapsulation as exe, DLL and LIB, etc. The simulation tools used by the data source identification and calling methods include but are not limited to typical engine system-level commercial simulation tools, such as PROOSIS, FloMASTER, AMEsim, Dymolia, SIMULINK, etc., and when developing the data source identification method of the data management module, the simulation tools analyzed may include but are not limited to simulation programs developed in languages ​​such as C, C++, Python, Java and Fortran.

[0083] The fourth step is to formulate storage and call standards and specifications for simulation result data, and combine the functions of database, integrated simulation module, resource scheduling module, etc. to establish a direct relationship between the data type, characteristics and model generated by each designer's simulation process and the simulation results.

[0084] The fifth step is to develop a model library to store existing model files, initial field files generated by the calculation process, case files, etc., and create index files for each file in the model library to facilitate searching. Therefore, model version management and calling can be performed by establishing a model library management and calling strategy, combined with a resource scheduling module and database.

[0085] The sixth step is to develop dynamic event monitoring modules, intelligent decision modules and main solver modules to separate the main solver from the traditional overall performance model. The algorithms that can be used by the main solver in the joint simulation process include but are not limited to NR, Broyden, RK4, Euler algorithm, etc. When facing a combination of models with different computational efficiencies, the use of an independent main solver can ensure accuracy and stable and reliable solutions.

[0086] Step 7: Develop the initial value prediction module.

[0087] The eighth step is to develop a joint simulation platform for aero-engine systems. By formulating the unified interface protocol, operation format, simulation step, solver, and solution algorithm required for joint simulation of various languages ​​and tools, the simulation environment required for multiple modeling languages, multiple design disciplines, and multiple simulation tools in joint simulation of aero-engine systems can be solved. By combining the integrated simulation module, resource scheduling module, and standard specification module in the joint simulation platform for aero-engine systems, designers can call different versions of models, data, and standard specifications to complete specific system-level joint simulation tasks. For example, OPC protocol, UDP protocol, and data file transmission can be used to directly connect and call designers, joint simulation models, visual display hardware equipment, test benches, and control equipment such as engine throttle levers.

[0088] The ninth step is to establish an information security assurance module and formulate an information security assurance strategy to ensure information security in the process of calling data, models, and standard specifications through the data main line.

[0089] The tenth step is to develop a data bus module based on the requirements of aero-engine system-level simulation models. Based on the model library, database, simulation task management and standard specification modules in the platform, the aero-engine system-level joint simulation tasks are associated with various functional modules through key information identification and transmission technology to reduce the current situation of oral discussions, paper document information transmission and review.

[0090] In one embodiment, Figure 4 As shown, a simulation method for an aeroengine is provided, and the method is applied to Figure 1-Figure 3 The simulation system of an aircraft engine in any example is used as an example to illustrate, comprising the following steps:

[0091] S201, determining initial simulation parameters according to the simulation requirements of the aircraft engine; the initial simulation parameters include sub-models of multiple dimensions, the whole machine performance model of the aircraft engine in a preset dimension, initial coupling relationship, initial field file and initial data.

[0092] Among them, simulation requirements refer to flight parameters that need to be met when simulating an aircraft engine. For example, flight parameters may include but are not limited to flight altitude, throttle lever parameters, etc. For example, simulation requirements may be: the throttle lever angle of the aircraft engine is from 50% to 100%. Initial simulation parameters refer to simulation parameters that need to be used in the simulation process of the aircraft engine at the current moment. Initial simulation parameters may include but are not limited to sub-models of multiple dimensions, the whole machine performance model of the aircraft engine in preset dimensions, initial coupling relationships, initial field files and initial data, etc. Sub-models may be models of different information dimensions such as 0-dimensional, 1-dimensional, 2-dimensional and 3-dimensional. Sub-models of multiple dimensions can form a whole machine performance model, which is used to perform calculation tasks of the aircraft engine. Any two or more sub-models can form a sub-model combination. The initial coupling relationship refers to the coupling equation group corresponding to the sub-model combination. For example, the initial coupling relationship corresponding to the 0-dimensional and 1-dimensional sub-models is different from the initial coupling relationship corresponding to the 0-dimensional and 3-dimensional sub-models. The initial field file refers to at least one high-dimensional parameter corresponding to the sub-model, that is, the initial field file corresponds to the 3D sub-model; the initial data refers to at least one low-dimensional parameter corresponding to the sub-model, that is, the initial data corresponds to the 0-dimensional, 1-dimensional or 2-dimensional sub-model. Generally, there is one whole-machine performance model for an aircraft engine. Although there may be several variations of the whole-machine performance model according to the simulation environment and / or simulation requirements, the variation is only the transformation of known and unknown quantities in the equation group corresponding to the whole-machine performance model, and the properties of the whole-machine performance model remain unchanged. The difference is that each sub-model can correspond to countless initial field files or initial data.

[0093] In an embodiment of the present application, the designer can input the simulation requirements of the aircraft engine on the platform operation interface of the simulation system of the aircraft engine, so that the simulation system of the aircraft engine can respond to the simulation requirements of the aircraft engine, call the dynamic event monitoring module and the intelligent decision-making module to analyze the simulation requirements, and select sub-models of different dimensions corresponding to the simulation requirements from the model library and the algorithm library, and combine the sub-models of multiple dimensions into a whole machine performance model, and select initial simulation parameters such as initial coupling relationships, multiple high-dimensional initial field files, low-dimensional initial data and iteration parameters from the database according to the sub-models of different dimensions.

[0094] S202, calling the initial simulation parameters to execute the current matching task corresponding to the current simulation step of the aircraft engine, and obtaining the current matching result of the current matching task in a preset dimension.

[0095] In the embodiment of the present application, the simulation system of the aircraft engine can split the calculation task of the aircraft engine to obtain the matching task corresponding to each simulation step, so that the above-mentioned initial simulation parameters can be called, the initial coupling relationship, the initial field file and the initial data are configured in the whole machine performance model, and the current matching task corresponding to the current simulation step of the aircraft engine is executed to obtain the current matching result of the current matching task in the preset dimension. Among them, the preset dimension can be any information dimension, and the current matching result refers to the execution result of the current matching task corresponding to the current simulation step.

[0096] For example, assuming that the calculation task of the aircraft engine is an acceleration and deceleration task under the condition of one hundred meters, the one hundred meters can be divided into 100 segments, each segment is a simulation step, and the matching task is the decomposition task corresponding to every 1 meter in the calculation task. The initial data may include but is not limited to the mass of the aircraft engine, the parameters of the motor, the throttle, etc. The initial field file includes finer-grained environmental conditions, such as weather conditions, road conditions, etc.

[0097] S203, obtaining the initial field file of the new dimension corresponding to the current matching result, and calling the initial field file of the new dimension to execute the new matching task corresponding to the next simulation step of the current simulation step, to obtain a new matching result of the new matching task in the new dimension.

[0098] In the embodiment of the present application, the label corresponding to each initial field file can be pre-set, and the label corresponds to the matching result, so that in cross-dimensional simulation (also known as scaling technology, mixed dimension, or multi-fidelity simulation), the simulation system of the aircraft engine can determine the retrieval label of the initial field file used by the cross-dimensional 3D CFD (Computational Fluid Dynamics) model according to the current matching result of the current matching task in the preset dimension, and then the initial field file of the new dimension can be determined from the database according to the retrieval label. Furthermore, a multi-fidelity simulation whole machine performance model can be established according to the 3D CFD model, and the initial field file of the new dimension can be called, and the initial field file of the new dimension can be configured in the multi-fidelity simulation whole machine performance model, and the new matching task corresponding to the next simulation step of the current simulation step can be executed to obtain the new matching result of the new matching task in the new dimension.

[0099] Exemplarily, assuming that the label corresponding to the initial field file of an aircraft engine 3D component is the matching result when the component inlet parameters are a combination of preset temperature, pressure, area, etc., then after determining the current matching result of the preset dimension corresponding to the current simulation step, the temperature, pressure, area and other data of the component inlet corresponding to the current matching result can be determined. Thus, the temperature, pressure, area and other data of the component inlet corresponding to the current matching result of the preset dimension can be used as a retrieval label, and the initial field file of a new dimension corresponding to the above-mentioned retrieval label can be retrieved from the database based on the existing labels of each initial field file. It should be noted that the embodiment of the present application can not only determine the initial field file of a high dimension based on the matching result of a low dimension, or, it can also determine the initial field file of a low dimension based on the matching result of a high dimension, that is, the embodiment of the present application has no limitation on the preset dimension and the new dimension.

[0100] S204, determining a target simulation result of the aircraft engine according to the current matching result and the new matching result.

[0101] In the embodiment of the present application, the simulation system of the aircraft engine can integrate models of different dimensions for joint simulation and joint solution according to the current matching results and the new matching results, and determine the matching results corresponding to each simulation step length, so that the target simulation result of the aircraft engine can be determined according to the matching results corresponding to each simulation step length. The target simulation result refers to the final simulation result corresponding to the calculation task of the aircraft engine.

[0102] In the above-mentioned simulation method of the aircraft engine, the initial simulation parameters are determined according to the simulation requirements of the aircraft engine; the initial simulation parameters include sub-models of multiple dimensions, the whole machine performance model of the aircraft engine in the preset dimensions, the initial coupling relationship, the initial field file and the initial data; the initial simulation parameters are called to execute the current matching task corresponding to the current simulation step of the aircraft engine, and the current matching result of the current matching task in the preset dimension is obtained; the initial field file of the new dimension corresponding to the current matching result is obtained, and the initial field file of the new dimension is called to execute the new matching task corresponding to the next simulation step of the current simulation step, and the new matching result of the new matching task in the new dimension is obtained; according to the current matching result and the new matching result, the target simulation result of the aircraft engine is determined. Since the initial simulation parameters include the initial coupling relationship, the initial field file and the initial data, and the embodiment of the present application can call the initial simulation parameters to determine the current matching results of the preset dimension, and use the current matching results of the preset dimension to determine the initial field file of the new dimension, the embodiment of the present application can adaptively determine the initial simulation parameters of another dimension according to the matching results of one dimension during the joint simulation of the aircraft engine, so as to quickly determine more accurate initial simulation parameters without having to search for the initial simulation parameters multiple times from a large number of simulation parameters, thereby improving the efficiency of the adaptive multi-disciplinary and multi-fidelity joint simulation of the aircraft engine.

[0103] In one embodiment, a method for determining initial simulation parameters is provided, namely, "determining initial simulation parameters according to the simulation requirements of the aircraft engine" in the above S201, such as Figure 5 As shown, including:

[0104] S301, determining whether the overall performance model of the aircraft engine includes candidate simulation parameters that meet the simulation requirements. If the overall performance model includes the candidate simulation parameters, executing S302; if the overall performance model does not include the candidate simulation parameters, executing S303;

[0105] S302: Determine initial simulation parameters from candidate simulation parameters.

[0106] S303: Determine initial simulation parameters using target computing resources.

[0107] Among them, the overall performance model of the aircraft engine may include parameters in the model library, database and algorithm library for simulating the aircraft engine, the candidate simulation parameters refer to the simulation parameters in the overall performance model that meet the simulation requirements, and the target computing resources refer to the idle computing resources at the current moment.

[0108] In an embodiment of the present application, the simulation system of the aircraft engine can determine whether the overall performance model of the aircraft engine includes candidate simulation parameters that meet the simulation requirements. If it is determined that the overall performance model includes candidate simulation parameters that meet the simulation requirements, the simulation system of the aircraft engine can dynamically select initial simulation parameters directly from multiple candidate simulation parameters in the overall performance model to reduce unnecessary waste of resources and time; if the overall performance model does not include candidate simulation parameters that meet the simulation requirements, the simulation system of the aircraft engine can determine the initial simulation parameters using target computing resources through distributed simulation technology.

[0109] In this embodiment, it is determined whether the overall performance model of the aircraft engine includes candidate simulation parameters that meet the simulation requirements; if the overall performance model includes candidate simulation parameters, the initial simulation parameters are determined from the candidate simulation parameters; if the overall performance model does not include candidate simulation parameters, the initial simulation parameters are determined using target computing resources. By determining the initial simulation parameters through methods such as dynamic monitoring and intelligent decision-making, the most suitable sub-models of multiple dimensions, the overall performance model of the aircraft engine in the preset dimensions, the initial coupling relationship, the initial field file and the initial data can be flexibly determined.

[0110] In one embodiment, a method for implementing the current matching task is provided, namely, the above-mentioned "calling the initial simulation parameters to execute the current matching task corresponding to the current simulation step of the aircraft engine to obtain the current matching result of the current matching task in the preset dimension" in S202, including:

[0111] A solver is used to execute a current matching task corresponding to a current simulation step according to initial simulation parameters, and a current matching result of the current matching task in a preset dimension is obtained; the solver and the overall performance model are set independently.

[0112] In the embodiment of the present application, the overall performance model and the main model can be independently designed in the simulation system of the aircraft engine, that is, multiple simulation parameters in the overall performance model of the aircraft engine can be separated from the main model, and the overall performance model can be downgraded to a subordinate model at the same level as the subsystems and components, so that the overall solution is no longer driven by the overall performance model, but is driven according to the simulation task requirements. The overall performance model itself no longer has a solver, and it only needs to provide multiple corresponding simulation parameters according to the simulation task requirements. The solver in the main model can be used to execute the current matching task corresponding to the aircraft engine according to the initial simulation parameters to obtain the current matching result. In this way, in the process of the solver executing the current matching task, the overall performance model only needs to determine multiple simulation parameters, and there is no need to perform other operations or tasks. This can avoid the problem that in the related technology, when the whole machine is coupled to simulate, the overall performance model needs to be used as the main model to drive all subsystems and component models for simulation calculations.

[0113] In the above embodiment, a method for adjusting the initial simulation parameters is provided, namely: Figure 4 The simulation method of the aircraft engine of the embodiment is as follows: Figure 6 As shown, it also includes:

[0114] S205, when the simulation requirements or the current matching results or the new matching results meet the preset simulation conditions, adjust the initial simulation parameters to obtain the adjusted initial simulation parameters; the preset simulation conditions include monitoring the discrete signal corresponding to the simulation requirements, and / or the error of the current matching result is greater than the preset error threshold.

[0115] S206, using the adjusted initial simulation parameters as new initial simulation parameters, returning to execute calling the initial simulation parameters to execute the current matching task corresponding to the current simulation step of the aircraft engine, and obtaining the current matching result of the current matching task in the preset dimension.

[0116] In the embodiment of the present application, the simulation system of the aircraft engine can determine whether the simulation requirement or the current matching result or the new matching result meets the preset simulation conditions. If it is determined that the simulation requirement, the current matching result, and the new matching result do not meet the preset simulation conditions, the initial simulation parameters are used to simulate the aircraft engine for the next simulation step to obtain the matching result of the next simulation step of the aircraft engine; if it is determined that the simulation requirement or the current matching result or the new matching result meets the preset simulation conditions, the current matching task is suspended and the initial simulation parameters are adjusted. Thus, the simulation system of the aircraft engine can use the adjusted initial simulation parameters as new initial simulation parameters, and call the new initial simulation parameters to execute the current matching task corresponding to the current simulation step of the aircraft engine, and obtain the new current matching result of the current matching task in the preset dimension. Among them, the preset simulation conditions may include but are not limited to at least one of the following conditions: the occurrence of discrete events during the simulation process, the detection of discrete signals corresponding to the simulation requirement, the error of the current matching result being greater than the preset error threshold, and the change of the information dimension.

[0117] Exemplarily, the dynamic event monitoring module in the simulation system of the aircraft engine can monitor the simulation requirements and initial simulation parameters in the simulation calculation process in real time, and determine whether there are discrete events and time-continuous events caused by changes in simulation requirements and / or input parameters, for example, discrete events can include signals such as valve switches. In addition, the dynamic event monitoring module in the simulation system of the aircraft engine can also pre-set the optimal use range and preset error threshold of subsystem models and component models of different fidelity, and monitor in real time whether the error of the current matching result is greater than the preset error threshold. If the discrete signal corresponding to the simulation requirement is not monitored, and the error of the current matching result is less than or equal to the preset error threshold, the initial simulation parameters are used to simulate the aircraft engine for the next simulation step to obtain the target simulation result of the aircraft engine; if the discrete signal corresponding to the simulation requirement is monitored, and / or the error of the current matching result is greater than the preset error threshold, the solver can be controlled to suspend the simulation task at the current moment, and the initial simulation parameters can be adjusted to call different models to balance the calculation accuracy and solution efficiency. In addition, the monitoring results of the dynamic event monitoring module can be fed back to the intelligent decision-making module in real time or regularly.

[0118] In this embodiment, when a discrete signal corresponding to the simulation requirement is monitored and / or when the error of the current matching result is greater than a preset error threshold, the initial simulation parameters can be adjusted. That is, in the process of joint simulation of the aircraft engine, according to the requirements of different simulation tasks for different models, the error changes in the model calculation results, etc., the coupling relationship between the various components of the aircraft engine and the initial simulation parameters such as the optimal model can be adaptively adjusted, thereby realizing adaptive multi-disciplinary and multi-fidelity joint simulation of the whole machine.

[0119] In one embodiment, a method for determining an initial field file of a new dimension is provided, namely, the “obtaining an initial field file of a new dimension corresponding to the current matching result” in the above S203, including:

[0120] The current matching result is input into the preset initial value prediction network for prediction, and the initial field file of the next simulation step of the current simulation step in the new dimension is obtained.

[0121] In the embodiment of the present application, optionally, the initial value prediction module in the simulation system of the aircraft engine can directly input the current matching result into the preset initial value prediction network for prediction, and obtain the initial field file of the next simulation step of the current simulation step in the new dimension; or, the initial value prediction module in the simulation system of the aircraft engine can also input the current matching result into the preset initial value prediction network for prediction, obtain the search tag corresponding to the current matching result, and then retrieve the initial field file of the next simulation step of the current simulation step in the new dimension from the database according to the search tag; or, the initial value prediction module in the simulation system of the aircraft engine can also first perform data preprocessing on the current matching result to obtain the preprocessed current matching result, and then input the preprocessed current matching result into the preset initial value prediction network for prediction, and obtain the initial field file of the next simulation step of the current simulation step in the new dimension. Of course, the embodiment of the present application does not limit the specific implementation method of the initial value prediction step. Among them, the initial value prediction network can include but is not limited to any intelligent learning algorithm such as the random forest method and the gradient boosting algorithm.

[0122] In this embodiment, the current matching result is input into the preset initial value prediction network for prediction, and the initial field file of the next simulation step of the current simulation step in the new dimension is obtained. The most suitable initial field file and initial data corresponding to each simulation step can be selected, and the initial field file required for the matching task can be accurately predicted. At the same time as the main model is iteratively calculated, the initial field file of the next simulation step can be calculated in parallel, which can effectively improve the efficiency of joint simulation solution, reduce computing costs, and make multi-fidelity transient calculations that were originally unfeasible due to the huge amount of calculation possible. In addition, the initial value prediction network can be updated in real time according to the simulation requirements of the next simulation step, the initial simulation parameters of the next simulation step, and the new matching results corresponding to the next simulation step, so as to obtain a more accurate initial value prediction network, and improve the efficiency of subsequent high-precision calculation processes.

[0123] In the above embodiment, a training method of an initial value prediction network is provided, that is, the above aircraft engine simulation method, further comprising:

[0124] Get the historical data set; the historical data set includes historical matching results and labels corresponding to historical initial field files.

[0125] The initial value prediction network is trained according to the historical data set to obtain the initial value prediction network.

[0126] The initial value prediction network is updated according to the simulation requirements of the next simulation step, the initial simulation parameters of the next simulation step and the new matching results corresponding to the next simulation step.

[0127] In the embodiment of the present application, the simulation system of the aircraft engine can obtain a historical data set from a database and / or a public web page, wherein the historical data set includes historical matching results, historical initial field files, and labels corresponding to the historical initial field files. The historical matching results refer to the real matching results obtained in the process of performing the matching task at the historical moment, and the historical initial field files refer to the real initial field files at the historical moment. Since the data volume of the initial field files is large, when storing the historical initial field files, corresponding labels will be set for each historical initial field file. Thus, the simulation system of the aircraft engine can input the historical matching results in the historical data set into the initial value prediction network for prediction, obtain the labels corresponding to the predicted initial field files, and then calculate the target loss according to the labels corresponding to the predicted initial field files and the labels corresponding to the historical initial field files, and adjust the initial model parameters of the initial value prediction network according to the target loss to obtain an intermediate prediction network. Then, the intermediate initial value prediction network can be iteratively trained according to the historical data set to finally obtain a trained initial value prediction network.

[0128] In the embodiment of the present application, the simulation system of the aircraft engine can also determine the initial simulation parameters of the next simulation step according to the simulation requirements of the next simulation step of the aircraft engine, wherein the initial simulation parameters of the next simulation step include the sub-model of the next simulation step, the whole machine performance model of the aircraft engine in the preset dimension, the initial coupling relationship, the initial field file and the initial data. Thus, the simulation system of the aircraft engine can call the initial simulation parameters of the next simulation step to execute the current matching task corresponding to the next simulation step of the aircraft engine, and obtain the new matching result corresponding to the next simulation step of the aircraft engine. Thus, the initial value prediction module in the simulation system of the aircraft engine can use the incremental learning method to comprehensively retrain the initial value prediction network according to the simulation requirements of the next simulation step, the initial simulation parameters of the next simulation step and the new matching result corresponding to the next simulation step, combined with the historical data set, to obtain an updated initial value prediction network.

[0129] In this embodiment, a historical data set can be obtained, wherein the historical data set includes historical matching results and labels corresponding to historical initial field files, and an initial value prediction network is trained based on the historical data set to obtain an accurate initial value prediction network.

[0130] Based on all the above embodiments, the present application also provides a complete simulation method for an aircraft engine, such as Figure 7 As shown, the method includes:

[0131] S401, determining whether the overall performance model of the aircraft engine includes candidate simulation parameters that meet the simulation requirements; if the overall performance model includes the candidate simulation parameters, executing S402; if the overall performance model does not include the candidate simulation parameters, executing S403;

[0132] S402: Determine initial simulation parameters from candidate simulation parameters.

[0133] S403, using the target computing resources to determine initial simulation parameters; the initial simulation parameters include sub-models in multiple dimensions, the whole-machine performance model of the aircraft engine in a preset dimension, initial coupling relationship, initial field file and initial data;

[0134] S404, using a solver to execute a current matching task corresponding to a current simulation step of the aircraft engine according to initial simulation parameters, and obtaining a current matching result of the current matching task in a preset dimension; the solver and the overall performance model are independently set;

[0135] S405, obtaining a historical data set; the historical data set includes historical initial field files and initial data;

[0136] S406, training the initial value prediction network according to the historical data set to obtain the initial value prediction network;

[0137] S407, inputting the current matching result into a preset initial value prediction network for prediction, and obtaining an initial field file of the next simulation step of the current simulation step in a new dimension;

[0138] S408, calling the initial field file of the new dimension to execute a new matching task corresponding to the next simulation step of the current simulation step, and obtaining a new matching result of the new matching task in the new dimension;

[0139] S409, determining a target simulation result of the aircraft engine according to the current matching result and the new matching result;

[0140] S410, updating the initial value prediction network according to the simulation requirement of the next simulation step, the initial simulation parameters of the next simulation step, and the new matching result corresponding to the next simulation step;

[0141] S411, when the simulation requirement or the current matching result or the new matching result meets the preset simulation condition, adjusting the initial simulation parameters to obtain the adjusted initial simulation parameters; the preset simulation condition includes monitoring a discrete signal corresponding to the simulation requirement and / or an error of the current matching result being greater than a preset error threshold;

[0142] S412, taking the adjusted initial simulation parameters as new initial simulation parameters, and returning to execute S404.

[0143] In the above-mentioned simulation method of the aircraft engine, since the initial simulation parameters include the initial coupling relationship, the initial field file and the initial data, and the embodiment of the present application can call the initial simulation parameters to determine the current matching results of the preset dimension, and use the current matching results of the preset dimension to determine the initial field file of the new dimension, the embodiment of the present application can adaptively determine the initial simulation parameters of another dimension according to the matching results of one dimension during the joint simulation of the aircraft engine, so that more accurate initial simulation parameters can be quickly determined without having to search for the initial simulation parameters multiple times from a large number of simulation parameters, so that the efficiency of the adaptive multi-disciplinary and multi-fidelity joint simulation of the aircraft engine can be improved.

[0144] In summary, this application establishes a multi-disciplinary and multi-fidelity joint simulation model of a small bypass ratio turbofan engine based on the independently developed gas turbine performance joint simulation software GPCS (Gas-turbine Performance Co-simulation Software), and proposes a dynamic event-driven joint simulation method by combining the decision tree method. By dynamically judging simulation events and calling requirements for sub-models, the iterative initial data, convergence conditions, nonlinear equations and algebraic loops are adjusted. This method can provide an adaptive solution for multi-disciplinary and multi-fidelity joint simulation of aero-engines, which can give full play to the advantages of models of different dimensions and precisions and different coupling methods, and improve the accuracy, efficiency and stability of engine joint simulation calculations.

[0145] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0146] Based on the same inventive concept, the embodiment of the present application also provides an aircraft engine simulation device for implementing the aircraft engine simulation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more aircraft engine simulation devices provided below can refer to the limitations of the aircraft engine simulation method above, and will not be repeated here.

[0147] In an exemplary embodiment, Figure 8 As shown, a simulation device for an aircraft engine is provided, comprising: a determination module 31, a first execution module 32, a second execution module 33 and a simulation module 34, wherein:

[0148] The determination module 31 is used to determine the initial simulation parameters according to the simulation requirements of the aircraft engine; the initial simulation parameters include sub-models of multiple dimensions, the whole machine performance model of the aircraft engine in the preset dimensions, the initial coupling relationship, the initial field file and the initial data.

[0149] The first execution module 32 is used to call the initial simulation parameters to execute the current matching task corresponding to the current simulation step of the aircraft engine, and obtain the current matching result of the current matching task in a preset dimension.

[0150] The second execution module 33 obtains the initial field file of the new dimension corresponding to the current matching result, and calls the initial field file of the new dimension to execute the new matching task corresponding to the next simulation step of the current simulation step, and obtains the new matching result of the new matching task in the new dimension.

[0151] The simulation module 34 is used to determine the target simulation result of the aircraft engine according to the current matching result and the new matching result.

[0152] In one embodiment, the determination module 31 includes:

[0153] A judgment unit, used to determine whether the overall performance model of the aircraft engine includes candidate simulation parameters that meet the simulation requirements;

[0154] a first determining unit, configured to determine initial simulation parameters from the candidate simulation parameters if the overall performance model includes the candidate simulation parameters;

[0155] The second determining unit is configured to determine the initial simulation parameters using the target computing resources if the overall performance model does not include the candidate simulation parameters.

[0156] In one embodiment, the first execution module 32 is specifically configured to:

[0157] A solver is used to execute a current matching task corresponding to a current simulation step of an aero-engine according to initial simulation parameters, and a current matching result of the current matching task in a preset dimension is obtained; the solver is independently set up from the overall performance model.

[0158] In one embodiment, the second execution module 33 is specifically configured to:

[0159] The current matching result is input into the preset initial value prediction network for prediction, and the initial field file of the next simulation step of the current simulation step in the new dimension is obtained.

[0160] In one embodiment, the above-mentioned aircraft engine simulation device further includes:

[0161] An initial simulation parameter adjustment module is used to adjust the initial simulation parameters to obtain adjusted initial simulation parameters when the simulation requirement or the current matching result or the new matching result meets the preset simulation conditions; the preset simulation conditions include monitoring the discrete signal corresponding to the simulation requirement and / or the error of the current matching result is greater than the preset error threshold;

[0162] The third execution module is used to use the adjusted initial simulation parameters as new initial simulation parameters, return to execute and call the initial simulation parameters to execute the current matching task corresponding to the current simulation step of the aircraft engine, and obtain the current matching result of the current matching task in a preset dimension.

[0163] In one embodiment, the above-mentioned aircraft engine simulation device further includes:

[0164] The historical data set acquisition module is used to acquire the historical data set; the historical data set includes historical matching results and labels corresponding to historical initial field files;

[0165] A training module is used to train the initial value prediction network according to the historical data set to obtain the initial value prediction network;

[0166] The initial value prediction network updating module is used to update the initial value prediction network according to the simulation requirements of the next simulation step, the initial simulation parameters of the next simulation step and the new matching results corresponding to the next simulation step.

[0167] Each module in the above-mentioned aircraft engine simulation device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0168] In an exemplary embodiment, a computer device is provided. The computer device is arranged in a simulation device of an aircraft engine. The computer device may be a terminal. The internal structure diagram thereof may be as shown in FIG. Fig. 9As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a simulation method of an aircraft engine is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0169] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0170] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0171] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0172] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0173] It should be noted that the user information (including but not limited to relevant information of designers, user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0174] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0175] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0176] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A simulation method for an aircraft engine, characterized in that: The method comprises: Determine initial simulation parameters according to the simulation requirements of the aircraft engine; the initial simulation parameters include sub-models of multiple dimensions, the whole machine performance model of the aircraft engine in preset dimensions, initial coupling relationship, initial field file and initial data; Calling the initial simulation parameters to execute the current matching task corresponding to the current simulation step of the aircraft engine, and obtaining the current matching result of the current matching task in the preset dimension; Obtaining an initial field file of a new dimension corresponding to the current matching result, and calling the initial field file of the new dimension to execute a new matching task corresponding to the next simulation step of the current simulation step, to obtain a new matching result of the new matching task in the new dimension; A target simulation result of the aircraft engine is determined according to the current matching result and the new matching result.

2. The method according to claim 1, characterized in that Determining the initial simulation parameters according to the simulation requirements of the aircraft engine includes: Determining whether the overall performance model of the aircraft engine includes candidate simulation parameters that meet the simulation requirements; If the overall performance model includes the candidate simulation parameters, determining the initial simulation parameters from the candidate simulation parameters; If the overall performance model does not include the candidate simulation parameters, the target computing resources are used to determine the initial simulation parameters.

3. The method according to claim 2, characterized in that The calling of the initial simulation parameters to execute the current matching task corresponding to the current simulation step of the aircraft engine to obtain the current matching result of the current matching task in the preset dimension includes: A solver is used to execute a current matching task corresponding to a current simulation step of the aircraft engine according to the initial simulation parameters to obtain a current matching result of the current matching task in the preset dimension; the solver is independently set up from the overall performance model.

4. The method according to any one of claims 1 to 3, characterized in that The obtaining of the initial field file of the new dimension corresponding to the current matching result includes: The current matching result is input into a preset initial value prediction network for prediction, and an initial field file of the next simulation step of the current simulation step in a new dimension is obtained.

5. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: When the simulation requirement or the current matching result or the new matching result satisfies a preset simulation condition, adjusting the initial simulation parameter to obtain an adjusted initial simulation parameter; the preset simulation condition includes monitoring a discrete signal corresponding to the simulation requirement, and / or an error of the current matching result is greater than a preset error threshold; The adjusted initial simulation parameters are used as new initial simulation parameters, and the initial simulation parameters are returned to execute the current matching task corresponding to the current simulation step of the aircraft engine, so as to obtain the current matching result of the current matching task in the preset dimension.

6. The method according to claim 4, characterized in that The training method of the initial value prediction network includes: Obtain a historical data set; the historical data set includes historical matching results and labels corresponding to historical initial field files; Training an initial value prediction network according to the historical data set to obtain the initial value prediction network; The initial value prediction network is updated according to the simulation requirements of the next simulation step, the initial simulation parameters of the next simulation step and the new matching result corresponding to the next simulation step.

7. A simulation device for an aircraft engine, characterized in that: The device comprises: A determination module is used to determine initial simulation parameters according to the simulation requirements of the aircraft engine; the initial simulation parameters include sub-models of multiple dimensions, the whole machine performance model of the aircraft engine in the preset dimensions, initial coupling relationship, initial field file and initial data; A first execution module is used to call the initial simulation parameters to execute the current matching task corresponding to the current simulation step of the aircraft engine, and obtain the current matching result of the current matching task in the preset dimension; The second execution module obtains the initial field file of the new dimension corresponding to the current matching result, and calls the initial field file of the new dimension to execute the new matching task corresponding to the next simulation step of the current simulation step, to obtain the new matching result of the new matching task in the new dimension; The simulation module is used to determine the target simulation result of the aircraft engine according to the current matching result and the new matching result.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images