Construction method and device of engine simulation model, server, medium and product
By building and optimizing the engine simulation model, the problem of insufficient simulation model accuracy in the existing technology is solved, high-precision virtual calibration is achieved, strict calibration requirements are met, and costs are reduced.
Patent Information
- Application Number
- CN202411167627.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-23
- Publication Date
- 2024-12-03
AI Technical Summary
The existing engine simulation model is insufficient in accuracy and cannot meet the strict calibration requirements, especially in high altitude and high temperature environments, resulting in problems such as overspeeding of the turbocharger and over-cylinder pressure.
By obtaining the layout diagram of the engine, determining the overall layout and component position relationship, building a simulation model, and calibrating and training each component until preset conditions are met, the target coefficients and parameters of the simulation model are optimized, the pulse effect is corrected, and the model accuracy is improved. .
It significantly improves the accuracy of the engine simulation model, shortens the development cycle, reduces costs, and meets the high standard requirements of virtual calibration.
Smart Images

Figure CN119066770A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of engine simulation technology, and in particular to a method, device, server, medium and product for constructing an engine simulation model. Background Art
[0002] With the improvement of global environmental awareness and increasingly stringent emission regulations, engine manufacturers are facing unprecedented challenges. In actual applications, the power and economy of engines are affected by a variety of environmental factors. For example, the thin air at high altitudes can lead to reduced engine performance, while high temperature environments may aggravate emission problems. These factors not only increase the thermal load of the engine, but may also cause turbocharger overspeed and cylinder pressure overrun, thus placing higher requirements on engine calibration.
[0003] VTB (Virtual Testbed) combines software simulation models and hardware-in-the-loop test systems to perform functional tests and virtual calibration of controllers without a real vehicle or engine. The core of VTB lies in its software simulation model, and the accuracy of the model directly affects the accuracy and efficiency of virtual calibration. Therefore, it is crucial to design a high-precision and high-efficiency engine simulation model. Summary of the invention
[0004] The present application provides a method, device, server, medium and product for constructing an engine simulation model to solve the problem of how to improve the accuracy of the engine simulation model to meet calibration requirements.
[0005] The first aspect of the present application provides a method for constructing an engine simulation model, comprising the following steps: obtaining a layout diagram of the engine; determining the overall layout of the engine, the positional relationship and the connection relationship of each component based on the layout diagram to construct an engine simulation model, and calibrating each component of the engine; training the simulation model based on the calibrated components and training data until a preset stop condition is met, thereby obtaining a trained engine simulation model.
[0006] Optionally, calibrating each component of the engine includes: obtaining a target coefficient of each component; inputting the target coefficient into an engine simulation model for calibration to obtain a measurement value of each component.
[0007] Optionally, the components of the engine include: one or more of: a pressure drop element, a heat transfer element, an actuator element, and a cylinder parameter calibration.
[0008] Optionally, the training data are actual measurement values under steady-state and transient conditions, and the simulation model is trained based on the calibrated components and the training data, including: comparing and analyzing the actual measurement values under steady-state and transient conditions with the measurement values of each component obtained by calibration to obtain error values; adjusting the target coefficient of each component based on the error value until the error between the actual measurement values under steady-state and transient conditions and the measurement values calibrated by the engine simulation model is within a preset range, thereby obtaining a trained engine simulation model.
[0009] Optionally, before training the simulation model according to the calibrated components and training data, the method further includes: preprocessing the training data to determine discrete points and abnormal points in the training data; and removing the discrete points and abnormal points.
[0010] Optionally, after calibrating various components of the engine, the method includes: identifying a pulse effect existing in the engine simulation model; and correcting target parameters of the engine simulation model based on analysis results of the pulse effect.
[0011] The second aspect of the present application provides a device for constructing an engine simulation model, including: an acquisition module for acquiring a layout diagram of the engine; a calibration module for determining the overall layout of the engine, the positional relationship and the connection relationship of each component based on the layout diagram to construct a simulation model of the engine, and calibrate each component of the engine; a training module for training the simulation model based on the calibrated components and training data until a preset stop condition is met, thereby obtaining a trained engine simulation model.
[0012] Optionally, the calibration module is further used to obtain target coefficients of each component; the target coefficients are input into the engine simulation model for calibration to obtain measurement values of each component.
[0013] Optionally, the components of the engine include: one or more of: a pressure drop element, a heat transfer element, an actuator element, and a cylinder parameter calibration.
[0014] Optionally, the training data are actual measurement values under steady-state and transient conditions, and the training module is further used to compare and analyze the actual measurement values under steady-state and transient conditions and the measurement values of each component obtained by calibration to obtain error values; adjust the target coefficient of each component according to the error value until the error between the actual measurement values under steady-state and transient conditions and the measurement values calibrated by the engine simulation model is within a preset range, thereby obtaining a trained engine simulation model.
[0015] Optionally, the engine simulation model construction device also includes: a processing module, which is used to pre-process the training data to determine discrete points and abnormal points in the training data before training the simulation model according to the calibrated components and training data; and remove discrete points and abnormal points.
[0016] Optionally, the engine simulation model construction device further includes: a correction module, for identifying pulse effects existing in the engine simulation model after calibrating various components of the engine;
[0017] The target parameters of the engine simulation model are corrected based on the analysis results of the pulse effect.
[0018] The third aspect of the present application provides a server, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a method for constructing an engine simulation model as described in the above embodiment.
[0019] A fourth aspect of the present application provides a computer-readable storage medium having a computer program or instructions stored thereon. When the computer program or instructions are executed, they are used to implement the method for constructing an engine simulation model as described in the above embodiment.
[0020] The fifth aspect of the present application provides a computer program product, including: a computer program or instructions, which, when executed, implements the method for constructing an engine simulation model as described in the above embodiment.
[0021] Therefore, this application has at least the following beneficial effects:
[0022] The embodiment of the present application constructs a simulation model of the engine according to the overall layout of the engine, the positional relationship of each component, and the connection relationship. By calibrating each component of the engine to optimize the engine simulation model, the accuracy of the model can be significantly improved, the development cycle can be shortened, the cost can be reduced, and the high standards required by the virtual calibration platform can be met.
[0023] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:
[0025] Figure 1 A flowchart of a method for constructing an engine simulation model according to an embodiment of the present application;
[0026] Figure 2 An example diagram of the construction of a motivation simulation model provided according to an embodiment of the present application;
[0027] Figure 3 A block diagram of a device for constructing an engine simulation model according to an embodiment of the present application;
[0028] Figure 4 Schematic diagram of the structure of a server according to an embodiment of the present application. DETAILED DESCRIPTION
[0029] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.
[0030] The following describes the construction method, device, server, medium and product of the engine simulation model of the embodiment of the present application with reference to the accompanying drawings. In view of the problems mentioned in the above background technology, the present application provides a construction method of an engine simulation model, in which the simulation model of the engine is constructed according to the overall layout of the engine, the positional relationship and the connection relationship of each component, and the engine simulation model is optimized by calibrating each component of the engine, which can significantly improve the accuracy of the model, shorten the development cycle, reduce costs, and meet the high standards of the virtual calibration platform.
[0031] Specifically, Figure 1 A flow chart of a method for constructing an engine simulation model provided in an embodiment of the present application.
[0032] like Figure 1 As shown, the method for constructing the engine simulation model includes the following steps:
[0033] In step S101 , a layout diagram of the engine is acquired.
[0034] It is understandable that the layout diagram of the engine in the embodiment of the present application is the basis for constructing the simulation model. The layout diagram is the physical structure information of the engine, including but not limited to: the overall appearance and internal structure layout of the engine. The location of each component, such as cylinder, intake system, exhaust system, turbocharger, cooling system, lubrication system, combustion chamber, etc. The connection between components, including the connection relationship between pipes, valves, sensors and actuators, etc.
[0035] In step S102, the overall layout of the engine, the positional relationship and the connection relationship of each component are determined according to the layout diagram to construct an engine simulation model, and the various components of the engine are calibrated.
[0036] The embodiment of the present application can be based on the detailed layout diagram of the engine, including the overall layout of the engine, the positional relationship of each component and the connection method, etc. Next, collect the geometric parameters of the engine, which should include but are not limited to: cylinder form: such as inline, V-type, horizontally opposed, etc.; cylinder diameter and stroke: the diameter of the cylinder and the piston stroke; displacement: the total displacement of the engine; cylinder center distance: the distance between the centers of adjacent cylinders in a multi-cylinder engine; intake form: naturally aspirated or turbocharged, etc.; rated power and speed: the maximum output power and corresponding speed of the engine; net power and maximum torque: the engine output power and torque after considering all loads and accessories; emission technology route: such as EGR (Exhaust Gas Recirculation), DPF (Diesel Particulate Filter, particle filter), SCR (Selective Catalytic Reduction) and other emission control technologies. The parameters of each component of the engine are crucial to the construction of the simulation model. It is necessary to collect detailed parameters of the following components, such as combustion chamber: shape, volume, compression ratio, etc.; injection system: injector type, injection pressure, injection amount, etc.; intake and exhaust system: intake duct design, exhaust duct design, turbocharger parameters, etc.; cooling system: coolant flow path, radiator parameters, etc.; lubrication system: oil circuit design, oil pump parameters, etc.
[0037] In actual implementation, the embodiment of the present application can be used in simulation software (such as AVL CRUISE M) to preliminarily construct a simulation model of the engine by setting the spatial positions of various components and their mutual connections and inputting component parameters according to the information on the layout diagram.
[0038] In one embodiment of the present application, calibrating each component of the engine includes: obtaining a target coefficient of each component; inputting the target coefficient into an engine simulation model for calibration to obtain a measurement value of each component.
[0039] The engine components include: one or more of: pressure drop elements, heat transfer elements, actuator elements, and cylinder parameter calibration. The target coefficients refer to those parameters that affect the performance and behavior of the engine, such as flow coefficient, heat transfer coefficient, combustion efficiency, etc.
[0040] In the embodiment of the present application, various components of the engine are calibrated, as follows:
[0041] 1) Calibration of pressure drop element
[0042] Before starting the calibration of the pressure drop element, it is first necessary to define the parameters of each pressure drop element. These parameters include but are not limited to the geometric dimensions of the element, material properties, and expected working conditions. Set an initial flow coefficient for each pressure drop element. The flow coefficient is a dimensionless value that reflects the pressure loss when the fluid passes through the element. The initially set flow coefficient can be based on empirical values, similar engineering cases, or theoretical calculations. The embodiment of the present application can input the determined flow coefficient into the engine simulation model to obtain the calibration value of the pressure drop element.
[0043] 2) Calibration of heat transfer elements
[0044] Before calibration begins, key parameters of the heat transfer element need to be defined. These parameters generally include the material properties, geometric dimensions, surface characteristics, and properties of the working fluid of the element. Parameter definition should be based on the design specifications of the element and the actual working conditions. Set an initial heat transfer coefficient for the heat transfer element. The heat transfer coefficient is a parameter that characterizes the heat transfer capacity of the element, which can be obtained through theoretical calculations, empirical formulas, or reference data of similar elements. In the embodiment of the present application, the determined heat transfer coefficient can be input into the engine simulation model to obtain the calibration value of the heat transfer element.
[0045] 3) Calibration of actuator components
[0046] First, the key parameters of the actuator element can be defined. These parameters usually include the physical characteristics of the actuator (such as size, material), working principle (such as linear or nonlinear behavior), working range (such as maximum and minimum stroke), and control strategy. Set an initial flow coefficient and heat transfer coefficient for the actuator. These coefficients can be obtained through theoretical calculations, empirical formulas or reference data of similar actuators. In the embodiment of the present application, the determined flow coefficient and heat transfer coefficient can be input into the engine simulation model to obtain the calibration value of the actuator element.
[0047] 4) Calibration of cylinder parameters
[0048] The embodiment of the present application can also parametrically define the geometric parameters and material properties of the cylinder to achieve fine modeling of the core components of the engine, as follows: First, define the physical properties of the working medium (such as air, fuel) of the cylinder, including specific heat capacity, density, viscosity, etc. to set the combustion fuel type, combustion efficiency, emission characteristics, etc. And set boundary conditions according to actual working conditions, such as intake temperature, pressure, flow, etc., and set initial conditions, including initial temperature, pressure and fuel amount in the cylinder. Secondly, the embodiment of the present application can use the parametric design function of the simulation software to parameterize the cylinder to ensure that the engine model can be flexibly adjusted to adapt to different design variables, and define key parameters that affect the simulation results, such as injection timing, injection amount, ignition advance angle, etc.; Finally, adjust the key parameters according to the training data to improve the prediction accuracy of the model. In the actual execution process, the embodiment of the present application can optimize the cylinder model parameters by comparing with the actual vehicle test data until the model prediction is consistent with the actual data. The parameterized cylinder model is applied to the virtual calibration process to perform simulation analysis under different working conditions. The simulation results are used to formulate calibration strategies, such as adjusting the injection strategy and ignition timing, to achieve the optimization of emissions and performance.
[0049] Furthermore, after calibrating the components of the engine, the method includes: identifying the pulse effect existing in the engine simulation model; and correcting the target parameters of the engine simulation model based on the analysis results of the pulse effect.
[0050] It is understandable that in the engine simulation model, the pulse effect may be caused by a variety of factors, such as the dynamic response of the fuel injection system, the transient behavior of the turbocharger, and the feedback regulation of the control system. First, it is necessary to identify the pulse effect in the model through simulation testing and data analysis. The identified pulse effect is analyzed in depth to determine its source and scope of influence, including precise control of the fuel injection time, modeling of the dynamic characteristics of the turbocharger, and optimization of the control system response speed. According to the analysis results of the pulse effect, the relevant parameters in the engine model, such as the injector response time, the dynamic characteristics of the turbocharger, etc., are adjusted, and a series of tests and verifications are carried out to ensure the effectiveness of the compensation correction. In the actual implementation process, multiple iterations may be required to gradually optimize the compensation strategy. The embodiment of the present application can verify the effect of the compensation correction method by comparing the simulation results before and after compensation. Indicators such as total harmonic distortion rate are used to quantitatively evaluate the compensation effect.
[0051] In step S103, the engine simulation model is trained according to the calibrated components and training data until a preset stop condition is met, thereby obtaining a trained engine simulation model.
[0052] In one embodiment of the present application, a simulation model is trained based on the calibrated components and training data, including: comparing and analyzing the actual measured values under steady-state and transient conditions and the measured values of each component obtained by calibration to obtain an error value; adjusting the target coefficient of each component according to the error value until the error between the actual measured values under steady-state and transient conditions and the measured values calibrated by the engine simulation model is within a preset range, thereby obtaining a trained engine simulation model.
[0053] The training data may include actual measurements under steady-state and transient conditions. The actual measurements under steady-state tests may include: operating data under main injection and no EGR mode; operating data under conventional mode; operating data under DOC heating mode; operating data under DPF regeneration mode; operating data under SCR heating mode; and operating data under the regulatory cycle WHSC mode. The actual measurements under transient tests may include: operating data under the regulatory cycle WHTC (Worldwide harmonized Light vehicles Test Cycle); operating data under regulatory cycles similar to certification procedures such as RDE (Real Driving Emissions).
[0054] In order to accurately evaluate and optimize the emission performance of the engine, it is necessary to design tests for hydrocarbon, carbon monoxide, and black smoke emissions. This includes: Emission test conditions: determine the test temperature, pressure, oxygen concentration and other environmental conditions;
[0055] Emission testing methods: select appropriate testing equipment and methods, such as gas analyzers, particulate matter measuring equipment, etc.; Emission data recording: record emission data under different operating conditions, including emission levels under steady-state and transient conditions.
[0056] In the embodiment of the present application, the output of the simulation model under the same steady-state and transient conditions (i.e., the calibrated parameters such as pressure, temperature and flow of each component) is compared with the actual measured values to calculate the error value.
[0057] Analyze the error value to determine in which aspects the engine simulation model deviates from the actual situation. According to the error analysis results, adjust the target coefficients of related components, such as flow coefficient, heat transfer coefficient, etc., to reduce the error.
[0058] Repeat the above comparative analysis and parameter adjustment steps until the error values under steady-state and transient conditions are reduced to a preset acceptable range. In the actual implementation process, the embodiment of the present application can set an error threshold, and when the error between the model output and the actual measurement value is lower than this threshold, the model training is considered complete.
[0059] Furthermore, an independent validation dataset is used to test the trained model to ensure that the calibrated target coefficients can provide accurate simulation results under various working conditions. Part of the test data under steady-state and transient conditions in the validation dataset is not used in the training.
[0060] In one embodiment of the present application, before training the simulation model according to the calibrated components and training data, it also includes: preprocessing the training data to determine discrete points and abnormal points in the training data; removing discrete points and abnormal points.
[0061] Specifically, the embodiment of the present application can pre-process the training data to check whether the quality of the test data and the changing trend in the whole test process are reasonable, and firstly perform a quality check on the training data. This includes checking the integrity, consistency and whether there are obvious errors in the data. Statistical charts (such as box plots, histograms) can be used to identify outliers and discrete points in the data. Among them, the discrete points may be caused by measurement errors, equipment failures or other abnormal operating conditions. If they are not eliminated, the construction and calibration results of the simulation model may be misleading. The embodiment of the present application can use the following methods to eliminate discrete points: 1) Box plot analysis: identify and eliminate data points outside the box plot; 2) Standard deviation analysis: eliminate those points that exceed the mean ± 3 standard deviations; 3) Sequence analysis: check the data sequence and eliminate those points that do not match the trend.
[0062] Furthermore, the embodiment of the present application can remove abnormal points by checking the three-dimensional pulse spectrum of pressure, temperature and air supply ratio under different speeds and torques. If there are high gradient areas, it may indicate that the data is abnormal and these abnormal points need to be removed.
[0063] In addition, the embodiments of the present application can also ensure that the pressure after the air filter is less than the pressure before the air filter through pressure drop evaluation, and evaluate the pressure drop characteristics to eliminate unreasonable data points; check the rationality of the changes in intake and exhaust temperatures with operating conditions through temperature change rationality analysis, and eliminate data that does not meet expectations; eliminate unreasonable data points by verifying that the injection time is earlier than the ignition time, and the ignition time is earlier than the corresponding time of 50% of the heat release rate; analyze the heat release rate curve to ensure that it matches the injection strategy and the combustion process; analyze the trend of NOx emissions changing with the EGR rate through the relationship between emissions and EGR rates to ensure that it complies with the emission control strategy and the effects of post-treatment technology; and eliminate abnormal emission data points by comparing with the emission data of similar engines.
[0064] Combine the following Figure 2The method for constructing the engine simulation model of the embodiment of the present application is described in detail, including: data packet preparation (1), training data preprocessing (2), pressure drop element calibration (3), heat transfer element calibration (4), actuator calibration (5), cylinder parameterization calibration (6), other corrections (7), and accuracy verification (8), as follows:
[0065] Data package preparation (1), the data package contains engine layout, engine geometry parameters, engine component parameters, and test data. Engine geometry parameters include cylinder type, bore, stroke, displacement, cylinder center distance, intake type, rated power, rated speed, net power, maximum torque, emission technology route, etc. Test data include steady-state test data and transient test data. The steady-state test mainly includes main injection only and no EGR mode, conventional mode, DOC heating mode, DPF regeneration mode, SCR heating mode, regulatory cycle WHSC mode, etc.; transient test includes regulatory cycle WHTC and regulatory cycle similar to certification procedures such as RDE, etc. The test should also include test design for hydrocarbon, carbon monoxide and black smoke emissions.
[0066] Test data preprocessing (2) is used to check the quality of the test data and whether the change trend during the entire test process is reasonable. In the test process, it is inevitable that discrete data will appear, which will mislead the entire calibration process. Therefore, it is necessary to find and remove the discrete points in the test data through test preprocessing. To judge the rationality of the test data, first of all, we need to look at the three-dimensional pulse spectrum of pressure, temperature, air supply ratio, theoretical air-fuel ratio, etc. at different speeds and torques. If there is a high gradient, it is considered that there are abnormal values, and the abnormal test points need to be removed; secondly, we need to judge whether the pressure and temperature changes at the inlet and outlet are reasonable, such as the pressure after the air filter should be less than the pressure before the air filter, and the pressure drop characteristics need to be evaluated; in addition to the consistency of the three-dimensional characteristics, the combustion parameters also need to look at the rationality of time, such as the injection time should be earlier than the ignition time, and the ignition time should be earlier than the corresponding time of 50% heat release rate; finally, we need to judge whether the emission results are reasonable, such as the change of NOx emissions with EGR rate.
[0067] Pressure drop element calibration (3) is used to calibrate the flow coefficient of the modules that can bring pressure changes in the entire engine model. The modules that need to be calibrated include the air filter, intake manifold, exhaust manifold, and exhaust gas after-processor. The calibration process of the pressure drop element is to first define the parameters of the pressure drop element, then import the test data, and manually adjust the flow coefficient to find the corresponding flow coefficient when the test result is closest to the simulation result.
[0068] Heat transfer element calibration (4) is to calibrate the heat transfer coefficient of the modules that can bring about temperature changes in the entire engine model. The modules that need to be calibrated include the air filter, intake manifold, intercooler, exhaust manifold, and exhaust gas after-processor. The calibration process of the heat transfer element is to first define the parameters of the heat transfer element, then import the test data, and manually adjust the heat transfer coefficient to find the corresponding heat transfer coefficient when the test result is closest to the simulation result.
[0069] Actuator calibration (5) calibrates the flow coefficient and heat transfer coefficient of each actuator in the entire engine model for pressure drop and heat transfer. The modules that need to be calibrated include EGR valve and exhaust valve. The actuator calibration process is to first define the parameters of the actuator components, then import the test data, and manually adjust the flow coefficient to find the corresponding flow coefficient when the test result is closest to the simulation result.
[0070] Cylinder parametric calibration (6) parametrically defines the cylinder's geometric parameters (such as diameter, piston stroke, compression ratio, etc.) and material properties.
[0071] Other corrections (7) are used to compensate for pulse effects in the simulation.
[0072] Accuracy verification (8): steady-state test and transient test are carried out on the constructed engine simulation model, and the results are compared with the experimental results.
[0073] According to the method for constructing an engine simulation model proposed in the embodiment of the present application, the simulation model of the engine is constructed according to the overall layout of the engine, the positional relationship and the connection relationship of each component, and the engine simulation model is optimized by calibrating each component of the engine. This can significantly improve the accuracy of the model, shorten the development cycle, reduce costs, and meet the high standards of the virtual calibration platform.
[0074] Next, a device for constructing an engine simulation model according to an embodiment of the present application will be described with reference to the accompanying drawings.
[0075] Figure 3 It is a block diagram of a device for constructing an engine simulation model according to an embodiment of the present application.
[0076] like Figure 3 As shown, the engine simulation model construction device 10 includes: an acquisition module 100, a calibration module 200 and a training module 300.
[0077] Among them, the acquisition module 100 is used to obtain the layout diagram of the engine; the calibration module 200 is used to determine the overall layout of the engine, the position relationship and connection relationship of each component according to the layout diagram to construct a simulation model of the engine, and calibrate the various components of the engine; the training module 300 is used to train the engine simulation model according to the calibrated components and training data until the preset stop condition is met, and a trained engine simulation model is obtained.
[0078] In one embodiment of the present application, the calibration module 200 is further used to obtain target coefficients of each component; the target coefficients are input into the engine simulation model for calibration to obtain measurement values of each component.
[0079] In one embodiment of the present application, the components of the engine include: one or more of a pressure drop element, a heat transfer element, an actuator element, and a turbocharger.
[0080] In one embodiment of the present application, the training data are actual measurement values under steady-state and transient conditions, and the training module 300 is further used to compare and analyze the actual measurement values under steady-state and transient conditions and the measurement values of each component obtained by calibration to obtain an error value; adjust the target coefficient of each component according to the error value until the error between the actual measurement values under steady-state and transient conditions and the measurement values calibrated by the engine simulation model is within a preset range, thereby obtaining a trained engine simulation model.
[0081] In one embodiment of the present application, the engine simulation model construction device 10 also includes: a processing module, which is used to pre-process the training data to determine discrete points and abnormal points in the training data before training the simulation model according to the calibrated components and training data; and remove discrete points and abnormal points.
[0082] In one embodiment of the present application, the engine simulation model construction device 10 also includes: a correction module for identifying the pulse effect existing in the engine simulation model after calibrating the various components of the engine; and correcting the target parameters of the engine simulation model based on the analysis results of the pulse effect.
[0083] It should be noted that the above explanation of the embodiment of the method for constructing an engine simulation model is also applicable to the device for constructing an engine simulation model of this embodiment, and will not be repeated here.
[0084] According to the engine simulation model construction device proposed in the embodiment of the present application, the engine simulation model is constructed according to the overall layout of the engine, the positional relationship and the connection relationship of each component, and the engine simulation model is optimized by calibrating each component of the engine. This can significantly improve the accuracy of the model, shorten the development cycle, reduce costs, and meet the high standards of the virtual calibration platform.
[0085] Figure 4 A schematic diagram of the structure of a server provided in an embodiment of the present application. The server may include:
[0086] Memory 401 , processor 402 , and a computer program stored in the memory 401 and executable on the processor 402 .
[0087] When the processor 402 executes the program, the method for constructing the engine simulation model provided in the above embodiment is implemented.
[0088] Furthermore, the server also includes:
[0089] The communication interface 403 is used for communication between the memory 401 and the processor 402 .
[0090] The memory 401 is used to store computer programs that can be executed on the processor 402 .
[0091] The memory 401 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.
[0092] If the memory 401, the processor 402 and the communication interface 403 are implemented independently, the communication interface 403, the memory 401 and the processor 402 can be connected to each other through a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0093] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can communicate with each other through an internal interface.
[0094] The processor 402 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.
[0095] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for constructing an engine simulation model.
[0096] An embodiment of the present application also provides a computer-readable storage medium having a computer program or instructions stored thereon. When the computer program or instructions are executed, they are used to implement the above-mentioned method for constructing an engine simulation model.
[0097] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.
[0098] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.
[0099] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.
[0100] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array, a field programmable gate array, etc.
[0101] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.
[0102] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.
Claims
1. A method for constructing an engine simulation model, characterized in that: The following steps are involved: Get the layout diagram of the engine; Determine the overall layout of the engine, the positional relationship and the connection relationship of each component according to the layout diagram to construct the engine simulation model, and calibrate each component of the engine; The engine simulation model is trained according to the calibrated components and training data until a preset stop condition is met, thereby obtaining a trained engine simulation model.
2. The method for constructing an engine simulation model according to claim 1, characterized in that: The calibrating of the components of the engine includes: Obtaining target coefficients of each component; The target coefficients are input into the engine simulation model for calibration to obtain the measured values of the components.
3. The method for constructing an engine simulation model according to claim 1 or 2, characterized in that: The components of the engine include: one or more of a pressure drop element, a heat transfer element, an actuator element, and a cylinder parameter calibration.
4. The method for constructing an engine simulation model according to claim 2, characterized in that: The training data are actual measured values under steady-state and transient conditions. The engine simulation model is trained according to the calibrated components and the training data, including: Comparing and analyzing the actual measured values under the steady-state and transient conditions with the measured values of each component obtained by calibration to obtain error values; The target coefficients of the components are adjusted according to the error values until the errors between the actual measured values under the steady-state and transient conditions and the measured values calibrated by the engine simulation model are within a preset range, thereby obtaining a trained engine simulation model.
5. The method for constructing an engine simulation model according to claim 1, characterized in that: Before training the engine simulation model according to the calibrated components and training data, the method further includes: Preprocessing the training data to determine discrete points and abnormal points in the training data; The discrete points and the abnormal points are removed.
6. The method for constructing an engine simulation model according to claim 1, characterized in that: After calibrating the various components of the engine, including: identifying pulse effects present in the engine simulation model; The target parameters of the engine simulation model are corrected based on the analysis results of the pulse effect.
7. A device for constructing an engine simulation model, characterized in that: include: An acquisition module, used for acquiring a layout diagram of an engine; A calibration module, used to determine the overall layout of the engine, the positional relationship and the connection relationship of each component according to the layout diagram, to construct a simulation model of the engine, and to calibrate each component of the engine; The training module is used to train the engine simulation model according to the calibrated components and training data until a preset stop condition is met, thereby obtaining a trained engine simulation model.
8. A server, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for constructing an engine simulation model as described in any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed, the method for constructing an engine simulation model according to any one of claims 1 to 6 is implemented.
10. A computer program product comprising: A computer program or instruction, characterized in that, when the computer program or instruction is executed, it implements the method for constructing an engine simulation model as described in any one of claims 1-6.
