Method and device for constructing numerical virtual model of engine compartment and storage medium

Abstract

The application discloses a method for constructing a numerical virtual model of an engine compartment, an intelligent temperature control device for the engine compartment, a simulation system and a storage medium. The method comprises the following steps: obtaining the structure and thermal physical parameters of the engine compartment, and establishing a three-dimensional fluid simulation model and a one-dimensional thermal fluid simulation model respectively; coupling the two models, so that the air flow output by the three-dimensional model flowing through the radiator and the intercooler is automatically transmitted to the one-dimensional model as input; in a joint simulation environment, taking the fan speed as an optimization variable, automatically performing simulation calculation on multiple groups of preset working conditions, and outputting simulation results including at least the temperature in the compartment; screening the working conditions with the temperature in the safe range, inputting the parameter subset and the corresponding fan speed to form a training sample set; training a machine learning model based on the sample set to obtain a numerical model for temperature control, and the model can directly output a fan speed recommendation value according to the real-time input vehicle speed, ambient temperature and thermal load.

Description

Technical Field

[0001] This application relates to the field of engine compartment thermal management technology, specifically to a method for constructing a numerical virtual model of an engine compartment, an intelligent temperature control device for an engine compartment, a simulation system, and a storage medium. Background Technology

[0002] As automotive performance improves and designs become increasingly compact, the thermal load on the engine compartment increases significantly while heat dissipation space becomes increasingly limited, placing higher demands on precise thermal management. Currently, the commonly used one-dimensional system simulations or empirical models have a fundamental flaw: they cannot accurately depict the difference in actual airflow between the radiator and intercooler. This neglected airflow dissipation leads to discrepancies between simulation predictions and actual operating conditions, creating a dilemma for temperature control strategies based on such models: a conservative overcooling approach results in energy waste; while insufficient cooling in pursuit of efficiency may lead to localized overheating risks. Neither approach allows for precise and efficient temperature control while ensuring safety.

[0003] Therefore, there is an urgent need for a technology that can automatically and structurally integrate multi-scale heat flow characteristics to establish an engine compartment temperature prediction model with both high accuracy and real-time response capabilities, thereby providing a reliable technical foundation for the realization of intelligent temperature control systems. Summary of the Invention

[0004] The purpose of this application is to provide a method for constructing a numerical virtual model of an engine compartment, an intelligent temperature control device for an engine compartment, a simulation system, and a storage medium, in order to solve the problem in the prior art that the temperature control strategy is not effective because it cannot accurately represent the actual flow difference between the radiator and the intercooler.

[0005] To achieve the above objectives, the first aspect of this application provides a method for constructing a numerical virtual model of an engine compartment, comprising: Obtain the structural and thermophysical parameters of the engine compartment; A three-dimensional fluid simulation model of the engine compartment was established based on structural parameters, and a one-dimensional thermofluid simulation model of the engine compartment was established based on thermophysical parameters. The three-dimensional fluid simulation model is coupled with the one-dimensional thermal fluid simulation model so that the air flow rate through the radiator and intercooler output by the three-dimensional fluid simulation model is automatically transmitted to the one-dimensional thermal fluid simulation model as an input parameter. In the joint simulation environment of the engine compartment, the fan speed is used as the optimization variable to automatically perform simulation calculations on multiple sets of preset operating condition data to obtain the simulation output corresponding to each set of operating condition data. The simulation output includes at least the air temperature in the engine compartment. Each set of operating condition data includes at least vehicle speed, ambient temperature, engine thermal load and fan speed. The simulation output is used to select simulation conditions in which the air temperature inside the engine compartment is within a preset safe temperature range. The subset of input parameters for each selected simulation condition and its corresponding fan speed are used to form a valid training sample. The model training dataset is constructed based on all the valid training samples. The subset of input parameters includes at least vehicle speed, ambient temperature and engine thermal load. The machine learning model is trained using the model training dataset to obtain a numerical model for engine compartment temperature control. The numerical model is used to directly output the corresponding recommended fan speed value based on the real-time input vehicle speed, ambient temperature and engine thermal load.

[0006] In this embodiment, a three-dimensional fluid simulation model is coupled with a one-dimensional thermal fluid simulation model so that the airflow rate through the radiator and intercooler output by the three-dimensional fluid simulation model is automatically transmitted to the one-dimensional thermal fluid simulation model as an input parameter. This includes: integrating the three-dimensional fluid simulation model and the one-dimensional thermal fluid simulation model through a parameter optimization platform so that the parameter optimization platform can automatically schedule the three-dimensional fluid simulation model to perform calculations and transmit the airflow rate through the radiator and intercooler output by the three-dimensional fluid simulation model as an input parameter to the one-dimensional thermal fluid simulation model.

[0007] In this embodiment, in the co-simulation environment of the engine compartment, the fan speed is used as the optimization variable, and multiple sets of preset operating condition data are automatically simulated to obtain the simulation output corresponding to each set of operating condition data. The simulation output includes at least the air temperature inside the engine compartment, including: defining an objective function and constraints in the parameter optimization platform, wherein the objective function is to make the air temperature inside the engine compartment output by the one-dimensional thermofluid simulation model within a preset safe temperature range, and the constraints include at least the physical upper and lower limits of the fan speed; according to the objective function and constraints, the fan speed is automatically adjusted as the input variable, and the three-dimensional fluid simulation model and the one-dimensional thermofluid simulation model are coupled and calculated in a loop until the simulation result that satisfies the objective function is obtained.

[0008] In this embodiment, simulation conditions where the air temperature inside the engine compartment is within a preset safe temperature range are selected from the simulation output. The subset of input parameters for each selected simulation condition and its corresponding fan speed constitute a valid training sample. A model training dataset is constructed based on all valid training samples, including: establishing a mapping relationship between the subset of input parameters corresponding to the simulation conditions that meet the preset safe temperature requirements and the corresponding fan speed to form a model training dataset; wherein, the fan speed is an optimized value that keeps the air temperature inside the engine compartment within a safe range.

[0009] In this embodiment, a machine learning model is trained using a model training dataset to obtain a numerical model for engine compartment temperature control. The numerical model is used to directly output a recommended value for the corresponding fan speed based on the real-time input vehicle speed, ambient temperature, and engine thermal load. This includes: dividing the model training dataset into a training set and a validation set; using the training set to iteratively train the initial machine learning model, and using the validation set to verify and optimize the model performance during the training process; and deploying the trained machine learning model as a numerical model for engine compartment temperature control if it meets the preset accuracy requirements. The numerical model is configured to receive real-time monitored or estimated vehicle speed, ambient temperature, and engine thermal load as input, and output a corresponding fan speed setpoint, which is used to guide or control the real-time operation of the engine compartment cooling fan.

[0010] In this embodiment of the application, the method further includes: comparing and verifying the air temperature inside the engine compartment obtained by simulation calculation with the experimental results; and correcting the three-dimensional fluid simulation model and the one-dimensional thermal fluid simulation model based on the results of the comparison and verification.

[0011] A second aspect of this application provides an intelligent temperature control device for an engine compartment, the device comprising: The memory is configured to store instructions; and The processor is configured to execute a method for constructing a numerical virtual model of the engine compartment according to any of the above.

[0012] In this embodiment of the application, the device further includes an early warning module, wherein the early warning module is configured to: receive engine compartment temperature monitoring data; and, based on the numerical model and the temperature monitoring data, issue an early warning when the calculated fan speed has reached its limit and the engine compartment temperature still cannot be maintained within a safe range.

[0013] A third aspect of this application provides an intelligent engine compartment temperature control simulation system, comprising: Engine compartment; Cooling fan, installed in the engine compartment; The aforementioned intelligent temperature control device for the engine compartment is installed inside the engine compartment to control the speed of the cooling fan in order to regulate the temperature of the engine compartment.

[0014] A fourth aspect of this application provides a machine-readable storage medium storing instructions for causing a machine to execute a method for constructing a numerical virtual model of an engine compartment according to any one of the preceding claims.

[0015] The above technical solution enables the construction of a numerical model for engine compartment temperature control that combines high precision and real-time response. This model accurately depicts the actual flow difference between the radiator and the intercooler by coupling three-dimensional fluid simulation and one-dimensional thermal simulation. Furthermore, it utilizes machine learning methods to extract lightweight real-time mapping relationships from multi-condition simulation data, thereby providing accurate and efficient recommended fan speed values ​​for engine compartment temperature control. This achieves precise and energy-saving control while ensuring safety.

[0016] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0017] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings: Figure 1 The illustration shows a flowchart of a method for constructing a numerical virtual model of an engine compartment according to an embodiment of this application; Figure 2 A schematic diagram of a numerical virtual model of an engine compartment according to an embodiment of this application is shown. Figure 3 This illustration schematically shows a working diagram of an intelligent temperature control system for an engine compartment according to an embodiment of this application; Figure 4 This illustration schematically shows a flow chart of an engine nacelle fan control module according to an embodiment of this application; Figure 5 This illustration schematically shows a process diagram of an intelligent early warning module for an engine compartment according to an embodiment of this application; Figure 6 The diagram illustrates the internal structure of a computer device according to an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0019] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application all comply with relevant laws and regulations. In the embodiments of this application, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this application, and do not imply that the applicant has already used or necessarily used such solutions.

[0020] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0021] Figure 1 The illustration schematically shows a flowchart of a method for constructing a numerical virtual model of an engine compartment according to an embodiment of this application. Figure 1 As shown, it includes the following steps: Step 101: Obtain the structural and thermophysical parameters of the engine compartment.

[0022] Step 102: Establish a three-dimensional fluid simulation model of the engine compartment based on structural parameters, and establish a one-dimensional thermofluid simulation model of the engine compartment based on thermophysical parameters.

[0023] In one embodiment, design data and material property database of the engine compartment are obtained, and structural parameters are extracted from them, including the geometric dimensions, spatial relative positions, assembly relationships of key components such as radiators, intercoolers, fans, and fairings, as well as the overall envelope shape of the engine compartment, and thermophysical parameters, wherein the thermophysical parameters include the density, specific heat capacity, thermal conductivity, surface emissivity, etc. of the aforementioned components and compartment materials.

[0024] First, based on structural parameters, the system uses 3D modeling software to construct a 3D geometric model of the air domain inside and outside the engine compartment. This model requires special handling of rotating components such as the fan region as a rotating fluid domain, and simplifies porous media components such as the radiator and intercooler into porous media regions with corresponding flow resistance and thermal resistance characteristics. This 3D geometric model is then imported into computational fluid dynamics (CFD) software for mesh discretization, boundary condition setting, and turbulence model selection, thereby establishing a 3D fluid simulation model. The core objective of this model is to accurately calculate the 3D distribution of the flow field at a given vehicle speed and initial fan speed, and critically output the airflow rates through the radiator and intercooler.

[0025] Simultaneously, based on thermophysical parameters, the system establishes a one-dimensional thermofluid simulation model of the engine compartment in a one-dimensional system simulation software. This model abstracts the engine compartment as a network composed of nodes such as heat sources, radiators, intercoolers, fans, connecting pipes, and the environment. Each node and connection is assigned characteristic parameters such as heat capacity, thermal resistance, and flow resistance derived from thermophysical parameters. This model is used to quickly solve the equilibrium state of the entire heat flow network under different boundary conditions. Its core inputs include vehicle speed, ambient temperature, engine heat load, and airflow rates through the radiator and intercooler provided by the three-dimensional model. The core output is the predicted air temperature at key monitoring points within the engine compartment.

[0026] This step constructs two complementary simulation models, one adept at describing detailed flow in three-dimensional space and the other at rapid thermal equilibrium at the system level, providing a foundation for subsequent coupling and data generation.

[0027] In one embodiment, the method further includes: comparing and verifying the simulated air temperature inside the engine compartment with the experimental results; and the system correcting the three-dimensional fluid simulation model and the one-dimensional thermal fluid simulation model based on the results of the comparison and verification.

[0028] In one embodiment, bench or vehicle tests are conducted to obtain measured data on engine compartment temperature under key operating conditions. The simulation results are compared with the experimental results, and the model parameters are corrected based on the deviations until the model accuracy meets the requirements.

[0029] Step 103: Couple the three-dimensional fluid simulation model with the one-dimensional thermal fluid simulation model so that the air flow rate through the radiator and intercooler output by the three-dimensional fluid simulation model is automatically transmitted to the one-dimensional thermal fluid simulation model as an input parameter.

[0030] Because the radiator and intercooler exhibit uneven flow distribution and leakage in the actual flow field, using a uniform default flow rate value in the one-dimensional model can lead to deviations in the heat balance calculation. To address this issue, this application integrates the two models.

[0031] In one embodiment, a three-dimensional fluid simulation model is coupled with a one-dimensional thermal fluid simulation model so that the airflow rate through the radiator and intercooler output by the three-dimensional fluid simulation model is automatically passed to the one-dimensional thermal fluid simulation model as an input parameter. This includes: the system integrates the three-dimensional fluid simulation model and the one-dimensional thermal fluid simulation model through a parameter optimization platform so that the parameter optimization platform can automatically schedule the three-dimensional fluid simulation model to perform calculations and pass the airflow rate through the radiator and intercooler output by the three-dimensional fluid simulation model as an input parameter to the one-dimensional thermal fluid simulation model.

[0032] In this embodiment, in the co-simulation environment of the engine compartment, the fan speed is used as the optimization variable, and multiple sets of preset operating condition data are automatically simulated to obtain the simulation output corresponding to each set of operating condition data. The simulation output includes at least the air temperature inside the engine compartment, including: defining an objective function and constraints in the parameter optimization platform, wherein the objective function is to make the air temperature inside the engine compartment output by the one-dimensional thermofluid simulation model within a preset safe temperature range, and the constraints include at least the physical upper and lower limits of the fan speed; according to the objective function and constraints, the fan speed is automatically adjusted as the input variable, and the three-dimensional fluid simulation model and the one-dimensional thermofluid simulation model are coupled and calculated in a loop until the simulation result that satisfies the objective function is obtained.

[0033] In one embodiment, the system integrates and encapsulates a 3D fluid simulation model and a 1D thermal fluid simulation model through a parameter optimization platform. This platform reads and identifies the input and output interfaces of the two models, constructing an automated data transfer link and execution flow. This automated coupled simulation flow is configured to perform the following operations sequentially: When the flow is invoked, the parameter optimization platform first drives the 3D fluid simulation model to perform calculations based on preset input conditions, including the current vehicle speed, ambient temperature, and fan speed. After the 3D simulation is completed, the platform automatically parses and extracts key result data from its output file, namely the airflow rate through the radiator and the airflow rate through the intercooler. Subsequently, the platform automatically uses the airflow rate as an input parameter, assigns a value, and drives the 1D thermal fluid simulation model to perform a new round of thermal balance calculations, thereby achieving automated and accurate data transfer and coupled simulation from the 3D model to the 1D model.

[0034] Within this integrated framework, to generate sample data for training the real-time control model, the parameter optimization platform is further configured to perform multi-condition optimization tasks. Specifically, in the co-simulation environment of the engine compartment, using fan speed as the optimization variable, multiple sets of preset operating condition data are automatically simulated and calculated. Each set of operating condition data includes at least vehicle speed, ambient temperature, and engine thermal load, i.e., engine heat source temperature. The optimization process includes: (1) Define the objective function and constraints in the parameter optimization platform. The objective function is to ensure that the air temperature inside the engine compartment output by the one-dimensional thermal fluid simulation model is within the preset safe temperature range; the constraints include at least the physical feasible upper and lower limits of the fan speed.

[0035] (2) The parameter optimization platform initiates an automated optimization process based on the objective function and constraints. The platform automatically generates a series of candidate values ​​for the fan speed using its integrated optimization algorithm and repeatedly executes the aforementioned automated coupled simulation process. Each iteration generates a corresponding result for the air temperature inside the engine compartment.

[0036] (3) In each iteration, the platform adjusts the candidate values ​​of the fan speed based on the evaluation of the temperature results. This iterative process continues until a fan speed value that keeps the air temperature in the engine compartment within a safe range is found, or a preset iteration upper limit is reached. At the end of the optimization, the platform outputs all operating condition data that satisfy the objective function and their corresponding complete simulation results.

[0037] This step not only establishes a precise coupling between the three-dimensional and one-dimensional models, but also constructs an intelligent co-simulation environment that can be used for automatic optimization, laying the foundation for the rapid prediction and control of engine compartment temperature in the future.

[0038] Step 104: In the joint simulation environment of the engine compartment, with the fan speed as the optimization variable, automatically perform simulation calculations on multiple sets of preset operating condition data to obtain the simulation output corresponding to each set of operating condition data. The simulation output includes at least the air temperature in the engine compartment. Each set of operating condition data includes at least vehicle speed, ambient temperature, engine thermal load, and fan speed.

[0039] In one embodiment, the system receives the optimization results output in step 103. The optimization results include multiple sets of simulation records, each set of records including at least the operating condition input parameters, including vehicle speed, ambient temperature, engine thermal load, and the optimized fan speed that can achieve the temperature target; simulation intermediate variables, including the air flow rate through the radiator and the air flow rate through the intercooler; and the final simulation output, namely the air temperature in the engine compartment.

[0040] The system extracts operating conditions (vehicle speed, ambient temperature, engine thermal load) and corresponding optimized fan speeds from these records, forming a mapping sample of (operating conditions, recommended fan speed). All optimization results are processed in this way to construct the model training dataset. Each sample in this dataset represents the optimal or feasible fan speed recommended to maintain a safe engine compartment temperature under specific external conditions.

[0041] Step 105: Select simulation conditions from the simulation output where the air temperature inside the engine compartment is within a preset safe temperature range, and construct a valid training sample by taking the subset of input parameters for each selected simulation condition and its corresponding fan speed, and build a model training dataset based on all valid training samples; the subset of input parameters includes at least vehicle speed, ambient temperature and engine thermal load.

[0042] In one embodiment, the system filters out simulation conditions where the air temperature inside the engine compartment is within a preset safe temperature range from the simulation output, and uses a subset of input parameters for each selected simulation condition and its corresponding fan speed to form a valid training sample. Based on all the valid training samples, the system constructs a model training dataset, including: establishing a mapping relationship between the subset of input parameters corresponding to the simulation conditions that meet the preset safe temperature requirements and the corresponding fan speed to form a model training dataset; wherein, the fan speed is the optimized value for maintaining the air temperature inside the engine compartment within a safe range.

[0043] In one embodiment, the system processes the simulation dataset output in step 104. The dataset contains multiple records, each of which includes at least: operating condition input parameters (vehicle speed, ambient temperature, engine thermal load, fan speed) and the corresponding air temperature inside the engine compartment.

[0044] The system first filters records from the dataset where the engine compartment air temperature is greater than or equal to a preset minimum temperature limit and less than or equal to a preset maximum temperature limit, based on a preset safe range for engine compartment air temperature. These records are considered valid operating conditions, indicating that under these conditions, the corresponding fan speed can maintain the compartment temperature at a safe level. For each selected valid operating condition record, the system extracts a subset of its input parameters as feature inputs to the model. This subset includes at least vehicle speed, ambient temperature, and engine thermal load. Simultaneously, the fan speed from this record is extracted as the model's label output.

[0045] All valid operating conditions were processed in the manner described above, and a one-to-one mapping was established between (vehicle speed, ambient temperature, engine thermal load) and fan speed, thus constructing the model training dataset. This dataset constitutes a set of mapping relationships from real-time operating conditions to recommended fan speeds, providing direct and high-quality supervised learning samples for the next step of training the machine learning model.

[0046] In another embodiment, the fan speed is the optimal fan speed obtained through the optimization process in step 103, which keeps the air temperature inside the engine compartment within a safe range. The model trained on this dataset will possess optimal energy-saving characteristics.

[0047] Step 106: Train the machine learning model using the model training dataset to obtain a numerical model for engine compartment temperature control. The numerical model is used to directly output the corresponding recommended fan speed value based on the real-time input vehicle speed, ambient temperature and engine thermal load.

[0048] In one embodiment, a machine learning model is trained using a model training dataset to obtain a numerical model for engine compartment temperature control. The numerical model is used to directly output a recommended value for the corresponding fan speed based on real-time input vehicle speed, ambient temperature, and engine thermal load. This includes: dividing the model training dataset into a training set and a validation set; iteratively training the initial machine learning model using the training set and validating and optimizing the model performance during training using the validation set; and deploying the trained machine learning model as a numerical model for engine compartment temperature control if the preset accuracy requirements are met. The numerical model is configured to receive real-time monitored or estimated vehicle speed, ambient temperature, and engine thermal load as input and output a corresponding fan speed setpoint, which is used to guide or control the real-time operation of the engine compartment cooling fan.

[0049] In one embodiment, the model training dataset constructed in step 105 is randomly divided into a training subset and a validation subset according to a preset ratio. The training subset is used for model learning, and the validation subset is used for evaluating and adjusting the model.

[0050] The system uses a training subset to iteratively train an initial machine learning model. During training, the model learns a complex nonlinear mapping relationship between input features and output labels. Simultaneously, a validation subset is periodically used to evaluate the model's performance during training, and model parameters are optimized and adjusted based on the evaluation results. This includes updating model weights using gradient descent or adjusting model hyperparameters such as the learning rate and the number of network layers to prevent overfitting and improve generalization ability.

[0051] When the trained machine learning model reaches the preset performance accuracy requirements on the validation set—for example, when the prediction error falls below a certain threshold—training stops, and its final parameters and structure are solidified and deployed as a numerical model for engine compartment temperature control. This deployed model is integrated into the software or hardware controller of the engine compartment intelligent temperature control system. In actual operation, the numerical model is configured to receive real-time vehicle speed, ambient temperature, and engine thermal load estimates from vehicle real-time bus data (CAN), environmental sensors, and the engine control unit (ECU) as inputs. Based on the learned mapping relationship, it directly outputs a corresponding recommended fan speed value in milliseconds. This recommended value can be directly sent as a setpoint to the fan inverter or controller, thereby achieving real-time, accurate, and energy-saving closed-loop control of the engine compartment cooling fan.

[0052] This application overcomes the thermal balance errors caused by the uniform simplification of flow rates in traditional methods by accurately obtaining the differential flow rates between the radiator and intercooler through 3D fluid simulation and using it as input for 1D thermal fluid simulation, thus significantly improving the overall accuracy of the system model. Based on this, using fan speed as the optimization variable, coupled simulation and operating condition optimization are automatically executed in the parameter optimization platform to generate batch datasets of optimal fan speeds and real-time operating conditions that meet the engine compartment temperature safety constraints. This method enables the engine compartment temperature control system to dynamically track and apply the most energy-efficient fan speed while ensuring the safety of the compartment temperature, significantly improving the real-time performance, stability, and energy efficiency of temperature control, and providing an efficient and reliable solution for the thermal safety and energy efficiency management of vehicle engine compartments.

[0053] It should be noted that the numerical virtual model construction method and intelligent temperature control system for engine compartments proposed in this application are not only applicable to engine compartments of various vehicles, but can also be extended to other enclosed or semi-enclosed equipment compartments with similar heat dissipation structures and temperature control requirements, such as generator compartments and ship engine compartments.

[0054] In one embodiment, firstly, a 3D modeling software (including UG, SolidWorks, Catia, Pro-e, etc.) is used, taking UG modeling as an example, to establish a fluid model of the engine compartment. This fluid model includes the rotational domain of the fan entity (excluding the radiator entity), the porous medium fluid domain of the radiator and intercooler, the fluid domain inside the engine compartment, and the large-area fluid domain outside the engine compartment, and is converted into an exportable standard format file (such as the fadongjicangliutiyu.stp file).

[0055] Import the engine compartment fluid domain model into fluid simulation software (including StarCCM+, Fluent, StarCD, FIDAP, STREAM, Shipflow, or XFLow). Here, Fluent is used as an example. Mesh generation and boundary conditions are set, including vehicle speed V1 and rotating fan speed V2. The calculation and post-processing are then performed to extract the airflow rates in the porous media regions of the radiator and intercooler, denoted as Q. 散 With Q 中 .

[0056] To automate the simulation process, the mesh generation, boundary condition setting, and solution calculation processes of the Fluent fluid simulation model were written as preprocessing and solution scripts, and the Q-factor extraction was performed during post-processing. 散 With Q 中 The process is written into a post-processing script, thereby realizing automated calculation and result output of three-dimensional fluid simulation.

[0057] Next, one-dimensional thermal fluid simulation software (including KULI, Amesim, Dymola, Flownex, etc.) is used. Here, KULI is taken as an example to build a one-dimensional thermal balance model of the engine compartment. This model includes components such as radiator, intercooler, and fan. Initial condition parameters are set, including inlet air temperature T1, vehicle speed V1, fan speed V2, engine heat source temperature T2, and radiator airflow Q obtained from the three-dimensional simulation. 散 and intercooler airflow Q 中 The engine compartment air temperature T3 was extracted through simulation calculation and post-processing.

[0058] To improve the efficiency of one-dimensional simulation, the model building, initialization parameter setting, and simulation calculation process in KULI simulation are scripted, and the post-processing process of extracting T3 is also scripted, thereby realizing the automated calculation and result output of one-dimensional thermofluid simulation.

[0059] To improve model confidence, the airflow rate Q output from the 3D simulation will be... 散 Q 中 The engine compartment air temperature T3 output by the one-dimensional simulation was compared and verified with the experimental test results. Based on the comparison results, the parameters of the three-dimensional fluid simulation model and the one-dimensional thermal fluid model were corrected to improve the model prediction accuracy.

[0060] To achieve collaboration and optimization of multi-level simulations, parameter optimization tools (including multidisciplinary simulation software or self-developed optimization programs) are used. Here, Isight software is used as an example to realize data transmission and automated coupling calculation between Fluent 3D fluid simulation and KULI 1D thermofluid simulation.

[0061] The specific process of Isight simulation data transmission is as follows: Fluent 3D fluid simulation uses vehicle speed V1 and rotary fan speed V2 as variable input parameters, and outputs radiator airflow Q. 散 and intercooler airflow Q 中 The Isight platform will Q 散 With Q 中 As input parameters, they are passed to KULI one-dimensional thermal equilibrium simulation, such as Figure 2 As shown.

[0062] Isight Automated Calculation: This function utilizes Isight's file parser and variable designer to modify boundary conditions for Fluent 3D fluid simulation and KULI 1D thermal fluid simulation. Fluent 3D fluid simulation uses vehicle speed V1 and rotating fan speed V2[] (a set of fan speeds) as variable parameters for preprocessing data input and outputs the radiator airflow rate Q after post-processing. 散 With intercooler airflow Q 中KULI one-dimensional simulation uses vehicle speed V1, fan speed V2, ambient temperature T1, engine heat source temperature T2, and Fluent output Q. 散 With Q 中 The system automatically completes preprocessing input, simulation calculation, and post-processing output, taking the engine compartment temperature T3 as the variable. The system uses the engine compartment temperature safety requirement T3∈[Tmin, Tmax] as the objective function, where Tmin and Tmax are the minimum and maximum extreme temperatures of the engine compartment air, respectively.

[0063] Through data transfer and automated simulation loops in the parameter optimization platform, all design variable combinations that satisfy the above objective function are output.

[0064] Based on the design variables (V1, V2, T1, T2) and output result T3 simulated by the parameter optimization platform, a numerical model library is established. The mapping function relationship between input and output is trained through machine learning and other methods to achieve real-time response from design variables to output results.

[0065] Ultimately, the parameter optimization platform can quickly calculate and output all operating condition combinations that satisfy the objective function. With V1, T1, and T2 as fixed inputs, the system searches for the minimum fan speed V that satisfies the objective function. 2min This refers to the most energy-efficient wind speed for controlling engine compartment temperature.

[0066] The engine compartment intelligent temperature control system is further integrated with external data acquisition equipment (including temperature and wind speed measuring instruments, electromagnetic sensors, infrared temperature measuring instruments, etc.) and linked with a numerical virtual model to achieve real-time data acquisition, transmission, and temperature control decision output, such as... Figure 3 As shown.

[0067] The fan control module calculates the optimal fan speed based on a numerical virtual model and adjusts the fan frequency converter to achieve precise regulation of the fan speed, such as... Figure 4 As shown.

[0068] The intelligent early warning module, based on the prediction results of the numerical virtual model, triggers an early warning when the engine compartment temperature cannot meet the objective function by adjusting the fan speed, i.e., T3 ≥ Tmax or T3 ≤ Tmin. Figure 5 As shown.

[0069] In one embodiment, an intelligent temperature control device for an engine compartment is provided, the device comprising: The memory is configured to store instructions; and The processor is configured to execute any of the above methods for constructing a numerical virtual model of the engine compartment.

[0070] In this embodiment of the application, the device further includes an early warning module, wherein the early warning module is configured to: receive engine compartment temperature monitoring data; and, based on the numerical model and the temperature monitoring data, issue an early warning when the calculated fan speed has reached its limit and the engine compartment temperature still cannot be maintained within a safe range.

[0071] In one embodiment, an intelligent temperature control simulation system for an engine compartment is provided, comprising: an engine compartment; a cooling fan installed in the engine compartment; and an intelligent temperature control device for the engine compartment, installed in the engine compartment, for controlling the speed of the cooling fan to regulate the temperature of the engine compartment.

[0072] This application also provides a machine-readable storage medium storing instructions that cause a machine to execute the above-described method for constructing a numerical virtual model of an engine compartment.

[0073] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor A01, a network interface A02, a memory (not shown), and a database (not shown) connected via a robot bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02, and a database (not shown). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A04. The database stores various types of data required for constructing and driving the intelligent temperature control system for the engine compartment. The network interface A02 communicates with external terminals via a network connection. When the computer program B02 is executed by the processor A01, it implements a method for constructing a numerical virtual model of the engine compartment.

[0074] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0075] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0076] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0077] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0078] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0079] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0080] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0081] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0082] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0083] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method of constructing a numerical virtual model of an engine compartment, characterized in that, include: Obtain the structural and thermophysical parameters of the engine compartment; A three-dimensional fluid simulation model of the engine compartment is established based on the structural parameters, and a one-dimensional thermofluid simulation model of the engine compartment is established based on the thermophysical parameters. The three-dimensional fluid simulation model is coupled with the one-dimensional thermal fluid simulation model so that the air flow rate through the radiator and intercooler output by the three-dimensional fluid simulation model is automatically transmitted to the one-dimensional thermal fluid simulation model as an input parameter. In the joint simulation environment of the engine compartment, the fan speed is used as the optimization variable to automatically perform simulation calculations on multiple sets of preset operating condition data to obtain the simulation output corresponding to each set of operating condition data. The simulation output includes at least the air temperature in the engine compartment. Each set of operating condition data includes at least vehicle speed, ambient temperature, engine thermal load and fan speed. The simulation output is used to select simulation conditions in which the air temperature inside the engine compartment is within a preset safe temperature range. The subset of input parameters for each selected simulation condition and its corresponding fan speed are used to form a valid training sample. The model training dataset is constructed based on all the valid training samples. The subset of input parameters includes at least vehicle speed, ambient temperature and engine thermal load. The machine learning model is trained using the model training dataset to obtain a numerical model for engine compartment temperature control. The numerical model is used to directly output the corresponding recommended fan speed value based on the real-time input vehicle speed, ambient temperature and engine thermal load.

2. The method of claim 1, wherein, The coupling of the three-dimensional fluid simulation model with the one-dimensional thermal fluid simulation model, so that the airflow rate through the radiator and intercooler output by the three-dimensional fluid simulation model is automatically transmitted as an input parameter to the one-dimensional thermal fluid simulation model, includes: The three-dimensional fluid simulation model is integrated with the one-dimensional thermal fluid simulation model through a parameter optimization platform, so that the parameter optimization platform can automatically schedule the three-dimensional fluid simulation model to perform calculations and pass the air flow rate through the radiator and intercooler as input parameters to the one-dimensional thermal fluid simulation model.

3. The method for constructing a numerical virtual model of an engine compartment according to claim 2, characterized in that, In the joint simulation environment of the engine compartment, the fan speed is used as the optimization variable to automatically perform simulation calculations on multiple sets of preset operating condition data, and the simulation output corresponding to each set of operating condition data is obtained. The simulation output includes at least the air temperature inside the engine compartment, including: In the parameter optimization platform, an objective function and constraints are defined. The objective function is to ensure that the air temperature inside the engine compartment output by the one-dimensional thermal fluid simulation model is within a preset safe temperature range. The constraints include at least the physical upper and lower limits of the fan speed. Based on the objective function and constraints, the fan speed is automatically adjusted as the input variable, and the three-dimensional fluid simulation model and the one-dimensional thermofluid simulation model are cyclically called for coupled calculation until the simulation result that satisfies the objective function is obtained.

4. The method for constructing a numerical virtual model of an engine compartment according to claim 1, characterized in that, The simulation conditions in which the air temperature inside the engine compartment is within a preset safe temperature range are selected from the simulation output. A subset of input parameters for each selected simulation condition and its corresponding fan speed are used to form a valid training sample. A model training dataset is then constructed based on all valid training samples, including: A mapping relationship is established between the subset of input parameters corresponding to the simulation conditions that meet the preset safety temperature requirements and the corresponding fan speed to form the model training dataset; wherein, the fan speed is the optimized value that keeps the air temperature in the engine compartment within a safe range.

5. The method for constructing a numerical virtual model of an engine compartment according to claim 1, characterized in that, The machine learning model is trained using the model training dataset to obtain a numerical model for engine compartment temperature control. This numerical model directly outputs a recommended fan speed value based on real-time input vehicle speed, ambient temperature, and engine thermal load, including: The model training dataset is divided into a training set and a validation set; The initial machine learning model is iteratively trained using the training set, and the model performance during the training process is verified and optimized using the validation set. Once the trained machine learning model meets the preset accuracy requirements, it is deployed as the numerical model for engine compartment temperature control. The numerical model is configured to receive real-time monitored or estimated vehicle speed, ambient temperature, and engine thermal load as input, and output a corresponding fan speed setpoint, which is used to guide or control the real-time operation of the engine compartment cooling fan.

6. The method for constructing a numerical virtual model of an engine compartment according to claim 1, characterized in that, The method further includes: The simulated air temperature inside the engine compartment was compared and verified with the experimental results. Based on the results of the comparative verification, the three-dimensional fluid simulation model and the one-dimensional thermofluid simulation model are revised.

7. An intelligent temperature control device for an engine compartment, characterized in that, The device includes: The memory is configured to store instructions; and The processor is configured to execute the method for constructing a numerical virtual model of the engine compartment according to any one of claims 1 to 6.

8. The intelligent temperature control device for the engine compartment according to claim 7, characterized in that, The device further includes an early warning module, wherein the early warning module is configured to: Receive engine compartment temperature monitoring data; Based on the numerical model and the temperature monitoring data, an early warning is issued when the calculated fan speed has reached its limit and the engine compartment temperature still cannot be maintained within a safe range.

9. An intelligent temperature control simulation system for an engine compartment, characterized in that, include: Engine compartment; A cooling fan is installed inside the engine compartment; The intelligent temperature control device for the engine compartment according to claim 7 or 8 is installed in the engine compartment and is used to control the speed of the cooling fan to regulate the temperature of the engine compartment.

10. A machine-readable storage medium, characterized in that, The machine-readable storage medium stores instructions for causing the machine to perform the method of constructing the numerical virtual model of the engine compartment according to any one of claims 1 to 6.

Images