A thermal management control virtual calibration method, device and equipment

Abstract

This application provides a virtual calibration method, apparatus, and device for thermal management control, applied in the field of new energy vehicle technology. The method includes: determining the signal types of multiple raw signals required for interaction between the actual vehicle controller and the hardware-in-the-loop system, as well as the signal conversion rules corresponding to each raw signal. Based on the signal types and signal conversion rules, the signal values ​​of the thermal management simulation model to be constructed in the hardware-in-the-loop system are determined, and the thermal management simulation model is constructed according to the signal values. Using the thermal management simulation model to virtually calibrate the thermal management control parameters operating in the actual vehicle controller can solve the problems existing in traditional virtual calibration methods, such as not considering the signal matching problem between the actual vehicle controller and the simulation model, and the difficulty in balancing real-time performance and accuracy when using a unified modeling approach for subsystems with different simulation complexities.

Description

Technical Field

[0001] This application relates to the field of new energy vehicle technology, and in particular to a virtual calibration method, device and equipment for thermal management control. Background Technology

[0002] The thermal management system of new energy vehicles is highly complex, involving the coordinated control of multiple subsystems such as batteries, motors, electronic controls, and passenger compartments. The calibration of traditional thermal management control algorithms is highly dependent on real vehicle testing, requiring environmental chamber tests and extreme climate road tests after the prototype vehicle is manufactured. Due to limitations of vehicle resources, environmental climate, and seasons, the calibration cycle is long and costly, which seriously restricts the efficiency of new model development.

[0003] To address these issues, virtual calibration technology is increasingly being applied to the development of thermal management control algorithms. Related virtual calibration methods primarily involve constructing a vehicle thermal management simulation model, creating a closed-loop test environment between the hardware-in-the-loop system and the actual vehicle controller, thus enabling control parameter calibration during the digital prototype stage. However, this method fails to adequately consider the matching issue of signal interaction between the actual vehicle controller and the hardware-in-the-loop system when constructing the simulation model. The actual vehicle controller outputs raw signals collected by sensors (such as resistance, voltage, and current values), while the simulation model requires physical quantities (such as temperature, pressure, and flow rate). This signal difference prevents the model from directly receiving controller signals, affecting the accuracy and efficiency of virtual calibration. Furthermore, the simulation complexity varies significantly among different subsystems within the thermal management system, making it difficult to balance real-time performance and accuracy requirements using a uniform modeling approach. Summary of the Invention

[0004] The purpose of this application is to provide a virtual calibration method, device, and equipment for thermal management control, so as to solve the problems in traditional virtual calibration methods that do not consider the signal matching between the actual vehicle controller and the simulation model, and the problem that it is difficult to balance real-time performance and accuracy when using a unified modeling method for subsystems with different simulation complexities.

[0005] In a first aspect, embodiments of this application provide a virtual calibration method for thermal management control, applied to a virtual calibration system. The virtual calibration system includes a vehicle controller and a hardware-in-the-loop system (HIL), with the vehicle controller connected to the HIL via a signal interface. The method includes: determining the signal types of multiple raw signals required for interaction between the vehicle controller and the HIL, and the signal conversion rules corresponding to each raw signal; determining the signal values ​​of the thermal management simulation model to be constructed in the HIL based on the signal types and signal conversion rules, and constructing the thermal management simulation model according to the signal values; and using the thermal management simulation model to virtually calibrate the thermal management control parameters operating in the vehicle controller.

[0006] The virtual calibration method for thermal management control provided in this application solves the problem that the simulation model cannot directly receive the controller's original signals by identifying the original signal types and conversion rule definitions required for interaction between the actual vehicle controller and the hardware-in-the-loop system. This achieves high-fidelity communication between the actual vehicle controller and the simulation model, improving the accuracy and efficiency of virtual calibration. By constructing a thermal management simulation model according to unified signal values, the consistency and standardization of the simulation model's input signals are ensured, providing a reliable signal interaction foundation for subsequent virtual calibration. By using the constructed simulation model to virtually calibrate the thermal management control parameters during the digital prototype stage, the calibration work that originally needed to be carried out after the prototype vehicle was manufactured is brought forward to the digital prototype stage. This significantly reduces dependence on actual vehicle resources and environmental climate, effectively shortens the actual vehicle calibration cycle, and reduces the development cost of new vehicle models.

[0007] One possible implementation involves determining the signal types of the raw signals required for interaction between the vehicle controller and the hardware-in-the-loop system, as well as the corresponding signal conversion rules. This includes: obtaining a list of signals for the entire vehicle; selecting multiple raw signals required for interaction between the vehicle controller and the hardware-in-the-loop system from the signal list, and determining the signal type of each raw signal; and for any given raw signal, determining the corresponding signal conversion rules based on the sensor type corresponding to the raw signal.

[0008] One possible implementation involves determining the signal conversion rule corresponding to the original signal based on the sensor type. This includes: if the sensor type is determined to be a resistive temperature sensor, determining the signal conversion rule to convert the resistance value to a temperature value; and / or, if the sensor type is determined to be a voltage sensor, determining the signal conversion rule to convert the voltage value to a corresponding signal value; and if the sensor type is determined to be a current sensor, determining the signal conversion rule to convert the current value to a corresponding signal value.

[0009] One possible implementation involves determining the signal values ​​of the thermal management simulation model to be built in the hardware-in-the-loop system based on the signal type and signal conversion rules. This includes: for any input port in the thermal management simulation model, selecting the target original signal corresponding to the input port from multiple original signals; and determining the signal value of the input port based on the signal type and signal conversion rules of the target original signal.

[0010] One possible implementation involves constructing a thermal management simulation model based on signal values. This includes: dividing the vehicle thermal management system into at least two target subsystems according to the simulation complexity of each subsystem; determining the target modeling method corresponding to the simulation complexity of any target subsystem for each subsystem, and constructing a target simulation model using this method; and coupling the target simulation models corresponding to each target subsystem to obtain the thermal management simulation model.

[0011] One possible implementation involves determining the target modeling method corresponding to the simulation complexity of the target subsystem, including: when the target subsystem is determined to have high simulation complexity, constructing the target simulation model using a fusion of machine learning and physical models; and / or, when the target subsystem is determined to have low simulation complexity, constructing the target simulation model using physical modeling.

[0012] One possible implementation involves using a thermal management simulation model to virtually calibrate the thermal management control parameters operating in the actual vehicle controller. This includes: determining multiple sets of thermal management control parameters to be calibrated based on preset thermal management modes and operating conditions; running the multiple sets of thermal management control parameters based on the thermal management simulation model to determine the thermal management effect corresponding to each set; and selecting thermal management control parameters that meet preset requirements from the multiple sets of thermal management control parameters based on the thermal management effect.

[0013] Secondly, embodiments of this application provide a virtual calibration device for thermal management control, applied to a virtual calibration system. The virtual calibration system includes a vehicle controller and a hardware-in-the-loop system, with the vehicle controller connected to the hardware-in-the-loop system via a signal interface. The device includes a determination module and a virtual calibration module.

[0014] The determination module is used to determine the signal types of multiple raw signals required for interaction between the vehicle controller and the hardware-in-the-loop system, as well as the signal conversion rules corresponding to each raw signal.

[0015] The determination module is also used to determine the signal values ​​of the thermal management simulation model to be built in the hardware-in-the-loop system based on the signal type and signal conversion rules, and to build the thermal management simulation model according to the signal values.

[0016] The virtual calibration module is used to virtually calibrate the thermal management control parameters of the actual vehicle controller using a thermal management simulation model.

[0017] One possible implementation involves a module that, when determining the signal types of the raw signals required for interaction between the vehicle controller and the hardware-in-the-loop system, and the corresponding signal conversion rules, specifically performs the following: Obtaining a list of vehicle signals; filtering out multiple raw signals required for interaction between the vehicle controller and the hardware-in-the-loop system from the signal list, and determining the signal type of each raw signal; and for any given raw signal, determining the corresponding signal conversion rules based on the sensor type corresponding to the raw signal.

[0018] One possible implementation involves a determining module that, when determining the signal conversion rule corresponding to the original signal based on the sensor type, specifically: if the sensor type is determined to be a resistive temperature sensor, determines the signal conversion rule to convert the resistance value to a temperature value; and / or, if the sensor type is determined to be a voltage sensor, determines the signal conversion rule to convert the voltage value to a corresponding signal value; and if the sensor type is determined to be a current sensor, determines the signal conversion rule to convert the current value to a corresponding signal value.

[0019] One possible implementation involves a module that, when determining the signal values ​​of the thermal management simulation model to be built in the hardware-in-the-loop system based on signal type and signal conversion rules, specifically performs the following: for any input port in the thermal management simulation model, it filters out the target original signal corresponding to the input port from multiple original signals. Then, it determines the signal value of the input port based on the signal type and signal conversion rules of the target original signal.

[0020] One possible implementation involves defining a module that, when constructing a thermal management simulation model based on signal values, specifically: Dividing the vehicle thermal management system into at least two target subsystems according to the simulation complexity of each subsystem. For any target subsystem, determining the target modeling method corresponding to its simulation complexity, and constructing a target simulation model using this method. Finally, coupling the target simulation models corresponding to each target subsystem yields the thermal management simulation model.

[0021] One possible implementation involves a module that, when determining the target modeling method corresponding to the simulation complexity of the target subsystem, specifically: if the target subsystem is determined to have high simulation complexity, constructing the target simulation model using a fusion of machine learning and physical models; and / or, if the target subsystem is determined to have low simulation complexity, constructing the target simulation model using physical modeling.

[0022] One possible implementation involves a virtual calibration module. When virtually calibrating the thermal management control parameters operating in the actual vehicle controller using a thermal management simulation model, the module specifically performs the following: First, it determines multiple sets of thermal management control parameters to be calibrated based on a preset thermal management mode and operating condition requirements. Then, it runs the multiple sets of thermal management control parameters based on the thermal management simulation model, determining the thermal management effect corresponding to each set. Finally, based on the thermal management effect, it selects the thermal management control parameters that meet the preset requirements from the multiple sets of parameters to be calibrated.

[0023] Thirdly, embodiments of this application provide a virtual calibration device for thermal management control, which has the function of implementing the virtual calibration method for thermal management control described in the first aspect or any possible implementation thereof. This function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-described function.

[0024] Fourthly, embodiments of this application provide a computer-readable storage medium storing instructions that, when executed on a computer, enable the computer to perform the thermal management control virtual calibration method described in the first aspect or any possible implementation thereof.

[0025] Fifthly, embodiments of this application provide a computer program product containing instructions that, when run on a computer, enable the computer to execute the thermal management control virtual calibration method described in the first aspect or any possible implementation thereof.

[0026] The technical effects of any of the design methods in aspects two through five can be found in aspect one or in different possible implementations of aspect one, and will not be repeated here. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0028] Figure 1 A system architecture diagram of a virtual calibration system provided in this application embodiment; Figure 2 A flowchart illustrating a virtual calibration method for thermal management control provided in this application embodiment; Figure 3A specific example diagram of a virtual calibration method for thermal management control provided in this application embodiment; Figure 4 A schematic diagram of a virtual calibration device for thermal management control provided in this application embodiment; Figure 5 This is a system architecture diagram of a virtual calibration system for thermal management control provided in an embodiment of this application. Detailed Implementation

[0029] 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. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0030] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0031] In current simulation models, the matching issue of signal interaction between the actual vehicle controller and the hardware-in-the-loop system is not fully considered. The actual vehicle controller outputs raw signals collected by sensors, such as resistance, voltage, and current values, while the simulation model requires physical quantities such as temperature, pressure, and flow rate. This signal difference prevents the model from directly receiving controller signals, affecting the accuracy and efficiency of virtual calibration. Furthermore, the simulation complexity of different subsystems in the thermal management system varies greatly, making it difficult to balance real-time performance and accuracy requirements using a uniform modeling approach.

[0032] Based on this, embodiments of this application provide a method, apparatus, and device for virtual calibration of thermal management control. This method can be applied to a virtual calibration system, which includes a vehicle controller and a hardware-in-the-loop system (HIL). The vehicle controller is connected to the HIL via a signal interface. The method includes determining the signal types of multiple raw signals required for interaction between the vehicle controller and the HIL, as well as the signal conversion rules corresponding to each raw signal. Based on the signal types and signal conversion rules, the signal values ​​of the thermal management simulation model to be constructed in the HIL are determined, and the thermal management simulation model is constructed according to the signal values. The thermal management simulation model is then used to virtually calibrate the thermal management control parameters operating in the vehicle controller.

[0033] The virtual calibration method for thermal management control provided in this application solves the problem that the simulation model cannot directly receive the original signals from the controller by identifying the original signal types and conversion rule definitions required for interaction between the actual vehicle controller and the hardware-in-the-loop system. This achieves high-fidelity communication between the actual vehicle controller and the simulation model, improving the accuracy and efficiency of virtual calibration. By constructing a thermal management simulation model according to unified signal values, the consistency and standardization of the input signals of the simulation model are ensured, providing a reliable signal interaction foundation for subsequent virtual calibration. By using the constructed simulation model to virtually calibrate the thermal management control parameters in the digital prototype stage, the calibration work that originally had to be carried out after the prototype vehicle was manufactured can be brought forward to the digital prototype stage, significantly reducing the dependence on actual vehicle resources and environmental climate, effectively shortening the actual vehicle calibration cycle, and reducing the development cost of new models.

[0034] The methods provided in the embodiments of this application will now be described in conjunction with the specific accompanying drawings.

[0035] On the one hand, embodiments of this application provide a virtual calibration system. For example... Figure 1 As shown, the virtual calibration system 100 may include: a vehicle controller 101 and a hardware-in-the-loop system 102.

[0036] The vehicle controller 101 is the actual electronic control unit used in the vehicle to run the thermal management control algorithm. This vehicle controller 101 is connected to the hardware-in-the-loop system 102 through multiple signal interfaces. Each signal interface corresponds to a sensor type and is used to transmit a specific type of raw signal. The vehicle controller 101 can receive analog sensor signals from the hardware-in-the-loop system 102 through its various signal interfaces and output control commands to the hardware-in-the-loop system 102.

[0037] The hardware-in-the-loop system 102 is a real-time simulation device used to load the thermal management simulation model and interact in a closed loop with the vehicle controller 101. The hardware-in-the-loop system 102 may include a processor, a memory, and multiple input / output interfaces. The memory stores a pre-built thermal management simulation model; the processor runs the simulation model and calculates the state parameters of the thermal management system in real time based on the control commands output by the vehicle controller 101; the multiple input / output interfaces are connected one-to-one with multiple signal interfaces of the vehicle controller 101, used to convert the physical quantities (such as temperature, pressure, and flow rate) calculated by the processor into raw signals (such as resistance, voltage, and current values) of the corresponding sensor types, and send them to the vehicle controller 101 through the corresponding signal interfaces, while simultaneously receiving control commands output by the vehicle controller 101 through each signal interface.

[0038] For example, the hardware-in-the-loop system 102 can employ a real-time simulation system such as dSPACE or NI PXI. This system has high-speed data processing capabilities and multiple input / output interfaces, which can meet the real-time requirements of virtual calibration of the thermal management control algorithm. The signal interface between the vehicle controller 101 and the hardware-in-the-loop system 102 can be connected using a dedicated wiring harness to ensure the reliability and real-time performance of signal transmission. Different signal interfaces can correspond to different types of sensors, such as resistive temperature sensor interfaces, voltage pressure sensor interfaces, and current flow sensor interfaces. Each interface is signal-matched according to the characteristics of the corresponding sensor.

[0039] It should be noted that the above Figure 1 The virtual calibration system 100 shown is merely an example illustrating the application scenario of the solution in this application, and is not intended to limit the application scenario of the solution in this application.

[0040] On the one hand, embodiments of this application provide a virtual calibration method for thermal management control, which can be performed by... Figure 1 The virtual calibration system 100 shown is executed. For example... Figure 2 As shown, the method may include the following steps.

[0041] S201, determine the signal types of multiple raw signals required for interaction between the vehicle controller and the hardware-in-the-loop system, as well as the signal conversion rules corresponding to each raw signal.

[0042] In a virtual calibration system, a large number of signals need to be exchanged between the vehicle controller and the hardware-in-the-loop system. The vehicle controller outputs raw signals collected by sensors, such as resistance, voltage, and current values, while the thermal management simulation model running in the hardware-in-the-loop system requires physical quantity values, such as temperature, pressure, and flow rate. The signal types differ between the two systems; direct connection would lead to signal mismatch, affecting the accuracy and efficiency of the virtual calibration. Therefore, it is necessary to analyze the raw signals required for the interaction, clarifying the type of each signal and its corresponding conversion rules.

[0043] Signal types can be classified according to the working principle of the sensor, such as resistive signals, voltage signals, current signals, pulse signals, and digital signals.

[0044] One possible implementation involves obtaining a list of signals from the entire vehicle. From this list, several raw signals required for interaction between the vehicle controller and the hardware-in-the-loop system are selected, and the signal type of each raw signal is determined. For any given raw signal, a signal conversion rule is determined based on the sensor type corresponding to that raw signal.

[0045] Furthermore, the step of determining the signal conversion rule corresponding to the original signal based on the sensor type can include: if the sensor type is determined to be a resistive temperature sensor, determining the signal conversion rule to convert the resistance value to a temperature value; if the sensor type is determined to be a voltage sensor, determining the signal conversion rule to convert the voltage value to a corresponding signal value; and if the sensor type is determined to be a current sensor, determining the signal conversion rule to convert the current value to a corresponding signal value.

[0046] For example, if the sensor type is determined to be a resistive temperature sensor, the signal conversion rule is to convert the resistance value to a temperature value. Temperature sensors commonly used in thermal management systems are mostly negative temperature coefficient thermistors, whose resistance decreases as temperature increases, exhibiting a non-linear relationship. It is necessary to establish the correspondence between resistance and temperature values ​​based on the resistance-temperature characteristic curve or calibration table provided by the sensor manufacturer. In practical applications, the conversion from resistance to temperature can be achieved using a lookup table method or polynomial fitting.

[0047] When the sensor type is determined to be a voltage sensor, the signal conversion rule is to convert the voltage value into the corresponding signal value. For example, some pressure sensors output a voltage signal of 0-5V, and their output voltage has a linear relationship with the pressure value. It is necessary to establish a linear conversion relationship between the voltage value and the pressure value based on the sensor's range. Assuming the pressure sensor's range is 0-10 bar and the corresponding output voltage is 0-5V, the conversion rule can be expressed as: Pressure value = (Voltage value / 5V) × 10 bar.

[0048] When the sensor type is determined to be a current-type sensor, the signal conversion rule is to convert the current value into the corresponding signal value. For example, some flow sensors use a current output of 4-20mA, and their output current has a linear relationship with the flow rate. It is necessary to establish a linear conversion relationship between the current value and the flow rate based on the sensor's range. Assuming the flow sensor's range is 0-100L / min, and the corresponding output current is 4-20mA, the conversion rule can be expressed as: Flow rate = [(Current value - 4mA) / (20mA - 4mA)] × 100L / min.

[0049] S202, based on the signal type and signal conversion rules, determine the signal values ​​of the thermal management simulation model to be built in the hardware-in-the-loop system, and build the thermal management simulation model according to the signal values.

[0050] One possible implementation involves determining the signal values ​​of the thermal management simulation model to be built in the hardware-in-the-loop system based on the signal type and signal conversion rules. This includes: for any input port in the thermal management simulation model, selecting the target original signal corresponding to the input port from multiple original signals; and determining the signal value of the input port based on the signal type and signal conversion rules of the target original signal.

[0051] For example, for any input port in a thermal management simulation model, the target raw signal corresponding to that input port is selected from multiple raw signals. This selection process needs to be matched based on the physical meaning of the input port and the measurement requirements. If the simulation model has a battery inlet water temperature input port, which is expected to receive the coolant temperature value at the battery pack inlet, then raw signals related to battery inlet water temperature measurement are selected from the list of raw signals. These signals typically come from a temperature sensor installed at the battery pack inlet. The selection criteria can include signal name, sensor installation location, signal purpose, etc.

[0052] After determining the target original signal, the signal value of the input port needs to be determined according to the signal type of the target original signal and the corresponding signal conversion rules. Different signal types correspond to different conversion methods. Taking battery water inlet temperature as an example, assuming that the signal comes from a resistive temperature sensor, according to the determined signal conversion rules, the resistance value output by the vehicle controller needs to be converted into a temperature value. The specific conversion process can be as follows: the original signal received from the vehicle controller is a resistance value R. According to the resistance-temperature characteristic curve of the temperature sensor or by looking up a table, the temperature value T corresponding to the resistance value is found. Then, the temperature value T is assigned to the battery water inlet temperature input port of the simulation model.

[0053] Furthermore, a thermal management simulation model is constructed based on the signal values, including: dividing the vehicle thermal management system into at least two target subsystems according to the simulation complexity of each subsystem; determining the target modeling method corresponding to the simulation complexity of any target subsystem for each target subsystem, and constructing a target simulation model using the target modeling method; and coupling the target simulation models corresponding to each target subsystem to obtain the thermal management simulation model.

[0054] Specifically, the vehicle thermal management system involves multiple subsystems, each with significantly different physical characteristics and simulation complexity. Taking the air conditioning circuit as an example, it involves complex thermodynamic processes such as refrigerant phase change, heat exchanger heat transfer, and compressor compression, exhibiting fast dynamic response and strong nonlinearity, resulting in a large computational burden for simulation. In contrast, subsystems such as the coolant circuit, air ducts, and passenger compartment mainly involve single-phase fluid flow and heat exchange, with relatively simpler physical processes and lower computational burden for simulation. Using a uniform modeling approach would either fail to meet the accuracy requirements of highly complex subsystems or waste computational resources on less complex subsystems. Therefore, differentiated modeling strategies are needed based on the varying simulation complexity of each subsystem.

[0055] First, the vehicle's thermal management system is divided into subsystems. Based on physical principles and functional modules, the thermal management system can be broken down into several relatively independent subsystems. For example, it can be divided into an air conditioning circuit subsystem, a coolant circuit subsystem, an air duct subsystem, and a passenger compartment subsystem. Next, the simulation complexity of each subsystem is evaluated. Evaluation metrics can include: the degree of nonlinearity of the physical process, dynamic response speed, number of state variables, and coupling strength between components. Based on the evaluation results, each subsystem is classified into two categories: high simulation complexity and low simulation complexity. For any target subsystem, a target modeling method corresponding to its simulation complexity is determined, and a target simulation model is constructed using this method.

[0056] One possible approach is to construct a target simulation model by integrating machine learning with a physical model, given that the target subsystem is determined to have high simulation complexity.

[0057] For example, for highly complex simulation subsystems, a simulation model can be constructed by combining machine learning with physical models. Figure 3 As shown, taking the air conditioning loop subsystem as an example, the air conditioning loop subsystem may include an electric compressor 1, a blower 2, an evaporator 3, a thermal expansion valve 4, a condenser 5, an electronic expansion valve 6, a plate heat exchanger 7, an air conditioning loop 8, and an open-loop water loop 12.

[0058] The specific implementation of this method may include the following steps: First, a physical baseline model of the air conditioning circuit is constructed based on thermodynamic principles and component characteristics. This physical baseline model is based on fundamental laws such as mass conservation, energy conservation, and momentum conservation, and can accurately describe the dynamic characteristics of components such as the compressor, condenser, evaporator, and expansion valve. However, due to its small calculation step size and numerous iterations, the simulation speed is slow, making it difficult to meet the real-time requirements of hardware-in-the-loop testing. Then, a large number of training datasets are generated based on this physical baseline model.

[0059] The dataset's input parameters can include compressor speed, condenser inlet air temperature, condenser inlet air volume, evaporator inlet air humidity, evaporator inlet air volume, evaporator inlet air temperature, electronic expansion valve superheat, thermostatic expansion valve superheat, open-loop battery circuit inlet water temperature, and water flow rate. The dataset's output parameters can include compressor power, system refrigerant high pressure, system refrigerant low pressure, HVAC outlet air temperature, plate heat exchanger refrigerant outlet temperature and pressure, and battery inlet water temperature. The range of input parameter values ​​is determined based on actual operating conditions, covering various operating conditions from low to high temperatures and from low to high loads.

[0060] Then, a surrogate model of the air conditioning loop is constructed based on machine learning algorithms (such as neural networks, support vector machines, and random forests). Taking neural networks as an example, the input parameters can be used as the network input layer, and the output parameters as the network output layer. The network is trained using a training dataset, allowing it to learn the nonlinear mapping relationship between the input and output. After training, the surrogate model is validated for accuracy, ensuring that the error between its output and the physical benchmark model is within an acceptable range. The air conditioning loop model constructed through this fusion approach retains the theoretical foundation of the physical model while possessing the fast computational capabilities of the machine learning model, meeting the real-time requirements of hardware-in-the-loop testing while ensuring accuracy.

[0061] Another possible approach is to construct a target simulation model using physical modeling, provided that the target subsystem has low simulation complexity.

[0062] For example, for subsystems with low simulation complexity, physical modeling can be used to construct simulation models. Taking the coolant loop subsystem as an example, this subsystem mainly includes components such as a water pump, radiator, thermostat, and battery cooling channel. The coolant flows in the pipeline and exchanges heat with the environment or battery. This physical process can be described using the lumped parameter method or a one-dimensional flow model. In modeling environments such as MATLAB Simulink, physical models based on fluid networks and thermal capacity and resistance can be built. For example, the water pump can calculate the flow rate based on the rotational speed and pressure difference, the radiator can calculate the heat transfer based on the heat transfer coefficients on the air side and the coolant side, and the battery cooling channel can calculate the battery temperature change based on the coolant flow rate and inlet temperature. These physical models are based on the basic formulas of thermodynamics and fluid mechanics, have fast calculation speed, can meet real-time requirements, and have sufficient physical interpretability.

[0063] S203 uses a thermal management simulation model to virtually calibrate the thermal management control parameters operating in the actual vehicle controller.

[0064] One possible implementation involves determining multiple sets of thermal management control parameters to be calibrated based on a preset thermal management mode and operating conditions. The thermal management simulation model is then used to run these multiple sets of control parameters to determine the thermal management effect corresponding to each set. Based on the thermal management effect, the thermal management control parameters that meet the preset requirements are selected from the multiple sets of control parameters to be calibrated.

[0065] Specifically, firstly, based on the preset thermal management modes and operating conditions, multiple sets of thermal management control parameters to be calibrated are determined. Thermal management modes may include battery cooling mode, battery heating mode, passenger compartment cooling mode, passenger compartment heating mode, defrosting and defogging mode, etc. Different thermal management modes correspond to different control logic and objectives. Operating conditions may include various operating conditions such as ambient temperature, light intensity, vehicle speed, driving cycle, battery state of charge, and battery temperature. Based on these modes and requirements, a set of control parameters to be calibrated is determined, such as target values ​​for compressor speed, water pump flow rate, electronic expansion valve opening, fan speed, and mode damper position. For each parameter to be calibrated, based on experience and theoretical analysis, a certain parameter value range and step size are set, generating multiple sets of parameter combinations to be calibrated. For example, the compressor speed can be between 2000 rpm and 6000 rpm, with a step size of 500 rpm; the water pump flow rate can be between 5 L / min and 20 L / min, with a step size of 2 L / min. The values ​​of different parameters are combined to form multiple sets of parameters to be calibrated.

[0066] Furthermore, based on the constructed thermal management simulation model, multiple sets of thermal management control parameters to be calibrated are run to determine the thermal management effect corresponding to each set of parameters. The actual vehicle controller is connected to the hardware-in-the-loop system, the control parameters to be calibrated are written into the actual vehicle controller, and then the thermal management simulation model is run in the hardware-in-the-loop system to simulate the vehicle's operation under specified conditions. The simulation model calculates the response of the thermal management system in real time according to the control commands output by the actual vehicle controller, including indicators such as battery temperature change, passenger compartment temperature change, system power consumption, compressor start-stop frequency, and temperature control accuracy. By running multiple sets of parameters, the thermal management effect data corresponding to each set of parameters is recorded. For example, for the battery cooling mode, the time required for the battery temperature to drop from the initial temperature to the target temperature, the temperature fluctuation amplitude during the cooling process, and the total system power consumption can be recorded under different combinations of compressor speed and water pump flow rate. For the passenger compartment cooling mode, the response time for the passenger compartment temperature to reach the set temperature, the temperature control accuracy, and the blower power consumption can be recorded under different combinations of compressor speed and damper position.

[0067] Furthermore, based on the thermal management effect, thermal management control parameters that meet preset requirements are selected from multiple sets of thermal management control parameters to be calibrated. These preset requirements can be set according to design goals and priority levels, and may include: temperature control accuracy requirements (e.g., battery temperature control within ±2℃), response time requirements (e.g., cabin cooling time not exceeding 5 minutes), energy consumption requirements (e.g., minimizing total system power consumption), and component lifespan requirements (e.g., minimizing compressor start-stop cycles). Based on these requirements, the thermal management effects of multiple sets of parameters are comprehensively evaluated and ranked. Weighted scoring methods, Pareto front analysis, and other methods can be used to select one or more sets of parameters with optimal overall performance. For example, in battery cooling mode, two evaluation indicators can be set: temperature control accuracy and energy consumption. Parameters that meet the temperature control accuracy requirement are ranked from low to high energy consumption, and the parameter with the lowest energy consumption is selected as the calibration result. In cabin cooling mode, two evaluation indicators can be set: response time and temperature control accuracy. Parameters that simultaneously meet the response time and accuracy requirements are selected, and then further optimized based on other auxiliary indicators.

[0068] For example, a virtual calibration of the battery thermal management mode of a certain new energy vehicle was performed. The control parameters to be calibrated included compressor speed and water pump flow rate. The compressor speed ranged from 2000-6000 rpm with a step size of 500 rpm, resulting in 9 possible values; the water pump flow rate ranged from 5-20 L / min with a step size of 2 L / min, resulting in 8 possible values. These combined to form 72 sets of parameters to be calibrated. A thermal management simulation model was run in a hardware-in-the-loop system, simulating a cooling condition with an ambient temperature of 35℃, an initial battery temperature of 40℃, and a target battery temperature of 25℃. The simulation was run 72 times, recording three indicators for each set of parameters: battery cooling time, temperature fluctuation amplitude, and total system power consumption. Based on design requirements, priority was given to ensuring the cooling time did not exceed 10 minutes. Under this premise, the parameter combination with the smallest temperature fluctuation amplitude and lowest power consumption was selected. After comparison and selection, the parameter combination of a compressor speed of 3500 rpm and a water pump flow rate of 12 L / min was finally determined as the calibration result. These parameters enable the battery temperature to drop to 25°C within 9.5 minutes, with a temperature fluctuation range of ±1.5°C. The total system power consumption is 1.2kWh, which meets the design requirements.

[0069] Furthermore, before using the thermal management simulation model to virtually calibrate the thermal management control parameters operating in the actual vehicle controller, it is necessary to test and verify the signal transmission between the actual vehicle controller and the hardware-in-the-loop system to ensure that high-fidelity communication can be achieved between the two.

[0070] One possible approach is to first define the type and key information of each signal. Signal types can include analog signals (such as voltage and current signals), digital signals (such as PWM and pulse signals), and bus signals (such as CAN and LIN signals). For each signal, key information such as its transmission frequency, communication protocol, level range, and accuracy requirements also needs to be defined. For example, the resistance signal output by a temperature sensor is an analog signal with a low frequency of change, but it requires high-precision acquisition and conversion; the compressor speed control signal can be a PWM signal, and its frequency and duty cycle range need to be defined; communication between the battery management system and the thermal management controller may be implemented through a CAN bus, requiring the definition of protocol information such as CAN ID, data length, and update cycle.

[0071] Furthermore, the vehicle controller is connected to the hardware-in-the-loop system via a specialized hardware interface. Depending on the signal type, appropriate interface boards and wiring harnesses are selected. For example, for analog signals, an analog input / output board with high-precision analog-to-digital conversion can be used; for PWM signals, a dedicated PWM acquisition and generation board can be used; and for CAN bus signals, a CAN interface card can be used. During connection, it is essential to ensure proper shielding and grounding of the signal lines to avoid introducing additional electromagnetic interference. After connection, the configuration parameters of the hardware interface are set, such as sampling rate, range, and filtering parameters, to match the signal characteristics.

[0072] Furthermore, communication testing software is used to comprehensively test and verify the accuracy and real-time performance of signal transmission. Specialized test scripts can be written to send specific test signals to the vehicle controller, observing whether the controller can accurately receive and respond correctly. For example, for temperature sensor signals, a set of known resistance values ​​can be input to the controller, and then the controller's output temperature value can be read to verify whether it matches the expected conversion result. For control command signals, the duty cycle of the controller's output PWM signal can be monitored to verify whether it matches the set target value. Simultaneously, signal delay and error during transmission are monitored. A synchronization pulse can be generated in the hardware-in-the-loop system to measure the time difference from signal output to controller response, assessing whether the transmission delay is within acceptable limits. For analog signals, multiple measurements can be collected to calculate noise levels and measurement errors.

[0073] For example, the following communication tests were conducted on the thermal management controller of a certain new energy vehicle: First, the controller was connected to the dSPACE hardware-in-the-loop system via a dedicated wiring harness. For the battery inlet water temperature sensor signal, an analog input channel was configured with a sampling rate of 100Hz. A series of known resistance values ​​(corresponding to temperature points within the range of -40℃ to 120℃) were output by dSPACE, and the temperature value output by the controller via the CAN bus was read and compared with the expected value to verify that the error was within ±0.5℃. For the compressor speed control signal, the frequency and duty cycle of the PWM signal output by the controller were monitored and compared with the set target speed to verify the control accuracy. Simultaneously, a synchronization pulse was generated by dSPACE, and the delay time from the controller receiving the sensor signal to outputting the control command was measured. The average delay was 15ms, meeting the real-time requirements. For the CAN bus signal, CANalyzer software was used to monitor the messages on the bus to verify that the CAN ID, data format, and update cycle were consistent with the controller's design document.

[0074] The above primarily describes the solutions provided in the embodiments of this application from the perspective of the working principle of the device. It is understood that, in order to achieve the above functions, the thermal management control virtual calibration device includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the algorithm steps of the various examples described in the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0075] This application embodiment can divide the thermal management control virtual calibration device into functional modules according to the above method example. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module.

[0076] It should be noted that the module division in this embodiment is illustrative and represents only one logical functional division; in actual implementation, other division methods may be used. When dividing functional modules according to their respective functions, Figure 4 A schematic diagram of a possible configuration of the virtual calibration device for thermal management control involved in the above and embodiment examples is shown. Figure 4 As shown, the thermal management control virtual calibration device 400 may include: a determination module 401 and a virtual calibration module 402.

[0077] The determination module 401 is used to support the execution of the thermal management control virtual calibration device 400. Figure 2 S201 and S202 in the schematic virtual calibration method for thermal management control.

[0078] Virtual calibration module 402 is used to support the execution of the thermal management control virtual calibration device 400. Figure 2 S203 in the schematic virtual calibration method for thermal management control.

[0079] One possible implementation involves a module that, when determining the signal types of the raw signals required for interaction between the vehicle controller and the hardware-in-the-loop system, and the corresponding signal conversion rules, specifically performs the following: Obtaining a list of vehicle signals; filtering out multiple raw signals required for interaction between the vehicle controller and the hardware-in-the-loop system from the signal list, and determining the signal type of each raw signal; and for any given raw signal, determining the corresponding signal conversion rules based on the sensor type corresponding to the raw signal.

[0080] One possible implementation involves a determining module that, when determining the signal conversion rule corresponding to the original signal based on the sensor type, specifically: if the sensor type is determined to be a resistive temperature sensor, determines the signal conversion rule to convert the resistance value to a temperature value; and / or, if the sensor type is determined to be a voltage sensor, determines the signal conversion rule to convert the voltage value to a corresponding signal value; and if the sensor type is determined to be a current sensor, determines the signal conversion rule to convert the current value to a corresponding signal value.

[0081] One possible implementation involves a module that, when determining the signal values ​​of the thermal management simulation model to be built in the hardware-in-the-loop system based on signal type and signal conversion rules, specifically performs the following: for any input port in the thermal management simulation model, it filters out the target original signal corresponding to the input port from multiple original signals. Then, it determines the signal value of the input port based on the signal type and signal conversion rules of the target original signal.

[0082] One possible implementation involves defining a module that, when constructing a thermal management simulation model based on signal values, specifically: Dividing the vehicle thermal management system into at least two target subsystems according to the simulation complexity of each subsystem. For any target subsystem, determining the target modeling method corresponding to its simulation complexity, and constructing a target simulation model using this method. Finally, coupling the target simulation models corresponding to each target subsystem yields the thermal management simulation model.

[0083] One possible implementation involves a module that, when determining the target modeling method corresponding to the simulation complexity of the target subsystem, specifically: if the target subsystem is determined to have high simulation complexity, constructing the target simulation model using a fusion of machine learning and physical models; and / or, if the target subsystem is determined to have low simulation complexity, constructing the target simulation model using physical modeling.

[0084] One possible implementation involves a virtual calibration module. When virtually calibrating the thermal management control parameters operating in the actual vehicle controller using a thermal management simulation model, the module specifically performs the following: First, it determines multiple sets of thermal management control parameters to be calibrated based on a preset thermal management mode and operating condition requirements. Then, it runs the multiple sets of thermal management control parameters based on the thermal management simulation model, determining the thermal management effect corresponding to each set. Finally, based on the thermal management effect, it selects the thermal management control parameters that meet the preset requirements from the multiple sets of parameters to be calibrated.

[0085] It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0086] The thermal management control virtual calibration device 400 provided in this application embodiment is used to perform the above-mentioned... Figure 2 The virtual calibration method for thermal management control shown can therefore achieve the same effect as the virtual calibration method for thermal management control described above.

[0087] This application also provides a virtual calibration device for thermal management control, which can execute the virtual calibration method and related steps of thermal management control described in the above method embodiments.

[0088] This application also provides a computer-readable storage medium storing instructions thereon, which, when executed, perform the thermal management control virtual calibration method and related steps described in the above method embodiments.

[0089] This application also provides a computer program product that, when run on a computer, causes the computer to execute the thermal management control virtual calibration method and related steps described in the above method embodiments.

[0090] In some embodiments, the methods shown in this application can be implemented as computer program instructions encoded in a machine-readable format on a computer-readable storage medium or on other non-transitory media or articles of art.

[0091] This application also provides a virtual calibration system 500 for thermal management control, such as... Figure 5As shown, the thermal management control virtual calibration system 500 includes at least one processor 501 and at least one interface circuit 502.

[0092] As an example, when the thermal management control virtual calibration system 500 includes a processor and an interface circuit, the processor can be... Figure 5 The processor 501 shown in the solid box (or the processor 501 shown in the dashed box) can be an interface circuit. Figure 5 The interface circuit 502 is shown in the solid box (or the dashed box). When the thermal management control virtual calibration system 500 includes two processors and two interface circuits, then the two processors include... Figure 5 The processor 501 shown in the solid box and the processor 501 shown in the dashed box, these two interface circuits include Figure 5 Interface circuit 502 is shown in both solid and dashed boxes. No limitations are imposed on this.

[0093] The processor 501 and the interface circuit 502 can be interconnected via a line. For example, the interface circuit 502 can be used to receive signals. Alternatively, the interface circuit 502 can be used to send signals to other devices (such as the processor 501). For instance, the interface circuit 502 can read computer instructions stored in memory and send those instructions to the processor 501. The processor 501 executes the instructions and, in conjunction with input / output devices, implements the various steps in the above embodiments, such as implementing... Figure 2 and Figure 3 The steps performed in the illustrated method embodiment are shown. Of course, this thermal management control virtual calibration system may also include other discrete components, and this application embodiment does not specifically limit this.

[0094] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0095] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0096] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0097] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0098] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, or the part that contributes to it, or all or part of the technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0099] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A virtual calibration method for thermal management control, characterized in that, The method is applied to a virtual calibration system, which includes a vehicle controller and a hardware-in-the-loop system, wherein the vehicle controller is connected to the hardware-in-the-loop system via a signal interface; the method includes: Determine the signal types of multiple raw signals required for interaction between the vehicle controller and the hardware-in-the-loop system, as well as the signal conversion rules corresponding to each raw signal; Based on the signal type and the signal conversion rule, determine the signal values ​​of the thermal management simulation model to be built in the hardware-in-the-loop system, and build the thermal management simulation model according to the signal values; The thermal management simulation model is used to virtually calibrate the thermal management control parameters operating in the actual vehicle controller.

2. The method according to claim 1, characterized in that, Determine the signal type of the original signal required for interaction between the vehicle controller and the hardware-in-the-loop system, and the signal conversion rules corresponding to the original signal, including: Get the signal list of the entire vehicle; Select multiple raw signals required for interaction between the vehicle controller and the hardware-in-the-loop system from the signal list, and determine the signal type of each raw signal; For any of the original signals, a signal conversion rule corresponding to the original signal is determined based on the sensor type corresponding to the original signal.

3. The method according to claim 2, characterized in that, The step of determining the signal conversion rule corresponding to the original signal based on the sensor type corresponding to the original signal includes: If the sensor type is determined to be a resistive temperature sensor, the signal conversion rule is determined to be to convert the resistance value into a temperature value. And / or, if the sensor type is determined to be a voltage sensor, the signal conversion rule is determined to be to convert the voltage value into the corresponding signal value; If the sensor type is determined to be a current sensor, the signal conversion rule is determined to be to convert the current value into the corresponding signal value.

4. The method according to claim 1, characterized in that, The step of determining the signal values ​​of the thermal management simulation model to be built in the hardware-in-the-loop system based on the signal type and the signal conversion rule includes: For any input port in the thermal management simulation model, a target original signal corresponding to the input port is selected from a plurality of original signals; The signal value of the input port is determined based on the signal type of the original target signal and the signal conversion rule.

5. The method according to claim 1, characterized in that, The step of constructing the thermal management simulation model according to the signal value includes: Based on the simulation complexity of each subsystem in the vehicle thermal management system, the vehicle thermal management system is divided into at least two types of target subsystems; For any of the target subsystems, determine the target modeling method corresponding to the simulation complexity of the target subsystem, and construct the target simulation model using the target modeling method; The target simulation models corresponding to each of the target subsystems are coupled to obtain the thermal management simulation model.

6. The method according to claim 5, characterized in that, The determination of the target modeling method corresponding to the simulation complexity of the target subsystem includes: Given that the target subsystem is determined to have high simulation complexity, a simulation model of the target is constructed by integrating machine learning and physical models. And / or, if the target subsystem is determined to have low simulation complexity, a physical modeling approach is used to construct the target simulation model.

7. The method according to claim 1, characterized in that, The virtual calibration of the thermal management control parameters operating in the actual vehicle controller using the thermal management simulation model includes: Based on the preset thermal management mode and operating conditions, multiple sets of thermal management control parameters to be calibrated are determined; Based on the thermal management simulation model, run multiple sets of thermal management control parameters to be calibrated, and determine the thermal management effect corresponding to each set of thermal management control parameters to be calibrated; Based on the aforementioned thermal management effect, thermal management control parameters that meet preset requirements are selected from multiple sets of thermal management control parameters to be calibrated.

8. A virtual calibration device for thermal management control, characterized in that, An apparatus for use in a virtual calibration system, the virtual calibration system comprising a vehicle controller and a hardware-in-the-loop system, the vehicle controller being connected to the hardware-in-the-loop system via a signal interface; the apparatus includes: The determination module is used to determine the signal types of multiple raw signals required for interaction between the vehicle controller and the hardware-in-the-loop system, as well as the signal conversion rules corresponding to each raw signal; The determining module is further configured to determine the signal value of the thermal management simulation model to be constructed in the hardware-in-the-loop system according to the signal type and the signal conversion rule, and construct the thermal management simulation model according to the signal value; The virtual calibration module is used to virtually calibrate the thermal management control parameters operating in the actual vehicle controller using the thermal management simulation model.

9. A virtual calibration device for thermal management control, characterized in that, The thermal management control virtual calibration device includes a processor and a memory, the memory storing machine-executable instructions that can be executed by the processor, and the processor executing the machine-executable instructions to implement the thermal management control virtual calibration method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the thermal management control virtual calibration method according to any one of claims 1 to 7.

Images