Vehicle thermal management method and device for new energy vehicle and new energy vehicle

Abstract

The application discloses a whole vehicle thermal management method and device of a new energy vehicle and the new energy vehicle. The method comprises the following steps: acquiring multi-source driving data of the new energy vehicle; analyzing the multi-source driving data by using a pre-trained working condition prediction model to obtain a working condition type, a working condition duration and working condition parameters of a target working condition that the new energy vehicle is about to enter; determining thermal regulation requirements of a plurality of thermal management subsystems of the new energy vehicle in the working condition duration respectively based on the working condition parameters; making a global collaborative thermal management decision based on the working condition type and the thermal regulation requirements of the plurality of thermal management subsystems to determine thermal management targets of the thermal management subsystems; and sending thermal management control instructions corresponding to the thermal management targets of the thermal management subsystems to the thermal management subsystems before the new energy vehicle enters the target working condition. The application solves the technical problem that the traditional vehicle thermal management control logic based on passive feedback has a lagging response and is difficult to guarantee thermal safety requirements.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and more specifically, to a method, device, and new energy vehicle for overall vehicle thermal management. Background Technology

[0002] Thermal management of new energy vehicles is crucial for ensuring vehicle safety, performance, range, and comfort. Currently, most new energy vehicle thermal management systems employ a passive control strategy based on sensor feedback, with its core mechanism being "detection-comparison-response." This involves real-time data collection from sensors such as temperature and power sensors to monitor the operating status of the battery, motor, electronic control system, and cabin. Only when a parameter exceeds a preset threshold are actuators such as water pumps, compressors, and electronic expansion valves triggered for adjustment. While this control method is simple in structure and low in implementation cost, under complex and variable driving conditions, especially in scenarios with sudden changes in conditions (such as sudden uphill climbs in urban areas, high-speed traffic jams, or instantaneous fast charging), the thermal load on the motor and battery can rise sharply within seconds. System delays in sensor data acquisition, control system processing, and actuator response prevent the thermal management system from effectively dissipating or preheating within critical timeframes. This can cause localized battery temperatures to exceed safety thresholds in a short period, leading to instantaneous overheating of motor windings or power devices, and in severe cases, even triggering the risk of thermal runaway. Meanwhile, because the control strategy relies on fixed thresholds and fails to dynamically adapt to changes in vehicle travel path, driver intentions, and environmental conditions, it results in insufficient heat dissipation during high-speed cruising and excessive cooling during urban congestion, leading to significant energy waste. Furthermore, existing thermal management methods treat the battery, motor, and cabin as independent entities, implementing single-point control strategies without a global coordination mechanism. This prevents efficient heat transfer and reuse between systems; for example, waste heat from the motor cannot be used for battery preheating in low-temperature environments, exacerbating range reduction caused by low temperatures.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a method, device, and vehicle for thermal management of new energy vehicles, which at least solves the technical problem that traditional vehicle thermal management control logic based on passive feedback has a lag in response and is difficult to guarantee thermal safety requirements.

[0005] According to one aspect of the embodiments of this application, a method for thermal management of a new energy vehicle is provided, comprising: acquiring multi-source driving data of the new energy vehicle, wherein the multi-source driving data includes: vehicle navigation data, vehicle status data, and driver operation intention data; analyzing the multi-source driving data using a pre-trained operating condition prediction model to obtain the operating condition type, operating condition duration, and operating condition parameters of the target operating condition that the new energy vehicle is about to enter; determining the thermal regulation requirements of multiple thermal management subsystems of the new energy vehicle during the operating condition duration based on the operating condition parameters, wherein the thermal management subsystems include: a battery thermal management subsystem, a motor and electronic control thermal management subsystem, and a cabin air conditioning thermal management subsystem; performing global collaborative thermal management decision-making based on the operating condition type and the thermal regulation requirements of multiple thermal management subsystems to determine the thermal management objectives of each thermal management subsystem, wherein the thermal management objectives include target operating state parameters; and sending thermal management control commands corresponding to their respective thermal management objectives to each thermal management subsystem before the new energy vehicle enters the target operating condition.

[0006] Optionally, the method further includes: after the new energy vehicle enters the target operating condition, acquiring the actual operating status parameters of each thermal management subsystem; if the parameter difference between the actual operating status parameter of any thermal management subsystem and the corresponding target operating status parameter is greater than a preset threshold, adjusting the thermal management control command corresponding to the thermal management subsystem based on the target operating status parameter and parameter difference, and sending the adjusted thermal management control command to the thermal management subsystem.

[0007] Optionally, multi-source driving data of new energy vehicles is acquired, including: acquiring in-vehicle navigation data, wherein the in-vehicle navigation data includes at least one of the following: road conditions, speed limits, altitude changes, and destination distance of the road segment to be driven; acquiring vehicle status data, wherein the vehicle status data includes at least one of the following: vehicle speed, battery state of charge, charging and discharging power and temperature, motor speed, load rate and temperature, electronic control operating temperature, and cooling medium temperature; acquiring operation intention data, wherein the operation intention data includes at least one of the following: accelerator pedal opening change rate, braking frequency, gear selection, driving mode selection, and cabin set temperature; and performing noise reduction and standardization processing on the in-vehicle navigation data, vehicle status data, and operation intention data to obtain multi-source driving data.

[0008] Optionally, the training process of the working condition prediction model includes: constructing an initial prediction model, wherein the initial prediction model is an error backpropagation neural network; acquiring multiple sets of historical multi-source driving data under various working conditions to construct a training sample set, wherein each set of historical multi-source driving data is used as a training sample, and the working condition type, working condition duration, and working condition parameters within a preset time period after the collection time of each set of historical multi-source driving data are determined as the corresponding sample labels, and the working condition type includes at least one of the following: high temperature uphill, low temperature downhill, urban congestion, fast charging start; using the training sample set to iteratively train the initial prediction model to obtain the working condition prediction model.

[0009] Optionally, the operating parameters include at least one of the following: battery charging and discharging power, motor load rate, and vehicle speed. Based on the operating parameters, the thermal regulation requirements of multiple thermal management subsystems of the new energy vehicle during the duration of the operating conditions are determined, including: for the battery thermal management subsystem, determining the target operating temperature of the battery based on the battery charging and discharging power, and determining the thermal regulation requirements of the battery thermal management subsystem based on the difference between the current battery temperature and the target operating temperature; for the motor and electronic control thermal management subsystem, determining the heat generation rate of the motor based on the motor load rate, and determining the thermal regulation requirements of the motor and electronic control thermal management subsystem based on the heat generation rate, the current temperature of the motor, and the rated maximum operating temperature; for the cabin air conditioning thermal management subsystem, determining the cabin wind resistance heat transfer efficiency based on the vehicle speed, and determining the thermal regulation requirements of the cabin air conditioning thermal management subsystem based on the wind resistance heat transfer efficiency, the current ambient temperature, and the cabin set temperature.

[0010] Optionally, a global collaborative thermal management decision is made based on the operating condition type and the thermal regulation requirements of multiple thermal management subsystems to determine the thermal management objectives of each thermal management subsystem. This includes: determining the thermal management objectives of each thermal management subsystem based on its thermal regulation requirements when there are no conflicts among the thermal regulation requirements of multiple thermal management subsystems; determining a target priority table corresponding to the operating condition type when there are conflicts among the thermal regulation requirements of multiple thermal management subsystems, wherein the target priority table includes the management priority of each thermal management subsystem, and the management priority of each thermal management subsystem is different in the priority tables corresponding to different operating condition types; correcting the thermal regulation requirements of each thermal management subsystem according to the target priority table while ensuring that each thermal management subsystem can operate normally, wherein the higher the priority of the thermal management subsystem, the smaller the difference between the corrected thermal regulation requirements and the initial thermal regulation requirements; and determining the thermal management objectives of each thermal management subsystem based on the corrected thermal regulation requirements of each thermal management subsystem.

[0011] Optionally, the method further includes: when the parameter difference between the actual operating state parameters of any thermal management subsystem and the corresponding target operating state parameters is greater than a preset threshold, performing online iterative training on the operating condition prediction model based on the parameter difference, and updating the model parameters of the operating condition prediction model.

[0012] According to another aspect of the embodiments of this application, a vehicle thermal management device for a new energy vehicle is also provided, comprising: an acquisition module for acquiring multi-source driving data of the new energy vehicle, wherein the multi-source driving data includes: vehicle navigation data, vehicle status data, and driver operation intention data; a prediction module for analyzing the multi-source driving data using a pre-trained operating condition prediction model to obtain the operating condition type, operating condition duration, and operating condition parameters of the target operating condition that the new energy vehicle is about to enter; an analysis module for determining the thermal regulation requirements of each of the multiple thermal management subsystems of the new energy vehicle during the operating condition duration based on the operating condition parameters, wherein the thermal management subsystems include: a battery thermal management subsystem, a motor and electronic control thermal management subsystem, and a cabin air conditioning thermal management subsystem; a decision module for making a global collaborative thermal management decision based on the operating condition type and the thermal regulation requirements of the multiple thermal management subsystems to determine the thermal management target of each thermal management subsystem, wherein the thermal management target includes target operating state parameters; and a management module for sending thermal management control commands corresponding to their respective thermal management targets to each thermal management subsystem before the new energy vehicle enters the target operating condition.

[0013] According to another aspect of the embodiments of this application, a computer program product is also provided, the computer program product comprising: a computer program, wherein when the computer program is executed by a processor, it implements the above-described method for thermal management of new energy vehicles.

[0014] According to another aspect of the embodiments of this application, a new energy vehicle is also provided, the new energy vehicle including: a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the above-described new energy vehicle thermal management method through the computer program.

[0015] In this embodiment, a pre-trained operating condition prediction model is used to analyze multi-source driving data to obtain the operating condition type, duration, and parameters of the target operating condition that the new energy vehicle is about to enter. This enables forward-looking prediction of the thermal demand operating conditions of the new energy vehicle. Based on the operating condition parameters, the thermal management subsystems of the new energy vehicle, such as the battery thermal management subsystem, motor and electronic control thermal management subsystem, and cabin air conditioning thermal management subsystem, are determined, along with their respective thermal regulation requirements during the operating condition duration. Global collaborative thermal management decisions are made based on the operating condition type and the thermal regulation requirements of multiple thermal management subsystems to determine the thermal management objectives of each subsystem. Before the new energy vehicle enters the target operating condition, thermal management control commands corresponding to their respective thermal management objectives are sent to each thermal management subsystem. This achieves proactive, forward-looking, and precise control of the new energy vehicle's thermal management system, eliminating thermal response lag caused by sudden changes in operating conditions, enhancing the collaborative efficiency and operational stability of multiple subsystems, and significantly improving the vehicle's range and the reliability of the thermal management system while ensuring the thermal safety of core components and passenger comfort. It effectively solves the technical problem of traditional passive feedback-based vehicle thermal management control logic response lag, which makes it difficult to guarantee thermal safety requirements. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0017] Figure 1 This is a schematic diagram of an optional vehicle thermal management method for a new energy vehicle according to an embodiment of this application;

[0018] Figure 2 This is an optional flowchart for training a working condition prediction model according to an embodiment of this application;

[0019] Figure 3 This is a schematic diagram of heat exchange between optional thermal management subsystems according to an embodiment of this application;

[0020] Figure 4 This is a schematic diagram of the execution flow of a vehicle thermal management method for a new energy vehicle according to an embodiment of this application;

[0021] Figure 5 This is a schematic diagram of an optional vehicle thermal management device for a new energy vehicle according to an embodiment of this application;

[0022] Figure 6 This is a schematic diagram of an optional electronic device according to an embodiment of this application. Detailed Implementation

[0023] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first," "second," etc., used in the specification, claims, and drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] Example 1

[0026] According to an embodiment of this application, a vehicle thermal management method for a new energy vehicle is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0027] Figure 1 This is a schematic flowchart of a vehicle thermal management method for a new energy vehicle according to an embodiment of this application, as shown below. Figure 1 As shown, the method includes the following steps S102-S110:

[0028] Step S102: Obtain multi-source driving data of the new energy vehicle, including: vehicle navigation data, vehicle status data and driver operation intention data.

[0029] Optionally, the aforementioned multi-source driving data refers to multi-dimensional information used to characterize the vehicle's operating environment and dynamic behavior, including but not limited to in-vehicle navigation data, vehicle status data, and driver's operational intent data. Specifically, in-vehicle navigation data reflects the path ahead, vehicle status data reflects the real-time operating parameters of each subsystem of the new energy vehicle, and driver's operational intent data reflects the driver's behavioral tendencies.

[0030] Step S104: Analyze the multi-source driving data using the pre-trained working condition prediction model to obtain the working condition type, duration, and parameters of the target working condition that the new energy vehicle is about to enter.

[0031] Optionally, the above-mentioned operating conditions refer to the driving states and driving environment categories that new energy vehicles will soon enter, including but not limited to typical driving conditions such as high-temperature hill climbing, low-temperature downhill driving, urban congestion, fast charging start-up, flat road cruising, high-speed driving and idling parking, as well as special driving conditions such as driving in rainy weather and driving on icy and snowy roads.

[0032] Optionally, the above-mentioned operating parameters are quantitative indicators used to describe the key physical characteristics and dynamic properties of the target operating conditions, including but not limited to road slope percentage, battery charging and discharging power, motor load rate, vehicle speed, and ambient temperature change trend.

[0033] Step S106: Determine the thermal regulation requirements of each of the multiple thermal management subsystems of the new energy vehicle during the duration of the operating condition based on the operating condition parameters. The thermal management subsystems include: battery thermal management subsystem, motor and electronic control thermal management subsystem, and cabin air conditioning thermal management subsystem.

[0034] Optionally, the aforementioned thermal management subsystem is a functional unit in a new energy vehicle responsible for temperature control of specific components, including but not limited to the battery thermal management subsystem, the motor and electronic control thermal management subsystem, and the cabin air conditioning thermal management subsystem. Specifically, the battery thermal management subsystem regulates the temperature of the power battery to maintain its operation within a high-efficiency and safe operating range, including a coolant circulation loop, a refrigerant direct cooling loop, a heating device, and a temperature sensor; the motor and electronic control thermal management subsystem controls the heat dissipation and insulation of the drive motor and power electronic devices, including a water pump, electronic expansion valve, oil cooler, radiator, and temperature monitoring module; and the cabin air conditioning thermal management subsystem regulates the temperature and humidity of the passenger compartment to ensure comfort, including a compressor, evaporator, condenser, blower, damper actuator, and temperature and humidity sensors.

[0035] Optionally, the aforementioned thermal regulation requirements are the temperature control targets and energy distribution requirements that each thermal management subsystem needs to achieve in order to adapt to the heat production and heat consumption characteristics under the target operating conditions. These include, but are not limited to, the increase in coolant flow rate, the reduction of heat dissipation threshold, or the start of preheating circuit required by the battery thermal management subsystem; the increase in water pump speed, the activation of oil cooler, or the graded adjustment of heat dissipation power required by the motor and electronic control thermal management subsystem; and the reduction of cooling power, the activation of heating mode, the adjustment of blower air volume, or the optimization of refrigerant distribution ratio required by the cabin air conditioning thermal management subsystem.

[0036] Step S108: Based on the operating condition type and the thermal regulation requirements of multiple thermal management subsystems, a global collaborative thermal management decision is made to determine the thermal management objectives of each thermal management subsystem, wherein the thermal management objectives include target operating state parameters.

[0037] Optionally, the aforementioned thermal management objective is the optimal set of control commands set for each thermal management subsystem to achieve efficient and coordinated operation of the thermal management system of new energy vehicles. These include, but are not limited to, the coolant flow rate setpoint, heat dissipation start threshold, and preheating circuit opening time of the battery thermal management subsystem; the water pump speed target, oil cooler working mode, and heat dissipation power level of the motor and electronic control thermal management subsystem; the compressor frequency, blower speed, refrigerant distribution ratio, and heater start / stop status of the cabin air conditioning thermal management subsystem; and target operating status parameters such as valve opening degree and energy flow direction between subsystems.

[0038] Step S110: Before the new energy vehicle enters the target operating condition, send thermal management control commands corresponding to their respective thermal management targets to each thermal management subsystem.

[0039] In this embodiment, a pre-trained operating condition prediction model is used to analyze multi-source driving data to obtain the operating condition type, duration, and parameters of the target operating condition that the new energy vehicle is about to enter. This enables forward-looking prediction of the thermal demand operating conditions of the new energy vehicle. Based on the operating condition parameters, the thermal management subsystems of the new energy vehicle, such as the battery thermal management subsystem, motor and electronic control thermal management subsystem, and cabin air conditioning thermal management subsystem, are determined, along with their respective thermal regulation requirements during the operating condition duration. Global collaborative thermal management decisions are made based on the operating condition type and the thermal regulation requirements of multiple thermal management subsystems to determine the thermal management objectives of each subsystem. Before the new energy vehicle enters the target operating condition, thermal management control commands corresponding to their respective thermal management objectives are sent to each thermal management subsystem. This achieves proactive, forward-looking, and precise control of the new energy vehicle's thermal management system, eliminating thermal response lag caused by sudden changes in operating conditions, enhancing the collaborative efficiency and operational stability of multiple subsystems, and significantly improving the vehicle's range and the reliability of the thermal management system while ensuring the thermal safety of core components and passenger comfort. It effectively solves the technical problem of traditional passive feedback-based vehicle thermal management control logic response lag, which makes it difficult to guarantee thermal safety requirements.

[0040] The following section explains each step of the whole vehicle thermal management method for new energy vehicles in conjunction with the specific implementation process.

[0041] As an optional solution, regarding step S102 above, obtaining multi-source driving data of new energy vehicles includes:

[0042] Obtain in-vehicle navigation data, which includes at least one of the following: road conditions, speed limits, altitude changes, and distance to the destination for the route to be traveled.

[0043] For example, the above-mentioned method of obtaining vehicle navigation data can be understood as follows: the vehicle navigation system receives the destination set by the user and plans the optimal driving route, generates trajectory data containing continuous path points, and calls a high-precision digital elevation model and a real-time traffic information database to analyze the road segment to be driven on the path, and extracts the road conditions of the road segment to be driven (including the geometric attributes of the road segment, such as flat road, uphill, downhill, continuous curves, traffic operation status, such as smooth, slow, congested, stationary, and potential changes in driving mode, such as about to enter a tunnel, bridge, school zone or speed limit zone), road speed limit, altitude change, and distance between the road segment to be driven and the destination.

[0044] Acquire vehicle status data, which includes at least one of the following: vehicle speed, battery state of charge, charging and discharging power and temperature, motor speed, load rate and temperature, electronic control operating temperature, and cooling medium temperature.

[0045] For example, the above-mentioned method of acquiring vehicle status data can be understood as follows: real-time acquisition through various sensors and electronic control units integrated inside the new energy vehicle, including: the battery management system acquiring the battery's state of charge, charging and discharging power, and temperature through high-precision voltage, current, and temperature sensors; the motor controller acquiring the vehicle's driving speed, motor speed, load rate, and temperature through speed encoders, current sensors, and temperature probes; the electronic control unit monitoring the electronic control operating temperature through thermocouples or infrared sensors; and the cooling system acquiring the cooling medium temperature in real time through flow meters and pressure sensors, and transmitting it to the thermal management system via the vehicle communication network.

[0046] Acquire operational intent data, which includes at least one of the following: accelerator pedal opening change rate, braking frequency, gear selection, driving mode selection, and cabin temperature setting.

[0047] For example, the acquisition method of the above-mentioned operation intention data can be understood as follows: real-time collection and analysis through the vehicle human-machine interaction system and driving behavior perception module, specifically including: collecting the accelerator pedal opening and its rate of change through the pedal position sensor to reflect the intensity and abruptness of the driver's acceleration intention; obtaining the braking frequency through the brake pressure sensor and pedal travel sensor to identify the driver's deceleration intention; outputting gear information by the transmission control unit, including forward gear, reverse gear, neutral gear and driving mode selection (such as economy, sport, off-road, snow mode), reflecting the vehicle's power distribution and energy efficiency priority preference; and setting the cabin temperature by the air conditioning control panel to determine the priority of the occupants' thermal comfort needs.

[0048] To eliminate the differences in dimensions, magnitudes, and distributions of multi-source driving data, noise reduction and standardization processes are performed on in-vehicle navigation data, vehicle status data, and operation intention data to obtain multi-source driving data.

[0049] For example, the above data processing operation can be understood as follows: First, the vehicle navigation data, vehicle status data, and operation intention data are timestamped according to a unified time base to ensure that the sampling time of each dimension of data is consistent; then, adaptive filtering algorithms are applied to each dimension of data, including Kalman filtering to process dynamic noise, median filtering to suppress impulse interference, and wavelet transform decomposition to remove high-frequency glitches, thereby improving the stability and signal-to-noise ratio of the signal; then, the data of each dimension is subjected to min-max standardization or Z-score standardization to map the original data of different dimensions and magnitudes to a unified interval (such as [0, 1] or [-1, 1]), eliminating the influence of dimensions and ensuring the convergence and fairness of the subsequent input condition prediction model training; finally, the processed data of each dimension are concatenated into a fixed-length multi-source driving data vector according to a preset dimension to form a standardized data sequence output with a fixed period.

[0050] As an optional solution, regarding step S104 above, Figure 2 This is an optional flowchart of the working condition prediction model training process according to an embodiment of this application, such as... Figure 2 As shown, the working condition prediction model can be trained by following these steps:

[0051] Step S11: Construct an initial prediction model, wherein the initial prediction model is an error backpropagation neural network.

[0052] For example, step S11 above can be understood as: constructing an error backpropagation neural network with a multi-layer (including input layer, output layer and hidden layer) fully connected structure, including: first, determining the network input layer dimension as the total number of features of multi-source driving data, the output layer dimension as the preset number of working condition types, and setting the number of hidden layers (usually 1~2 layers) and the number of neurons in each layer according to experience (dynamically adjusted according to the input dimension and the number of training samples); then, using Sigmoid or ReLU as the hidden layer activation function and Softmax as the output layer activation function to achieve multi-class probability output, and initializing the network weights and biases, setting hyperparameters such as learning rate, batch size and maximum number of iterations, and completing the construction of the initial prediction model.

[0053] Step S12: Obtain multiple sets of historical multi-source driving data under various working conditions to construct a training sample set. Each set of historical multi-source driving data is used as a training sample, and the working condition type, working condition duration, and working condition parameters within a preset time period after the collection time of each set of historical multi-source driving data are determined as the corresponding sample labels. The working condition type includes at least one of the following: high temperature uphill, low temperature downhill, urban congestion, and fast charging start.

[0054] For example, step S12 above can be understood as follows: conducting large-scale real-vehicle tests under various operating conditions, simultaneously collecting vehicle navigation data, vehicle status data, and operation intention data to form multiple sets of historical multi-source driving data; subsequently, based on high-precision positioning and path analysis technology, identifying the start and end times of each operating condition, dividing the driving path into multiple operating condition segments, and further dividing the multiple sets of historical multi-source driving data according to the operating condition segments; next, taking each operating condition segment as a unit, extracting the multi-source driving data within a preset time window before the start time of that operating condition segment as training samples, and using the type of the corresponding operating condition segment (such as high-temperature climbing), the duration of the operating condition (such as 120 seconds), and the operating condition parameters (such as vehicle speed of 50km / h, motor load rate of 80%, etc.) as corresponding sample labels to construct a training sample set; finally, dividing the training sample set into a training set and a test set according to the proportion, providing high-quality, generalizable supervised training samples for the initial prediction model.

[0055] Step S13: Iteratively train the initial prediction model using the training sample set to obtain the working condition prediction model.

[0056] For example, step S13 above can be understood as follows: inputting training samples into the initial prediction model, obtaining the working condition prediction result through the input layer, hidden layer and output layer, then calculating the cross-entropy loss function between the working condition prediction result and the sample label through the forward propagation network, then calculating the gradient layer by layer through the backpropagation algorithm, and updating the parameters of the initial prediction model using the Adam optimizer until the loss function converges or reaches the preset training rounds, terminating the iterative training process, and freezing the parameters of the trained initial prediction model to form a working condition prediction model with working condition prediction capability, which serves as the decision basis for subsequent forward control. The structure of the working condition prediction model is scalable and supports subsequent online incremental learning and parameter fine-tuning.

[0057] Furthermore, in step S104, the load condition prediction model can be loaded into memory. For example, the raw data of the load condition prediction model can be loaded from non-volatile memory into volatile memory so that the processor can run the load condition prediction model. The raw data of the load condition prediction model refers to unprocessed data, which typically includes the parameters and structural data of the load condition prediction model. The structural data can be the computational relationships based on the parameters, such as the forward propagation computational relationships between intermediate layers and between neurons. Specifically, the structural data can include the structure-related code of the load condition prediction model, such as code used to perform related calculations between intermediate layers and between neurons.

[0058] In one implementation, a region can be partitioned in memory for loading the load condition prediction model, which may include a structural data storage area and a parameter storage area. The structural data storage area stores structurally related code, and the parameters referenced by it can be accessed via pointers to the addresses of specific parameters in the parameter storage area. During the training of the load condition prediction model, frequent parameter updates may be required; in this case, updating the parameter values ​​in the parameter storage area is sufficient.

[0059] Through the embodiments of this application, an error backpropagation neural network is used as the initial prediction model. Multiple sets of historical multi-source driving data containing navigation paths, vehicle status and driver operation intentions are used as inputs. The actual operating conditions, duration and key parameters of the corresponding road segments to be driven are used as labels for iterative training. This achieves high-precision prediction of vehicle driving conditions in complex driving scenarios, identifies possible sudden changes in thermal demand in the future, and eliminates thermal control response lag.

[0060] As an optional approach, step S106 above determines the thermal regulation requirements of each of the multiple thermal management subsystems of the new energy vehicle during the duration of the operating condition based on the operating condition parameters.

[0061] Alternatively, the determination of the above-mentioned thermal regulation requirements can be mainly divided into the following situations:

[0062] For the battery thermal management subsystem, the target operating temperature of the battery is determined based on the battery charging and discharging power, and the thermal regulation requirements of the battery thermal management subsystem are determined based on the difference between the current battery temperature and the target operating temperature.

[0063] For example, determining the thermal regulation requirements of the battery thermal management subsystem can be understood as: based on the electrochemical characteristics and thermal balance relationship, converting the battery's power load into an optimal temperature control target, and generating a precise thermal regulation requirement signal based on the temperature deviation. The specific implementation process includes: First, based on a preset optimal battery operating temperature curve or a nonlinear function of battery charging / discharging power and optimal operating temperature, define target operating temperatures corresponding to different battery charging / discharging power ranges (e.g., a target operating temperature of 25℃ at low discharge power and 35℃ at high discharge power to reduce thermal resistance loss); then, acquire the current charging / discharging power of the battery in real time and calculate the corresponding target operating temperature using a lookup table or polynomial fitting model; next, calculate the difference between the target operating temperature and the current battery temperature reported in real time by the battery management system to obtain the temperature deviation; finally, based on the sign and magnitude of the temperature deviation, and combined with heat capacity and heat conduction models, quantify and generate the thermal regulation requirements of the battery thermal management subsystem to guide the adjustment of coolant flow rate, refrigerant distribution ratio, or heating power. For example, if the target battery operating temperature is 35℃ and the current battery temperature is 28℃, the temperature deviation is +7℃. In this case, it is necessary to actively suppress heat dissipation and reserve heat dissipation margin, generating thermal regulation requirements to increase the battery coolant flow rate or increase the refrigerant distribution ratio. This achieves thermal management feedback control from the current battery temperature to the target operating temperature.

[0064] For the motor electrical control thermal management subsystem, the heat generation rate of the motor is determined based on the motor load rate, and the thermal regulation requirements of the motor electrical control thermal management subsystem are determined based on the heat generation rate, the current temperature of the motor, and the rated maximum operating temperature.

[0065] For example, determining the thermal regulation requirements of the motor control thermal management subsystem can be understood as follows: First, based on the physical relationship between motor load loss and heat accumulation, the heat generation rate is quantified, and the required heat dissipation intensity is calculated in real time in conjunction with the thermal safety margin. The specific implementation process includes: First, based on the current motor load rate, the heat generation rate of the motor is calculated using a preset empirical formula for heat loss (e.g., copper loss is proportional to the square of the current and resistance, and iron loss is proportional to the square of the magnetic induction intensity). The heat generation rate and power are non-linearly positively correlated with the motor load rate. Next, the heat generation rate is input into the motor thermodynamic equivalent model, which includes parameters such as heat capacity, thermal resistance, and convective heat transfer coefficient, to deduce the temperature rise trend over time under the current heat dissipation conditions. Then, the deduced temperature rise trajectory is compared with the motor's rated maximum operating temperature (e.g., 130℃) to calculate the temperature safety margin (i.e., rated temperature minus the predicted peak temperature). Finally, based on the size and rate of decrease of the temperature safety margin, a gradient thermal regulation demand signal is generated. For example, when the temperature safety margin is higher than a set threshold, basic cooling is maintained; when the temperature safety margin approaches a critical value, the water pump speed and coolant flow rate are linearly increased; and when the temperature safety margin is lower than a safety threshold, an emergency cooling mode is triggered to ensure that the motor is always at a safe temperature under high load.

[0066] For the cabin air conditioning thermal management subsystem, the cabin's wind resistance heat exchange efficiency is determined based on the vehicle's driving speed, and the thermal regulation requirements of the cabin air conditioning thermal management subsystem are determined based on the wind resistance heat exchange efficiency, the current ambient temperature, and the cabin set temperature.

[0067] For example, determining the thermal regulation requirements of the motor control thermal management subsystem can be understood as: incorporating vehicle driving dynamics into the cabin thermal load calculation, dynamically correcting the impact of the external environment on the heat exchange inside the cabin, thereby accurately quantifying the thermal regulation requirements of the air conditioning system. The specific implementation process includes: First, based on the vehicle's current speed, the wind speed and airflow disturbance intensity on the vehicle body surface are calculated using an aerodynamic model, thereby deriving the drag heat transfer efficiency of the cabin enclosure structure (such as glass and body panels). This drag heat transfer efficiency increases non-linearly with the square of the vehicle speed. Next, combining the current ambient temperature and the user-set target cabin temperature, a cabin heat load equation is constructed based on the external heat inflow / outflow efficiency caused by drag heat transfer, occupant heat dissipation, and solar radiation. Then, the difference between the current cabin heat load and the cooling / heating capacity provided by the air conditioning system is calculated to generate the required thermal regulation power. Finally, the thermal regulation power is mapped to the thermal regulation demand of the air conditioning actuator, adjusting the compressor power, blower speed, and mixing damper opening of the air conditioning system to achieve adaptive adjustment of cooling / heating intensity according to changes in vehicle speed. For example, at high speeds, if the cabin cools too quickly due to strong ventilation, the cooling power is reduced to avoid excessive cooling. At low speeds or when stationary, the cooling is enhanced to compensate for the weakening of convective heat transfer, thereby optimizing energy consumption while ensuring comfort.

[0068] Unlike existing technologies that independently control each thermal management subsystem, where each subsystem manages its own thermal needs based solely on feedback from its sensors, this embodiment aims to achieve global thermal demand balance by avoiding conflicts in the thermal management needs of individual subsystems. Based on the thermal adjustment needs of multiple subsystems, it coordinates the adjustment of three major thermal management subsystems: battery thermal management, motor and electronic control thermal management, and cabin air conditioning thermal management. Before changes in operating conditions, the operating states of each subsystem are adjusted synchronously, completely eliminating the contradictions in thermal demand and the problem of energy consumption superposition under independent control. This achieves global intelligent collaborative decision-making for the entire vehicle's thermal management system. For example, when a high-temperature climbing condition is anticipated, the high heat dissipation demand of the motor overlaps with the cabin cooling demand; therefore, priority should be given to ensuring motor heat dissipation, and the cabin cooling power should be appropriately reduced. Furthermore, under low-temperature downhill conditions, there are heat flow interactions and resource sharing relationships between the battery thermal management subsystem, motor and electronic control thermal management subsystem, and cabin air conditioning thermal management subsystem. Figure 3 As shown, coordinated control of the thermal management subsystem is even more necessary.

[0069] As an optional approach, regarding step S108 above, a global collaborative thermal management decision is made based on the operating condition type and the thermal regulation requirements of multiple thermal management subsystems to determine the thermal management objectives of each thermal management subsystem.

[0070] Optionally, it can be determined whether the execution paths of the thermal regulation requirements of each thermal management subsystem share the same actuator or the same energy source (such as refrigerant circuit or water pump flow) and whether the direction of heat flow is the same. Based on the judgment result, it can be determined whether there is a conflict in the thermal regulation requirements of multiple thermal management subsystems. If it is detected that there is no overlap of actuators, no power competition, and no conflict in the direction of heat flow (such as no one needing to be heated while the other needs to be cooled), it is determined that there is no conflict in the thermal regulation requirements, thereby determining the thermal management objectives of each thermal management subsystem.

[0071] Optionally, the thermal management objectives of each thermal management subsystem are determined as follows:

[0072] For example, when there is no conflict in the thermal regulation requirements of multiple thermal management subsystems, determining the thermal management objectives of each thermal management subsystem based on its thermal regulation requirements can be understood as follows: when there is no conflict in the thermal regulation requirements of multiple thermal management subsystems, for each thermal management subsystem, based on its corresponding thermal regulation requirements and a preset thermal management strategy model, independently calculates the thermal management objectives corresponding to the thermal regulation requirements, including parameters such as target temperature, target flow rate, and target power; finally, the thermal management objectives of each subsystem are output in parallel as input instructions for the actuator, ensuring that each thermal management subsystem achieves independent optimization without competing for resources.

[0073] When multiple thermal management subsystems have conflicting thermal regulation requirements, a target priority table corresponding to the target operating condition type is determined. This target priority table includes the management priority of each thermal management subsystem, with different management priorities for each subsystem in different operating condition types. While ensuring the normal operation of each thermal management subsystem, the thermal regulation requirements of each subsystem are corrected based on the target priority table. The higher the priority of a thermal management subsystem, the smaller the difference between the corrected and initial thermal regulation requirements. The thermal management objectives of each thermal management subsystem are then determined based on the corrected thermal regulation requirements.

[0074] For example, the target priority table corresponding to the target operating condition type mentioned above can be understood as follows: based on historical experience or actual vehicle testing, a unique target priority table is established for each type of operating condition. This target priority table takes the thermal management subsystem as the dimension and clarifies the relative priority ranking and resource allocation settings of each thermal management subsystem under different operating conditions. The specific target priority table is shown in Table 1 below:

[0075] Table 1

[0076]

[0077]

[0078] For example, modifying the thermal regulation requirements of each thermal management subsystem can be understood as follows: obtaining the current operating condition type, and indexing and matching it in a preset target priority table based on the operating condition type, directly retrieving the corresponding relative priority sorting and resource allocation settings, and performing resource allocation and requirement modification step by step: prioritizing the thermal regulation requirements of the highest priority thermal management subsystem; within the remaining available resources, trying to meet the thermal regulation requirements of the second highest priority thermal management subsystem; if the remaining available resources are insufficient, linearly modifying the thermal regulation requirements of the second highest priority thermal management subsystem proportionally; only when the thermal regulation requirements of the aforementioned subsystems are met and there are still remaining available resources are the thermal regulation requirements of the lowest priority thermal management subsystem allowed to be met; otherwise, the thermal regulation requirements of the lowest priority thermal management subsystem are modified to maintain minimum ventilation or shut down active regulation, retaining only passive heat exchange capacity.

[0079] For example, determining the thermal management objectives of each thermal management subsystem can be understood as follows: For the battery thermal management subsystem, based on the corrected thermal regulation requirements and combined with the battery internal resistance thermal model, its target temperature range (e.g., 30–35℃ during high-power discharge and 15–25℃ during low-temperature charging) is calculated as the thermal management objective; for the motor and electronic control thermal management subsystem, based on the corrected thermal regulation requirements and combined with the motor copper / iron loss heat generation model and the temperature resistance limit of the insulation material, its target temperature range (e.g., 80–95℃ during continuous high load) is calculated as the thermal management objective; for the cabin air conditioning thermal management subsystem, based on the corrected thermal regulation requirements and combined with ambient temperature, vehicle speed (affecting wind resistance heat transfer), solar radiation intensity, and user-set temperature, the net heat load compensation required to achieve comfort (e.g., maintaining within ±1.5℃ of the set value) is calculated as the thermal management objective.

[0080] Through the embodiments of this application, a priority table matching mechanism for multiple thermal management subsystems based on dynamic matching of operating conditions is adopted. When thermal regulation demand conflicts, the thermal regulation demand of each thermal management subsystem is weighted and corrected according to the preset priority. The thermal regulation demand of high-priority thermal management subsystems is given priority, realizing the global optimal allocation of thermal resources and multi-objective collaborative balance. Under the premise of ensuring the safety and performance of core components, the system energy consumption is reduced, control conflicts are avoided, and the thermal management efficiency of the whole vehicle is improved.

[0081] For example, regarding the above step S110, before the new energy vehicle enters the target operating condition, sending thermal management control instructions corresponding to their respective thermal management targets to each thermal management subsystem can be understood as follows: after the operating condition prediction model outputs the target operating condition type and the expected start time (such as "entering the high temperature ramp-up operating condition in 30 seconds"), immediately calling the thermal management target (such as the battery target temperature of 35°C) that matches the target operating condition type and operating condition parameters, and generating the corresponding thermal management control instructions, such as increasing the motor coolant flow rate to 12L / min and reducing the cabin fan speed to 1200rpm. Based on the physical thermal inertia and actuator response delay characteristics of each thermal management subsystem, the pre-trigger advance of the corresponding thermal management control commands is calculated. For example, the battery thermal management system, due to its large heat capacity and slow response, needs to start 15–25 seconds in advance; the motor cooling circuit responds faster, requiring 10–15 seconds in advance; and the cabin air conditioning, due to its small duct inertia, can complete adjustment 5–10 seconds in advance. Before the pre-trigger advance, the thermal management control commands are encapsulated and issued to each thermal management subsystem to ensure that the thermal management system has completed state switching before the heat load increases, forming a lag-free closed-loop control and fundamentally eliminating thermal response delay.

[0082] Since the above-mentioned operating condition predictions and thermal management control command generation are all based on historical data and physical models, there are system errors, environmental disturbances, sensor drift, or unmodeled dynamics. If only thermal management control commands are relied upon, the actual control accuracy cannot be guaranteed. Therefore, real-time feedback must be established to dynamically correct thermal management control commands to ensure that the thermal management objectives of each thermal management subsystem are consistent with the current actual driving conditions of new energy vehicles.

[0083] As an optional solution, the feedback adjustment of thermal management control commands can be performed in the following manner:

[0084] After the new energy vehicle enters the target operating condition, the actual operating status parameters of each thermal management subsystem are acquired. If the parameter difference between the actual operating status parameter of any thermal management subsystem and the corresponding target operating status parameter is greater than a preset threshold, the thermal management control command corresponding to the thermal management subsystem is adjusted based on the target operating status parameter and parameter difference of the thermal management subsystem, and the adjusted thermal management control command is sent to the thermal management subsystem.

[0085] Optionally, the above-mentioned actual operating status parameters are physical quantity feedback information of each subsystem in real time during the operation of the thermal management system under the target operating conditions. These include, but are not limited to, battery temperature, battery coolant flow rate, motor operating temperature, electronic control heat dissipation power, cabin temperature setpoint, air conditioning compressor operating power, coolant circuit pressure, water pump speed, fan air volume, electronic expansion valve opening, and current and power consumption of each actuator.

[0086] Optionally, the aforementioned target operating state parameters are dynamically generated based on the thermal management target, and are the expected control parameter values ​​that each thermal management subsystem should achieve under ideal operating conditions. These include, but are not limited to, the target temperature range of the battery, the target flow rate of the battery coolant, the target operating temperature of the motor, the target heat dissipation power of the electronic control system, the target temperature setpoint of the cabin, the target operating power of the air conditioning compressor, the target pressure of the coolant circuit, the target speed of the water pump, the target air volume of the fan, and the target opening of the electronic expansion valve. These parameters are used to assess the degree of deviation between the actual operating state and the expected target, and to drive the dynamic correction of the control commands.

[0087] For example, the dynamic correction of the above control commands can be understood as follows: First, after obtaining the actual operating state parameters of each thermal management subsystem, they are compared item by item with the corresponding target operating state parameters to calculate the parameter differences between each parameter. The parameter differences of different physical quantities such as temperature, flow rate, and power are then normalized to achieve a unified assessment. Next, a preset threshold is used to determine whether the parameter differences exceed the limits. The preset threshold is dynamically configured based on the thermal safety boundary, control accuracy requirements, and response characteristics of each thermal management subsystem. For example, the allowable deviation for battery temperature is ±2℃, while the allowable deviation for cabin temperature is ±1.5℃. If these limits are exceeded, correction logic is triggered. Then, when the parameter difference of any thermal management subsystem exceeds the corresponding preset threshold... The system immediately initiates a closed-loop correction mechanism, generating adjusted control commands based on the target operating state parameters and parameter differences. For example, for cases with small parameter differences, proportional correction is used, linearly adjusting the actuator setpoint according to the deviation ratio, such as increasing the water pump speed by 5% for every 0.5°C increase. For cases with significant parameter differences, an integral term can be introduced to eliminate steady-state error, continuously accumulating the deviation and adding the adjustment amount until the error returns to zero. For huge parameter differences approaching safety limits, an emergency intervention mechanism is activated, directly enforcing safety protection commands, such as immediately increasing the cooling power to the maximum limit. Finally, the corrected control commands are sent to the controller of the corresponding thermal management subsystem via the vehicle communication bus, achieving continuous adaptive correction of the thermal management control commands.

[0088] Optionally, if the difference between the actual operating state parameters of any thermal management subsystem and the corresponding target operating state parameters is greater than a preset threshold, the operating condition prediction model is iteratively trained online based on the parameter difference to update the model parameters of the operating condition prediction model.

[0089] For example, firstly, when the difference between the actual operating state parameters and the target operating state parameters of any thermal management subsystem exceeds a preset threshold, it is determined that the operating condition prediction model has a target operating condition prediction error. Based on the actual operating state parameters and the magnitude of the parameter difference, a lightweight online iterative training process is initiated for the operating condition prediction model. An incremental learning algorithm (such as online gradient descent or mini-batch stochastic gradient descent) is used to locally update the parameters of the operating condition prediction model, avoiding the computational overhead and real-time conflicts caused by full retraining. The updated operating condition prediction model parameters are written into the controller's online model cache area, and the new parameters are enabled in the next stage of target operating condition prediction. The historical model is retained through a version management mechanism, which supports safe rollback when performance is rolled back. This allows the operating condition prediction model to continuously adapt to individual vehicle differences, environmental changes, and system aging in actual operation, realizing an intelligent leap from static pre-training to dynamic adaptive optimization.

[0090] Figure 4This is a schematic diagram illustrating the execution flow of a vehicle thermal management method for a new energy vehicle according to an embodiment of this application, as shown below. Figure 4 As shown, the execution process of the vehicle thermal management method for new energy vehicles includes:

[0091] Step 1: Obtain multi-source driving data of new energy vehicles;

[0092] Step 2: Predict the target working condition using a pre-trained working condition prediction model;

[0093] Step 3: Determine the thermal regulation requirements of multiple thermal management subsystems;

[0094] Step 4: Based on the target operating conditions and the thermal regulation requirements of the thermal management subsystem, collaboratively determine the thermal management objectives of each subsystem;

[0095] The fifth step is to generate thermal management control commands based on the thermal management objectives and then send these commands to the corresponding thermal management subsystems.

[0096] Step 6: Determine whether the difference between the actual operating status parameters and the target operating status parameters is greater than a preset threshold. If it is greater, proceed to step 7; otherwise, proceed to step 8.

[0097] Step 7: Adjust the thermal management control commands corresponding to the thermal management subsystem based on the target operating state parameters and parameter differences, update the model parameters of the operating condition prediction model, send the adjusted thermal management control commands to Step 5, and send the updated model parameters of the operating condition prediction model to Step 2.

[0098] Step 8: Maintain the current thermal management control commands and repeat the above steps in the next target operating condition.

[0099] Through the above steps, multi-source driving data, including onboard navigation data, vehicle status data, and driver's operational intent data, are acquired from new energy vehicles. This enables a comprehensive perception of the operating environment and driver behavior of new energy vehicles, providing multi-dimensional, high-confidence input data for target operating condition prediction. Analyzing the multi-source driving data using a pre-trained operating condition prediction model yields the type, duration, and parameters of the target operating condition that the new energy vehicle is about to enter. This enables proactive identification of changes in thermal demand, transforming passive response into active prediction and significantly shortening the response time of the thermal management system. Based on operating condition types and multiple thermal management subsystems... The system enables global collaborative thermal management decision-making based on thermal regulation requirements, defining the thermal management objectives of each thermal management subsystem. This achieves resource coordination and priority scheduling among different thermal management subsystems, avoiding energy consumption accumulation and objective conflicts caused by independent control of each subsystem, thus improving the overall thermal management efficiency of the thermal management system. Before the new energy vehicle enters the target operating condition, thermal management control commands corresponding to their respective thermal management objectives are sent to each thermal management subsystem, enabling proactive execution of thermal management control commands. This shifts from post-temperature over-limit adjustment to pre-conditioning, completely eliminating the risk of thermal runaway in the thermal management system and significantly improving its safety and energy efficiency. Furthermore, after controlling the new energy vehicle with thermal management control commands predicted based on the predicted operating condition type, the actual operating status parameters of the new energy vehicle can be obtained to adjust the thermal management control commands and the model parameters of the operating condition prediction model, improving the accuracy of subsequent operating condition predictions, forming a closed-loop control system, and ensuring the accuracy of thermal management control commands generated based on the operating condition type.

[0100] Example 2

[0101] According to an embodiment of this application, a vehicle thermal management device for new energy vehicles is also provided for implementing the vehicle thermal management method for new energy vehicles in Embodiment 1, such as... Figure 5 As shown, the vehicle thermal management device for this new energy vehicle includes at least: an acquisition module 51, a prediction module 52, an analysis module 53, a decision-making module 54, and a management module 55, wherein:

[0102] The acquisition module 51 is used to acquire multi-source driving data of new energy vehicles, including: vehicle navigation data, vehicle status data and driver operation intention data.

[0103] The prediction module 52 is used to analyze multi-source driving data using a pre-trained working condition prediction model to obtain the working condition type, duration and parameters of the target working condition that the new energy vehicle is about to enter.

[0104] Analysis module 53 is used to determine the thermal regulation requirements of each of the multiple thermal management subsystems of the new energy vehicle during the duration of the operating condition based on the operating condition parameters. The thermal management subsystems include: battery thermal management subsystem, motor and electronic control thermal management subsystem, and cabin air conditioning thermal management subsystem.

[0105] Decision module 54 is used to make global collaborative thermal management decisions based on operating condition type and thermal regulation requirements of multiple thermal management subsystems, and to determine the thermal management objectives of each thermal management subsystem, wherein the thermal management objectives include target operating state parameters;

[0106] The management module 55 is used to send thermal management control commands corresponding to their respective thermal management targets to each thermal management subsystem before the new energy vehicle enters the target operating condition.

[0107] The following section explains the functions of each module of the thermal management device for new energy vehicles, based on a specific implementation process.

[0108] Optionally, the above-mentioned device is further configured to acquire the actual operating status parameters of each thermal management subsystem after the new energy vehicle enters the target operating condition; if the parameter difference between the actual operating status parameter of any thermal management subsystem and the corresponding target operating status parameter is greater than a preset threshold, adjust the thermal management control command corresponding to the thermal management subsystem based on the target operating status parameter and parameter difference of the thermal management subsystem, and send the adjusted thermal management control command to the thermal management subsystem.

[0109] Optionally, the aforementioned acquisition module is further used to acquire multi-source driving data of the new energy vehicle, including: acquiring in-vehicle navigation data, wherein the in-vehicle navigation data includes at least one of the following: road conditions, speed limits, altitude changes, and destination distance of the road segment to be driven; acquiring vehicle status data, wherein the vehicle status data includes at least one of the following: vehicle speed, battery state of charge, charging and discharging power and temperature, motor speed, load rate and temperature, electronic control operating temperature, and cooling medium temperature; acquiring operation intention data, wherein the operation intention data includes at least one of the following: accelerator pedal opening change rate, braking frequency, gear selection, driving mode selection, and cabin set temperature; and performing noise reduction and standardization processing on the in-vehicle navigation data, vehicle status data, and operation intention data to obtain multi-source driving data.

[0110] Optionally, the aforementioned prediction module is further used in the training process of the working condition prediction model, including: constructing an initial prediction model, wherein the initial prediction model is an error backpropagation neural network; acquiring multiple sets of historical multi-source driving data under various working conditions to construct a training sample set, wherein each set of historical multi-source driving data is used as a training sample, and the working condition type, working condition duration, and working condition parameters within a preset time period after the collection time of each set of historical multi-source driving data are determined as the corresponding sample labels, wherein the working condition type includes at least one of the following: high temperature uphill, low temperature downhill, urban congestion, fast charging start; and iteratively training the initial prediction model using the training sample set to obtain the working condition prediction model.

[0111] Optionally, the operating parameters include at least one of the following: battery charging and discharging power, motor load rate, and vehicle speed. The aforementioned analysis module is also used to determine the thermal regulation requirements of multiple thermal management subsystems of the new energy vehicle during the duration of the operating conditions based on the operating parameters, including: for the battery thermal management subsystem, determining the target operating temperature of the battery based on the battery charging and discharging power, and determining the thermal regulation requirements of the battery thermal management subsystem based on the difference between the current battery temperature and the target operating temperature; for the motor and electronic control thermal management subsystem, determining the heat generation rate of the motor based on the motor load rate, and determining the thermal regulation requirements of the motor and electronic control thermal management subsystem based on the heat generation rate, the current temperature of the motor, and the rated maximum operating temperature; for the cabin air conditioning thermal management subsystem, determining the cabin wind resistance heat transfer efficiency based on the vehicle speed, and determining the thermal regulation requirements of the cabin air conditioning thermal management subsystem based on the wind resistance heat transfer efficiency, the current ambient temperature, and the cabin set temperature.

[0112] Optionally, the aforementioned decision-making module is further configured to perform global collaborative thermal management decisions based on operating condition types and the thermal regulation requirements of multiple thermal management subsystems, determining the thermal management objectives of each thermal management subsystem. This includes: determining the thermal management objectives of each thermal management subsystem based on its thermal regulation requirements when there are no conflicts among the thermal regulation requirements of multiple thermal management subsystems; determining a target priority table corresponding to the operating condition type of the target operating condition when there are conflicts among the thermal regulation requirements of multiple thermal management subsystems, wherein the target priority table includes the management priority of each thermal management subsystem, and the management priority of each thermal management subsystem differs in the priority tables corresponding to different operating condition types; correcting the thermal regulation requirements of each thermal management subsystem according to the target priority table while ensuring that each thermal management subsystem can operate normally, wherein the higher the priority of the thermal management subsystem, the smaller the difference between the corrected thermal regulation requirements and the initial thermal regulation requirements; and determining the thermal management objectives of each thermal management subsystem based on the corrected thermal regulation requirements of each thermal management subsystem.

[0113] Optionally, the above-mentioned device is further configured to perform online iterative training on the operating condition prediction model based on the parameter difference when the parameter difference between the actual operating state parameters of any thermal management subsystem and the corresponding target operating state parameters is greater than a preset threshold, and update the model parameters of the operating condition prediction model.

[0114] It should be noted that each module in the vehicle thermal management device for new energy vehicles in this embodiment corresponds one-to-one with each implementation step of the vehicle thermal management method for new energy vehicles in Embodiment 1. Since Embodiment 1 has been described in detail, some details not shown in this embodiment can be referred to Embodiment 1, and will not be elaborated further here.

[0115] Example 3

[0116] According to an embodiment of this application, a computer program product is also provided, which includes a computer program, wherein when the computer program is executed by a processor, it implements the vehicle thermal management method for new energy vehicles in Embodiment 1.

[0117] According to an embodiment of this application, a non-volatile storage medium is also provided, which includes a stored computer program, wherein the device containing the non-volatile storage medium executes the vehicle thermal management method for new energy vehicles in Embodiment 1 by running the computer program.

[0118] According to an embodiment of this application, a processor is also provided for running a computer program, wherein the computer program executes the vehicle thermal management method for new energy vehicles in Embodiment 1.

[0119] According to an embodiment of this application, a new energy vehicle is also provided, which includes a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the vehicle thermal management method of the new energy vehicle in Embodiment 1 through the computer program.

[0120] Specifically, the computer program executes the following steps during runtime: acquiring multi-source driving data of the new energy vehicle, including: vehicle navigation data, vehicle status data, and driver's operational intent data; analyzing the multi-source driving data using a pre-trained operating condition prediction model to obtain the operating condition type, duration, and parameters of the target operating condition that the new energy vehicle is about to enter; determining the thermal regulation requirements of multiple thermal management subsystems of the new energy vehicle during the operating condition duration based on the operating condition parameters, including: battery thermal management subsystem, motor and electronic control thermal management subsystem, and cabin air conditioning thermal management subsystem; performing global collaborative thermal management decision-making based on the operating condition type and the thermal regulation requirements of multiple thermal management subsystems to determine the thermal management objectives of each thermal management subsystem, including target operating state parameters; and sending thermal management control commands corresponding to their respective thermal management objectives to each thermal management subsystem before the new energy vehicle enters the target operating condition.

[0121] As an optional implementation, the aforementioned new energy vehicle may also include electronic devices, mobile terminals, computer terminals, or similar computing devices. Figure 6 A hardware block diagram of an electronic device for implementing a vehicle thermal management method for new energy vehicles is shown. (For example...) Figure 6 As shown, the electronic device 60 may include one or more (shown as 602a, 602b, ..., 602n) processors 602 (processors 602 may include, but are not limited to, processing devices such as microprocessors or programmable logic devices), a memory 604 for storing data, and a transmission device 606 for communication functions. In addition, it may also include: a display, an input / output interface, a universal serial bus port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 6 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, electronic device 60 may also include components that are more... Figure 6 The more or fewer components shown, or having the same Figure 6 The different configurations shown.

[0122] It should be noted that the aforementioned one or more processors 602 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element of the electronic device 60. As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0123] The memory 604 can be used to store software programs and modules for application software, such as the program instructions / data storage device corresponding to the vehicle thermal management method for new energy vehicles in this embodiment. The processor 602 executes various functional applications and data processing by running the software programs and modules stored in the memory 604, thereby realizing the aforementioned vehicle thermal management method for new energy vehicles. The memory 604 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 604 may further include memory remotely located relative to the processor 602, and these remote memories can be connected to the electronic device 60 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0124] The transmission device 606 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the electronic device 60. In one example, the transmission device 606 includes a network adapter that can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 606 may be a radio frequency module used for wireless communication with the Internet.

[0125] The display can be, for example, a touchscreen LCD display that allows the user to interact with the user interface of the electronic device 60.

[0126] The sequence numbers of the above embodiments are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0127] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0128] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be 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 system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0129] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0130] 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.

[0131] 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 computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory, random access memory, portable hard drive, magnetic disk, or optical disk.

[0132] The above are merely preferred embodiments of this application. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for overall thermal management of a new energy vehicle, characterized in that, include: Acquire multi-source driving data of new energy vehicles, wherein the multi-source driving data includes: vehicle navigation data, vehicle status data and driver operation intention data; The multi-source driving data is analyzed using a pre-trained working condition prediction model to obtain the working condition type, duration, and parameters of the target working condition that the new energy vehicle is about to enter. Based on the operating condition parameters, the thermal regulation requirements of each of the multiple thermal management subsystems of the new energy vehicle during the duration of the operating condition are determined. The thermal management subsystems include: battery thermal management subsystem, motor and electronic control thermal management subsystem, and cabin air conditioning thermal management subsystem. Based on the operating condition type and the thermal regulation requirements of multiple thermal management subsystems, a global collaborative thermal management decision is made to determine the thermal management objectives of each thermal management subsystem, wherein the thermal management objectives include target operating state parameters; Before the new energy vehicle enters the target operating condition, thermal management control commands corresponding to the respective thermal management targets are sent to each of the thermal management subsystems.

2. The method according to claim 1, characterized in that, The method further includes: After the new energy vehicle enters the target operating condition, the actual operating status parameters of each of the thermal management subsystems are obtained; If the difference between the actual operating state parameter and the corresponding target operating state parameter of any thermal management subsystem is greater than a preset threshold, the thermal management control command corresponding to the thermal management subsystem is adjusted based on the target operating state parameter and the parameter difference, and the adjusted thermal management control command is sent to the thermal management subsystem.

3. The method according to claim 1, characterized in that, Acquire multi-source driving data of new energy vehicles, including: The vehicle navigation data is acquired, wherein the vehicle navigation data includes at least one of the following: road conditions, speed limits, altitude changes, and destination distance of the route to be traveled; The vehicle status data is obtained, wherein the vehicle status data includes at least one of the following: vehicle speed, battery state of charge, charging and discharging power and temperature, motor speed, load rate and temperature, electronic control operating temperature, and cooling medium temperature. The operation intent data is acquired, wherein the operation intent data includes at least one of the following: accelerator pedal opening change rate, braking frequency, gear selection, driving mode selection, and cabin set temperature; The in-vehicle navigation data, the vehicle status data, and the operation intention data are subjected to noise reduction and standardization processing to obtain the multi-source driving data.

4. The method according to claim 1, characterized in that, The training process of the working condition prediction model includes: Construct an initial prediction model, wherein the initial prediction model is an error backpropagation neural network; A training sample set is constructed by acquiring multiple sets of historical multi-source driving data under various working conditions. Each set of historical multi-source driving data is used as a training sample, and the working condition type, working condition duration, and working condition parameters within a preset time period after the collection time of each set of historical multi-source driving data are determined as the corresponding sample labels. The working condition type includes at least one of the following: high temperature uphill, low temperature downhill, urban congestion, and fast charging start. The initial prediction model is iteratively trained using the training sample set to obtain the working condition prediction model.

5. The method according to claim 1, characterized in that, The operating condition parameters include at least one of the following: battery charging and discharging power, motor load rate, and vehicle speed. Based on the operating condition parameters, the thermal regulation requirements of each of the multiple thermal management subsystems of the new energy vehicle during the duration of the operating condition are determined, including: For the battery thermal management subsystem, the target operating temperature of the battery is determined based on the battery charging and discharging power, and the thermal regulation requirements of the battery thermal management subsystem are determined based on the difference between the current battery temperature and the target operating temperature. For the motor electronic control thermal management subsystem, the heat generation rate of the motor is determined based on the motor load rate, and the thermal regulation requirements of the motor electronic control thermal management subsystem are determined based on the heat generation rate, the current temperature of the motor and the rated maximum operating temperature. For the cabin air conditioning thermal management subsystem, the cabin's wind resistance heat exchange efficiency is determined based on the vehicle's driving speed, and the thermal regulation requirements of the cabin air conditioning thermal management subsystem are determined based on the wind resistance heat exchange efficiency, the current ambient temperature, and the cabin set temperature.

6. The method according to claim 1, characterized in that, Based on the operating condition type and the thermal regulation requirements of multiple thermal management subsystems, a global collaborative thermal management decision is made to determine the thermal management objectives of each thermal management subsystem, including: When there is no conflict in the thermal regulation requirements of the multiple thermal management subsystems, the thermal management objectives of each thermal management subsystem are determined based on the thermal regulation requirements of each thermal management subsystem. In the event of conflicting thermal regulation requirements among multiple thermal management subsystems, a target priority table corresponding to the operating condition type of the target operating condition is determined. The target priority table includes the management priority of each thermal management subsystem, and the management priority of each thermal management subsystem is different in the priority tables corresponding to different operating condition types. Under the condition that each of the thermal management subsystems can operate normally, the thermal regulation requirements of each of the thermal management subsystems are corrected according to the target priority table. The higher the priority of the thermal management subsystem, the smaller the difference between the corrected thermal regulation requirements and the initial thermal regulation requirements. The thermal management objectives of each thermal management subsystem are determined based on the modified thermal regulation requirements of each thermal management subsystem.

7. The method according to claim 2, characterized in that, The method further includes: If the difference between the actual operating state parameters of any thermal management subsystem and the corresponding target operating state parameters is greater than a preset threshold, the operating condition prediction model is trained online based on the parameter difference to update the model parameters of the operating condition prediction model.

8. A vehicle thermal management device for a new energy vehicle, characterized in that, include: The acquisition module is used to acquire multi-source driving data of new energy vehicles, wherein the multi-source driving data includes: vehicle navigation data, vehicle status data and driver operation intention data; The prediction module is used to analyze the multi-source driving data using a pre-trained working condition prediction model to obtain the working condition type, working condition duration and working condition parameters of the target working condition that the new energy vehicle is about to enter. An analysis module is used to determine the thermal regulation requirements of each of the multiple thermal management subsystems of the new energy vehicle during the duration of the operating condition based on the operating condition parameters. The thermal management subsystems include: a battery thermal management subsystem, a motor and electronic control thermal management subsystem, and a cabin air conditioning thermal management subsystem. The decision module is used to make global collaborative thermal management decisions based on the operating condition type and the thermal regulation requirements of multiple thermal management subsystems, and to determine the thermal management objectives of each thermal management subsystem, wherein the thermal management objectives include target operating state parameters; The management module is used to send thermal management control commands corresponding to their respective thermal management targets to each of the thermal management subsystems before the new energy vehicle enters the target operating condition.

9. A computer program product, characterized in that, include: A computer program, wherein when executed by a processor, the computer program implements the vehicle thermal management method for any one of claims 1 to 7 for new energy vehicles.

10. A new energy vehicle, characterized in that, include: A memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute, through the computer program, the whole vehicle thermal management method for any one of claims 1 to 7.

Images