Preheating control method for vehicle, vehicle, and storage medium

Abstract

The embodiment of the specification provides a preheating control method of a vehicle, and relates to the technical field of vehicle thermal management. The method comprises the following steps: in response to triggering of a heating event in the vehicle, acquiring at least one heating capability index representing current performance of a thermal management system performing the heating event, and determining current health assessment information of the thermal management system according to the heating capability index; performing multi-dimensional feature extraction by combining configuration information of the heating event and the health assessment information, to obtain an execution state feature; performing preheating strategy configuration based on the execution state feature, to obtain preheating control parameters, wherein the preheating control parameters comprise at least one of a preheating start advance amount, a preheating power parameter and a preheating termination parameter; and controlling the thermal management system to perform corresponding preheating operations according to the preheating control parameters. Therefore, an adaptive adjustment process of matching the preheating control parameters with the actual heating capability of the thermal management system is realized, and the accuracy of preheating control is improved.

Description

Technical Field

[0001] This specification relates to the field of vehicle thermal management technology, specifically to vehicle preheating control technology within the field of vehicle thermal management technology, and more specifically, to a vehicle preheating control method, a vehicle, and a storage medium. Background Technology

[0002] In low-temperature environments, new energy vehicles typically require preheating of the cabin and battery before the user-set departure time to ensure that the cabin and battery temperatures reach target ranges upon departure, while also considering preheating energy consumption. Related technologies require preheating control to rationally determine the timing of heating start, heating intensity, and conditions for ending heating to meet the preheating needs of different vehicle states and usage conditions.

[0003] To achieve the above objectives, related technologies often employ a control method with fixed preheating parameters, that is, preheating is started according to a fixed duration. However, as the thermal management system ages, it may not be able to achieve the intended preheating effect, affecting the accuracy and effectiveness of the preheating operation. Summary of the Invention

[0004] This specification provides a vehicle preheating control method, a vehicle, electronic equipment, and a storage medium to improve the accuracy and effectiveness of preheating operations.

[0005] To achieve the above technical objectives, the embodiments of this specification provide the following technical solutions: In a first aspect, one embodiment of this specification provides a vehicle preheating control method, comprising: In response to the triggering of a heating event in the vehicle, health assessment information of the thermal management system that performed the heating event is obtained, the health assessment information being determined based on at least one index characterizing the current heating capacity of the thermal management system; By combining the health assessment information and the configuration information of the heating event, multi-dimensional features are extracted to obtain the current execution status features of the thermal management system. Based on the execution state characteristics, a preheating strategy is configured to obtain the preheating control parameters corresponding to the current thermal management system. The preheating control parameters include at least one of preheating start advance, preheating power parameters, and preheating termination parameters. The thermal management system is controlled to perform corresponding preheating operations according to the preheating control parameters.

[0006] Optionally, in some possible implementations, the heating capacity index includes a heating assessment index and a system health index. The step of obtaining at least one heating capacity index characterizing the current performance of the thermal management system performing the heating event, and determining the current health assessment information of the thermal management system based on the heating capacity index, includes: The heating evaluation index is determined based on the response process of the heating components corresponding to the thermal management system. The system health index is determined based on the lag information of the thermal management system during the heating execution steps; Determine the weight information of the thermal management system configuration; The heating assessment index and the system health index are weighted based on the weight information to obtain the current health assessment information of the thermal management system.

[0007] In this implementation, the heating assessment index and system health index of the thermal management system executing heating events are obtained. The heating assessment index is determined based on the response process of the heating components in the vehicle, and the system health index is determined based on the lag in the heating execution steps of the thermal management system. Then, the weight information configured in the thermal management system is determined, and the heating assessment index and system health index are weighted based on the weight information to obtain health assessment information. This enables a comprehensive assessment of the current heating capacity of the thermal management system from two dimensions: the capacity of the heating components themselves and the system response lag. This improves the accuracy and comprehensiveness of the health assessment information and addresses the problem of insufficient reliability of subsequent preheating decision input.

[0008] Optionally, in some possible implementations, the step of extracting multi-dimensional features by combining the health assessment information and the configuration information of the heating event to obtain the current execution state features of the thermal management system includes: The scene state parameters are extracted based on the configuration information of the heating event to obtain the scene state information; Vehicle status parameters are extracted based on the health assessment information to obtain vehicle status information; Vehicle state features are obtained by extracting features based on the vehicle state parameters, and scene state features are obtained by extracting features based on the scene state parameters. By combining the vehicle state characteristics and the scene state characteristics, the current execution state characteristics of the thermal management system are obtained.

[0009] In this implementation, scene state information is obtained by extracting scene state parameters based on the configuration information of the heating event, vehicle state information is obtained by extracting vehicle state parameters based on the health assessment information, vehicle state features are obtained by extracting features based on the vehicle state parameters, scene state features are obtained by extracting features based on the scene state parameters, and execution state features are obtained by combining vehicle state features and scene state features. This achieves the structured fusion of vehicle's own state information and external scene information, thereby providing multi-source decision input for preheating strategy configuration and improving the adaptability of the preheating strategy to different vehicle states and different usage scenarios.

[0010] Optionally, in some possible implementations, the step of extracting vehicle state features based on the vehicle state parameters and extracting scene state features based on the scene state parameters includes: Determine the multiple health assessment indices and battery status information included in the vehicle status parameters; Feature extraction is performed based on the multiple health assessment indices and the battery status information to obtain the vehicle status features; Determine the environmental information and travel information included in the scenario state parameters; Feature extraction is performed based on the environmental information and the travel information to obtain the scene state features.

[0011] In this implementation, multiple health assessment indices and battery status information contained in the vehicle status parameters are determined, and feature extraction is performed on these indices to obtain vehicle status features. At the same time, environmental information and travel information contained in the scenario status parameters are determined, and feature extraction is performed on these information to obtain scenario status features. This allows for the subdivision of vehicle status features into health and battery-related features and scenario status features into environment and travel-related features, thereby achieving a more refined characterization of preheating requirements and constraints and improving the targeting and accuracy of preheating control parameter configuration.

[0012] Optionally, in some possible implementations, configuring the preheating strategy based on the execution state characteristics to obtain the preheating control parameters currently corresponding to the thermal management system includes: The execution status characteristics are input into the preheating decision model, so that the preheating control parameters corresponding to the current thermal management system are output through the preheating decision model; The preheating decision model is trained using training samples, which consist of simulation data and real vehicle data. The sample features of the training samples include at least one of thermal system health status, environmental status, and battery status. The labels of the training samples include the minimum preheating advance amount and the minimum power level required to meet the departure temperature requirements.

[0013] In this implementation, the preheating decision model is input into the execution state characteristics and outputs preheating control parameters. The preheating decision model is trained using training samples, which consist of simulation data and real vehicle data. The sample characteristics include at least one of the thermal system health status, environmental status, and battery status. The sample labels include the minimum preheating advance amount and the minimum power level to meet the departure temperature target. This enables the configuration of preheating strategies based on a data-driven approach, achieving the goal of ensuring departure temperature meets the target while also considering preheating energy consumption, and improving the ability to jointly optimize preheating parameters.

[0014] Optionally, in some possible implementations, controlling the thermal management system to perform corresponding preheating operations according to the preheating control parameters includes: Obtain the estimated departure time corresponding to the heating event, and determine the preheating start advance, preheating power parameters, and preheating termination parameters indicated by the preheating control parameters; Before the estimated departure time, the execution time is determined according to the preheating start advance, and the preheating operation is triggered based on the execution time; The preheating power parameters are mapped to control commands for the thermal management system. During the preheating process corresponding to the control command, the temperature rise status of the preheated object is obtained, and if the temperature rise status is lower than the expected temperature rise condition, the preheating power parameter is adjusted until the preheating termination parameter is met.

[0015] In this implementation, by obtaining the estimated start time corresponding to the heating event, the preheating start advance, preheating power parameters, and preheating termination parameters indicated by the preheating control parameters are determined. Before the estimated start time, the execution time is determined according to the preheating start advance and the preheating operation is triggered. The preheating power parameters are mapped to the control instructions of the thermal management system. During the preheating process corresponding to the execution of the control instructions, the temperature rise status of the preheated object is obtained. When the temperature rise status is lower than the expected temperature rise condition, the preheating power parameters are adjusted until the preheating termination parameters are met. This achieves closed-loop control of preheating start, power execution, process monitoring, and termination judgment, thereby achieving the purpose of dynamically compensating for insufficient actual temperature rise and improving the on-time compliance rate of preheating operations.

[0016] Optionally, in some possible implementations, adjusting the preheating power parameter when the temperature rise is lower than the expected temperature rise condition until the preheating termination parameter is met includes: Obtain vehicle termination condition parameters, which are configured based on at least one of cabin temperature conditions, battery temperature conditions, departure time conditions, and battery energy constraints. Configure the expected temperature rise conditions based on the aforementioned termination condition parameters; If the temperature rise is lower than the termination condition parameter included in the expected temperature rise condition, adjust the preheating power parameter. If the state parameter corresponding to the temperature rise state reaches the preheating termination parameter, the preheating operation is stopped.

[0017] In this implementation, the vehicle's termination condition parameters are obtained. These termination condition parameters are configured based on at least one of the following: cabin temperature conditions, battery temperature conditions, departure time conditions, and battery energy constraints. Based on the termination condition parameters, expected temperature rise conditions are configured. When the temperature rise is lower than the termination condition parameters included in the expected temperature rise conditions, the preheating power parameters are adjusted. If the state parameter corresponding to the temperature rise reaches the preheating termination parameter, the preheating operation is stopped. This achieves the linkage between preheating power adjustment and multi-condition termination judgment, thereby preventing insufficient preheating and excessive consumption of battery energy, and improving the balance between preheating effect and battery safety and energy consumption.

[0018] Optionally, in some possible implementations, the method further includes: Record the actual preheating results corresponding to the preheating operation; Based on the difference between the actual preheating result and the target result of the preheating operation, determine whether the preheating has met the standard; If the preheating does not meet the target, the subsequent preheating control parameters will be adjusted, and the preheating decision model used in the preheating strategy configuration will be incrementally trained once the cumulative number of training samples reaches the preset sample number threshold.

[0019] In this implementation, the actual preheating results corresponding to the preheating operation are recorded. The difference between the actual preheating results and the target results of the preheating operation is used to determine whether the preheating has met the standard. If the preheating has not met the standard, the subsequent preheating control parameters are corrected. When the cumulative number of training samples reaches the preset sample number threshold, the preheating decision model used for the preheating strategy configuration is incrementally trained to achieve a closed loop of preheating effect feedback, parameter correction and model update. This achieves the goal of continuously tracking the actual degradation process of the thermal management system and improving the long-term preheating compliance rate and the adaptability of the preheating strategy.

[0020] Secondly, one embodiment of this specification provides a vehicle preheating control device, comprising: The acquisition unit is configured to acquire health assessment information of the thermal management system that performs the heating event in response to the triggering of a heating event in the vehicle. The health assessment information is determined based on at least one index characterizing the current heating capacity of the thermal management system. The processing unit is used to extract multi-dimensional features by combining the health assessment information and the configuration information of the heating event to obtain the current execution status features of the thermal management system. The processing unit is further configured to perform preheating strategy configuration based on the execution state characteristics to obtain the preheating control parameters corresponding to the thermal management system, wherein the preheating control parameters include at least one of preheating start advance, preheating power parameters, and preheating termination parameters; The control unit is used to control the thermal management system to perform corresponding preheating operations according to the preheating control parameters.

[0021] Thirdly, one embodiment of this specification also provides a vehicle preheating control system, including sensors and a vehicle controller, wherein the sensors are used to collect vehicle-related data; and the vehicle controller is used to execute the vehicle preheating control method as described in the first aspect or any possible implementation thereof.

[0022] Fourthly, one embodiment of this specification also provides a vehicle, the vehicle comprising: a memory for storing executable program code; and a processor for calling and running the executable program code from the memory, causing the vehicle to perform the vehicle preheating control method of the first aspect or any possible implementation thereof.

[0023] Fifthly, one embodiment of this specification also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the vehicle preheating control method as described above.

[0024] Sixthly, embodiments of this specification provide a computer program product or computer program, the computer program product including a computer program that can be stored in a computer-readable storage medium or in the cloud; the processor of the computer device reads the computer program, and when the processor executes the computer program, it implements the steps of the above-described vehicle preheating control method.

[0025] As can be seen from the above technical solutions, the vehicle preheating control method provided in this specification, by responding to the triggering of a heating event in the vehicle, obtains at least one heating capacity index characterizing the current performance of the thermal management system executing the heating event, and determines the current health assessment information of the thermal management system based on the heating capacity index. This expands the input of preheating decisions from fixed calibration parameters to the actual current heating capacity of the thermal management system, achieving the effect of providing a data basis for preheating control to reflect the degradation state of the thermal system. Furthermore, by combining health assessment information and configuration information of heating events to extract multi-dimensional features, the execution state characteristics corresponding to the current thermal management system are obtained, thereby linking the external scene conditions of the vehicle with the internal health of the thermal management system. The system performs structured fusion of preheating states and configures the current preheating strategy based on execution state characteristics to obtain preheating control parameters, including at least one of preheating start advance, preheating power parameters, and preheating termination parameters. This enables dynamic configuration of multiple execution dimensions, achieving the effect of adaptively adjusting the preheating strategy according to the actual heating capacity of the thermal management system. The system then controls the thermal management system to perform corresponding preheating operations based on the preheating control parameters, transforming the configured preheating control parameters into actual execution actions of the thermal management system. This achieves the goal of starting preheating as needed before departure and completing preheating according to the actual heating capacity. In other words, the preheating strategy adaptively adjusts as the thermal system degrades, improving the accuracy and effectiveness of preheating operation execution. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this specification. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0027] Figure 1 This is a schematic diagram illustrating the application environment of a vehicle preheating control method provided as one embodiment of this specification.

[0028] Figure 2 This is a schematic flowchart illustrating a vehicle preheating control method according to one embodiment of this specification.

[0029] Figure 3 This is a schematic diagram of the functional modules of a vehicle preheating control device provided for one embodiment of this specification.

[0030] Figure 4 This is a structural schematic diagram of a vehicle provided for one embodiment of this specification. Detailed Implementation

[0031] Unless otherwise defined, the technical or scientific terms used in the embodiments of this specification shall have the ordinary meaning understood by one of ordinary skill in the art to which this specification pertains. The terms "first," "second," and similar terms used in the embodiments of this specification do not indicate any order, quantity, or importance, but are merely used to avoid confusion of constituent elements.

[0032] Unless the context otherwise requires, throughout this specification, "a plurality of" means "at least two," and "including" is interpreted as open-ended or encompassing, that is, "including, but not limited to." In the description of this specification, terms such as "one embodiment," "some embodiments," "exemplary embodiment," "example," "specific example," or "some examples" are intended to indicate that a particular feature, structure, material, or characteristic associated with that embodiment or example is included in at least one embodiment or example of this specification. The illustrative representations of the above terms do not necessarily refer to the same embodiment or example.

[0033] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this specification.

[0034] In low-temperature environments, new energy vehicles typically require preheating of the cabin and battery before the user-set departure time to ensure that the cabin and battery temperatures reach target ranges upon departure, while also considering preheating energy consumption. Related technologies require preheating control to rationally determine the timing of heating start, heating intensity, and conditions for ending heating to meet the preheating needs of different vehicle states and usage conditions.

[0035] To achieve the above objectives, related technologies often employ a control method with fixed preheating parameters, that is, preheating is started according to a fixed duration. However, as the thermal management system ages, it may not be able to achieve the intended preheating effect, affecting the accuracy and effectiveness of the preheating operation.

[0036] To address the aforementioned problems, this specification provides a vehicle preheating control system, and the vehicle preheating control method provided in this specification is applied to the vehicle preheating control system. This evaluation system, through an active quantitative evaluation mode driven by heating hysteresis decomposition and multi-dimensional delay characteristics, integrates health assessment information characterizing the current heating capacity of the thermal management system with heating event configuration information into execution state characteristics. Based on these characteristics, the system dynamically configures the preheating start advance, preheating power parameters, and preheating termination parameters, thus improving preheating control from fixed-parameter execution to an adaptive adjustment process based on the actual heating capacity of the thermal system.

[0037] Specifically, the vehicle information interaction system may include systems composed of... Figure 1 The operating environment formed by server 110 and vehicle 120 is described. Vehicle 120 communicates with server 110 via a network connection. The functions implemented within vehicle 120 can be local processing or information received by vehicle 120 and uploaded to cloud server 110, which then processes the information and sends it back to vehicle 120. Server 110 can be an electronic device with certain computing capabilities. It may have a network communication module, processor, and memory, etc. Of course, server 110 can also refer to software running on the electronic device. Server 110 can also be a distributed server, which can be a system with multiple processors, memory, network communication modules, etc., working together. Alternatively, server 110 can also be a cluster of several servers 110. Or, with the development of science and technology, server 110 can also be a new technical means capable of realizing the corresponding functions of the embodiments described in the specification. For example, it can be a new form of "server" based on quantum computing.

[0038] Specifically, when evaluating heat pump performance based on the aforementioned evaluation system, it acquires at least one heating capacity index characterizing the current performance of the thermal management system (TMS) in response to a heating event triggered in the vehicle. Based on this heating capacity index, it determines the current health assessment information of the TMS, thus extending the input for preheating decisions from fixed calibration parameters to the actual current heating capacity of the TMS. This provides a data foundation for preheating control that reflects the degradation state of the thermal system. Furthermore, by combining the health assessment information and the configuration information of the heating event to extract multi-dimensional features, it obtains the current execution state characteristics of the TMS, thereby linking the external vehicle conditions with the internal health state of the TMS. The system performs structured fusion and configures the current preheating strategy based on execution state characteristics to obtain preheating control parameters, including at least one of preheating start advance, preheating power parameters, and preheating termination parameters. This enables dynamic configuration of multiple execution dimensions, achieving the effect of adaptively adjusting the preheating strategy according to the actual heating capacity of the thermal management system. The system then controls the thermal management system to perform corresponding preheating operations based on the preheating control parameters, transforming the configured preheating control parameters into actual execution actions of the thermal management system. This achieves the goal of starting preheating as needed before departure and completing preheating according to the actual heating capacity. In other words, the preheating strategy adaptively adjusts as the thermal system degrades, improving the accuracy and effectiveness of preheating operation execution.

[0039] First, the names that may appear in the embodiments will be explained.

[0040] The Heating Capability Health Index (HCHI) comprehensively reflects the current heating capacity level of a thermal system, ranging from 0 to 100.

[0041] The Heat Pump Performance Index (HPPI) is used to reflect the degree of degradation in the heating capacity of a heat pump.

[0042] The Thermal Health Index (THI) is used to reflect the degree of degradation in the overall response speed of a thermal management system.

[0043] Extreme Gradient Boosting (XGBoost) is an ensemble learning algorithm based on gradient boosting decision trees, used to build warm-up decision models.

[0044] A positive temperature coefficient heater (PTC) is a heating element whose resistance increases with increasing temperature, and is used for auxiliary heating.

[0045] An electronic expansion valve (EXV) is an actuator used to regulate the refrigerant flow in a thermal management system.

[0046] The Thermal Management System Electronic Control Unit (TMS ECU) is a controller used to control the various actuators of the thermal management system.

[0047] Model Predictive Control (MPC) is a control method based on predictive models and rolling optimization of control variables.

[0048] Reinforcement learning (RL) is a machine learning method that optimizes policies by interacting with the environment and using reward signals.

[0049] The coefficient of performance (COP) is the ratio of heating capacity to electrical energy consumption, used to measure the heating efficiency of a heat pump.

[0050] Based on the above concept, this specification provides a vehicle preheating control method. The vehicle preheating control method provided in this specification will be described exemplarily below with reference to the accompanying drawings.

[0051] To be applied Figure 1 Taking a vehicle as an example, this specification provides illustrative examples of some embodiments of the vehicle's preheating control method, such as... Figure 2 As shown, Figure 2 This specification provides a schematic flowchart of a vehicle preheating control method according to one embodiment of the invention; the vehicle preheating control method includes: 201. In response to the triggering of a heating event in the vehicle, obtain at least one heating capacity index that characterizes the current performance of the thermal management system that performed the heating event, and determine the current health assessment information of the thermal management system based on the heating capacity index.

[0052] In this embodiment, the heating event can refer to a cabin preheating event, a battery preheating event, or a combined cabin and battery preheating event. The heating event is typically associated with the user-set expected departure time, target temperature, navigation route, and environmental conditions. For example, a user can set a departure time of 7:30 AM the following morning via the vehicle's infotainment system, mobile terminal, or cloud service, expecting a target cabin temperature of 25°C and requiring the battery temperature to meet the travel requirements. Upon receiving this information, the system can trigger the corresponding preheating control process. More generally, the heating event can also be predicted based on historical travel patterns or automatically triggered by the vehicle controller based on low-temperature parking conditions. All of these methods can achieve the generation of preheating requests and subsequent control integration.

[0053] A thermal management system generally refers to components or systems in a vehicle that can perform heating, heat pump heating, heat distribution, and / or thermal management execution control. Examples include, but are not limited to: heat pump systems, PTC heaters, circulating pumps, electronic expansion valves, thermal management controllers, coolant circuits, refrigerant circuits, or combinations thereof. "Performing a preheating operation" can refer to at least one actuator in the thermal management system generating a heating action based on preheating control parameters.

[0054] Correspondingly, health assessment information broadly refers to information used to characterize the current heating capacity level of a thermal management system. Specifically, it can be a single health index or a comprehensive index obtained by fusing multiple health indicators from different performance dimensions; it can be a continuous value or graded information. The heating capacity index, as defined, can refer to information obtained after calculation, weighting, mapping, combination, or grading based on at least one indicator reflecting the heating capacity of the heat source, the system's response capability, or other heating-related capabilities. For example, it can include a heat pump performance index, a thermal system health index, a heating capacity health index, or a combination of the above. By adopting a broader approach to health information representation, preheating control application scenarios under different health assessment frameworks can be covered.

[0055] It is understandable that the health assessment information is dynamically updated. The update timing may include each heating event triggering, periodic updates during vehicle operation, or when the thermal system status meets preset conditions. The updated health assessment information is used together with the heating event configuration information to extract execution status features, so that the preheating decision model outputs preheating control parameters based on the current actual heating capacity of the thermal management system, rather than relying on fixed parameters under the new vehicle status.

[0056] Optionally, considering that a single health indicator may not fully characterize the heating capacity of the thermal management system and could lead to assessment bias, a weighted fusion approach combining the heating assessment index and the system health index can be adopted. Specifically, to determine the health assessment information, the heating assessment index can be determined based on the response process of the corresponding heating components of the thermal management system; the system health index can be determined based on the hysteresis information of the thermal management system during the heating execution steps; then, the weight information configured in the thermal management system can be determined; and finally, the heating assessment index and the system health index can be weighted based on the weight information to obtain the current health assessment information of the thermal management system.

[0057] The heating assessment index and system health index can be obtained either by real-time calculation or by the most recent heating assessment index and system health index of the assessment thermal management system saved in historical records. The specific method of acquisition depends on the actual scenario.

[0058] Specifically, the heating performance evaluation index is an indicator used to quantify the degree of degradation of the current heating capacity of the heating components in the vehicle's thermal management system relative to the baseline state. It is determined based on the response process of the heating components during the heating process, such as the rate of temperature rise after heating starts, the time required to reach the set temperature, the stability of output power, or the change in actual heating capacity. The index can be set from 0 to 100. The higher the value, the closer the current heating capacity of the heating components is to a good state. It serves as one of the basic inputs for evaluating the heating capacity of the thermal management system in preheating control and can correspond to the heat pump performance index HPPI.

[0059] The system health index is an indicator used to quantify the overall heating response capability or health status of a thermal management system. It is determined based on the lag in the thermal management system's execution of heating steps, such as the delay between the issuance of a heating command and the actual temperature response, the lag in the action of circulating pumps or valves, the flow establishment time of the heating loop, and the deviation between the time required to reach the target temperature rise and the baseline value. The index can be set from 0 to 100. The higher the value, the more timely the overall system response and the better the health status. In preheating control, it is configured together with the heating assessment index to reflect the degree of degradation of the current heating capacity of the thermal management system and can be correlated with the thermal system health index (THI).

[0060] Specifically, the HCHI calculation formula can be used for the weighted calculation process: HCHI = w1 * HPPI + w2 * THI HPPI is the heat pump performance index (0~100), which is derived from the thermal response curve evolution evaluation method and reflects the degree of degradation of the heating capacity of the heat pump body. THI is the thermal system health index (0~100), which is derived from the heating hysteresis characteristic assessment method and reflects the degree of degradation of the overall response speed of the thermal system. w1 and w2 are weighting coefficients, with the default values ​​being w1=0.6 and w2=0.4 (the heat pump is the main heat source and has a higher weight).

[0061] Correspondingly, the HCHI score ranges from 0 to 100. A score of 100 indicates that the heating capacity is in excellent condition, while a lower score indicates more severe degradation in heating capacity.

[0062] Furthermore, HCHI can be classified into different levels: HCHI>= 85: Heating capacity is normal, preheating parameters can be set according to standard; 70 <= HCHI < 85: Heating capacity is slightly degraded; preheating needs to be started earlier and power increased. 55 <= HCHI < 70: Heating capacity is moderately degraded, preheating needs to be significantly advanced and power increased; HCHI<55: Heating capacity is severely degraded, requiring maximum preheating and full power operation.

[0063] For example, the vehicle controller reads the current thermal management system's heating assessment index as 85 and the system health index as 70. The weighting information is set as follows: heating assessment index weight 0.6, system health index weight 0.4. The controller calculates the health assessment information as 0.6 × 85 + 0.4 × 70 = 79. This value indicates that the current thermal management system's heating capacity is slightly degraded. The controller uses this health assessment information as one of the inputs for subsequent multi-dimensional feature extraction.

[0064] As can be seen, this embodiment defines HCHI (Heating Capacity Health Index) as the core input for preheating control, forming a closed-loop linkage between thermal system health assessment (HPPI+THI) and preheating control strategy to achieve an adaptive architecture of assessment-driven control. Specifically, it obtains the heating assessment index and system health index of the thermal management system executing heating events. The heating assessment index is determined based on the response process of the heating components in the vehicle, and the system health index is determined based on the hysteresis of the heating execution steps of the thermal management system. Then, it determines the weight information configured in the thermal management system, and weights the heating assessment index and system health index based on the weight information to obtain health assessment information. This achieves a comprehensive assessment of the current heating capacity of the thermal management system from two dimensions: the capacity of the heating components themselves and the system response hysteresis. This improves the accuracy and comprehensiveness of health assessment information and addresses the problem of insufficient reliability of subsequent preheating decision input.

[0065] Understandably, HCHI can be expanded from a weighted average of HPPI and THI to a comprehensive assessment incorporating more sub-indicators. For example, based on HPPI and THI, sub-indicators such as battery internal resistance growth rate, PTC actual power decay rate, heat exchanger heat transfer capacity decay rate, and refrigerant quantity change rate can be further added, with weights assigned to each, and a more comprehensive heating capacity profile can be formed through weighted summation or hierarchical fusion. This extended scheme can reflect the degree of degradation of the thermal management system from multiple dimensions such as the heat pump itself, system response, battery heating difficulty, and PTC auxiliary capability, improving the comprehensiveness of health assessment; however, it requires adding logic for obtaining or estimating the corresponding parameters, and the workload of calibration and verification also increases accordingly.

[0066] In addition, the weighting information refers to the coefficients used to weight and integrate the heating assessment index and the system health index. It can be fixed at the default value, or it can be adjusted in real time or periodically during vehicle operation or preheating decision-making based on at least one of the following: the current working mode of the thermal management system, the participation level of the heat pump and PTC, the ambient temperature, or the confidence level of each index. For example, the weight of the heating assessment index is increased when the heat pump is the main heat source, and the weight of the system health index is increased when the ambient temperature is low or the PTC auxiliary ratio is increased. This allows the health assessment information to more accurately reflect the actual heating capacity of the thermal management system under different operating conditions.

[0067] 202. By combining health assessment information and heating event configuration information, multi-dimensional features are extracted to obtain the current execution status features of the thermal management system.

[0068] In this embodiment, the configuration information for a heating event refers to the setting parameters, time constraints, and travel conditions related to the current vehicle preheating or heating event, used to describe the target, execution timing, and usage scenario of the heating event. Its sources may include the departure time and target temperature set by the user through the vehicle's infotainment system, mobile app, or in-vehicle navigation system; it may also include the departure time predicted by the system based on the user's historical travel patterns; and information such as the distance to the navigation destination and estimated travel time provided by the navigation system. Specific content may include at least one of the following: estimated departure time, time since departure, distance to the navigation destination, user's historical preferred temperature, target cabin temperature, target battery temperature, and preheating mode selection. In the preheating control method, this configuration information, together with health assessment information, is used for multi-dimensional feature extraction to obtain the current execution state characteristics of the thermal management system, thereby ensuring that the preheating strategy not only reflects the current heating capacity of the thermal management system but also adapts to the time constraints and user needs of the current trip.

[0069] Specifically, execution state characteristics refer to a set of feature quantities used to characterize the comprehensive state required for the current preheating decision, formed by multi-dimensional feature extraction from the configuration information of heating events and the health assessment information of the thermal management system during the vehicle preheating control process. Therefore, for configuring execution state characteristics, scene state parameters can be extracted based on the configuration information of heating events to obtain scene state information; then, vehicle state parameters can be extracted based on the health assessment information to obtain vehicle state information; and feature extraction can be performed based on the vehicle state parameters to obtain vehicle state characteristics, and feature extraction can also be performed based on the scene state parameters to obtain scene state characteristics; finally, by combining the vehicle state characteristics and scene state characteristics, the current execution state characteristics of the thermal management system can be obtained.

[0070] Among them, vehicle state characteristics refer to the feature quantities extracted based on the health assessment information of the thermal management system and the vehicle's own state parameters during the vehicle preheating control process. These characteristics characterize the impact of the vehicle's current heating capacity and battery status on preheating decisions. Their sources include multiple health assessment indices such as the heating capacity health index, heat pump performance index, and thermal system health index from the health assessment information, as well as battery state of charge, battery health status, and current battery temperature. By extracting features from the above parameters, vehicle state characteristics are obtained and used as a component of the execution state characteristics. These are then input into the preheating decision model to configure at least one of the following: preheating start advance, preheating power parameters, and preheating termination parameters.

[0071] Scene state features refer to the feature quantities extracted from scene state parameters in the heating event configuration information during the vehicle preheating control process. These features characterize the impact of the vehicle's external environment and the current travel requirements on preheating decisions. Their sources include environmental information and travel information. Environmental information may include current ambient temperature, altitude, wind speed, etc., while travel information may include distance to the navigation destination, estimated departure time from the current time, and the user's historical preferred temperature, etc. By extracting features from these parameters respectively, scene state features are obtained, which, together with vehicle state features, constitute execution state features. This allows the preheating strategy to simultaneously adapt to thermal management system degradation, changes in the external environment, and user travel needs.

[0072] For example, the heating event configuration information includes: estimated departure time 7:30, navigation distance 30km, current ambient temperature -5℃, altitude 50m, and wind speed 2m / s. The controller extracts scene state parameters from these to form scene state information. Health assessment information includes HCHI=79, HPPI=85, and THI=70. The controller combines this with battery SOC=80%, SOH=95%, and battery temperature -5℃ to form vehicle state information. The controller extracts features from both the vehicle state parameters and the scene state parameters to obtain vehicle state features and scene state features, and then concatenates them to form execution state features, which are used as input to the preheating decision model.

[0073] As can be seen, this embodiment obtains scene state information by extracting scene state parameters based on the configuration information of heating events, obtains vehicle state information by extracting vehicle state parameters based on health assessment information, obtains vehicle state features based on vehicle state parameters, obtains scene state features based on scene state parameters, and obtains execution state features by combining vehicle state features and scene state features. This achieves the structured fusion of vehicle's own state information and external scene information, thereby providing multi-source decision input for preheating strategy configuration and improving the adaptability of the preheating strategy to different vehicle states and different usage scenarios.

[0074] Furthermore, considering that health assessment indices, battery status, environmental information, and trip information have different dimensions of influence on preheating, there may be a situation where mixed extraction reduces the feature representation ability. Therefore, a grouped approach can be adopted to extract features separately. Thus, multiple health assessment indices and battery status information included in the vehicle status parameters can be identified; then, feature extraction is performed separately based on these indices to obtain vehicle status features; and environmental information and trip information included in the scene status parameters can be identified; then, feature extraction is performed separately based on these information to obtain scene status features.

[0075] Vehicle state parameters refer to a set of raw parameters extracted from the health assessment information of the thermal management system during the vehicle preheating control process, used to characterize the vehicle's own heating capacity and battery status. Specifically, these parameters may include multiple health assessment indices such as heating capacity health index, heat pump performance index, and thermal system health index, as well as battery status information such as battery state of charge, battery health status, and current battery temperature. After feature extraction, these vehicle state parameters yield vehicle state features, which are used as components of the execution state features and input into the preheating decision model. This allows the preheating strategy to reflect the current degradation level of the thermal management system and the battery's constraints on preheating.

[0076] Scene state parameters refer to a set of raw parameters extracted from the configuration information of heating events during vehicle preheating control. These parameters characterize the vehicle's external environment and the needs of the current trip. Specifically, they may include environmental information such as current ambient temperature, altitude, and wind speed, and trip information such as distance to the navigation destination, estimated departure time from the current time, and the user's historical preferred temperature. After feature extraction, these scene state parameters yield scene state features, which, together with vehicle state features, constitute execution state features. These features enable the preheating strategy to adapt to different environmental conditions and user travel needs.

[0077] Based on the above feature descriptions, we can obtain the multidimensional features in the following example: Thermal system health characteristics (vehicle condition characteristics).

[0078] Feature 1: HCHI value (0~100): Core input, reflecting the current heating capacity level; Feature 2: HPPI value (0~100): Performance of the heat pump itself; Feature 3: THI value (0~100): Thermal system response capability.

[0079] Environmental state characteristics (scene state characteristics).

[0080] Feature 4: Current ambient temperature T_ambient (°C): The lower the temperature, the more difficult the preheating. Feature 5: Altitude (m): Thin air at high altitudes affects heat pump efficiency; Feature 6: Air pressure (kPa): Air pressure affects air density, which in turn affects heat transfer efficiency; Vehicle and battery status characteristics (vehicle status characteristics).

[0081] Feature 7: Current Battery SOC (%): When the SOC is too low, the preheating power needs to be limited to protect the battery; Feature 8: Battery SOH (%): Battery health status affects available preheating energy budget; Feature 9: Current battery temperature T_battery (°C): The lower the starting temperature, the greater the preheating requirement.

[0082] Trip status characteristics (scenario status characteristics).

[0083] Feature 10: Navigation destination distance (km): Long-distance travel places higher demands on battery temperature; Feature 11: Estimated departure time from current time (min): Constrains the available warm-up time window; Feature 12: User's historical preferred temperature (°C): Personalized target temperature.

[0084] It is evident that by constructing 12-dimensional multi-source features (health status + environment + battery + travel), the system comprehensively covers all dimensions of factors affecting preheating decisions, enabling the preheating strategy to not only adapt to thermal system degradation, but also to different environmental conditions and user needs.

[0085] For example, vehicle status parameters include health assessment indices such as HCHI=79, HPPI=85, and THI=70; battery status information includes SOC=80%, SOH=95%, and battery temperature -5℃. The controller extracts features from these parameters to obtain vehicle status features. Scene status parameters include environmental information such as ambient temperature -5℃, altitude 50m, and wind speed 2m / s; trip information includes navigation distance 30km, estimated remaining departure time 60min, and user-preferred temperature 25℃. The controller extracts features from these parameters to obtain scene status features. Finally, the vehicle status features and scene status features together constitute the execution status features.

[0086] As can be seen, this embodiment determines multiple health assessment indices and battery status information contained in the vehicle status parameters, and extracts features based on these indices to obtain vehicle status features. Simultaneously, it determines environmental and travel information contained in the scenario status parameters, and extracts features based on these information to obtain scenario status features. This achieves the goal of subdividing vehicle status features into health and battery-related features and scenario status features into environment and travel-related features, thereby more precisely characterizing preheating requirements and constraints and improving the targeting and accuracy of preheating control parameter configuration.

[0087] 203. Configure the preheating strategy based on the execution status characteristics to obtain the preheating control parameters corresponding to the current thermal management system. The preheating control parameters include at least one of the following: preheating start advance, preheating power parameters, and preheating termination parameters.

[0088] In this embodiment, the preheating control parameters refer to a set of parameters output by the preheating decision model based on the execution state characteristics, used to control the thermal management system to perform preheating operations. These parameters include at least one of the following: preheating start advance, preheating power parameters, and preheating termination parameters. The preheating start advance is used to limit how many minutes before the expected departure time preheating should begin; the preheating power parameters are used to limit the power output level or power combination of heating components such as heat pumps and PTC heaters; and the preheating termination parameters are used to limit the criteria for stopping preheating or the target temperature margin. Depending on actual control requirements, only one parameter can be output for single-parameter adjustment, or two or three parameters can be output simultaneously for joint configuration, thereby achieving a balance between achieving the target temperature at departure and preheating energy consumption.

[0089] Among them, the preheating start advance refers to the time parameter output by the preheating decision model based on the execution status characteristics, which is used to limit the start time of the preheating operation. It indicates how many minutes before the expected departure time the preheating will start, usually in minutes. This parameter can be dynamically adjusted according to factors such as heating capacity health index, ambient temperature, battery temperature, and expected remaining departure time, so that the thermal management system can start preheating in advance when the thermal system degrades or the ambient temperature is low, thereby ensuring that the cabin temperature and battery temperature meet the target requirements at the time of departure.

[0090] Preheating power parameters refer to parameters output by the preheating decision model that are used to limit the heating power configuration of the thermal management system during the preheating process. They can be expressed as discrete power levels or continuous power values, and correspond to different power combination strategies of the heat pump and PTC heater. These parameters are used to generate control commands such as compressor target speed command, PTC gear command, circulating pump flow command, and electronic expansion valve opening command, thereby adjusting the balance between heating rate and preheating energy consumption while meeting the preheating effect.

[0091] Preheating termination parameters refer to the criteria parameters output by the preheating decision model or configured according to the preheating control strategy to determine whether to stop the preheating operation. These parameters may include at least one of the following: target temperature margin, cabin temperature conditions, battery temperature conditions, departure time conditions, and battery energy constraints. Preheating will stop when any of the following conditions are met: the cabin air outlet temperature reaches the sum of the target temperature and the target temperature margin; the battery temperature reaches the minimum temperature required for the trip; the preheating duration reaches the preheating start advance; or the battery state of charge drops below the preset energy budget lower limit. This is to avoid insufficient preheating or excessive consumption of battery energy.

[0092] It is understandable that the preheating control parameters are not fixed calibration values, but are configured in real time by the preheating decision model based on the execution status characteristics. The execution status characteristics include health assessment information that is updated as the heating capacity of the thermal management system degrades, such as the Heating Capacity Health Index (HCHI), the Heat Pump Performance Index (HPPI), and the Thermal System Health Index (THI). When the HCHI decreases due to a decrease in heat pump efficiency, PTC decay, or system response lag, the preheating start advance, preheating power parameters, and preheating termination parameters output by the model will change accordingly. For example, the preheating start advance may be increased, the preheating power level may be upgraded, or the target temperature margin may be increased. This allows the preheating control parameters to be dynamically updated with the current health status, achieving adaptive compensation for thermal system degradation.

[0093] Specifically, the preheating control parameters can be output through the preheating decision model. That is, the execution state characteristics are input into the preheating decision model, so that the preheating decision model can output the preheating control parameters corresponding to the current thermal management system.

[0094] The preheating control parameters refer to the set of parameters output by the preheating decision model based on the execution state characteristics, used to control the thermal management system to perform preheating operations. These parameters include at least one of the following: preheating start advance, preheating power parameters, and preheating termination parameters. The preheating start advance is used to limit how many minutes before the expected departure time preheating should begin; the preheating power parameters are used to limit the power output level or power combination of heating components such as heat pumps and PTC heaters; and the preheating termination parameters are used to limit the criteria for stopping preheating or the target temperature margin. Depending on actual control requirements, only one parameter can be output for single-parameter adjustment, or two or three parameters can be output simultaneously for joint configuration, thereby achieving a balance between achieving the target temperature at departure and preheating energy consumption.

[0095] For example, the model outputs three preheating decision parameters: (a) Warm-up start advance: Optimal warm-up start advance T_advance (minutes): How many minutes before departure should warm-up begin; (b) Preheating power parameters: Preheating power level P_level (levels 1 to 5, corresponding to the power combination strategy of heat pump + PTC); (c) Preheating termination parameters: Target temperature margin Delta_T_margin (°C): The margin added to the standard target temperature (e.g., if the standard target is 25°C and the margin is 2°C, then the actual target is 27°C), used to compensate for the temperature drop after departure.

[0096] For the definition of power levels, taking a 5-level power allocation as an example: Level 1 (Energy Saving Mode): Only the heat pump operates, and the compressor speed is limited to 60% of the rated speed, with a heating capacity of approximately 2kW. Level 2 (Standard Mode): The heat pump operates at full speed, providing approximately 3.5kW of heating capacity; Level 3 (Enhanced Mode): Heat pump at full speed + PTC low-speed auxiliary (1kW), with a total heating capacity of approximately 4.5kW; Level 4 (Power Mode): Heat pump at full speed + PTC at medium speed (2kW), approximately 5.5kW total heating capacity; Level 5 (Extreme Speed ​​Mode): Heat pump at full speed + PTC at high speed (3kW), with a total heating capacity of approximately 6.5kW, suitable for extremely low HCHI or extremely cold environments.

[0097] It is evident that the 5-level power allocation strategy precisely controls the power combination of the heat pump and PTC, minimizing energy consumption while meeting the preheating effect. That is, healthy systems use low power for long-term preheating (high efficiency), while degraded systems use high power for short-term preheating (maintaining effect).

[0098] In one possible scenario, 12-dimensional execution state features are input into a trained XGBoost preheating decision model. The model outputs a preheating start advance of 25 minutes, a preheating power level of 3, and a target temperature margin of 2°C. The model was trained using simulation data: under combined conditions of HCHI values ​​of 100, 85, 70, 55, and 40°C; ambient temperatures of -20, -10, 0, and 5°C; and battery temperatures of -15, -5, and 5°C, the optimal preheating parameters required to reach the target temperature were simulated and calculated. Simultaneously, successful and failed preheating cases from real-vehicle data were used, labeling the minimum preheating advance and minimum power level required to meet the initial temperature target.

[0099] Understandably, the XGBoost preheating decision model can effectively capture the nonlinear interactions between various features. Furthermore, its small size and fast inference speed make it suitable for deployment in automotive T-Boxes or thermal management ECUs. Therefore, this model is a necessary decision-making step in transforming thermal system health assessment results into executable preheating control parameters and enabling adaptive adjustments to the preheating strategy as the thermal system degrades. The XGBoost decision model simultaneously outputs three parameters: preheating start time, power level, and target margin, achieving joint optimization of all parameters of the preheating strategy, rather than adjusting only a single parameter.

[0100] In addition, for the training process of the model, the preheating decision model is trained through training samples, which consist of simulation data and real vehicle data. The sample features of the training samples include at least one of thermal system health status, environmental status and battery status. The labels of the training samples include the minimum preheating advance amount and the minimum power level to meet the temperature requirements at the start of departure.

[0101] The sources of training samples for the training data construction process include: (a) Simulation data: Based on the thermal system physical model, the optimal preheating parameters required to reach the target temperature are calculated under the combined conditions of different HCHI levels (100 / 85 / 70 / 55 / 40), different ambient temperatures (-20 / -10 / 0 / 5℃), and different initial battery temperatures (-15 / -5 / 5℃). (b) Real vehicle data: Collect successful and unsuccessful preheating cases from the fleet (whether the target temperature was reached at departure) and label the corresponding optimal preheating parameters.

[0102] The label generation rule is to find the minimum preheating advance amount and the lowest power level that meet the temperature requirements at the start of departure for each set of conditions as the optimal label (taking into account both effectiveness and energy consumption).

[0103] Furthermore, regarding the model deployment process, XGBoost parameters are set: max_depth=6,n_estimators=150,learning_rate=0.08,reg_alpha=0.1.

[0104] Multi-output strategy: Train three XGBoost models with three outputs respectively. (T_advance, P_level, Delta_T_margin), or use a multi-output regression wrapper.

[0105] The specific deployment process can be carried out by deploying the model on the vehicle T-Box or TMSECU after model quantization, with a total model size of <300KB and a single inference time of <5ms.

[0106] As can be seen, this embodiment inputs the execution state characteristics into the preheating decision model, and the preheating decision model outputs preheating control parameters. The preheating decision model is trained using training samples, which consist of simulation data and real vehicle data. The sample characteristics include at least one of the thermal system health status, environmental status, and battery status. The sample labels include the minimum preheating advance amount and the minimum power level to meet the departure temperature target. This enables the configuration of preheating strategies based on a data-driven approach, achieving the goal of ensuring the departure temperature meets the target while also considering preheating energy consumption, and improving the ability to jointly optimize preheating parameters.

[0107] Understandably, the XGBoost decision model can be replaced by a rule engine scheme based on lookup table interpolation. Specifically, a preheating parameter table is pre-calibrated on grids with different HCHI levels and ambient temperatures. The table records the preheating start-up advance, power level, and target temperature margin corresponding to each grid point. During runtime, the table is looked up based on the current HCHI and ambient temperature, and linear or bilinear interpolation is performed between grid points to obtain the actual preheating control parameters. This scheme requires no training data, is logically transparent, highly interpretable, and easy to calibrate and verify; however, its decision dimensions are mainly limited to HCHI and ambient temperature, making it difficult to fully express the nonlinear interaction relationships between multi-dimensional inputs such as battery state and travel state. It is suitable for scenarios with low control accuracy requirements or limited computing resources.

[0108] Furthermore, the preheating decision model can be replaced from an offline training plus online inference mode to a reinforcement learning online adaptive mode. Specifically, a reward function is constructed based on the preheating achievement rate and preheating energy consumption, with multi-dimensional information such as HCHI, ambient temperature, battery status, and travel status as state inputs, and preheating start advance, power level, and target temperature margin as action outputs. The policy network is directly updated based on the actual feedback from each preheating cycle. This scheme can continuously adapt to thermal system degradation and changes in user habits without relying on offline labeled samples, exhibiting stronger adaptive capabilities and being suitable for scenarios with strong online computing power and long learning cycles.

[0109] 204. Control the thermal management system to perform the corresponding preheating operation according to the preheating control parameters.

[0110] In this embodiment, the preheating triggering process refers to the vehicle controller obtaining the estimated departure time corresponding to the heating event after detecting that a heating event has been triggered, and determining the preheating execution time according to the preheating start advance in the preheating control parameters. When the execution time is reached, the thermal management system is automatically started to perform the preheating operation. The triggering conditions of the heating event may include the user setting the departure time through the vehicle system or mobile app, or the system predicting the departure time based on the user's historical travel patterns. After triggering, the controller obtains the health assessment information of the thermal management system and performs multi-dimensional feature extraction and preheating strategy configuration in combination with the configuration information of the heating event, so as to automatically start preheating according to the determined advance before the estimated departure time, so that the cabin temperature and battery temperature reach the target requirements at the time of departure.

[0111] For example, preheating trigger conditions may include: (a) The user sets the departure time (via the in-vehicle app or in-vehicle navigation). (b) The system predicts departure time based on the user's historical travel patterns (e.g., commuting at 7:30 on weekdays).

[0112] The system automatically starts preheating T_advance minutes before departure. For power distribution after preheating, corresponding hardware control is executed according to the P_level: first, a target speed command is sent to the compressor (via the CAN bus-compressor driver); then, a gear position command is sent to the PTC control relay (via the TMS ECU's PWM output or relay control); a flow rate command is sent to the circulating pump (ensuring flow matching in the heating circuit); and finally, an opening command is sent to the electronic expansion valve (optimizing refrigerant distribution).

[0113] In this process, the power distribution strategy can be replaced from discrete 5 levels to continuous power regulation. Specifically, the power output of the heat pump and PTC is changed from discrete levels 1 to 5 to continuously adjustable 0~100%, and model predictive control (MPC) is used to predict the future temperature trajectory based on the current temperature, target temperature, and remaining preheating time, optimizing the power curve in real time to minimize energy consumption while ensuring the preheating process meets the target. This solution provides finer power regulation, which helps reduce overshoot and energy waste; however, it places higher demands on the frequency response of the compressor driver, the continuous power regulation capability of the PTC, and the real-time computing resources of the MPC, making it suitable for vehicles with hardware that supports continuous regulation and sufficient controller computing power.

[0114] Specifically, for the execution process of the preheating operation, the estimated start time corresponding to the heating event can be obtained, and the preheating start advance, preheating power parameters, and preheating termination parameters indicated by the preheating control parameters can be determined. Then, before the estimated start time, the execution time is determined according to the preheating start advance, and the preheating operation is triggered based on the execution time. The preheating power parameters are mapped to the control commands of the thermal management system. Then, during the preheating process corresponding to the execution of the control commands, the temperature rise status of the preheated object is obtained, and if the temperature rise status is lower than the expected temperature rise condition, the preheating power parameters are adjusted until the preheating termination parameters are met.

[0115] The term "temperature rise state" broadly refers to a state quantity reflecting the degree or trend of temperature rise of the target object during the preheating process. This can be instantaneous temperature, average temperature rise rate, cumulative temperature rise value, temperature rise ratio per unit time, or other information that can characterize the progress of temperature rise. The term "expected temperature rise condition" broadly refers to the phased temperature rise target to be achieved under current control parameters and remaining time constraints. This definition of terminology can cover different monitoring and adjustment logics.

[0116] It's important to note that start-up timing control, power mapping, and dynamic process adjustment are not independent of each other. The preheating start-up advance determines the available preheating time window, the preheating power parameters determine the heating capacity available per unit time, and process monitoring and dynamic adjustment are used to compensate for health assessment deviations, environmental fluctuations, or execution errors. When these three elements work together, the probability of meeting targets on time can be increased, and problems such as underheating or excessive energy consumption caused by fixed parameters can be reduced.

[0117] In one possible scenario, the following example of HCHI dynamic adjustment is shown: Example 1: New car HCHI=95, ambient temperature -5℃, target cabin temperature 25℃ - Model output T_advance=15min, P_level=2 (standard mode), cabin temperature reaches 25℃ at departure.

[0118] Example 2: Old car HCHI=70, under the same conditions - model output T_advance=28min, P_level=3 (enhanced mode), extend the preheating and add PTC assistance to compensate for the decrease in heat pump efficiency.

[0119] Example 3: Severe degradation HCHI=50, environment -15℃ - model output T_advance=45min, P_level=5 (ultra-fast mode), running at full power as early as possible to ensure compliance.

[0120] In another example, the controller obtains the estimated departure time of 7:30 AM, and the preheating control parameters are a 25-minute lead time, power level 3, and a target temperature margin of 2°C. The controller determines the execution time as 7:05 AM and triggers preheating at 7:05 AM. Power level 3 is mapped to full-speed heat pump operation and 1kW low-end PTC auxiliary power. During preheating, the controller monitors the cabin temperature rise. After 10 minutes of preheating, the cabin temperature has only risen by 3°C, lower than the expected temperature rise of 5°C. The controller then increases the power level from 3 to 4, adding 2kW to the mid-end PTC. Preheating stops when the cabin temperature reaches 27°C, the battery temperature reaches 15°C, or 7:30 AM is reached.

[0121] As can be seen, this embodiment obtains the expected departure time corresponding to the heating event, determines the preheating start advance, preheating power parameters, and preheating termination parameters indicated by the preheating control parameters, determines the execution time according to the preheating start advance before the expected departure time, and triggers the preheating operation. The preheating power parameters are mapped to the control instructions of the thermal management system. During the preheating process corresponding to the execution of the control instructions, the temperature rise status of the preheated object is obtained, and the preheating power parameters are adjusted when the temperature rise status is lower than the expected temperature rise condition until the preheating termination parameters are met. This achieves closed-loop control of preheating start, power execution, process monitoring, and termination judgment, thereby achieving the purpose of dynamically compensating for insufficient actual temperature rise and improving the on-time compliance rate of preheating operations.

[0122] Furthermore, considering that preheating termination needs to take into account temperature compliance, departure time, and battery energy constraints, there may be situations where insufficient preheating or excessive consumption occurs due to a single condition judgment. Therefore, a method of configuring expected temperature rise conditions with multiple termination parameters and adjusting power accordingly can be adopted. That is, firstly, the vehicle's termination condition parameters are obtained, and the termination condition parameters are configured based on at least one of the following: cabin temperature conditions, battery temperature conditions, departure time conditions, and battery energy constraint conditions; then, expected temperature rise conditions are configured based on the termination condition parameters; and if the temperature rise state is lower than the termination condition parameters included in the expected temperature rise conditions, the preheating power parameters are adjusted; if the state parameters corresponding to the temperature rise state reach the preheating termination parameters, the execution of the preheating operation is stopped.

[0123] The termination condition parameters refer to a set of criteria parameters output by the preheating decision model or configured according to the preheating control strategy to determine whether to stop the preheating operation. These parameters are configured based on at least one of the following: cabin temperature conditions, battery temperature conditions, departure time conditions, and battery energy constraints. Specifically, the cabin temperature conditions may include the sum of the cabin exhaust temperature reaching the target temperature and the target temperature margin; the battery temperature conditions may include the battery temperature reaching the minimum temperature required for the trip; the departure time conditions may include the preheating duration reaching the preheating start advance or the expected departure time; and the battery energy constraints may include the battery state of charge decreasing beyond the preset energy budget lower limit. During the preheating process, the controller monitors the state variables corresponding to the above parameters in real time. When any termination condition parameter is met, the preheating operation is stopped, thereby ensuring that the cabin temperature and battery temperature meet the standards at departure and avoiding insufficient preheating or excessive consumption of battery energy.

[0124] Therefore, the preheating termination condition can be based on the following preheating termination criterion (if any one of them is met, the preheating will stop): (a) The cabin exhaust temperature reaches the target temperature + Delta_T_margin; (b) The battery temperature reaches the minimum temperature required for the trip; (c) The warm-up time has reached T_advance (departure time has arrived); (d) The battery SOC drops to the lower limit of the preheating energy budget (if the SOC drops by more than 5%, it will be forcibly stopped to prevent excessive consumption).

[0125] Based on the above example of preheating termination conditions, we can derive the following termination condition parameters from the controller: target cabin temperature 25°C plus a 2°C margin, i.e., 27°C; minimum battery temperature 15°C; departure time 7:30 AM; SOC drop not exceeding 5%. Based on these conditions, the expected temperature rise is configured as a 5°C increase over 10 minutes. After 10 minutes of preheating, the cabin temperature only rises by 3°C, below the expected temperature rise condition, and the controller increases the power level from 3 to 4. The controller stops preheating when the cabin temperature reaches 27°C, the battery temperature reaches 15°C, 7:30 AM is reached, or the SOC drop exceeds 5%.

[0126] As can be seen, this embodiment obtains the vehicle's termination condition parameters, which are configured based on at least one of the following: cabin temperature conditions, battery temperature conditions, departure time conditions, and battery energy constraints. Based on the termination condition parameters, the expected temperature rise conditions are configured. When the temperature rise is lower than the termination condition parameters included in the expected temperature rise conditions, the preheating power parameters are adjusted. If the state parameter corresponding to the temperature rise reaches the preheating termination parameter, the preheating operation is stopped. This achieves the linkage between preheating power adjustment and multi-condition termination judgment, thereby preventing insufficient preheating and excessive consumption of battery energy, and improving the balance between preheating effect and battery safety and energy consumption.

[0127] Optionally, considering the slow degradation process of the thermal management system and the potential bias in model predictions, long-term use of a fixed model may lead to inaccurate preheating strategies. Therefore, a method can be adopted that records actual results, corrects parameters, and performs incremental training after accumulating samples. Thus, the actual preheating results corresponding to the preheating operation can be recorded; then, based on the difference between the actual preheating results and the target results of the preheating operation, it can be determined whether the preheating has met the target. If the preheating has not met the target, the subsequent preheating control parameters are corrected, and the preheating decision model used for configuring the preheating strategy is incrementally trained once the accumulated training sample count reaches a preset sample count threshold.

[0128] The preset sample quantity threshold refers to the pre-set condition for the number of new samples to trigger incremental training of the preheating decision model. It is configured in the effect feedback and model update module. When the cumulative number of actual effect samples recorded after each preheating reaches this threshold, the system uses these new samples to perform incremental training on the preheating decision model to update the model parameters, so that the preheating strategy tracks the actual degradation process of the thermal management system. This threshold can be calibrated according to factors such as model complexity, vehicle controller computing power, thermal system degradation speed and preheating frequency. For example, it can be set to 20. Its purpose is to avoid the incremental training being unstable or overfitting due to too few samples, and to update the model in a timely manner after accumulating enough new samples to reflect the current thermal system state, thereby taking into account both the reliability of model update and adaptive response speed.

[0129] Specifically, after each preheating is completed (the user's departure time), the system records: (a) The actually achieved cabin temperature T_cabin_actual vs. the target temperature T_target; (b) The actually achieved battery temperature T_battery_actual vs. the target battery temperature; (c) The energy E_preheat (kWh) consumed by preheating.

[0130] In addition, for online model correction, if T_cabin_actual < T_target - 2°C (non-compliant) occurs in 3 consecutive preheating cycles, it indicates that the model-predicted T_advance is too short or P_level is too low, triggering online correction: (a) Short-term correction: Temporarily increase T_advance by 5 minutes and raise P_level by 1 level during the next preheating; (b) Long-term correction: After accumulating a sufficient number of new samples (>20), perform incremental training on the XGBoost model to update the weights.

[0131] For example, after preheating ends, the controller records that the actual cabin temperature is 24°C and the target cabin temperature is 27°C, which is non-compliant. The controller records this sample, and temporarily increases the startup advance amount for the next preheating by 5 minutes and raises the power level by 1 level. When the cumulative number of non-compliant samples reaches 20, the controller uses these new samples to perform incremental training on the XGBoost preheating decision model, and updates the model weights, so that the subsequent preheating strategy is more consistent with the actual heating capacity of the current thermal management system.

[0132] It can be seen that the effect feedback and online learning mechanism of this embodiment ensure that the decision model continuously tracks the actual degradation process of the thermal system. Even if there is a deviation in the HPPI / THI evaluation, self-correction can be performed through the feedback of the actual preheating effect; specifically, by recording the actual preheating result corresponding to the preheating operation, it is judged whether the preheating is up to standard according to the difference between the actual preheating result and the target result of the preheating operation. If the preheating is not up to standard, the subsequent preheating control parameters are corrected, and when the cumulative number of training samples reaches the preset sample number threshold, incremental training is performed on the preheating decision model used for preheating strategy configuration, so as to realize a closed loop of preheating effect feedback, parameter correction and model update, achieve the purpose of continuously tracking the actual degradation process of the thermal management system, and improve the long-term preheating compliance rate and the adaptive capability of the preheating strategy.

[0133] In the following, by combining the above various embodiments, the following execution steps of preheating control can be obtained: Step S1: The system obtains the latest evaluation results from the HPPI module and the THI module, and calculates the current HCHI value; Step S2: Collect multi-dimensional status information such as current ambient temperature, battery SOC / SOH / temperature, and user departure time; Step S3: Construct a 12-dimensional input feature vector [HCHI, HPPI, THI, T_ambient, altitude, wind, SOC, SOH, T_battery, distance, time_to_depart, T_preference]; Step S4: Input the feature vector into the XGBoost decision model to obtain the preheating parameter output [T_advance, P_level, Delta_T_margin]; Step S5: Start preheating T_advance minutes before departure time, and drive the heat pump, PTC, circulation pump and EXV actuator according to the P_level power rating; Step S6: Monitor the temperature rise curve in real time during the preheating process. If the temperature rise is significantly slower than expected (e.g., the temperature rise is less than 60% of the expected rise after 10 minutes), dynamically increase P_level to ensure that the target is met on time. Step S7: Stop preheating after the termination conditions are met, and record the execution parameters and actual effects of this preheating. Step S8: Evaluate whether the preheating meets the standards. If it does not, trigger the online correction logic and update the subsequent preheating strategy.

[0134] Specifically, the above steps can be assigned to different vehicle modules for execution. During system operation, the HCHI calculation module executes step S1, obtaining the latest evaluation results from the HPPI and THI modules, and fusing HPPI and THI to output the comprehensive heating capacity health index HCHI. The multi-dimensional state perception module executes step S2, collecting multi-dimensional state information such as current ambient temperature, battery SOC / SOH / temperature, and user departure time. In step S3, it works with the HCHI calculation module to construct a 12-dimensional input feature vector [HCHI, HPPI, THI, T_ambient, altitude, wind, SOC, SOH, T_battery, distance, time_to_depart, ...]. Step S4 is executed by the XGBoost preheating decision model, which inputs the feature vector into the model and outputs the preheating start advance T_advance, power level P_level, and target temperature margin Delta_T_margin; Step S5 is executed by the preheating execution control module, which starts preheating T_advance minutes before the departure time and drives the heat pump compressor, PTC heater, circulating pump, and electronic expansion valve according to the power level P_level; Step S6 is also executed by the preheating execution control module, which monitors the temperature rise curve in real time. If the temperature rise is significantly slower than expected (e.g., the temperature rise is less than 60% of the expected rise after 10 minutes), the P_level is dynamically increased to ensure timely achievement of the target. Step S7 is executed by the effect feedback and model update module. After the termination condition is met, the preheating is stopped, and the execution parameters and actual effects of this preheating are recorded. Step S8 is also executed by the effect feedback and model update module to evaluate whether the preheating meets the target. If it does not meet the target, the online correction logic is triggered to update the subsequent preheating strategy and form a closed loop with the XGBoost preheating decision model, thereby realizing the adaptive adjustment of preheating control according to the health status of the heating system, environmental conditions, and travel requirements.

[0135] This courseware demonstrates how the Heating Capability Health Index (HCHI) is defined to output a comprehensive capability index for preheating control, combining the Heating Capability Health Index (HPPI) and the Thermal System Health Index (THI). Using HCHI as the core input and incorporating multi-dimensional features such as environmental conditions, battery status, and travel status, an intelligent decision-making model for preheating parameters based on XGBoost is constructed. This model outputs the optimal preheating start-up time, preheating power, and termination conditions, enabling adaptive adjustment of the preheating strategy as the thermal system degrades.

[0136] In summary, this embodiment, by responding to the triggering of a heating event in the vehicle, obtains at least one heating capacity index characterizing the current performance of the thermal management system executing the heating event, and determines the current health assessment information of the thermal management system based on the heating capacity index. This expands the input of preheating decisions from fixed calibration parameters to the actual current heating capacity of the thermal management system, achieving the effect of providing a data foundation for preheating control that reflects the degradation state of the thermal system. Furthermore, by combining health assessment information and configuration information of the heating event to extract multi-dimensional features, the current execution state characteristics of the thermal management system are obtained, thereby structurally fusing external vehicle scene conditions with the internal health state of the thermal management system. By configuring the current preheating strategy based on execution state characteristics, preheating control parameters are obtained, including at least one of preheating start advance, preheating power parameters, and preheating termination parameters. This enables dynamic configuration of multiple execution dimensions, achieving the effect of adaptively adjusting the preheating strategy according to the actual heating capacity of the thermal management system. The thermal management system is then controlled to perform corresponding preheating operations based on the preheating control parameters, transforming the configured preheating control parameters into actual execution actions of the thermal management system. This achieves the goal of starting preheating as needed before departure and completing preheating according to the actual heating capacity. In other words, the preheating strategy is adaptively adjusted according to the degradation of the thermal system, improving the accuracy and effectiveness of preheating operation execution.

[0137] It should be noted that the various embodiments described in this specification emphasize the parts that differ from other embodiments, and the embodiments can be explained by comparison with each other. Any combination of the various embodiments described in this specification based on general technical knowledge is covered within the scope of this specification.

[0138] In one exemplary embodiment of this specification, a vehicle preheating control device 300 is also provided, such as... Figure 3 As shown, Figure 3 A functional block diagram of a vehicle preheating control device provided for one embodiment of this specification, the control device 300 including: The acquisition unit 301 is configured to acquire health assessment information of the thermal management system that performs the heating event in response to the triggering of a heating event in the vehicle. The health assessment information is determined based on at least one index characterizing the current heating capacity of the thermal management system. The processing unit 302 is used to extract multi-dimensional features by combining the health assessment information and the configuration information of the heating event to obtain the current execution status features of the thermal management system. The processing unit 302 is further configured to configure a preheating strategy based on the execution state characteristics to obtain the preheating control parameters corresponding to the thermal management system at present, wherein the preheating control parameters include at least one of preheating start advance, preheating power parameters and preheating termination parameters; The control unit 303 is used to control the thermal management system to perform corresponding preheating operations according to the preheating control parameters.

[0139] Specifically, the processing unit and control unit in this embodiment can correspond to physical components. For example, the processing unit can be a processing module such as a CPU, GPU, or FPGA. The specific physical component can be any component or combination of components with the above functions. The specific method depends on the actual scenario and is not limited here.

[0140] The aforementioned control device, in response to a heating event triggered in the vehicle, acquires at least one heating capacity index characterizing the current performance of the thermal management system executing the heating event. Based on this index, it determines the current health assessment information of the thermal management system, thus expanding the input for preheating decisions from fixed calibration parameters to the actual current heating capacity of the thermal management system. This provides a data foundation for preheating control that reflects the degradation state of the thermal system. Furthermore, by combining the health assessment information and the configuration information of the heating event to extract multi-dimensional features, it obtains the current execution state characteristics of the thermal management system, thereby structurally fusing external vehicle conditions with the internal health state of the thermal management system. The current preheating strategy is configured based on the execution status characteristics to obtain preheating control parameters, including at least one of preheating start advance, preheating power parameters, and preheating termination parameters. This enables dynamic configuration of multiple execution dimensions, achieving the effect of adaptively adjusting the preheating strategy according to the actual heating capacity of the thermal management system. The thermal management system is then controlled to perform corresponding preheating operations based on the preheating control parameters, transforming the configured preheating control parameters into actual execution actions of the thermal management system. This achieves the goal of starting preheating as needed before departure and completing preheating according to the actual heating capacity. In other words, the preheating strategy is adaptively adjusted according to the degradation of the thermal system, improving the accuracy and effectiveness of preheating operation execution.

[0141] Specific limitations regarding the vehicle preheating control device can be found in the above description of the vehicle preheating control method, and will not be repeated here. Each unit module in the aforementioned vehicle preheating control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in hardware or independently of the processor in a computer device, or stored in software in the memory of a computer device, so that the processor can call and execute the corresponding operations of each module.

[0142] In addition, in one exemplary embodiment of this specification, a vehicle is also provided, such as Figure 4 As shown, Figure 4 This is a structural schematic diagram of a vehicle provided for one embodiment of this specification.

[0143] For example, vehicle 400 and Figure 1Vehicle 120 in the text refers to the same vehicle.

[0144] For example, such as Figure 4 As shown, the vehicle 400 includes a memory 410 and a processor 420, wherein the memory 410 stores executable program code 430, and the processor 420 is used to call and execute the executable program code 430 to perform a method for vehicle preheating control.

[0145] For example, the memory 410 can be used to store the relevant program of the vehicle preheating control method provided in the embodiments of this application; the processor 420 can call the relevant program of the vehicle preheating control method stored in the memory 410 to execute the vehicle preheating control method of the embodiments of this application; for example, in response to the triggering of a heating event in the vehicle, the health assessment information of the thermal management system executing the heating event is obtained, and the health assessment information is determined based on at least one index characterizing the current heating capacity of the thermal management system. By combining health assessment information and heating event configuration information, multi-dimensional features are extracted to obtain the current execution status features of the thermal management system. The preheating strategy is configured based on the execution status characteristics to obtain the preheating control parameters corresponding to the current thermal management system. The preheating control parameters include at least one of the following: preheating start advance, preheating power parameters, and preheating termination parameters. The thermal management system is controlled to perform corresponding preheating operations based on the preheating control parameters.

[0146] This embodiment can divide the device into functional modules based on the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0147] When each functional module is divided according to its corresponding function, the device may further include an acquisition module, a prediction module, a determination module, and an output module. It should be noted that all relevant content regarding the steps involved in the above method embodiments can be referenced to the functional descriptions of the corresponding functional modules, and will not be repeated here.

[0148] It should be understood that the device provided in this embodiment is used to execute the above-described vehicle preheating control method, and therefore can achieve the same effect as the above-described implementation method.

[0149] When using an integrated unit, the device may include a processing module and a storage module. When the device is applied to a vehicle, the processing module can be used to control and manage the vehicle's movements. The storage module can be used to support the vehicle in executing program code, etc.

[0150] The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits as disclosed in this application. The processor may also be a combination of computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and microprocessors, etc., and the storage module may be a memory.

[0151] In addition, the device provided in the embodiments of this application may specifically be a chip, component or module. The chip may include a connected processor and a memory. The memory is used to store instructions. When the processor calls and executes the instructions, the chip can execute a vehicle preheating control method provided in the above embodiments.

[0152] This application also provides a computer-readable storage medium storing computer program code, which, when executed on a computer, causes the computer to perform the aforementioned method steps to implement the vehicle preheating control method provided in the above embodiments.

[0153] This application also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to implement a vehicle preheating control method provided in the above embodiments.

[0154] The vehicle, computer-readable storage medium, computer program product or chip provided in this application are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects of the corresponding methods provided above, and will not be repeated here.

[0155] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0156] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0157] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0158] The embodiments described above are merely illustrative of several implementation methods outlined in this specification. While the descriptions are specific and detailed, they should not be construed as limiting the scope of the solutions provided in this specification. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this specification, and these all fall within the scope of protection of this specification. Therefore, the scope of protection for this patent should be determined by the appended claims.

Claims

1. A method for controlling the preheating of a vehicle, characterized in that, include: In response to the triggering of a heating event in the vehicle, at least one heating capacity index characterizing the current performance of the thermal management system that performed the heating event is obtained, and the current health assessment information of the thermal management system is determined based on the heating capacity index. By combining the health assessment information and the configuration information of the heating event, multi-dimensional features are extracted to obtain the current execution status features of the thermal management system. Based on the execution state characteristics, a preheating strategy is configured to obtain the preheating control parameters corresponding to the thermal management system at present. The preheating control parameters include at least one of preheating start advance, preheating power parameters, and preheating termination parameters. The thermal management system is controlled to perform corresponding preheating operations according to the preheating control parameters.

2. The method according to claim 1, characterized in that, The heating capacity index includes a heating assessment index and a system health index. The step of obtaining at least one heating capacity index characterizing the current performance of the thermal management system performing the heating event, and determining the current health assessment information of the thermal management system based on the heating capacity index, includes: The heating evaluation index is determined based on the response process of the heating components corresponding to the thermal management system. The system health index is determined based on the lag information of the thermal management system during the heating execution steps; Determine the weight information of the thermal management system configuration; The heating assessment index and the system health index are weighted based on the weight information to obtain the current health assessment information of the thermal management system.

3. The method according to claim 1, characterized in that, The process of extracting multi-dimensional features by combining the health assessment information and the configuration information of the heating events yields the current execution state features of the thermal management system, including: The scene state parameters are extracted based on the configuration information of the heating event to obtain the scene state information; Vehicle status parameters are extracted based on the health assessment information to obtain vehicle status information; Vehicle state features are obtained by extracting features based on the vehicle state parameters, and scene state features are obtained by extracting features based on the scene state parameters. By combining the vehicle state characteristics and the scene state characteristics, the current execution state characteristics of the thermal management system are obtained.

4. The method according to claim 3, characterized in that, The step of extracting vehicle state features based on the vehicle state parameters and extracting scene state features based on the scene state parameters includes: Determine the multiple health assessment indices and battery status information included in the vehicle status parameters; Feature extraction is performed based on the multiple health assessment indices and the battery status information to obtain the vehicle status features; Determine the environmental information and travel information included in the scenario state parameters; Feature extraction is performed based on the environmental information and the travel information to obtain the scene state features.

5. The method according to claim 1, characterized in that, The preheating strategy configuration based on the execution state characteristics to obtain the current preheating control parameters of the thermal management system includes: The execution status characteristics are input into the preheating decision model, so that the preheating control parameters corresponding to the current thermal management system are output through the preheating decision model; The preheating decision model is trained using training samples, which consist of simulation data and real vehicle data. The sample features of the training samples include at least one of thermal system health status, environmental status, and battery status. The labels of the training samples include the minimum preheating advance amount and the minimum power level required to meet the departure temperature requirements.

6. The method according to claim 1, characterized in that, The step of controlling the thermal management system to perform corresponding preheating operations according to the preheating control parameters includes: Obtain the estimated departure time corresponding to the heating event, and determine the preheating start advance, preheating power parameters, and preheating termination parameters indicated by the preheating control parameters; Before the estimated departure time, the execution time is determined according to the preheating start advance, and the preheating operation is triggered based on the execution time; The preheating power parameters are mapped to control commands for the thermal management system. During the preheating process corresponding to the control command, the temperature rise status of the preheated object is obtained, and if the temperature rise status is lower than the expected temperature rise condition, the preheating power parameter is adjusted until the preheating termination parameter is met.

7. The method according to claim 6, characterized in that, The step of adjusting the preheating power parameters when the temperature rise is lower than the expected temperature rise condition until the preheating termination parameters are met includes: Obtain vehicle termination condition parameters, which are configured based on at least one of cabin temperature conditions, battery temperature conditions, departure time conditions, and battery energy constraints. Configure the expected temperature rise conditions based on the aforementioned termination condition parameters; If the temperature rise is lower than the termination condition parameter included in the expected temperature rise condition, adjust the preheating power parameter. If the state parameter corresponding to the temperature rise state reaches the preheating termination parameter, the preheating operation is stopped.

8. The method according to any one of claims 1-7, characterized in that, The method further includes: Record the actual preheating results corresponding to the preheating operation; Based on the difference between the actual preheating result and the target result of the preheating operation, determine whether the preheating has met the standard; If the preheating does not meet the target, the subsequent preheating control parameters will be adjusted, and the preheating decision model used in the preheating strategy configuration will be incrementally trained once the cumulative number of training samples reaches the preset sample number threshold.

9. A vehicle, characterized in that, The vehicles include: Memory, used to store executable program code; A processor is configured to call and run the executable program code from the memory, causing the vehicle to perform the vehicle preheating control method as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the method according to any one of claims 1 to 8.

Images