Expansion valve control method, system and equipment of vehicle thermal management system

Abstract

According to the expansion valve control method, system and equipment of the vehicle thermal management system, a thermal expansion valve is adjusted according to comparison between the temperature of a passenger compartment and the first temperature threshold value, it is ensured that the temperature in a vehicle is stable, and the comfort of passengers is directly guaranteed; the electronic expansion valve focuses the comparison between the battery temperature and the upper limit and the lower limit of a set range, the actual superheat degree is calculated by combining the pressure and the temperature of a refrigerant circulating system, fine opening adjustment is achieved through PI control and feed-forward adjustment, and it is ensured that the battery is in a safe working temperature range; according to the embodiment, pressure and temperature parameters of a refrigerant circulating system are introduced, so that control over the electronic expansion valve can dynamically adapt to refrigerant state changes under different environment temperatures and different loads; according to the embodiment, through cooperative control over the electronic control valve and the thermal control valve, the defect that a single control strategy gives consideration to different temperature control object requirements is overcome, and the problem that in the prior art, independent control is low in energy efficiency is solved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field related to thermal management, and particularly relates to an expansion valve control method, system and device of a vehicle thermal management system. BACKGROUND

[0002] The statements in this section merely provide background information related to the present application and do not necessarily constitute prior art.

[0003] In modern electric vehicles, the thermal management system has an important influence on the performance and life of the in-vehicle air conditioning, power battery and other key components. Especially in a high or low temperature environment, the coordinated work of the in-vehicle air conditioning system and the battery system is very important.

[0004] At present, thermal expansion valves and electronic expansion valves are commonly used in automobile thermal management systems, but independent control of the two often cannot achieve optimal energy efficiency and temperature control effect, especially when there is mutual influence between battery temperature management and passenger cabin temperature, the existing control strategy still has optimization space. SUMMARY

[0005] In order to overcome the shortcomings of the prior art, the present application provides a tunneling machine jam risk evaluation method and system, which can ensure prediction accuracy while realizing quantifiable and interpretable model results.

[0006] In order to achieve the above purpose, the present application adopts the following technical solutions: In a first aspect, the present application provides an expansion valve control method of a vehicle thermal management system, comprising: obtaining the passenger cabin temperature, the battery temperature, the refrigerant circulation system pressure and the refrigerant circulation system temperature; determining the control target of the thermal expansion valve according to the relationship between the passenger cabin temperature and the first temperature threshold; determining the control target of the electronic expansion valve according to the relationship between the battery temperature and the set temperature range, in combination with the actual superheat determined by the refrigerant circulation system pressure and the refrigerant circulation system temperature.

[0007] In a second aspect, the present application provides an expansion valve control system of a vehicle thermal management system, comprising: an acquisition module configured to obtain the passenger cabin temperature, the battery temperature, the refrigerant circulation system pressure and the refrigerant circulation system temperature; a first control module configured to determine the control target of the thermal expansion valve according to the relationship between the passenger cabin temperature and the first temperature threshold; a second control module configured to determine the control target of the electronic expansion valve according to the relationship between the battery temperature and the set temperature range, in combination with the actual superheat determined by the refrigerant circulation system pressure and the refrigerant circulation system temperature. In a third aspect, the present application provides an electronic device comprising a memory and a processor, and computer instructions stored on the memory and running on the processor, when the computer instructions are run by the processor, the method of the first aspect is completed.

[0008] In a fourth aspect, the present application provides a computer readable storage medium for storing computer instructions, when the computer instructions are executed by the processor, the method of the first aspect is completed.

[0009] The above one or more technical solutions have the following beneficial effects: In the present application, the thermal expansion valve adjusts according to the comparison between the passenger cabin temperature and the first temperature threshold, ensures the stability of the temperature in the vehicle, and directly ensures the comfort of the passengers; the electronic expansion valve focuses on the comparison between the battery temperature and the upper and lower limits of the set range, combines the pressure and temperature of the refrigerant circulation system to calculate the actual superheat, realizes fine opening adjustment through PI control and feedforward regulation, and ensures that the battery is in a safe working temperature range; the pressure and temperature parameters of the refrigerant circulation system are introduced in the embodiment, so that the control of the electronic expansion valve can dynamically adapt to the changes of the refrigerant state under different environmental temperatures and different loads; the cooperative control of the electronic control valve and the thermal control valve in the embodiment avoids the insufficient consideration of different temperature control objects by a single control strategy, and solves the problem of low energy efficiency in the prior art.

[0010] The advantages of the additional aspects of the present application will be partially given in the following description, partially will become obvious from the following description, or will be known by the practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0011] The drawings accompanying the specification of the present application form a part thereof, serve to provide further understanding of the present application, and together with the description of the exemplary embodiments of the present application and their explanations serve to explain the present application, and do not constitute an improper limitation of the present application.

[0012] Figure 1 The flow chart of the expansion valve control method of the vehicle thermal management system in the embodiment of the present application is shown in the figure; Figure 2 The flow chart of the control target determination of the electronic expansion valve in the embodiment of the present application is shown in the figure; Figure 3 The flow chart of the opening size determination of the electronic expansion valve in the embodiment of the present application is shown in the figure; Figure 4 The flow chart of the target superheat calculation in the embodiment of the present application is shown in the figure; Figure 5 The schematic diagram of the PID control in the embodiment of the present application is shown in the figure; Figure 6 The block diagram of the expansion valve control system of the vehicle thermal management system in the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0013] It should be noted that the following detailed description is exemplary in nature and is intended to provide further description of the application. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0014] It should be noted that the terms used herein are only intended to describe specific embodiments and are not intended to limit the exemplary embodiments according to the present application.

[0015] In the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0016] First, the hardware related to the vehicle thermal management system in the present embodiment is described. The thermal expansion valve is used for the passenger cabin evaporator to adjust the refrigerant flow to meet the temperature control requirements in the vehicle. The electronic expansion valve is used for the rear evaporator and the battery circuit to accurately adjust the refrigerant flow to meet the temperature control requirements of the battery and the rear evaporator of the passenger cabin. The passenger cabin temperature sensor is used to monitor the temperature in the vehicle in real time. The battery temperature sensor is used to monitor the battery temperature in real time. The pressure sensor is used to monitor the refrigerant circulation system pressure in real time to ensure that the refrigerant circulation system is within the normal working range As shown in Figure 1 The present embodiment proposes a control method for the expansion valve of the vehicle thermal management system, which comprises: S101: obtaining the passenger cabin temperature, the battery temperature, the refrigerant circulation system pressure and the refrigerant circulation system temperature; S102: determining the control target of the thermal expansion valve according to the relationship between the passenger cabin temperature and the first temperature threshold; S103: determining the control target of the electronic expansion valve according to the relationship between the battery temperature and the set temperature range, in combination with the actual superheat determined by the refrigerant circulation system pressure and the refrigerant circulation system temperature.

[0017] In the present embodiment, the thermal expansion valve adjusts according to the comparison between the passenger cabin temperature and the first temperature threshold, ensuring the stability of the temperature in the vehicle and directly ensuring the comfort of the passengers. The electronic expansion valve focuses on the comparison between the upper and lower limits of the set range of the battery temperature, in combination with the pressure and temperature of the refrigerant circulation system to calculate the actual superheat, and realizes fine opening adjustment through PI control and feedforward regulation to ensure that the battery is within the safe working temperature range. The present embodiment introduces the pressure and temperature parameters of the refrigerant circulation system, so that the control of the electronic expansion valve can dynamically adapt to the changes of the refrigerant state under different environmental temperatures and different loads. The cooperative control of the electronic control valve and the thermal control valve in the present embodiment avoids the insufficient consideration of the requirements of different temperature control objects by a single control strategy, and solves the problem of low energy efficiency in the prior art.

[0018] In the embodiment, the control target of the thermal expansion valve is determined according to the relationship between the passenger cabin temperature and the first temperature threshold, specifically: If the passenger cabin temperature is greater than the first temperature threshold, the thermal expansion valve opening degree is increased by a set percentage of the current thermal expansion valve flow opening degree in steps; If the passenger cabin temperature is less than the first temperature threshold, the thermal expansion valve opening degree is decreased by a set percentage of the current thermal expansion valve flow opening degree in steps For example, if T_cabin (passenger cabin temperature) > T_set_cabin (first temperature threshold), the thermal expansion valve increases the flow, and the valve opening degree of the thermal control valve is increased by 5% of the current flow in steps to enhance cooling; if T_cabin (passenger cabin temperature) < T_set_cabin (first temperature threshold), the thermal expansion valve reduces the flow, and the valve opening degree of the thermal control valve is decreased by 5% of the current flow in steps to reduce cooling.

[0019] In the embodiment, as shown in Figure 2 According to the relationship between the battery temperature and the set temperature range, the control target of the electronic expansion valve is determined in combination with the superheat degree of the refrigerant determined based on the pressure of the refrigerant circulation system, specifically: S201: Determine the actual superheat degree based on the saturation refrigerant circulation system temperature corresponding to the pressure of the refrigerant circulation system; Specifically, the actual superheat degree is equal to the PT sensor temperature (refrigerant circulation system temperature) minus the saturation temperature corresponding to the PT sensor pressure (refrigerant circulation system pressure), and the saturation temperature is calculated by table lookup, as shown in Table 1.

[0020] Table 1:

[0021] S202: Determine the opening size of the electronic expansion valve based on the determined actual superheat degree and target superheat degree in combination with the PI control algorithm; Specifically, the difference between the actual water temperature and the target water temperature is table-looked up with the outside temperature; at the same time, the superheat degree is compensated based on the vehicle calibration data for the outlet temperature difference; the above parameters are logically processed to obtain the target superheat degree.

[0022] S203: When the battery temperature is greater than the upper limit of the set temperature range, the opening degree of the current electronic expansion valve is increased by the determined opening size of the electronic expansion valve; S204: When the battery temperature is less than the lower limit of the set temperature, the opening degree of the current electronic expansion valve is decreased by the determined opening size of the electronic expansion valve.

[0023] In this embodiment, the electronic expansion valve calculates the deviation between the actual superheat and the target superheat, and combines it with the PI control algorithm to correct the opening in real time. This reduces the lag and overshoot of temperature regulation, reduces the risk of system oscillation, makes battery temperature control more precise, and indirectly extends battery life and reduces energy loss.

[0024] In this embodiment, if Figure 3 As shown, based on the determined actual superheat and target superheat, the opening size of the electronic expansion valve is determined in combination with the PI control algorithm, specifically: S301: Building and training a decision tree model based on vehicle operation data corresponding to different operating conditions; S302: Determine the operating condition category of the vehicle based on the current vehicle operating data and the trained decision tree model; S303: Determine the operating condition subclass to which the vehicle belongs using a fuzzy clustering algorithm based on the differentiated features corresponding to the current preliminary operating condition of the vehicle; S304: Determine PI controller parameters based on the operating condition subcategory of the vehicle, and determine the opening size of the electronic expansion valve based on the determined PI controller parameters and the difference between the actual superheat and the target superheat.

[0025] In this embodiment, the steps for constructing a decision tree are specifically as follows: Manually label historical operating data to determine the major operating conditions corresponding to each piece of data, such as low temperature, high temperature and high load.

[0026] The marking basis includes: ambient temperature range; combined characteristics of evaporator temperature difference and battery power such as Δ Tevap >8℃ and Pbat ≥50 kW High load on the battery.

[0027] For continuous features such as ambient temperature Tamb , evaporator inlet and outlet temperature difference Δ Tevap Divide the interval.

[0028] For example, ambient temperature: [-∞, 5°C) → low temperature, [5°C, +∞) → non-low temperature; evaporator temperature difference: [-∞, 8°C) → low load, [8°C, +∞) → high load; The discretization boundary is determined by analyzing the feature distribution histogram to ensure that the sample size in each interval is balanced.

[0029] Split rule design: 1. The root node is split.

[0030] Select ambient temperature as the root node feature, as ambient temperature has the most significant impact on the thermal management system operating conditions: Calculate the Gini coefficient (Gini) under different split thresholds and select the threshold that maximizes the reduction of impurity. Gini coefficient calculation formula:

[0031] in, p k The sample belongs to k The proportion of classes, such as Tamb When the temperature is ≤5℃, the proportion of low-temperature samples is 92%, the Gini value is 0.15, and the splitting effect is optimal.

[0032] 2. Child nodes split.

[0033] Non-low temperature working node: Select the evaporator temperature difference (Δ Tevap ) as a splitting feature; High load nodes: Select battery power ( Pbat )Split; Low-load nodes: Select the ambient temperature change rate (∣ T ˙ amb ∣) Split. The decision tree training process starts from the root node and splits layer by layer according to the above rules: each layer of nodes traverses all candidate features ( Tamb , Δ Tevap etc.), calculate the impurity reduction value after the split, that is, the Gini gain; select the feature and threshold with the largest gain for splitting, and generate the left and right child nodes: repeat the splitting until the stopping condition is met.

[0034] In this embodiment, the PI controller parameters are determined based on the operating condition subclass to which the vehicle belongs, specifically: If the vehicle's operating condition subcategory is a medium-sensitivity sub-condition, the PI controller parameters are determined using fuzzy rules; If the vehicle's operating condition subcategory is a high-sensitivity subcondition, the PI controller parameters are determined through reinforcement learning.

[0035] In this embodiment, different PI controller parameters are determined for different sensitivity sub-conditions. The high sensitivity sub-conditions are extremely sensitive to parameter changes, and the reinforcement learning tuning can realize fine adjustment of the parameters through a real-time reward and punishment mechanism, while ensuring system stability, the overheat adjustment time is shortened to within 1.5s. The medium sensitivity sub-conditions need to balance response speed and parameter stability. The fuzzy self-adaptive correction realizes "on-demand adjustment" through rule base matching, which can avoid system oscillation caused by frequent fluctuations, and quickly eliminate small deviations, so that the steady-state error is controlled within 0.3℃. The low sensitivity sub-conditions (such as parking) have the lowest requirement for parameter accuracy, and the fixed parameter + wide fault tolerance mechanism can reduce the consumption of computing resources, while ensuring that the overheat is long-term stable within the target value ±1℃ range, and the system reliability is prioritized. This embodiment can realize accurate matching of PI parameters and sub-conditions, balance control accuracy and system stability, and especially in complex dynamic conditions, it can significantly improve the control effect of electronic expansion valves.

[0036] In this embodiment, if the vehicle belongs to a high sensitivity sub-condition, the PI controller parameters are determined by reinforcement learning. Specifically, the high sensitivity sub-condition to which the vehicle belongs and the corresponding overheat error and key features are input into the trained reinforcement learning model as state input data to obtain the PI controller parameters; wherein the error reward determined based on the overheat error, the smoothing reward determined based on the PI controller parameters, and the constraint reward construct a multi-objective weighted reward function, and the training of the reinforcement learning model is guided by the multi-objective weighted reward function.

[0037] Specifically, for high sensitivity sub-conditions such as sudden acceleration and cold start, a deep Q network (DQN) is used as the core framework of reinforcement learning to realize dynamic tuning of PI parameters. The framework consists of a state perception layer, a decision layer, and an environment interaction layer: State perception layer: real-time acquisition of sub-condition features and system state, output standardized state vector; Decision layer: generate PI parameter adjustment actions through DQN model; Environment interaction layer: apply actions to the thermal management system, and feedback the control effect as a reward signal State space: encoded by high-dimensional vector, including: sub-condition identifier: such as sudden acceleration (H-HA) encoded as [1,0,0], cold start (L-CS) encoded as [0,1,0]; Overheat error: e = SHtarget - SHactual , normalized to [-1,1] by maximum error ±5℃; Error rate of change: ec =( e (k )- e ( k -1)) / Δ t， Δ t is the sampling period, normalized to [-1,1]; Key feature value: e.g. battery power Pbat , normalized to [-1,1], range - 100kW~100kW, ambient temperature Tamb, normalized to [-1,1], range - 30℃~50℃; State vector dimension: sub-working condition identifier + error feature + key feature.

[0038] Action space: define discretized parameter adjustment actions, to avoid decision complexity rise caused by continuous actions: Kp Adjustment amount: {-5%, 0, +5%}, no more than ±5% of the base value each time, to meet the fine adjustment needs of high sensitivity sub-working conditions; Ki Adjustment amount: {-5%, 0, +5%}; action combinations total 3x3=9, e.g. (+5%,0) means Kp increase 5%, Ki unchanged, encoded as [1,0,0,0,1,0,0,0,0].

[0039] Design multi-objective weighted rewards to balance control accuracy and parameter stability: R = w 1• Rerror + w 2• Rsmooth + w 3• Rconstraint Error reward Rerror : 10-2×∣ e ∣, the smaller the error, the higher the reward, maximum 10 points; Smooth reward Rsmooth : 5-10×(∣Δ Kp ∣+∣Δ Ki ∣), the smoother the parameter adjustment, the higher the reward, maximum 5 points; Constraint reward Rconstraint : if Kp , Ki exceeds the safety range, such as Kp >3.0), deduct 10 points, otherwise 0 points; Weight coefficients: w 1=0.6 (priority to ensure control accuracy), w 2=0.3, w 3=0.1 (determined by grid search optimization).

[0040] In DQN model training, the temporal difference error (TD error) is minimized: L =E[( r + γ • a ′max Q ∗( s ′, a ′)- Q ( s , a ))2] in, Q ∗ is the target network output, Q Output of the main network, iteratively update the network parameters through the Adam optimizer.

[0041] In this embodiment, if the vehicle's operating condition subcategory is a medium-sensitivity sub-condition, the PI controller parameters are determined using fuzzy rules, specifically: The superheat error and error change rate corresponding to different medium-sensitivity sub-operating conditions, as well as the correction rate of PI controller parameters are fuzzy processed respectively; Based on the superheat error and error change rate corresponding to the current vehicle, determine the fuzzy output subset corresponding to the current vehicle; Based on the current vehicle fuzzy output subset, the center of gravity method is used to convert the fuzzy output value into a correction value to obtain the PI controller parameters.

[0042] Specifically, for moderately sensitive sub-operating conditions such as cruising and steady-state operation, parameters are allowed to fluctuate within ±20%, control accuracy is moderate, and a certain adaptive margin must be retained. Fuzzy adaptive correction achieves dynamic adjustment of PI parameters by converting expert experience into fuzzy rules. The specific process is as follows: Fuzzification of input variables: taking superheat error as the e and error rate of change ec As input, it is divided into 5 fuzzy subsets: error e (Unit: °C): Negative large (NB, e ≤-2), negative small (NS, -2< e ≤-0.5), zero (ZO,-0.5< e ≤0.5), positive small (PS, 0.5< e ≤2)、Zhengda(PB, e >2); Error change rate ec (Unit: °C / s): Negative large (NB, ec ≤-1), negative small (NS, -1< ec ≤-0.2), zero (ZO,-0.2< ec≤0.2), positive small (PS, 0.2< ec ≤1)、Zhengda(PB, ec >1).

[0043] Output variable setting: The output is the correction rate of PI parameters, that is, Δ Kp / Kp ( Kp Correction ratio) and Δ Ki / Ki ( Ki Correction ratio), which is also divided into 5 fuzzy subsets: negative large (NB, -20%), negative small (NS, -10%), zero (ZO, 0), positive small (PS, +10%), and positive large (PB, +20%), corresponding to the parameter adjustment range of the medium-sensitivity sub-condition.

[0044] Rule base construction principles: High temperature working conditions focus on fast response, and the integral correction amplitude is synchronized with the proportion; low temperature working conditions focus on stability, and the integral correction amplitude is weaker than the proportion; when dynamic changes are drastic ( ec The absolute value is large), the correction amplitude takes the upper limit; in steady state ( ec Close to ZO), the correction range is the lower limit.

[0045] The Mamdani inference method is used to perform fuzzy synthesis on the membership of the input variables: The center of gravity method is used to convert the fuzzy output into an accurate correction value:

[0046] in wi is the rule strength, ui is the center value of the output subset (e.g. PB corresponds to + 20%). Kp =(0.56×10, rounded up to +11%).

[0047] In this embodiment, when the passenger compartment temperature conflicts with the battery temperature control requirements, battery temperature control takes priority, ensuring that the coolant temperature range of the battery thermal management system is met. When the battery temperature approaches the set value, the battery circuit temperature is adjusted to ensure that the battery is within the safe operating temperature range. During the passenger compartment temperature adjustment process, the inlet and outlet temperatures of the battery thermal management system meet the requirements.

[0048] like Figure 6 As shown, this embodiment provides an expansion valve control system for a vehicle thermal management system, including: an acquisition module configured to: acquire a passenger compartment temperature, a battery temperature, a refrigerant circulation system pressure, and a refrigerant circulation system temperature; The first control module is configured to determine a control target of the thermal expansion valve according to a relationship between a passenger compartment temperature and a first temperature threshold; The second control module is configured to determine a control target of the electronic expansion valve according to a relationship between the battery temperature and a set temperature range, in combination with an actual superheat degree determined by the refrigerant circulation system pressure and the refrigerant circulation system temperature.

[0049] In more embodiments, there are also provided: An electronic device includes a memory and a processor, and computer instructions stored in the memory and run on the processor, which, when executed by the processor, complete the method described in Embodiment One. For brevity, this will not be described here.

[0050] It should be understood that in the embodiments, the processor can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), ready programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0051] The memory can include read-only memory and random access memory, and provide instructions and data to the processor, and a portion of the memory can also include non-volatile random access memory. For example, the memory can also store device type information.

[0052] A computer-readable storage medium for storing computer instructions, which, when executed by a processor, complete the method described in Embodiment One.

[0053] The method in Embodiment One can be directly embodied as a hardware processor to complete, or be completed by a combination of hardware and software modules in the processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers or other mature storage media in the art. The storage medium is located in the memory, and the processor reads the information in the memory and combines the hardware to complete the steps of the above method. To avoid repetition, it will not be described in detail here.

[0054] A computer program product includes a computer program, which, when executed by a processor, implements the method described in Embodiment One.

[0055] The present application also provides at least one computer program product tangibly stored on a non-transitory computer readable storage medium. The computer program product includes computer executable instructions, for example, instructions embodied in program modules, executed by devices at the target real or virtual processor to perform the processes / methods as described above. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The functionality of the program modules can be combined or split between program modules as desired in various embodiments. Machine executable instructions for program modules can be executed within a local or distributed device. In a distributed device, program modules can be located in local and remote memory storage devices.

[0056] Computer program code for carrying out operations of the present application can be written in one or more programming languages. These computer program codes can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program codes, when executed by the computer or other programmable data processing apparatus, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program codes can be executed entirely on a computer, partially on a computer, as a stand-alone software package, partially on a computer and partially on a remote computer, or entirely on a remote computer or server.

[0057] In the context of the present application, the computer program code or related data can be carried by any suitable carrier to enable the device, apparatus or processor to perform the various processes and operations described above. Examples of carriers include signals, computer readable media, and the like. Examples of signals can include electrical, optical, radio, sound or other forms of propagated signals, such as carrier waves, infrared signals, and the like.

[0058] Those skilled in the art can understand that the units and algorithm steps of the examples described in conjunction with the embodiments can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0059] The above describes the specific embodiments of the present application in conjunction with the accompanying drawings, but is not a limitation on the scope of protection of the present application. Those skilled in the art should understand that various modifications or variations made by those skilled in the art on the basis of the technical solutions of the present application without inventive labor are still within the scope of protection of the present application.

Claims

1. A method for controlling an expansion valve of a vehicle thermal management system, characterized in that: include: Obtaining passenger compartment temperature, battery temperature, refrigerant circulation system pressure, and refrigerant circulation system temperature; determining a control target of the thermal expansion valve according to a relationship between the passenger compartment temperature and the first temperature threshold; A control target of the electronic expansion valve is determined according to a relationship between the battery temperature and the set temperature range and in combination with an actual superheat determined by the refrigerant circulation system pressure and the refrigerant circulation system temperature.

2. The expansion valve control method of a vehicle thermal management system according to claim 1, wherein: According to the relationship between the passenger compartment temperature and the first temperature threshold, the control target of the thermal expansion valve is determined, specifically: If the passenger compartment temperature is greater than a first temperature threshold, the thermal expansion valve opening is increased in a stepwise manner by a set percentage of the current thermal expansion valve flow opening; If the passenger compartment temperature is lower than the first temperature threshold, the opening of the thermal expansion valve is reduced in steps by a set percentage of the current flow opening of the thermal expansion valve.

3. The expansion valve control method of a vehicle thermal management system according to claim 1, wherein: Based on the relationship between the battery temperature and the set temperature range, combined with the refrigerant superheat determined by the refrigerant circulation system pressure, the control target of the electronic expansion valve is determined, specifically: determining an actual superheat based on a saturation corresponding to a refrigerant circulation system pressure and a temperature of the refrigerant circulation system; Based on the determined actual superheat and target superheat, the opening degree of the electronic expansion valve is determined in combination with a PI control algorithm; When the battery temperature is greater than the upper limit of the set temperature range, the current opening of the electronic expansion valve is increased according to the determined opening size of the electronic expansion valve; When the battery temperature is lower than the lower limit of the set temperature, the current opening of the electronic expansion valve is reduced according to the determined opening size of the electronic expansion valve.

4. The expansion valve control method of a vehicle thermal management system according to claim 3, wherein: Based on the determined actual superheat and target superheat, the opening degree of the electronic expansion valve is determined in combination with the PI control algorithm, specifically: Build and train a decision tree model based on the corresponding vehicle operation data under different working conditions; According to the current vehicle operation data, based on the trained decision tree model, determine the vehicle's operating condition category; According to the differentiated features corresponding to the current vehicle preliminary working condition, the fuzzy clustering algorithm is used to determine the working condition subclass to which the vehicle belongs; Based on the operating condition subcategory to which the vehicle belongs, PI controller parameters are determined, and based on the determined PI controller parameters and a difference between the actual superheat and the target superheat, an opening size of the electronic expansion valve is determined.

5. The expansion valve control method of a vehicle thermal management system according to claim 4, characterized in that: Based on the vehicle's operating condition subcategory, determine the PI controller parameters, specifically: If the vehicle's operating condition subcategory is a medium-sensitivity sub-condition, the PI controller parameters are determined using fuzzy rules; If the vehicle's operating condition subcategory is a high-sensitivity subcondition, the PI controller parameters are determined through reinforcement learning.

6. The expansion valve control method of a vehicle thermal management system according to claim 5, characterized in that: If the vehicle's operating condition subcategory is a high-sensitivity subcondition, the PI controller parameters are determined through reinforcement learning. Specifically, the vehicle's high-sensitivity subcondition and its corresponding superheat error and key features are used as state input data and input into a trained reinforcement learning model to obtain the PI controller parameters. A multi-objective weighted reward function is constructed based on the error reward determined by the superheat error, the smoothing reward determined by the PI controller parameters, and the constraint reward. The multi-objective weighted reward function guides the training of the reinforcement learning model.

7. The expansion valve control method of a vehicle thermal management system according to claim 5, wherein: If the vehicle's operating condition subcategory is a medium-sensitivity subcondition, the PI controller parameters are determined by fuzzy rules, specifically: The superheat error and error change rate corresponding to different medium-sensitivity sub-operating conditions, as well as the correction rate of PI controller parameters are fuzzy processed respectively; Based on the superheat error and error change rate corresponding to the current vehicle, determine the fuzzy output subset corresponding to the current vehicle; Based on the current vehicle fuzzy output subset, the center of gravity method is used to convert the fuzzy output value into a correction value to obtain the PI controller parameters.

8. An expansion valve control system for a vehicle thermal management system, characterized in that: include: an acquisition module configured to: acquire a passenger compartment temperature, a battery temperature, a refrigerant circulation system pressure, and a refrigerant circulation system temperature; The first control module is configured to determine a control target of the thermal expansion valve according to a relationship between a passenger compartment temperature and a first temperature threshold; The second control module is configured to determine a control target of the electronic expansion valve according to a relationship between the battery temperature and the set temperature range and an actual superheat determined by the refrigerant circulation system pressure and the refrigerant circulation system temperature.

9. An electronic device, characterized in that: The method comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method according to any one of claims 1 to 7 is completed.

10. A computer-readable storage medium, characterized in that Used to store computer instructions, which, when executed by a processor, complete the method according to any one of claims 1 to 7.

Images