System temperature control method and device, electronic equipment and storage medium

Abstract

The invention relates to a system temperature control method and device, electronic equipment and a storage medium. The method comprises the steps that a parameter value sequence corresponding to each preset parameter in a first preset time period in multiple preset parameters of a temperature control system of a vehicle is obtained; inputting the plurality of parameter value sequences into a pre-trained temperature prediction model to obtain a predicted temperature value of the temperature control system; acquiring an actual temperature value and a set temperature value of the temperature control system, and determining a target parameter value corresponding to the control parameter when the temperature control system is controlled according to the actual temperature value, the set temperature value and the predicted temperature value; and controlling the temperature control system according to the target parameter value, so that the system temperature of the temperature control system reaches the set temperature value. Therefore, the system temperature of the temperature control system can be controlled more accurately, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the technical field of temperature control systems, and in particular to a system temperature control method, device, electronic device, and storage medium. Background Art

[0002] In the field of temperature control systems, a controller generally controls the system temperature of the system by controlling the parameter values of control parameters preset in the system, so that the system temperature reaches a set temperature value.

[0003] Currently, the parameter values of the above control parameters are generally determined by preset rules. For example, a mapping relationship between the parameter value and the system temperature can be established in advance, so that the parameter value of the control parameter in the system can be determined according to the system temperature to be achieved.

[0004] However, the above methods are often coarse-grained, and the above rules are usually determined in the design stage. It is difficult to flexibly adjust them according to actual usage in the later stage, and it is impossible to accurately control the system temperature of the system to reach the set value. Summary of the Invention

[0005] The present application provides a system temperature control method, device, electronic device and storage medium to solve the technical problem that the system temperature control method in the prior art cannot accurately control the system temperature to reach the set value.

[0006] In a first aspect, the present application provides a system temperature control method, the method comprising:

[0007] Obtaining a sequence of parameter values corresponding to each of a plurality of preset parameters of a temperature control system of a vehicle within a first preset time period; wherein the preset parameters include a system temperature of the temperature control system, an ambient temperature of the temperature control system, and a control parameter for adjusting the system temperature of the temperature control system;

[0008] Inputting a plurality of said parameter value sequences into a pre-trained temperature prediction model to obtain a predicted temperature value of said temperature control system;

[0009] Obtaining an actual temperature value and a set temperature value of the temperature control system, and determining a target parameter value corresponding to the control parameter when controlling the temperature control system based on the actual temperature value, the set temperature value, and the predicted temperature value;

[0010] The temperature control system is controlled according to the target parameter value so that the system temperature of the temperature control system reaches the set temperature value.

[0011] As an optional implementation, multiple parameter value sequences are input into a pre-trained temperature prediction model to obtain a predicted temperature value of the temperature control system, including:

[0012] inputting the plurality of parameter value sequences into a pre-trained temperature prediction model to obtain a sequence of predicted temperature values of the temperature control system within a second preset time period; the second preset time period being later than the first preset time period, the second preset time period including a plurality of acquisition moments divided according to a preset time step, the sequence of predicted temperature values including a predicted temperature value corresponding to each of the acquisition moments;

[0013] The obtaining of the actual temperature value and the set temperature value of the temperature control system, and determining, based on the actual temperature value, the set temperature value, and the predicted temperature value, a target parameter value corresponding to the control parameter when controlling the temperature control system, includes:

[0014] For each collection moment within the second preset time period, obtaining an actual temperature value and a set temperature value of the temperature control system corresponding to the collection moment;

[0015] According to the actual temperature value, the set temperature value, and the predicted temperature value corresponding to the acquisition moment, a target parameter value of a corresponding control parameter when controlling the temperature control system corresponding to the acquisition moment is determined.

[0016] As an optional implementation, determining a target parameter value corresponding to the control parameter when controlling the temperature control system based on the actual temperature value, the set temperature value, and the predicted temperature value includes:

[0017] determining a temperature error based on the actual temperature value, the set temperature value, and the predicted temperature value;

[0018] Get the historical temperature error determined before the current moment;

[0019] Processing the temperature error and the historical temperature error using a preset feedback control algorithm to obtain a parameter value increment corresponding to the control parameter;

[0020] Obtaining historical parameter values corresponding to the control parameters;

[0021] A preset operation is performed on the historical parameter value and the parameter value increment to obtain a target parameter value corresponding to the control parameter when the temperature control system is currently controlled.

[0022] As an optional implementation, determining the current temperature error according to the actual temperature value, the set temperature value, and the predicted temperature value includes:

[0023] determining a first temperature difference between the set temperature value and the predicted temperature value, and a second temperature difference between the set temperature value and the actual temperature value;

[0024] Obtaining a model confidence level of the predicted temperature value output by the temperature prediction model, and determining a weight coefficient of the first temperature difference based on the model confidence level;

[0025] A weighted sum of the first temperature difference and the second temperature difference is performed according to the weight coefficient to obtain a current temperature error.

[0026] As an optional implementation, the temperature prediction model is trained in the following way:

[0027] Obtaining a sequence of historical parameter values corresponding to each of the multiple initial parameters of the temperature control system within a historical time period;

[0028] Preprocessing the plurality of historical parameter value sequences to obtain a training sample set;

[0029] Dividing the training sample set into training samples and test samples according to a preset allocation ratio;

[0030] Using the training samples to train an initial temperature prediction model, and using the test samples to test the initial temperature prediction model;

[0031] When the initial temperature prediction model meets a preset condition, the temperature prediction model is obtained.

[0032] As an optional implementation, the temperature prediction model is obtained when the initial temperature prediction model meets the following conditions:

[0033] Obtaining a training loss value change trend corresponding to the training sample and a test loss value change trend corresponding to the test sample, and stopping training when the training loss value change trend indicates a decrease in the training loss value and the test loss value change trend indicates an increase in the test loss value;

[0034] and / or, stopping the training when the number of training times reaches a preset threshold;

[0035] And / or, obtaining a training loss value of the training sample and a test loss value of the test sample, and stopping training when both the training loss value and the test loss value are less than a preset loss value threshold.

[0036] As an optional implementation, the control parameters include one or more of the following: the power of the power output module, the rotation speed of the fluid compression module, the rotation speed of the fluid delivery module, and the opening degree of the fluid regulating module.

[0037] In a second aspect, the present application provides a system temperature control device, the device comprising:

[0038] an acquisition module, configured to acquire a sequence of parameter values corresponding to each of a plurality of preset parameters of a temperature control system of a vehicle within a first preset time period; wherein the preset parameters include a system temperature of the temperature control system, an ambient temperature of the temperature control system, and a control parameter for adjusting the system temperature of the temperature control system;

[0039] a processing module, configured to input a plurality of said parameter value sequences into a pre-trained temperature prediction model to obtain a predicted temperature value of said temperature control system;

[0040] a determination module, configured to obtain an actual temperature value and a set temperature value of the temperature control system, and determine a target parameter value corresponding to the control parameter when controlling the temperature control system based on the actual temperature value, the set temperature value, and the predicted temperature value;

[0041] The control module is used to control the temperature control system according to the target parameter value so that the system temperature of the temperature control system reaches the set temperature value.

[0042] In a third aspect, the present application provides an electronic device comprising: a processor and a memory, wherein the processor is configured to execute a system temperature control program stored in the memory to implement the system temperature control method described in any one of the first aspects.

[0043] In a fourth aspect, the present application provides a storage medium storing one or more programs, which can be executed by one or more processors to implement the system temperature control method described in any one of the first aspects.

[0044] The technical solution of the embodiment of the present application is to pre-train a temperature prediction model for predicting the system temperature according to the system temperature change trend of the temperature control system, so that when the system temperature of the temperature control system is controlled, the temperature prediction model can be used to predict the system temperature change trend of the temperature control system according to multiple parameter value sequences corresponding to the first time period, thereby predicting the predicted temperature value of the temperature control system, and determining the target parameter value of the control parameter in the temperature control system based on the predicted temperature value, the actual temperature value of the temperature control system and the set temperature value. Since the temperature prediction model accurately predicts the future temperature of the temperature control system, the target parameter value can be determined more accurately, thereby achieving more accurate control of the system temperature of the temperature control system and improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art texts. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0047] One or more embodiments are exemplarily illustrated by pictures in the corresponding drawings. These exemplifications do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings are represented as similar elements. Unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0048] Figure 1 A flow chart of an embodiment of a system temperature control method provided in an embodiment of the present application;

[0049] Figure 2 A flow chart of another embodiment of a system temperature control method provided in an embodiment of the present application;

[0050] Figure 3 A flow chart of another embodiment of a system temperature control method provided in an embodiment of the present application;

[0051] Figure 4 A flow chart of another embodiment of a system temperature control method provided in an embodiment of the present application;

[0052] Figure 5 A flow chart of an embodiment of a method for training a temperature prediction model provided in an embodiment of the present application;

[0053] Figure 6This is a block diagram of an embodiment of a system temperature control device provided in an embodiment of the present application;

[0054] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0056] The disclosure below provides many different embodiments or examples for implementing different structures of the present application. In order to simplify the disclosure of the present application, the components and settings of specific examples are described in detail below. Of course, these are merely examples and are not intended to limit the present application. In addition, the present application may repeat reference numbers and / or letters in different examples. Such repetition is for the purpose of simplicity and clarity and does not in itself indicate the relationship between the various embodiments and / or settings discussed.

[0057] In order to solve the technical problem that the system temperature control method in the prior art cannot accurately control the system temperature to reach the set value, the present application provides a system temperature control method, device, electronic device and storage medium, which can pre-train a temperature prediction model for predicting the system temperature, so that when controlling the system temperature of the temperature control system, the temperature prediction model can be used to predict the predicted temperature value of the temperature control system, and the target parameter value of the control parameter in the temperature control system is determined based on the predicted temperature value, the actual temperature value of the temperature control system and the set temperature value. Since the temperature prediction model accurately predicts the future temperature of the temperature control system, the target parameter value can be determined more accurately, thereby achieving more accurate control of the system temperature of the temperature control system and improving user experience.

[0058] The system temperature control method provided in the present application is further explained below with reference to specific embodiments in conjunction with the accompanying drawings. The embodiments do not constitute a limitation on the embodiments of the present application.

[0059] See also Figure 1 , is a flow chart of an embodiment of a system temperature control method provided in an embodiment of the present application. Figure 1 As shown, the process may include the following steps:

[0060] Step 101: Obtain a sequence of parameter values corresponding to each of multiple preset parameters of a vehicle's temperature control system within a first preset time period; wherein the preset parameters include a system temperature of the temperature control system, an ambient temperature of the temperature control system, and a control parameter for adjusting the system temperature of the temperature control system.

[0061] Step 102: Input multiple parameter value sequences into a pre-trained temperature prediction model to obtain a predicted temperature value of the temperature control system.

[0062] The following is a unified description of step 101 and step 102:

[0063] The above-mentioned temperature control system refers to the vehicle's system to be temperature controlled, such as the vehicle's thermal management system, which may include: a power battery thermal management system, a motor cooling system, and a cabin air conditioning system, etc.

[0064] The above-mentioned preset parameters refer to the parameters involved in the operation of the temperature control system, which may include but are not limited to: the system temperature of the temperature control system, the ambient temperature of the temperature control system, and the control parameters used to adjust the system temperature of the temperature control system.

[0065] The above-mentioned control parameters refer to parameters related to the system temperature of the temperature control system, that is, the system temperature of the temperature control system can be adjusted through the control parameters, including but not limited to: the power of the power output module (the power output module refers to the module used to provide power to the vehicle, such as a motor), the speed of the fluid compression module (the fluid compression module refers to the module used to compress the fluid (such as refrigerant) in the system, such as a compressor), the speed of the fluid delivery module (the fluid delivery module refers to the module that delivers fluid (such as water) to the temperature control system, such as an electronic water pump), and the opening of the fluid regulating module (the fluid regulating module refers to the module used to regulate the flow of fluid (such as an electronic expansion valve)), etc.

[0066] The first preset time period refers to a preset time period before the current moment, such as the past 1 hour, 2 hours, or 30 minutes.

[0067] The above parameter value sequence refers to a sequence composed of parameter values of each preset parameter running within the first preset time period, and the parameter value sequence can be arranged in chronological order.

[0068] The temperature prediction model refers to a pre-trained model for predicting the predicted temperature value of the temperature control system that will currently operate, which may be a pre-trained LSTM (Long Short-Term Memory) model.

[0069] The predicted temperature value is the system temperature value that the temperature control system will currently reach as predicted by the temperature prediction model.

[0070] In some embodiments of the present application, in order to predict the system temperature change trend of the temperature control system during operation, thereby improving the accuracy of temperature control of the temperature control system, the execution entity of the embodiments of the present application may pre-train a temperature prediction model to use the temperature prediction model to predict the system temperature change trend of the temperature control system based on multiple parameter value sequences corresponding to the first time period, thereby obtaining the predicted temperature value of the temperature control system.

[0071] As for how to train the above temperature prediction model, it will be explained below and will not be described in detail here.

[0072] Based on this, the execution subject of the embodiment of the present application can obtain a plurality of preset parameters of the temperature control system, and a parameter value sequence corresponding to each preset parameter within a first preset time period, to obtain a plurality of parameter value sequences.

[0073] Afterwards, the plurality of parameter value sequences may be input into the pre-trained temperature prediction model to obtain the current predicted temperature value of the temperature control system.

[0074] Step 103: Obtain the current actual temperature value and set temperature value of the temperature control system.

[0075] Step 104 : Determine target parameter values of corresponding control parameters when controlling the temperature control system based on the actual temperature value, the set temperature value, and the predicted temperature value.

[0076] Step 105 : Control the temperature control system according to the target parameter value so that the system temperature of the temperature control system reaches the set temperature value.

[0077] The following is a unified description of steps 103 to 105:

[0078] The above actual temperature value refers to the actual system temperature value when the temperature control system is currently running.

[0079] The above-mentioned set temperature value refers to the pre-set target system temperature value that the temperature control system is to reach.

[0080] The above-mentioned target parameter value refers to the parameter value corresponding to each of the above-mentioned control parameters when the temperature control system is temperature controlled. That is, when the control parameter of the temperature control system is the target parameter value, the system temperature of the temperature control system can reach the above-mentioned set temperature value.

[0081] In some embodiments of the present application, after obtaining the current predicted temperature value of the temperature control system through the temperature prediction model, the current actual temperature value and set temperature value of the temperature control system can be obtained, so that the target parameter value of the corresponding control parameter when the temperature control system is currently controlled can be determined based on the above actual temperature value, set temperature value, and the above predicted temperature value.

[0082] As an optional implementation method, the execution subject of the embodiment of the present application can obtain the current actual temperature value of the temperature control system through a preset temperature measurement module, and obtain the set temperature value of the temperature control system through a visual interface.

[0083] As for how to determine the target parameter value of the corresponding control parameter when the temperature control system is currently controlled, it will be explained below and will not be described in detail here.

[0084] Afterwards, the temperature control system can be controlled according to the above-mentioned target parameter values, that is, the parameter values of the control parameters of the temperature control system are the above-mentioned target parameter values. By controlling the modules in the temperature control system (such as the power output module, the fluid compression module, the fluid delivery module, and the fluid regulation module) to operate with the above-mentioned target parameter values, the system temperature of the temperature control system can reach the above-mentioned set temperature value.

[0085] Among them, since the target parameter value is determined based on the predicted temperature value predicted by the temperature prediction model, the actual temperature value of the temperature control system, and the set temperature value, and the temperature prediction model can predict the system temperature value of the temperature control system according to the system temperature change trend of the temperature control system, therefore, the target parameter value determined based on the predicted temperature value is more in line with the system temperature change trend of the temperature control system, and can also make the system temperature of the temperature control system reach the above-mentioned set temperature value more accurately.

[0086] In addition, during the process of controlling the temperature control system, the actual temperature value of the temperature control system can be continuously monitored and fed back to the execution entity of this application so that it can be used next time to determine the target parameter value of the corresponding control parameter when controlling the control coefficient, forming a closed-loop control loop to continuously adjust the target parameter value to adapt to the dynamic changes of the temperature control system.

[0087] The technical solution of the embodiment of the present application is to obtain a parameter value sequence corresponding to each preset parameter in a first preset time period from multiple preset parameters of the vehicle's temperature control system, wherein the preset parameters include the system temperature of the temperature control system, the ambient temperature of the temperature control system, and the control parameters for adjusting the system temperature of the temperature control system. A pre-trained temperature prediction model is used to process the multiple parameter value sequences to obtain a predicted temperature value of the temperature control system, and the current actual temperature value and set temperature value of the temperature control system are obtained. According to the above actual temperature value, set temperature value, and predicted temperature value, a target parameter value of the corresponding control parameter when controlling the temperature control system is determined. According to the above target parameter value, the temperature control system is controlled so that the system temperature of the temperature control system reaches the above set temperature value. This technical solution pre-trains a temperature prediction model for predicting the system temperature according to the system temperature change trend of the temperature control system, so that when controlling the system temperature of the temperature control system, the temperature prediction model can predict the system temperature change trend of the temperature control system according to the corresponding multiple parameter value sequences in the first time period, thereby predicting the predicted temperature value of the temperature control system, and determining the target parameter value of the control parameter in the temperature control system based on the predicted temperature value, the actual temperature value of the temperature control system and the set temperature value. Since the temperature prediction model accurately predicts the future temperature of the temperature control system, the target parameter value can be determined more accurately, thereby achieving more accurate control of the system temperature of the temperature control system and improving user experience.

[0088] See also Figure 2 , which is a flow chart of another embodiment of a system temperature control method provided in an embodiment of the present application. Figure 2 The process shown in Figure 1 Based on the process shown, it is described that the temperature prediction model can output multiple predicted temperature values of the temperature control system within the second preset time period. Figure 2 As shown, the process may include the following steps:

[0089] Step 201: Obtain a parameter value sequence corresponding to each of a plurality of preset parameters of a temperature control system within a first preset time period.

[0090] For a detailed description of step 201 , please refer to the description of step 101 , which will not be repeated here.

[0091] Step 202: Input a plurality of parameter value sequences into a pre-trained temperature prediction model to obtain a predicted temperature value sequence of the temperature control system within a second preset time period.

[0092] The second preset time period may be a time period later than the first preset time period, and may be a preset time period after the current moment, such as 1 minute or 2 minutes after the current moment. The second preset time period may include multiple collection moments divided according to a preset time step, and the preset time step may be 1 second, 5 seconds, or 10 seconds, for example.

[0093] For example, assuming that the second preset time period is 60 seconds and the preset time step is 10 seconds, the collection moments included in the second time period may include: 10 seconds, 20 seconds, 30 seconds, 40 seconds, 50 seconds, and 60 seconds.

[0094] The above-mentioned predicted temperature value sequence may include the predicted temperature value corresponding to each of the above-mentioned acquisition moments, which may be arranged in chronological order.

[0095] In some embodiments of the present application, the temperature prediction model can predict a single predicted temperature value of the temperature control system at the current moment, or can predict multiple predicted temperature values of the temperature control system over a time period. Specifically, to improve the temperature control efficiency of the temperature control system, the temperature prediction model can predict multiple predicted temperature values of the temperature control system at multiple future acquisition moments.

[0096] Based on this, the executing entity of the embodiment of the present application can input multiple parameter value sequences into a pre-trained temperature prediction model, and use the above-mentioned temperature prediction model to process multiple parameter value sequences to obtain the predicted temperature value sequence of the temperature control system within the second preset time period output by the temperature prediction model.

[0097] As an optional implementation, the preset parameters may include a control parameter for the temperature control system, a system temperature of the temperature control system, and an ambient temperature of the temperature control system. Based on this, the parameter value sequence may include: a parameter value sequence of the control parameter in a first preset time period, a system temperature value sequence of the temperature control system in the first preset time period, and a ambient temperature value sequence of the temperature control system in the first preset time period.

[0098] To this end, the parameter value sequence, system temperature value sequence, and ambient temperature value sequence can be simultaneously input into the temperature prediction model to obtain a predicted temperature value sequence of the temperature control system within the second preset time period output by the temperature prediction model.

[0099] Step 203: For each collection moment within the second preset time period, obtain the actual temperature value and the set temperature value corresponding to the temperature control system at the collection moment.

[0100] Step 204 : Determine a target parameter value of a control parameter corresponding to the temperature control system at the acquisition moment according to the actual temperature value, the set temperature value, and the predicted temperature value corresponding to the acquisition moment.

[0101] Step 205: Control the temperature control system according to the target parameter value corresponding to the acquisition moment.

[0102] The following is a unified description of steps 203 to 205:

[0103] In some embodiments of the present application, after obtaining multiple predicted temperature values of the temperature control system within a second preset time period in the future, that is, the predicted temperature value of each collection moment in the multiple collection moments included in the second preset time period, the execution entity of the embodiment of the present application can obtain the actual temperature value and set temperature value of the temperature control system corresponding to each collection moment when each collection moment is reached, and determine the target parameter value of the corresponding control parameter when the temperature control system is currently controlled based on the actual temperature value, the set temperature value, and the predicted temperature value at the collection moment.

[0104] As for how to determine the target parameter value of the corresponding control parameter when controlling the temperature control system based on the actual temperature value, the set temperature value, and the predicted temperature value at the time of acquisition, it can be described in the following. Figure 3 The process shown is explained below and will not be described in detail here.

[0105] The control parameters corresponding to the target parameter values determined here are consistent with the control parameters in the input temperature prediction model.

[0106] For example: when the control parameters in the input temperature prediction model include the power of the power output module (the power output module refers to the module used to provide power to the vehicle, such as a motor) and the speed of the fluid compression module (the fluid compression module refers to the module used to compress the fluid (such as refrigerant) in the system, such as a compressor), the corresponding control parameters determined at this time when the temperature control system is currently controlled also include the power of the power output module and the speed of the fluid compression module.

[0107] For another example, when the control parameters in the input temperature prediction model include: the power of the power output module (the power output module refers to the module used to provide power to the vehicle, such as a motor), the speed of the fluid compression module (the fluid compression module refers to the module used to compress the fluid (such as refrigerant) in the system, such as a compressor), the speed of the fluid delivery module (the fluid delivery module refers to the module that delivers fluid (such as water) to the temperature control system, such as an electronic water pump), and the opening of the fluid regulating module (the fluid regulating module refers to the module used to regulate the flow of the fluid (such as an electronic expansion valve)), the corresponding control parameters determined at this time when the temperature control system is currently controlled also include: the power of the power output module, the speed of the fluid compression module, the speed of the fluid delivery module, and the opening of the fluid regulating module.

[0108] Afterwards, when the temperature control system is temperature controlled at the collection moment, the temperature control system can be controlled according to the target parameter value corresponding to the collection moment, so that the system temperature of the temperature control system reaches the corresponding set temperature value at each collection moment within the second preset time period.

[0109] The technical solution provided by the embodiments of the present application obtains a parameter value sequence corresponding to each of multiple preset parameters of a temperature control system within a first preset time period, inputs the multiple parameter value sequences into a pre-trained temperature prediction model, and obtains a predicted temperature value sequence of the temperature control system within a second preset time period. For each acquisition moment within the second preset time period, the actual temperature value and set temperature value of the temperature control system corresponding to the acquisition moment are obtained. Based on the actual temperature value, set temperature value, and predicted temperature value corresponding to the acquisition moment, a target parameter value corresponding to the control parameter when controlling the temperature control system at the acquisition moment is determined, and the temperature control system is controlled according to the target parameter value corresponding to the acquisition moment. This technical solution improves the accuracy and efficiency of controlling the system temperature of the temperature control system by using the temperature prediction model to predict multiple predicted temperature values of the temperature control system in the future second preset time period, and directly uses the predicted temperature value sequence output by the temperature prediction model to control the system temperature of the temperature control system to the corresponding set temperature value when controlling the system temperature value of the temperature control system within the second preset time period, thereby achieving improved accuracy and efficiency in controlling the system temperature of the temperature control system.

[0110] See also Figure 3 , which is a flow chart of another embodiment of a system temperature control method provided in an embodiment of the present application. Figure 3 The process shown in Figure 1 or Figure 2 Based on the process shown in FIG, it describes how to determine the target parameter value of the corresponding control parameter when controlling the temperature control system according to the actual temperature value, the set temperature value, and the predicted temperature value. Figure 3 As shown, the process may include the following steps:

[0111] Step 301: Determine the current temperature error based on the actual temperature value, the set temperature value, and the predicted temperature value.

[0112] The temperature error refers to the error temperature value that the temperature control system currently wants to achieve the set temperature value, which can be determined by combining the temperature difference between the set temperature value and the predicted temperature value, and the temperature difference between the set temperature value and the actual temperature value.

[0113] In some embodiments of the present application, the execution subject of the embodiments of the present application can determine the current temperature error of the temperature control system based on the above-mentioned actual temperature value, set temperature value, and predicted temperature value.

[0114] As an optional implementation, the execution subject of the embodiment of the present application may determine a first temperature difference between the set temperature value and the predicted temperature value, and a second temperature difference between the set temperature value and the actual temperature value.

[0115] Afterwards, the model confidence of the predicted temperature value output by the above-mentioned temperature prediction model can be obtained, and based on the model confidence, the weight coefficient of the above-mentioned first temperature difference can be determined, and the above-mentioned first temperature difference and second temperature difference can be weightedly summed according to the above-mentioned weight coefficient to obtain the current temperature error.

[0116] Among them, the above-mentioned model confidence refers to the accuracy of the predicted temperature value obtained by the temperature prediction model to predict the system temperature of the temperature control system (when the temperature prediction model outputs the corresponding preset temperature value, it also outputs the confidence corresponding to the predicted temperature value). The higher the model confidence, the higher the accuracy of the temperature prediction model, and the larger the corresponding weight coefficient, that is, the weight coefficient can be proportional to the above-mentioned model confidence.

[0117] Based on this, the corresponding relationship between the model confidence and the weight coefficient can be preset. After the model confidence of the temperature prediction model is determined, the corresponding weight coefficient can be determined from the above corresponding relationship according to the above model confidence.

[0118] As an exemplary embodiment, the first temperature difference may be multiplied by a weight coefficient to obtain a first value, the weight coefficient may be subtracted from a preset value to obtain a second weight coefficient corresponding to the second temperature difference, and the second temperature difference may be multiplied by the second weight coefficient to obtain a second value. Subsequently, the first value and the second value may be added to obtain the current temperature error.

[0119] As an embodiment, the actual temperature value, the set temperature value, and the predicted temperature value can be calculated by the following formula (1) to obtain the current temperature error:

[0120] etotal=α*(Tset-Tpred)+(1-α)*(Tset-Tactual) Formula (1)

[0121] The above-mentioned etotal is the above-mentioned temperature error, the above-mentioned α is the above-mentioned weight coefficient, the above-mentioned Tset is the above-mentioned set temperature value, the above-mentioned Tpred is the predicted temperature value, and the above-mentioned Tactual is the above-mentioned actual temperature value.

[0122] Step 302: Obtain historical temperature errors determined before the current moment.

[0123] Step 303: Process the temperature error and the historical temperature error using a preset feedback control algorithm to obtain a parameter value increment corresponding to the above control parameter.

[0124] The above parameter value increment refers to the increment between the corresponding parameter value of the control parameter of the temperature control system and the target parameter value determined last time.

[0125] In some embodiments of the present application, the execution subject of the embodiments of the present application may determine the parameter value increment corresponding to the above-mentioned control parameter based on the above-mentioned temperature error.

[0126] As an optional implementation method, the execution subject of the embodiment of the present application can obtain the historical temperature error determined before the current moment, and use a preset feedback control algorithm to process the above temperature error and the historical temperature error to obtain the parameter value increment corresponding to the control parameter.

[0127] As an implementation method, the two temperature errors closest to the current moment can be determined, namely, the first temperature error and the second temperature error, wherein the corresponding time of the second temperature error is earlier than the first temperature error, that is, the first temperature error is the temperature error at the previous acquisition moment, and the second temperature error is the temperature error at the previous acquisition moment before the previous acquisition moment.

[0128] Afterwards, the temperature error, the first temperature error, and the second temperature error may be processed using a preset feedback control algorithm to obtain parameter value increments corresponding to the control parameters.

[0129] As an exemplary embodiment, the feedback control algorithm may be a PID (Proportion Integral Differential) algorithm, based on which the temperature error, the first temperature error, and the second temperature error may be processed by the following formula (2) to obtain the parameter value increment corresponding to the control parameter:

[0130] Δu(t)=Kp*[etotal(t)-etotal(t-1)]+Ki*etotal(t)+Kd[etotal(t)-2etotal(t-1)+etotal(t-2)]

[0131] Formula (2)

[0132] Among them, the above-mentioned Δu(t) is the above-mentioned parameter value increment, the above-mentioned Kp is the preset proportional gain parameter, the above-mentioned etotal(t) is the above-mentioned temperature error, the above-mentioned etotal(t-1) is the first temperature error, the above-mentioned Ki is the preset integral gain parameter, the above-mentioned Kd is the preset differential gain parameter, and the above-mentioned etotal(t-2) is the above-mentioned second temperature error.

[0133] Step 304: Obtain historical parameter values corresponding to the above control parameters.

[0134] Step 305 : Perform a preset operation on the historical parameter values and parameter value increments to obtain a target parameter value corresponding to the control parameter when the temperature control system is currently being controlled.

[0135] The following is a unified description of step 304 and step 305:

[0136] The above historical parameter value refers to the parameter value of the corresponding control parameter when the temperature control system was controlled at the historical collection time. Optionally, the historical parameter value can be the parameter value when the temperature control system was most recently controlled before the current time, that is, the previous parameter value.

[0137] In some embodiments of the present application, the execution subject of the embodiments of the present application may obtain historical parameter values of corresponding control parameters when controlling the temperature control system.

[0138] As an optional implementation, after each temperature control operation of the temperature control system, the execution subject of the embodiment of the present application can store the corresponding target parameter values in a preset table in chronological order. Based on this, the execution subject of the embodiment of the present application can obtain the above historical parameter values from the above table.

[0139] Afterwards, a preset operation may be performed on the above historical parameter values and parameter value increments to obtain a target parameter value corresponding to the control parameter when the temperature control system is currently controlled.

[0140] As an optional implementation method, the above-mentioned historical parameter value may be the previous parameter value corresponding to each control parameter when the temperature control system was most recently temperature controlled. Based on this, for each control parameter, the previous parameter value corresponding to the control parameter may be added to the above-mentioned parameter value increment to obtain the target parameter value of the corresponding control parameter when the temperature control system is controlled.

[0141] As another optional implementation, the historical parameter values may be multiple historical parameter values corresponding to each control parameter when the temperature control system was performing temperature control within a historical time period. For each control parameter, a weighted sum of the multiple historical parameter values corresponding to the control parameter may be performed to obtain a target historical parameter value. Subsequently, the target historical parameter value corresponding to each control parameter may be added to the parameter value increment corresponding to the control parameter to obtain the target parameter value corresponding to the control parameter.

[0142] As an optional implementation, if the control parameter includes the power output module's power, the historical parameter value may be the historical power output of the power output module during historical periods, and the parameter value increment may be the power increment. Based on this, the historical power and the power increment may be subjected to the aforementioned predetermined calculation to obtain the target power value of the power output module.

[0143] As another optional implementation, if the control parameter includes the speed of the fluid compression module, the historical parameter value may be the historical speed of the fluid compression module at historical times, and the parameter value increment may be the speed increment. Based on this, the historical speed and speed increment may be subjected to the aforementioned predetermined calculation to obtain the target speed value for the fluid compression module.

[0144] As another optional implementation, if the control parameter includes the speed of the fluid delivery module, the historical parameter value may be the historical speed of the fluid delivery module at historical times, and the parameter value increment may be the speed increment. Based on this, the historical speed and speed increment may be subjected to the aforementioned predetermined calculation to obtain the target speed value of the fluid delivery module.

[0145] As another optional implementation, if the control parameter includes the opening of the fluid regulating module, the historical parameter value may be the historical opening of the fluid regulating module during historical periods, and the parameter value increment may be the opening increment. Based on this, the historical opening and the opening increment may be subjected to the aforementioned preset calculation to obtain the target opening value of the fluid regulating module.

[0146] As another optional implementation, the control parameter may include multiple control parameters, which may be any combination of two, three, or four of the power output module power, the speed of the fluid compression module, the speed of the fluid delivery module, and the opening of the fluid regulating module. Therefore, the historical parameter value may be any combination of two, three, or four of the historical power of the power output module, the historical speed of the fluid compression module, the historical speed of the fluid delivery module, and the historical opening of the fluid regulating module. The parameter value increment may be the power increment of the power output module, the speed increment of the fluid compression module, the speed increment of the fluid delivery module, and the opening increment of the fluid regulating module.

[0147] Based on this, the target parameter value of the control parameter can be any combination of the following two, three, or four: the target power value obtained after a preset calculation of the historical power and power increment corresponding to the power output module, the target speed value obtained after a preset calculation of the historical speed and speed increment corresponding to the fluid compression module, the target speed value obtained after a preset calculation of the historical speed and speed increment corresponding to the fluid conveying module, and the target opening value obtained after a preset calculation of the historical opening and opening increment corresponding to the fluid regulation module.

[0148] The technical solution provided in the embodiment of the present application determines the current temperature error based on the above-mentioned actual temperature value, set temperature value, and predicted temperature value, obtains the historical temperature error determined before the current moment, processes the temperature error and the historical temperature error using a preset feedback control algorithm, obtains the parameter value increment corresponding to the above-mentioned control parameter, obtains the historical parameter value corresponding to the above-mentioned control parameter, performs a preset operation on the above-mentioned historical parameter value and the parameter value increment, and obtains the target parameter value of the corresponding control parameter when the temperature control system is currently controlled. This technical solution accurately calculates the target parameter value for controlling the temperature control system based on the difference between the predicted set temperature value and the predicted temperature value through the PID control algorithm, thereby achieving real-time and precise control of the temperature control system, and improving the control performance and stability of the temperature control system to meet diverse temperature control needs and application scenarios.

[0149] See also Figure 4 , is a flow chart of an embodiment of another system temperature control method provided in an embodiment of the present application. Figure 4 The process shown in Figure 2 Based on the process shown in the figure, it describes how to use the temperature prediction model to obtain the predicted temperature value. Figure 4 As shown, the process may include the following steps:

[0150] Step 401: Preprocess multiple parameter value sequences to obtain processed data.

[0151] The above-mentioned preprocessing refers to a processing method for pre-processing the parameter value sequence, which may include but is not limited to: data cleaning, sliding window processing, and normalization processing of the parameter value sequence.

[0152] In some embodiments of the present application, when processing multiple parameter value sequences using a temperature prediction model, in order to more accurately process the multiple parameter value sequences, the multiple parameter value sequences may be preprocessed to obtain corresponding processed data.

[0153] As an optional implementation, multiple parameter value sequences can first be cleaned to remove obviously erroneous or abnormal data points, such as abnormal temperature values caused by sensor failure. Subsequently, the parameter value sequences can be processed into input and output data formats using a sliding window approach based on a predetermined time step. The sliding window refers to a data processing technique that extracts data segments of a fixed length (window size) from time series data or an ordered dataset. This is like sliding a fixed-size window across a long data strip to capture data. The input and output data formats described above refer to combining multiple parameter value sequences into a single input vector.

[0154] Finally, the parameter value sequence after format conversion can be normalized to map the data to a specific interval (such as [0, 1]) to obtain processed data to improve the efficiency and stability of model training.

[0155] Step 402: Input the processed data into a temperature prediction model to obtain a vector prediction value output by the temperature prediction model.

[0156] Step 403: Convert the vector prediction value to obtain a plurality of predicted temperature values of the temperature control system within a second preset time period.

[0157] The following is a unified description of step 402 and step 403:

[0158] The above-mentioned vector prediction value refers to the vector value corresponding to the predicted temperature value obtained by the temperature prediction model.

[0159] In some embodiments of the present application, after processing multiple parameter value sequences to obtain processed data, the above-mentioned processed data can be input into the above-mentioned temperature prediction model, and the output format of the temperature prediction model can be a vector format. Therefore, the vector prediction value output by the temperature prediction model can be obtained.

[0160] As an optional implementation, the temperature prediction model may include an input layer, a hidden layer, and an output layer. Accordingly, the temperature prediction model may obtain the processed data via the input layer, process the processed data via the hidden layer to obtain a vector prediction value corresponding to the predicted temperature value, and output the vector prediction value via the output layer. The hidden layer may include a plurality of pre-set processing units, each of which may be an LSTM unit.

[0161] Afterwards, the above-mentioned vector prediction value may be converted to obtain a plurality of predicted temperature values of the temperature control system within the second preset time period, and obtain a corresponding predicted temperature value sequence.

[0162] Among them, the number of predicted temperature values output by the temperature prediction model can be set when the temperature prediction model is trained, and it can be one or more, and the embodiment of the present application does not limit this.

[0163] The technical solution provided in the embodiment of the present application preprocesses multiple parameter value sequences to obtain processed data, inputs the processed data into a temperature prediction model to obtain vector prediction values output by the temperature prediction model, and converts the vector prediction values to obtain multiple predicted temperature values of the temperature control system within a second preset time period. This technical solution, after preprocessing multiple parameter value sequences, inputs the preprocessed processed data into the temperature prediction model so that the temperature prediction model predicts the processed data and obtains corresponding predicted temperature values. The preprocessing of multiple parameter value sequences enables the temperature prediction model to quickly and accurately determine the predicted temperature value of the temperature control system, thereby achieving efficient and accurate prediction of the predicted temperature value of the temperature control system by the temperature prediction model.

[0164] See also Figure 5 , which is a flow chart of an embodiment of a method for training a temperature prediction model provided in an embodiment of the present application. Figure 5 The process shown in Figure 1 or Figure 2 Based on the process shown in the figure, the specific method of training the temperature prediction model is described. Figure 5 As shown, the process may include the following steps:

[0165] Step 501: Obtain a historical parameter value sequence corresponding to each of a plurality of initial parameters of a temperature control system within a historical time period.

[0166] The above-mentioned initial parameters refer to parameters related to the operation of the temperature control system and used to train the temperature prediction model, which may include but are not limited to the preset parameters in step 101: control parameters of the temperature control system, system temperature of the temperature control system, ambient temperature of the temperature control system, ambient humidity, and vehicle speed, etc. The above-mentioned control parameters refer to parameters related to the system temperature of the temperature control system, that is, the system temperature of the temperature control system can be adjusted through the control parameters, such as motor power, compressor speed, electronic water pump speed, or electronic expansion valve opening, etc.

[0167] The above historical time period may be a pre-set time period within the historical time.

[0168] The above-mentioned historical parameter value sequence refers to a sequence composed of multiple parameter values corresponding to each initial parameter within a historical time period, which can be arranged in chronological order.

[0169] In some embodiments of the present application, in order to train the temperature prediction model, the execution entity of the embodiments of the present application can obtain the historical parameter values corresponding to each initial parameter in the historical time period among multiple initial parameters of the temperature control system to obtain multiple historical parameter value sequences.

[0170] Afterwards, the above multiple historical parameter value sequences can be used as the initial sample set for training the temperature prediction model.

[0171] Step 502: Preprocess the plurality of historical parameter value sequences to obtain a training sample set.

[0172] The above-mentioned preprocessing refers to a processing method for pre-processing multiple historical parameter value sequences, which may include but is not limited to: data cleaning, sliding window processing, normalization processing, and data set division of multiple historical parameter value sequences.

[0173] In some embodiments of the present application, the above-mentioned historical parameter value sequence may be preprocessed to obtain a training sample set for training a temperature prediction model.

[0174] As an optional implementation method, the above-mentioned historical parameter value sequence can be preprocessed through the following steps: First, multiple historical parameter value sequences can be cleaned to remove obviously erroneous or abnormal data points, such as abnormal temperature values caused by sensor failure. Afterwards, the historical parameter value sequence can be processed into the format of input data and output data using a sliding pane method according to a determined time step. The above-mentioned sliding pane refers to a data processing technology that extracts data segments of a fixed length (window size) from time series data or an ordered data set. It is like sliding and intercepting data through a fixed-size window on a long data band. The format of the above-mentioned input data and output data refers to synthesizing multiple parameter value sequences into an input vector.

[0175] Finally, the historical parameter value sequence after format conversion can be normalized to map the data to a specific interval (such as [0, 1]) to obtain a training sample set to improve the efficiency and stability of model training.

[0176] Step 503: Divide the training sample set into training samples and test samples according to a preset allocation ratio.

[0177] Step 504: Use the training samples to train the initial temperature prediction model, and use the test samples to test the initial temperature prediction model.

[0178] Step 505: When the initial temperature prediction model meets the preset conditions, the temperature prediction model is obtained.

[0179] The following is a unified description of steps 503 to 505:

[0180] The above allocation ratio is a preset ratio between training samples and test samples.

[0181] The above-mentioned training samples refer to the sample set used to train the initial temperature prediction model.

[0182] The above-mentioned test samples refer to a sample set used to test the trained initial temperature prediction model.

[0183] The initial temperature prediction model is a pre-set, untrained initial model that may include an initial input layer, an initial hidden layer, and an initial output layer. The initial input layer is used to obtain data input into the initial temperature prediction model, such as training samples or test samples. The initial hidden layer is used to process the received data and may include a preset number of initial processing units, such as LSTM units. These initial processing units can use a unique memory and forgetting mechanism to fully consider the correlation and trend of temperature data in the time series, gradually calculate and derive normalized predicted values of the system temperature at multiple future acquisition moments, and then denormalize the predicted values to obtain predicted temperature values. The initial output layer can output the predicted temperature values in the form of a vector.

[0184] The above-mentioned preset conditions refer to the pre-set conditions for stopping training.

[0185] In some embodiments of the present application, the initial temperature prediction model may be trained using the above training samples, and the initial temperature prediction model may be tested using the above test samples.

[0186] As an optional implementation method, the execution subject of the embodiment of the present application may test the trained initial temperature prediction model using a test sample each time after training the initial temperature prediction model using a training sample.

[0187] As another optional implementation method, the execution subject of the embodiment of the present application may use the training samples to test the trained initial temperature prediction model using the test samples after completing a preset number of training times.

[0188] As an optional implementation, the execution subject of the embodiment of the present application may train the initial temperature prediction model using a preset training algorithm, which may be a gradient descent-based optimization algorithm (e.g., Adam optimizer). The initial temperature prediction model may be trained using parameters such as a preset learning rate (e.g., 0.001), number of training iterations (e.g., 500), and batch size (e.g., 32).

[0189] As an exemplary embodiment, after each training is completed, the parameters in the initial temperature prediction model can be updated using the above-mentioned preset learning rate to obtain the initial temperature prediction model completed in this training, so as to train the updated initial temperature prediction model in the next training.

[0190] In some embodiments of the present application, when the initial temperature prediction model is trained, it may be determined whether the initial temperature prediction model meets a preset condition after each training is completed.

[0191] Optionally, if it is determined that the initial temperature prediction model meets the above preset conditions, it means that the training is completed, and the temperature prediction model can be obtained.

[0192] Optionally, if it is determined that the initial temperature prediction model does not meet the above preset conditions, it means that the initial temperature prediction model has not been trained yet. In this case, the initial temperature prediction model can continue to be trained using training samples and test samples.

[0193] As an optional implementation method, during the training of the initial temperature prediction model, the training loss value corresponding to the training sample can be determined by a preset loss function (such as mean square error), and the corresponding training loss value change trend can be determined, and the test loss value corresponding to the test sample can be determined by a preset loss function, and the corresponding test loss value change trend can be determined.

[0194] Afterwards, when the above-mentioned training loss value change trend indicates a decrease in the training loss value and the test loss value change trend indicates an increase in the test loss value, it means that the initial temperature prediction model at this time has overfitting, so the training can be stopped.

[0195] As another optional implementation, during the training of the initial temperature prediction model, the current number of training times may be determined in real time, and the training may be stopped when the number of training times reaches a preset threshold.

[0196] As another optional implementation method, during the training of the initial temperature prediction model, the training loss value corresponding to the training sample and the test loss value corresponding to the test sample can be determined by a preset loss function, and the training is stopped when the above training loss value and the test loss value are both less than the preset loss value threshold.

[0197] As another optional implementation method, during the training of the initial temperature prediction model, the training can be stopped when the following conditions are met to obtain a temperature prediction model: the above-mentioned training loss value change trend indicates that the training loss value decreases, and the test loss value change trend indicates that the test loss value increases, and the number of training times reaches a preset threshold.

[0198] As another optional implementation method, during the training of the initial temperature prediction model, the training can be stopped when the following conditions are met to obtain a temperature prediction model: the above-mentioned training loss value change trend represents a decrease in the training loss value, and the test loss value change trend represents an increase in the test loss value, and the above-mentioned training loss value and test loss value are both less than the preset loss value threshold.

[0199] As another optional implementation method, during the training of the initial temperature prediction model, the training can be stopped when the following conditions are met to obtain the temperature prediction model: the number of training times reaches a preset threshold, and the above-mentioned training loss value and test loss value are both less than the preset loss value threshold.

[0200] As another optional implementation method, during the training of the initial temperature prediction model, the training can be stopped to obtain a temperature prediction model when the following conditions are met: the above-mentioned training loss value change trend represents a decrease in the training loss value, and the test loss value change trend represents an increase in the test loss value, the above-mentioned training loss value and the test loss value are both less than the preset loss value threshold, and the number of training times reaches the preset number threshold.

[0201] The technical solution provided by the embodiment of the present application obtains a sequence of historical parameter values corresponding to each of the multiple initial parameters of the temperature control system within a historical time period, pre-processes the multiple historical parameter value sequences to obtain a training sample set, divides the training sample set into training samples and test samples according to a preset distribution ratio, trains the initial temperature prediction model using the training samples, and tests the initial temperature prediction model using the test samples, and obtains the temperature prediction model when the initial temperature prediction model meets the preset conditions. This technical solution, by using a large amount of historical data to train the temperature prediction model, can effectively learn the complex dependencies of temperature data in the time series, including information such as long-term trends and short-term fluctuations, thereby effectively improving the accuracy of future temperature predictions. A more accurate predicted temperature value can make the target parameter value based on it more accurate, thereby improving the accuracy of the temperature prediction model and thus improving the accuracy of temperature control of the temperature control system.

[0202] See also Figure 6 , is a block diagram of an embodiment of a system temperature control device provided in an embodiment of the present application. Figure 6 As shown, the device may include:

[0203] an acquisition module 61 configured to acquire a sequence of parameter values corresponding to each of a plurality of preset parameters of a vehicle temperature control system within a first preset time period; wherein the preset parameters include a system temperature of the temperature control system, an ambient temperature of the temperature control system, and a control parameter for adjusting the system temperature of the temperature control system;

[0204] A processing module 62 is configured to input the plurality of parameter value sequences into a pre-trained temperature prediction model to obtain a predicted temperature value of the temperature control system;

[0205] a determination module 63 for obtaining an actual temperature value and a set temperature value of the temperature control system, and determining a target parameter value corresponding to the control parameter when controlling the temperature control system based on the actual temperature value, the set temperature value, and the predicted temperature value;

[0206] The control module 64 is configured to control the temperature control system according to the target parameter value so that the system temperature of the temperature control system reaches the set temperature value.

[0207] like Figure 7 As shown, it is a structural diagram of an electronic device provided in an embodiment of the present application, including a processor 71, a communication interface 72, a memory 73 and a communication bus 74, wherein the processor 71, the communication interface 72, and the memory 73 communicate with each other through the communication bus 74.

[0208] Memory 73, for storing computer programs;

[0209] In one embodiment of the present application, the processor 71 is configured to execute a program stored in the memory 73 to implement the system temperature control method provided by any of the aforementioned method embodiments, including:

[0210] Obtaining a sequence of parameter values corresponding to each of a plurality of preset parameters of a temperature control system of a vehicle within a first preset time period; wherein the preset parameters include a system temperature of the temperature control system, an ambient temperature of the temperature control system, and a control parameter for adjusting the system temperature of the temperature control system;

[0211] Inputting a plurality of said parameter value sequences into a pre-trained temperature prediction model to obtain a predicted temperature value of said temperature control system;

[0212] Obtaining an actual temperature value and a set temperature value of the temperature control system, and determining a target parameter value corresponding to the control parameter when controlling the temperature control system based on the actual temperature value, the set temperature value, and the predicted temperature value;

[0213] The temperature control system is controlled according to the target parameter value so that the system temperature of the temperature control system reaches the set temperature value.

[0214] An embodiment of the present application further provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the system temperature control method provided in any of the aforementioned method embodiments are implemented.

[0215] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0216] Through the text of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, or of course by hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the relevant technology, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiment.

[0217] It should be understood that the terms used in the text are only for the purpose of the specific example embodiments of the text, and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used in the text may also be meant to include plural forms. The terms "comprise", "include", "contain" and "have" are inclusive and therefore specify the existence of the stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations of the text in the text are not interpreted as necessarily requiring them to be performed in the specific order of the text or instructions, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps can be used.

[0218] The foregoing is merely a list of specific embodiments of the present application, intended to enable those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the broadest scope consistent with the principles and novel features of the present application.

Claims

1. A system temperature control method, characterized in that: The method comprises: Obtaining a sequence of parameter values corresponding to each of a plurality of preset parameters of a temperature control system of a vehicle within a first preset time period; wherein the preset parameters include a system temperature of the temperature control system, an ambient temperature of the temperature control system, and a control parameter for adjusting the system temperature of the temperature control system; Inputting a plurality of said parameter value sequences into a pre-trained temperature prediction model to obtain a predicted temperature value of said temperature control system; Obtaining an actual temperature value and a set temperature value of the temperature control system, and determining a target parameter value corresponding to the control parameter when controlling the temperature control system based on the actual temperature value, the set temperature value, and the predicted temperature value; The temperature control system is controlled according to the target parameter value so that the system temperature of the temperature control system reaches the set temperature value.

2. The method according to claim 1, characterized in that Inputting a plurality of the parameter value sequences into a pre-trained temperature prediction model to obtain a predicted temperature value of the temperature control system comprises: inputting the plurality of parameter value sequences into a pre-trained temperature prediction model to obtain a sequence of predicted temperature values of the temperature control system within a second preset time period; the second preset time period being later than the first preset time period, the second preset time period including a plurality of acquisition moments divided according to a preset time step, the sequence of predicted temperature values including a predicted temperature value corresponding to each of the acquisition moments; The obtaining of the actual temperature value and the set temperature value of the temperature control system, and determining, based on the actual temperature value, the set temperature value, and the predicted temperature value, a target parameter value corresponding to the control parameter when controlling the temperature control system, includes: For each collection moment within the second preset time period, obtaining an actual temperature value and a set temperature value of the temperature control system corresponding to the collection moment; According to the actual temperature value, the set temperature value, and the predicted temperature value corresponding to the acquisition moment, a target parameter value of a corresponding control parameter when controlling the temperature control system corresponding to the acquisition moment is determined.

3. The method according to claim 1 or 2, characterized in that Determining a target parameter value corresponding to the control parameter when controlling the temperature control system according to the actual temperature value, the set temperature value, and the predicted temperature value includes: determining a temperature error based on the actual temperature value, the set temperature value, and the predicted temperature value; Get the historical temperature error determined before the current moment; Processing the temperature error and the historical temperature error using a preset feedback control algorithm to obtain a parameter value increment corresponding to the control parameter; Obtaining historical parameter values corresponding to the control parameters; A preset operation is performed on the historical parameter value and the parameter value increment to obtain a target parameter value corresponding to the control parameter when the temperature control system is currently controlled.

4. The method according to claim 3, characterized in that The determining of the current temperature error according to the actual temperature value, the set temperature value, and the predicted temperature value includes: determining a first temperature difference between the set temperature value and the predicted temperature value, and a second temperature difference between the set temperature value and the actual temperature value; Obtaining a model confidence level of the predicted temperature value output by the temperature prediction model, and determining a weight coefficient of the first temperature difference based on the model confidence level; A weighted sum of the first temperature difference and the second temperature difference is performed according to the weight coefficient to obtain a current temperature error.

5. The method according to claim 2, characterized in that The temperature prediction model is trained in the following way: Obtaining a sequence of historical parameter values corresponding to each of the multiple initial parameters of the temperature control system within a historical time period; Preprocessing the plurality of historical parameter value sequences to obtain a training sample set; Dividing the training sample set into training samples and test samples according to a preset allocation ratio; Using the training samples to train an initial temperature prediction model, and using the test samples to test the initial temperature prediction model; When the initial temperature prediction model meets a preset condition, the temperature prediction model is obtained.

6. The method according to claim 5, characterized in that The temperature prediction model is obtained when the initial temperature prediction model meets the following conditions: Obtaining a training loss value change trend corresponding to the training sample and a test loss value change trend corresponding to the test sample, and stopping training when the training loss value change trend indicates a decrease in the training loss value and the test loss value change trend indicates an increase in the test loss value; and / or, stopping the training when the number of training times reaches a preset threshold; And / or, obtaining a training loss value of the training sample and a test loss value of the test sample, and stopping training when both the training loss value and the test loss value are less than a preset loss value threshold.

7. The method according to claim 1, characterized in that The control parameters include one or more of the following: the power of the power output module, the rotation speed of the fluid compression module, the rotation speed of the fluid delivery module, and the opening of the fluid regulating module.

8. A system temperature control device, characterized in that: The device comprises: an acquisition module, configured to acquire a sequence of parameter values corresponding to each of a plurality of preset parameters of a temperature control system of a vehicle within a first preset time period; wherein the preset parameters include a system temperature of the temperature control system, an ambient temperature of the temperature control system, and a control parameter for adjusting the system temperature of the temperature control system; a processing module, configured to input a plurality of said parameter value sequences into a pre-trained temperature prediction model to obtain a predicted temperature value of said temperature control system; a determination module, configured to obtain an actual temperature value and a set temperature value of the temperature control system, and determine a target parameter value corresponding to the control parameter when controlling the temperature control system based on the actual temperature value, the set temperature value, and the predicted temperature value; The control module is used to control the temperature control system according to the target parameter value so that the system temperature of the temperature control system reaches the set temperature value.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the processor is configured to execute a system temperature control program stored in the memory to implement the system temperature control method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the system temperature control method according to any one of claims 1 to 7.

Images