Passenger compartment temperature adjusting method, device and equipment and storage medium

Abstract

The invention relates to a passenger compartment temperature adjusting method and device, equipment and a storage medium. The method comprises the steps that the current environment temperature of a vehicle, the current vehicle speed, a historical predicted temperature sequence output by a temperature prediction model at the last time point and the current passenger compartment temperature are obtained; according to the historical predicted temperature sequence and the current passenger compartment temperature, a temperature prediction model is adjusted, and an adjusted temperature prediction model is obtained; calling an adjusted temperature prediction model, and obtaining a current prediction temperature sequence by using the historical prediction temperature sequence, the current vehicle speed and the current environment temperature; and adjusting the current temperature of the passenger compartment according to the current predicted temperature sequence. According to the method, the accuracy of temperature adjustment of the passenger compartment can be improved, and then the temperature of the passenger compartment better meets the requirements of a user.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, equipment and storage medium for adjusting the temperature of a passenger compartment. Background Art

[0002] When the car is driving normally, the temperature in the passenger compartment is usually kept in a comfortable range. For example, when the temperature in the passenger compartment is too high, the gaseous refrigerant is compressed into liquid by the compressor, and the liquid refrigerant vaporizes in the evaporator to absorb heat, thereby reducing the temperature of the passenger compartment.

[0003] During the vehicle design phase, a correspondence between the passenger compartment temperature and the evaporator surface temperature is established, and the temperature of the passenger compartment is controlled based on the correspondence. However, as time goes by, the equipment in the vehicle will wear out and age. If the above correspondence is still used to control the temperature of the passenger compartment, the temperature of the passenger compartment cannot be accurately controlled, resulting in the passenger compartment temperature being too high or too low, which cannot meet the needs of users. A method for adjusting the temperature of the passenger compartment is urgently needed. Summary of the invention

[0004] The present application provides a passenger compartment temperature adjustment method, device, equipment and storage medium, which can improve the accuracy of passenger compartment temperature adjustment, thereby making the passenger compartment temperature more in line with user needs.

[0005] In a first aspect, the present application provides a method for adjusting the temperature of a passenger compartment, the method comprising:

[0006] Obtain the current ambient temperature of the vehicle, the current vehicle speed, the historical predicted temperature sequence output by the temperature prediction model at the previous time point, and the current passenger compartment temperature;

[0007] Adjusting the temperature prediction model according to the historical predicted temperature sequence and the current passenger compartment temperature to obtain an adjusted temperature prediction model;

[0008] Calling the adjusted temperature prediction model, and obtaining a current predicted temperature sequence using the historical predicted temperature sequence, the current vehicle speed, and the current ambient temperature;

[0009] The current cabin temperature is adjusted based on the current predicted temperature sequence.

[0010] Optionally, calling the adjusted temperature prediction model and obtaining a current predicted temperature sequence using the historical predicted temperature sequence, the current vehicle speed and the current ambient temperature includes:

[0011] Get the historical expected temperature series;

[0012] Determining the target speed requirement sequence according to the historical predicted temperature sequence and the historical expected temperature sequence;

[0013] The adjusted temperature prediction model is called, and the target speed demand sequence, the current vehicle speed and the current ambient temperature are used to obtain a current predicted temperature sequence.

[0014] Optionally, determining the target speed requirement sequence according to the historical predicted temperature sequence and the expected temperature sequence includes:

[0015] Determining a target value according to the historical predicted temperature sequence and the expected temperature sequence;

[0016] Determining an iteration result of a first iteration process according to the initial speed requirement sequence and the target value, and obtaining an iteration result of a current iteration process, wherein the iteration result includes a reference speed requirement sequence and a reference cost;

[0017] When the current iteration process is not the Kth iteration process and the reference cost is greater than the preset cost, the iteration result of the next iteration process is determined according to the iteration result of the current iteration process, and the iteration result of the current iteration process is obtained again;

[0018] When the current iteration process is the Kth iteration process or the reference cost is not greater than the preset cost, the reference speed requirement sequence in the iteration result of the current iteration process is determined as the target speed requirement sequence.

[0019] Optionally, determining an iteration result of a first iteration process according to the initial speed requirement sequence and the target value includes:

[0020] Determining a reference speed requirement sequence for a first iteration process according to the initial speed requirement sequence;

[0021] Determining a reference cost of the first iteration process according to the reference speed requirement sequence of the first iteration process and the target value;

[0022] According to the reference speed requirement sequence and the reference cost of the first iteration process, an iteration result of the first iteration process is obtained.

[0023] Optionally, determining the iteration result of the next iteration process according to the iteration result of the current iteration process includes:

[0024] Get the gradient sequence and target learning rate corresponding to the current iteration process;

[0025] Calculating a rotation speed variation sequence according to the gradient sequence and the target learning rate;

[0026] Determining a reference speed requirement sequence for a next iteration process according to the speed variation sequence and the reference speed requirement sequence for the current iteration process;

[0027] determining a reference cost of a next iteration process according to a reference speed requirement sequence of a next iteration process;

[0028] According to the reference speed requirement sequence and the reference cost of the next iteration process, the iteration result of the next iteration process is obtained.

[0029] Optionally, adjusting the current temperature in the passenger compartment according to the current predicted temperature sequence includes:

[0030] Determine the current speed requirement value according to the current predicted temperature sequence and the current expected temperature sequence;

[0031] According to the current speed requirement value, the current speed of the compressor is adjusted to adjust the current temperature in the passenger compartment.

[0032] Optionally, adjusting the temperature prediction model according to the historical predicted temperature sequence and the current passenger compartment temperature to obtain an adjusted temperature prediction model includes:

[0033] In the historical predicted temperature sequence, obtaining the historical predicted temperature at the current time point;

[0034] determining a loss value between the historical predicted temperature and the current passenger compartment temperature;

[0035] The temperature prediction model is adjusted according to the loss value to obtain an adjusted temperature prediction model.

[0036] In a second aspect, the present application provides a passenger compartment temperature adjustment device, the device comprising:

[0037] An acquisition unit, used to acquire the current ambient temperature of the vehicle, the current vehicle speed, the historical predicted temperature sequence output by the temperature prediction model at the previous time point, and the current passenger compartment temperature;

[0038] A first adjustment unit, configured to adjust the temperature prediction model according to the historical predicted temperature sequence and the current passenger compartment temperature to obtain an adjusted temperature prediction model;

[0039] A calling unit, used for calling the adjusted temperature prediction model, and obtaining a current predicted temperature sequence by using the historical predicted temperature sequence, the current vehicle speed and the current ambient temperature;

[0040] The second adjustment unit is used to adjust the current passenger compartment temperature according to the current predicted temperature sequence.

[0041] Optionally, the calling unit is used to:

[0042] Get the historical expected temperature series;

[0043] Determining the target speed requirement sequence according to the historical predicted temperature sequence and the historical expected temperature sequence;

[0044] The adjusted temperature prediction model is called, and the target speed demand sequence, the current vehicle speed and the current ambient temperature are used to obtain a current predicted temperature sequence.

[0045] Optionally, the calling unit is used to:

[0046] Determining a target value according to the historical predicted temperature sequence and the expected temperature sequence;

[0047] Determining an iteration result of a first iteration process according to the initial speed requirement sequence and the target value, and obtaining an iteration result of a current iteration process, wherein the iteration result includes a reference speed requirement sequence and a reference cost;

[0048] When the current iteration process is not the Kth iteration process and the reference cost is greater than the preset cost, the iteration result of the next iteration process is determined according to the iteration result of the current iteration process, and the iteration result of the current iteration process is obtained again;

[0049] When the current iteration process is the Kth iteration process or the reference cost is not greater than the preset cost, the reference speed requirement sequence in the iteration result of the current iteration process is determined as the target speed requirement sequence.

[0050] Optionally, the calling unit is used to:

[0051] Determining a reference speed requirement sequence for a first iteration process according to the initial speed requirement sequence;

[0052] Determining a reference cost of the first iteration process according to the reference speed requirement sequence of the first iteration process and the target value;

[0053] According to the reference speed requirement sequence and the reference cost of the first iteration process, an iteration result of the first iteration process is obtained.

[0054] Optionally, the calling unit is used to:

[0055] Get the gradient sequence and target learning rate corresponding to the current iteration process;

[0056] Calculating a rotation speed variation sequence according to the gradient sequence and the target learning rate;

[0057] Determining a reference speed requirement sequence for a next iteration process according to the speed variation sequence and the reference speed requirement sequence for the current iteration process;

[0058] determining a reference cost of a next iteration process according to a reference speed requirement sequence of a next iteration process;

[0059] According to the reference speed requirement sequence and the reference cost of the next iteration process, the iteration result of the next iteration process is obtained.

[0060] Optionally, the second adjustment unit is used to:

[0061] Determine the current speed requirement value according to the current predicted temperature sequence and the current expected temperature sequence;

[0062] According to the current speed requirement value, the current speed of the compressor is adjusted to adjust the current temperature in the passenger compartment.

[0063] Optionally, the first adjustment unit is used to:

[0064] In the historical predicted temperature sequence, obtaining the historical predicted temperature at the current time point;

[0065] determining a loss value between the historical predicted temperature and the current passenger compartment temperature;

[0066] The temperature prediction model is adjusted according to the loss value to obtain an adjusted temperature prediction model.

[0067] In a third aspect, the present application provides a passenger compartment temperature adjustment device, comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; at least one memory connected to the at least one bus, wherein the processor is configured to:

[0068] Obtain the current ambient temperature of the vehicle, the current vehicle speed, the historical predicted temperature sequence output by the temperature prediction model at the previous time point, and the current passenger compartment temperature;

[0069] Adjusting the temperature prediction model according to the historical predicted temperature sequence and the current passenger compartment temperature to obtain an adjusted temperature prediction model;

[0070] Calling the adjusted temperature prediction model, and obtaining a current predicted temperature sequence using the historical predicted temperature sequence, the current vehicle speed, and the current ambient temperature;

[0071] The current cabin temperature is adjusted based on the current predicted temperature sequence.

[0072] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the above-mentioned passenger compartment temperature adjustment method is implemented.

[0073] The above technical solution provided by the embodiment of the present application has the following advantages compared with the prior art: in the embodiment of the present application, the current ambient temperature of the vehicle, the current vehicle speed, the historical predicted temperature sequence output by the temperature prediction model at the previous time point and the current passenger compartment temperature are obtained; the temperature prediction model is adjusted according to the historical predicted temperature sequence and the current passenger compartment temperature to obtain the adjusted temperature prediction model; the adjusted temperature prediction model is called, and the current predicted temperature sequence is obtained using the historical predicted temperature sequence, the current vehicle speed and the current ambient temperature; the current passenger compartment temperature is adjusted according to the current predicted temperature sequence. It can be seen that the present application can adjust the temperature prediction model first when adjusting the passenger compartment temperature, so that the temperature prediction model can be automatically adjusted as the equipment changes, avoiding the influence of equipment changes on the processing results, improving the accuracy of the passenger compartment temperature adjustment, and thus making the passenger compartment temperature more in line with user needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0075] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0076] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0077] Figure 1 A flow chart of a method for adjusting the temperature of a passenger compartment provided in an embodiment of the present application;

[0078] Figure 2 A schematic diagram of a flow chart of a method for determining a current predicted temperature sequence provided in an embodiment of the present application;

[0079] Figure 3 A flow chart of a method for determining a target speed requirement sequence provided in an embodiment of the present application;

[0080] Figure 4A flowchart of an iterative result determination method provided in an embodiment of the present application;

[0081] Figure 5 A flowchart of another method for determining an iterative result provided in an embodiment of the present application;

[0082] Figure 6 A schematic diagram of a temperature adjustment method provided in an embodiment of the present application;

[0083] Figure 7 A schematic diagram of a flow chart of a temperature prediction model adjustment method provided in an embodiment of the present application;

[0084] Figure 8 A schematic diagram of a flow chart of a passenger compartment temperature adjustment device provided in an embodiment of the present application;

[0085] Fig. 9 A schematic diagram of a passenger compartment temperature adjustment device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0086] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0087] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0088] When the car is driving normally, the temperature in the passenger compartment is usually kept in a comfortable range. For example, when the temperature in the passenger compartment is too high, the gaseous refrigerant is compressed into liquid by the compressor, and the liquid refrigerant vaporizes in the evaporator to absorb heat, thereby reducing the temperature of the passenger compartment. During the vehicle design phase, a correspondence between the passenger compartment temperature and the evaporator surface temperature is established, and the temperature of the passenger compartment is controlled according to this correspondence. However, as time goes by, the equipment in the vehicle will wear and age. If the above correspondence is still used to control the temperature of the passenger compartment, the temperature of the passenger compartment cannot be accurately controlled, resulting in the passenger compartment temperature being too high or too low, which cannot meet the needs of users.

[0089] In order to solve the above problems, the embodiment of the present application provides a method for adjusting the temperature of the passenger compartment, which can improve the accuracy of adjusting the temperature of the passenger compartment, thereby making the temperature of the passenger compartment more in line with the needs of users, such as Figure 1 As shown, the specific steps include:

[0090] Step 101, obtaining the current ambient temperature of the vehicle, the current vehicle speed, the historical predicted temperature sequence output by the temperature prediction model at the previous time point, and the current passenger compartment temperature.

[0091] Among them, the current ambient temperature is the ambient temperature of the current vehicle at the current time point. The current vehicle speed is the speed of the current vehicle at the current time point. The temperature prediction model is used to predict the temperature. The model can be a neural network model or an algorithm based on temperature prediction. Preferably, the temperature prediction model in the present application is a neural network model. The predicted temperature sequence output by the temperature preset model at the previous time point is used as the historical predicted temperature sequence. The predicted temperature sequence includes at least one predicted temperature, and the number of predicted temperatures can be divided into the following two situations according to the settings of the technician: one is that the predicted temperature sequence only contains one predicted temperature, and the time point corresponding to the temperature is the next time point of the current time point; the other is that the predicted temperature sequence contains multiple predicted temperatures, and these temperatures correspond to consecutive time points after the current time point.

[0092] In this step, a temperature sensor is installed on the outside of the current vehicle, and its main function is to collect the current ambient temperature of the vehicle in real time. A speed sensor is arranged on the vehicle body, which is responsible for collecting the driving speed of the vehicle at the current time point. In addition, a temperature sensor is also arranged inside the passenger compartment of the vehicle to accurately collect the current temperature in the passenger compartment. When the vehicle control system needs to execute step 101, it will automatically read relevant data from the temperature sensor and the speed sensor to obtain the three key parameters of the current ambient temperature, the current vehicle speed and the current passenger compartment temperature. At the same time, the vehicle control system will also extract the historical predicted temperature sequence output at the previous time point to provide comprehensive data support for subsequent analysis and decision-making.

[0093] Step 102, adjusting the temperature prediction model according to the historical predicted temperature sequence and the current passenger compartment temperature to obtain an adjusted temperature prediction model.

[0094] In this step, the relevant parameters in the temperature prediction model are adjusted according to the current predicted temperature sequence and the current passenger compartment temperature to obtain an adjusted temperature prediction model.

[0095] Furthermore, the current passenger compartment temperature only includes the temperature of the passenger compartment at the current time point. Therefore, it is necessary to obtain the historical predicted temperature corresponding to the current time point in the historical predicted temperature sequence, and adjust the temperature prediction model according to the difference between the historical predicted temperature and the current passenger compartment temperature to obtain the adjusted temperature prediction model to improve the accuracy of subsequent temperature predictions.

[0096] Step 103, calling the adjusted temperature prediction model, using the historical predicted temperature sequence, the current vehicle speed and the current ambient temperature, to obtain the current predicted temperature sequence.

[0097] In this step, the historical predicted temperature sequence, the current vehicle speed and the current ambient temperature can be directly input into the adjusted temperature prediction model to obtain the current predicted temperature sequence. In the actual production process, the precise control of temperature is usually achieved by adjusting the compressor speed. Therefore, it is necessary to calculate the compressor speed demand sequence based on the predicted temperature sequence, and use this as a basis to achieve effective regulation of the passenger compartment temperature. Specifically, the compressor speed demand sequence is determined based on the historical predicted temperature sequence. Then the speed demand sequence, the current vehicle speed and the current ambient temperature are input into the adjusted temperature prediction model to obtain the current predicted temperature sequence.

[0098] Among them, the speed demand sequence includes speed demand values ​​corresponding to multiple future time points. The speed of the compressor can be adjusted according to the speed demand value, and then the temperature in the passenger compartment can be adjusted. This is because in practice, the refrigerant gas is compressed by the compressor and circulated in the refrigeration system to achieve the function of cooling or heating. The speed of the compressor reflects the amount of gas processed by the compressor per unit time, and the temperature of the passenger compartment is controlled by this amount of gas. Therefore, the temperature in the passenger compartment can be indirectly adjusted by adjusting the speed of the compressor.

[0099] Furthermore, the method for determining the speed requirement sequence of the compressor according to the historical predicted temperature sequence can be: pre-creating a correspondence between temperature and speed, and determining the speed requirement sequence according to the correspondence and the historical predicted temperature sequence. Alternatively, calling an optimization algorithm and using the historical predicted temperature sequence to obtain the speed requirement sequence. Other methods can also be used to determine the speed requirement sequence, which are not limited here.

[0100] In addition, in order to predict the temperature more accurately, the predicted vehicle speed corresponding to multiple future time points can be predicted based on the current vehicle speed, and the vehicle speed sequence can be obtained based on the current vehicle speed and the predicted vehicle speed. At the same time, the predicted ambient temperature corresponding to multiple future time points can be predicted based on the current ambient temperature, and the ambient temperature sequence can be obtained based on the current ambient temperature and the predicted ambient temperature. After that, the adjusted temperature prediction model is called, and the current predicted temperature sequence is obtained using the speed demand sequence, ambient temperature sequence, and historical predicted temperature sequence.

[0101] Furthermore, for the driver, there will be certain rules when driving the vehicle. Therefore, the driver's driving rules can be obtained first, and the predicted speeds corresponding to multiple future time points can be obtained based on the driving rules and the current vehicle speed. The specific steps are: take the current time point as the end time point, extend the preset time forward, determine the start time point, and then determine the target time period based on the end time point and the start time point. Then, obtain the speed change curve of the current vehicle in the target time period, analyze the speed change curve, obtain the driver's driving rules, and obtain the predicted speeds corresponding to multiple future time points based on the driving rules and the current vehicle speed.

[0102] The driving rule may be that the vehicle moves forward at a constant speed, or that the current vehicle accelerates or decelerates at a fixed acceleration, or other rules, which are not limited here.

[0103] Furthermore, based on the current ambient temperature, the specific steps for predicting the predicted ambient temperatures corresponding to multiple future time points are: obtaining the ambient temperature change curve through the weather forecast, and obtaining the predicted ambient temperatures corresponding to multiple future time points based on the change curve and the current ambient temperature.

[0104] It should be noted that when the temperature prediction model is a neural network model, before executing the embodiment of the present application, it is necessary to create an initial neural network and collect training data. Extract the compressor speed, vehicle speed, ambient temperature and passenger compartment temperature data from the existing vehicle data storage system. The extracted data should cover the vehicle operation information under different working conditions, so as to ensure the comprehensiveness and representativeness of the training data and provide a reliable data basis for subsequent model training. The data with the same timestamp are sorted together to form a data sample set. At the same time, to ensure data quality, data cleaning operations are performed to remove duplicate data and invalid data. In order to eliminate the dimensional differences between different feature data and improve the efficiency and accuracy of model training, data normalization is then performed to map the data to a specific numerical range (for example, between 0 and 1). Finally, the data is divided into a training set and a test set according to a predetermined ratio (for example, 7:3), wherein the training set is used for model training and the test set is used to evaluate the trained model. The specific evaluation method can be to evaluate the trained model using the test set based on the mean square error as the standard to judge the prediction accuracy and generalization ability of the model. If the model evaluation results do not meet the predetermined standards, it is necessary to readjust the model parameters or collect data again for training.

[0105] Step 104, adjusting the current passenger compartment temperature according to the current predicted temperature sequence.

[0106] The current predicted temperature is the predicted temperature sequence output by the temperature prediction model at the current time point.

[0107] In this step, the corresponding speed requirement sequence can be determined according to the current predicted temperature sequence, and the current speed of the compressor can be adjusted according to the speed requirement sequence to adjust the temperature in the passenger compartment.

[0108] Furthermore, since the speed demand sequence includes speed demand values ​​corresponding to multiple future time points, the speed demand value corresponding to the first future time point can be obtained in the speed demand sequence, and then at the first future time point, the current speed of the compressor is adjusted according to the speed demand value to adjust the temperature in the passenger compartment. Afterwards, the speed of the compressor can be adjusted according to the remaining speed demand values, or the speed of the compressor can be adjusted without being based on the remaining speed demand values, which is not limited here.

[0109] Among them, the first future time point is the future time point closest to the current time point, the second future time point is the future time point second closest to the current time point, the third future time point is the future time point second closest to the current time point... The Nth future time point is the future time point farthest from the current time point.

[0110] It should be noted that for the speed demand value, the closer the corresponding future time point is to the current time point, the more accurate the speed demand value corresponding to the future time point is. Therefore, the speed of the compressor can be adjusted only based on the speed demand value corresponding to the first future time point.

[0111] In an embodiment of the present application, the current ambient temperature of the vehicle, the current vehicle speed, the historical predicted temperature sequence output by the temperature prediction model at the previous time point, and the current passenger compartment temperature are obtained; the temperature prediction model is adjusted according to the historical predicted temperature sequence and the current passenger compartment temperature to obtain an adjusted temperature prediction model; the adjusted temperature prediction model is called, and the current predicted temperature sequence, the current vehicle speed, and the current ambient temperature are used to obtain the current predicted temperature sequence; the current passenger compartment temperature is adjusted according to the current predicted temperature sequence. It can be seen that the present application can adjust the temperature prediction model first when adjusting the passenger compartment temperature, so that the temperature prediction model can be automatically adjusted as the equipment changes, avoiding the influence of equipment changes on the processing results, improving the accuracy of the passenger compartment temperature adjustment, and thus making the passenger compartment temperature more in line with user needs.

[0112] In the embodiment of the present application, the expected temperature sequence can also be obtained, and then the target speed demand sequence is determined based on the historical predicted temperature sequence and the expected temperature sequence. Finally, the adjusted temperature prediction model is called to obtain the current predicted temperature sequence using the target speed demand sequence, the current vehicle speed and the current ambient temperature. Therefore, the embodiment of the present application provides a method for determining the current predicted temperature sequence. Figure 2 As shown, the specific steps include:

[0113] Step 201, obtaining a historical expected temperature sequence.

[0114] The historical expected temperature sequence includes the expected temperatures corresponding to the current time point and multiple future time points. The expected temperature is the temperature that the user expects to maintain. For example, if the user sets the temperature in the passenger compartment to 25 degrees, the historical expected temperature in the historical expected temperature sequence is set to 25 degrees. Of course, the historical expected temperature sequence can also be obtained based on other methods, which are not limited here. For example, assuming that the previous time point is represented by 1, the current time point is represented by 2, and the next time point is represented by 3, the historical expected temperature sequence includes the historical expected temperatures corresponding to Np time points, and using t ref represents the expected temperature sequence, which includes t ref (2) t ref (3)......t ref (Np-2).

[0115] Step 202: Determine a target speed requirement sequence based on a historical predicted temperature sequence and a historical expected temperature sequence.

[0116] The historical predicted temperature sequence also includes the historical predicted temperatures corresponding to the current time point and multiple future time points. For example, tl is used to represent the historical predicted temperature sequence, which includes tl(2), tl(3)...tl(Np-2). The speed demand sequence includes the speed demand values ​​corresponding to multiple future time points. For example, u is used to represent the historical predicted temperature sequence, which includes u(3)...u(Nm-2). Nm and Np may be the same or different, which is not limited here.

[0117] In this step, a pre-trained speed demand determination model can be called to process the historical predicted temperature sequence and the historical expected temperature sequence to obtain the target speed demand sequence, or a cost function optimizer can be called to use the historical predicted temperature sequence and the historical expected temperature sequence to obtain the speed demand sequence.

[0118] Step 203 , calling the adjusted temperature prediction model, using the target speed demand sequence, the current vehicle speed and the current ambient temperature, to obtain the current predicted temperature sequence.

[0119] In this step, the target speed demand sequence, the current vehicle speed and the current ambient temperature can be input into the adjusted temperature prediction model to obtain the current predicted temperature sequence. Alternatively, the target speed demand sequence, the current vehicle speed and the current ambient temperature can be normalized first, and the processed data can be input into the adjusted temperature prediction model to obtain the current predicted temperature sequence.

[0120] In the embodiment of the present application, the target value can also be calculated based on the historical predicted temperature sequence and the historical expected temperature sequence, and then the target speed requirement sequence is determined based on the target result. Therefore, the embodiment of the present application provides a method for determining the target speed requirement sequence. Figure 3 As shown, the specific steps include:

[0121] Step 301, determining a target value based on a historical predicted temperature sequence and a historical expected temperature sequence.

[0122] In this step, the historical predicted temperature and the historical expected temperature corresponding to the same time point are subtracted to obtain the difference corresponding to the time point, and the square value of each difference is calculated to obtain a square value set. The values ​​in the square value set are added to obtain the target value.

[0123] For example, the formula for calculating the target value is where t ref (j) is the expected temperature corresponding to the jth time point, tl(j) is the historical predicted temperature corresponding to the jth time point, and S is the target value.

[0124] Step 302, determining the iteration result of the first iteration process according to the initial speed requirement sequence and the target value, and obtaining the iteration result of the current iteration process.

[0125] The iteration result includes a reference speed requirement sequence and a reference cost. The initial speed requirement sequence is set by a technician according to actual conditions, for example, the speed requirement in the initial speed requirement sequence is set to an empirical value.

[0126] In this step, the reference speed requirement sequence of the first iteration process is determined based on the initial speed requirement sequence, and then the reference cost is determined based on the reference speed requirement sequence and the target value. The reference speed sequence and the reference cost are determined as the iterative results of the first iteration process to obtain the iterative results of the current iteration process.

[0127] Step 303, when the current iteration process is not the Kth iteration process and the reference cost is greater than the preset cost, the iteration result of the next iteration process is determined according to the iteration result of the current iteration process, and the iteration result of the current iteration process is obtained again.

[0128] Among them, the K value and the preset cost are set by technicians based on experience. The preset cost is generally a value close to 0, and can also be set according to other methods, which is not limited here.

[0129] In this step, when the current iteration process is not the Kth iteration process and the reference cost of the current iteration process is not less than the preset cost, the iterative processing continues, and the iteration result of the next iteration process is determined according to the iteration result of the current iteration process, and the iteration result of the next iteration process is determined as the iteration result of the current iteration process.

[0130] Step 304 , when the current iteration process is the Kth iteration process or the reference cost is not greater than the preset cost, the reference speed requirement sequence in the iteration result of the current iteration process is determined as the target speed requirement sequence.

[0131] In this step, when the current iteration process is the Kth iteration process or the reference cost of the current iteration process is not greater than the preset cost, the iteration process is stopped, and the reference speed demand sequence corresponding to the current iteration process is determined as the target speed demand sequence.

[0132] In the embodiment of the present application, it is also necessary to determine the iteration result of the next iteration process according to the iteration result of the current iteration process. Therefore, the embodiment of the present application provides a method for determining the iteration result. Figure 4 As shown, the specific steps include:

[0133] Step 401, obtaining the gradient sequence and target learning rate corresponding to the current iteration process.

[0134] Among them, for a multivariate function y=f(x1, x2, ..., x n ), the gradient is a vector that contains the partial derivatives of the function in the direction of each variable. For example, for a binary function, its gradient vector is Consider the speed as a function of these input parameters ω = f(u1, u2, ..., u n ), then the gradient vector function with respect to the rotation speed is Afterwards, the reference speed requirement sequence in the current iteration process is brought in to obtain the gradient sequence corresponding to the current iteration process.

[0135] In addition, the target learning rate is a value set by technicians based on experience, which determines the step size of each parameter update. If the learning rate is too large, the algorithm may not converge or even diverge; if the learning rate is too small, the convergence speed will be very slow.

[0136] Step 402: Calculate a rotation speed variation sequence according to the gradient sequence and the target learning rate.

[0137] In this step, for each gradient in the gradient sequence, the gradient is multiplied by the target learning rate to obtain the corresponding speed change. Based on the same method, the speed change corresponding to each gradient is obtained, and then they are sorted in chronological order to obtain a speed change sequence.

[0138] Step 403: Determine the reference speed requirement sequence for the next iteration process according to the reference speed requirement sequence and the speed variation sequence of the current iteration process.

[0139] In this step, the reference speed demand value and the speed change corresponding to the same time point are subtracted to obtain a series of reference speed demand values, and these values ​​are sorted in chronological order to obtain a reference speed demand sequence for the next iteration process.

[0140] Step 404: Determine the reference cost of the next iteration process according to the reference speed requirement sequence of the next iteration process.

[0141] In this step, the demand cost is determined according to the reference speed demand sequence of the next iteration process, and then the demand cost is added to the target value to determine the reference cost of the next iteration process.

[0142] Furthermore, according to the formula Determine the demand cost. Where N u is the number of reference speed demand values ​​in the reference speed demand sequence, λ(j) is the weight coefficient of the j-th reference speed demand value, which is related to the smoothness requirement, and u(j) is the j-th reference speed demand value.

[0143] Furthermore, the above weight coefficient is related to the smoothness of the control input, which refers to the degree of stability and continuity of the control input over time. Intuitively speaking, the change of the control input is gentle, without drastic fluctuations and mutations. For example, when controlling the speed of a compressor, good control input smoothness means that the speed adjustment is gradual and uniform, rather than a sudden and large increase or decrease.

[0144] Step 405 , obtaining an iteration result of the next iteration process according to the reference speed requirement sequence and the reference cost of the next iteration process.

[0145] In this step, the reference speed requirement sequence and the reference cost of the next iteration process are determined as the iteration result of the next iteration process.

[0146] In the embodiment of the present application, the iteration result of the first iteration process is determined according to the initial speed requirement sequence and the target value. Therefore, the embodiment of the present application provides a method for determining the iteration result. Figure 5 As shown, the specific steps include:

[0147] Step 501: Determine a reference speed requirement sequence for a first iteration process according to an initial speed requirement sequence.

[0148] In this step, the gradient sequence and target learning rate corresponding to the initial speed demand sequence are obtained, and the speed change sequence is calculated according to the gradient sequence and the target learning rate. The initial speed demand value and the speed change corresponding to the same time point are subtracted to obtain the reference speed demand sequence of the first iteration process.

[0149] Step 502 : determining a reference cost of the first iteration process according to the reference speed requirement sequence and the target value of the first iteration process.

[0150] In this step, the demand cost is determined according to the reference speed demand sequence of the first iteration process, and the demand cost is added to the target value to obtain the reference cost of the first iteration process.

[0151] Step 503: Obtain an iteration result of the first iteration process according to the reference speed requirement sequence and the reference cost of the first iteration process.

[0152] In this step, the reference speed requirement sequence and the reference cost of the first iteration process are determined as the iteration result of the first iteration process.

[0153] In the embodiment of the present application, the expected temperature sequence is obtained, and the current temperature in the passenger compartment is adjusted according to the current predicted temperature sequence. Therefore, the embodiment of the present application provides a temperature adjustment method, which is as follows: Figure 6As shown, the specific steps include:

[0154] Step 601, determining a current rotation speed requirement value according to a current predicted temperature sequence and a current expected temperature sequence.

[0155] In this step, the current speed demand sequence is determined according to the current predicted temperature sequence and the current expected temperature sequence, and the speed demand value corresponding to the current time point in the current speed demand sequence is determined as the current speed demand value.

[0156] It should be noted that the above method for determining the current speed requirement sequence is similar to the method for determining the target speed requirement sequence in step 202, and will not be described in detail here.

[0157] Step 602, adjusting the current speed of the compressor according to the current speed demand value to adjust the current temperature in the passenger compartment.

[0158] In this step, the current speed of the compressor is set as the target speed requirement value to adjust the current speed of the compressor to adjust the current temperature in the passenger compartment.

[0159] In the embodiment of the present application, when the temperature prediction model is a pre-trained neural network, the parameters in the neural network are adjusted according to the historical predicted temperature sequence and the loss value of the current passenger compartment temperature to obtain an adjusted neural network. Therefore, the embodiment of the present application provides a temperature prediction model adjustment method, which method is as follows: Figure 7 As shown, the specific steps include:

[0160] Step 701, obtaining the historical predicted temperature at the current time point in the historical predicted temperature sequence.

[0161] In this step, since the historical predicted temperatures are sorted in chronological order according to the corresponding time points, the first historical predicted temperature or the last historical predicted temperature is the historical predicted temperature at the current time point. Therefore, the first historical predicted temperature or the last historical predicted temperature can be determined as the historical predicted temperature at the current time point.

[0162] Step 702, determining the loss value between the historical predicted temperature and the current passenger compartment temperature.

[0163] In this step, a preset loss function is used to measure the difference between the target predicted temperature and the target reference temperature at the same target time point to obtain a loss value.

[0164] Step 703: adjust the temperature prediction model according to the loss value to obtain an adjusted temperature prediction model.

[0165] In this step, the gradient is calculated by back propagation according to the loss value, and the parameters in the temperature prediction model are adjusted by using the optimization algorithm to obtain the adjusted temperature prediction model.

[0166] like Figure 8 As shown, an embodiment of the present application provides a passenger compartment temperature adjustment device, which corresponds to the method embodiment and specifically includes:

[0167] An acquisition unit 801 is used to acquire the current ambient temperature of the vehicle, the current vehicle speed, the historical predicted temperature sequence output by the temperature prediction model at the previous time point, and the current passenger compartment temperature;

[0168] A first adjustment unit 802, configured to adjust the temperature prediction model according to the historical predicted temperature sequence and the current passenger compartment temperature to obtain an adjusted temperature prediction model;

[0169] The calling unit 803 is used to call the adjusted temperature prediction model, and obtain the current predicted temperature sequence by using the historical predicted temperature sequence, the current vehicle speed and the current ambient temperature;

[0170] The second adjustment unit 804 is used to adjust the current passenger compartment temperature according to the current predicted temperature sequence.

[0171] Optionally, the calling unit 803 is used to:

[0172] Get the historical expected temperature series;

[0173] Determining the target speed requirement sequence according to the historical predicted temperature sequence and the historical expected temperature sequence;

[0174] The adjusted temperature prediction model is called, and the target speed demand sequence, the current vehicle speed and the current ambient temperature are used to obtain a current predicted temperature sequence.

[0175] Optionally, the calling unit 803 is used to:

[0176] Determining a target value according to the historical predicted temperature sequence and the expected temperature sequence;

[0177] Determining an iteration result of a first iteration process according to the initial speed requirement sequence and the target value, and obtaining an iteration result of a current iteration process, wherein the iteration result includes a reference speed requirement sequence and a reference cost;

[0178] When the current iteration process is not the Kth iteration process and the reference cost is greater than the preset cost, the iteration result of the next iteration process is determined according to the iteration result of the current iteration process, and the iteration result of the current iteration process is obtained again;

[0179] When the current iteration process is the Kth iteration process or the reference cost is not greater than the preset cost, the reference speed requirement sequence in the iteration result of the current iteration process is determined as the target speed requirement sequence.

[0180] Optionally, the calling unit 803 is used to:

[0181] Determining a reference speed requirement sequence for a first iteration process according to the initial speed requirement sequence;

[0182] Determining a reference cost of the first iteration process according to the reference speed requirement sequence of the first iteration process and the target value;

[0183] According to the reference speed requirement sequence and the reference cost of the first iteration process, an iteration result of the first iteration process is obtained.

[0184] Optionally, the calling unit 803 is used to:

[0185] Get the gradient sequence and target learning rate corresponding to the current iteration process;

[0186] Calculating a rotation speed variation sequence according to the gradient sequence and the target learning rate;

[0187] Determining a reference speed requirement sequence for a next iteration process according to the speed variation sequence and the reference speed requirement sequence for the current iteration process;

[0188] determining a reference cost of a next iteration process according to a reference speed requirement sequence of a next iteration process;

[0189] According to the reference speed requirement sequence and the reference cost of the next iteration process, the iteration result of the next iteration process is obtained.

[0190] Optionally, the second adjusting unit 804 is configured to:

[0191] Determine the current speed requirement value according to the current predicted temperature sequence and the current expected temperature sequence;

[0192] According to the current speed requirement value, the current speed of the compressor is adjusted to adjust the current temperature in the passenger compartment.

[0193] Optionally, the first adjustment unit 802 is configured to:

[0194] In the historical predicted temperature sequence, obtaining the historical predicted temperature at the current time point;

[0195] determining a loss value between the historical predicted temperature and the current passenger compartment temperature;

[0196] The temperature prediction model is adjusted according to the loss value to obtain an adjusted temperature prediction model.

[0197] like Fig. 9 As shown, an embodiment of the present application provides a passenger cabin temperature adjustment device, including a processor 901, a communication interface 902, a memory 903 and a communication bus 904, wherein the processor 901, the communication interface 902, and the memory 903 communicate with each other through the communication bus 904.

[0198] Memory 903, used for storing computer programs;

[0199] In one embodiment of the present application, the processor 901 is used to execute the program stored in the memory 903 to implement the passenger compartment temperature adjustment method provided by any of the above method embodiments, including:

[0200] Obtain the current ambient temperature of the vehicle, the current vehicle speed, the historical predicted temperature sequence output by the temperature prediction model at the previous time point, and the current passenger compartment temperature;

[0201] Adjusting the temperature prediction model according to the historical predicted temperature sequence and the current passenger compartment temperature to obtain an adjusted temperature prediction model;

[0202] Calling the adjusted temperature prediction model, and obtaining a current predicted temperature sequence using the historical predicted temperature sequence, the current vehicle speed, and the current ambient temperature;

[0203] The current cabin temperature is adjusted based on the current predicted temperature sequence.

[0204] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps performed by the passenger compartment temperature adjustment method provided in any of the aforementioned method embodiments are implemented.

[0205] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0206] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for 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 some parts of the embodiments.

[0207] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of 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 described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0208] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be 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 invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for adjusting the temperature of a passenger compartment, characterized in that: The method comprises: Obtain the current ambient temperature of the vehicle, the current vehicle speed, the historical predicted temperature sequence output by the temperature prediction model at the previous time point, and the current passenger compartment temperature; Adjusting the temperature prediction model according to the historical predicted temperature sequence and the current passenger compartment temperature to obtain an adjusted temperature prediction model; Calling the adjusted temperature prediction model, and obtaining a current predicted temperature sequence using the historical predicted temperature sequence, the current vehicle speed, and the current ambient temperature; The current cabin temperature is adjusted based on the current predicted temperature sequence.

2. The method according to claim 1, characterized in that: The calling of the adjusted temperature prediction model, using the historical predicted temperature sequence, the current vehicle speed and the current ambient temperature to obtain the current predicted temperature sequence, includes: Get the historical expected temperature series; Determining the target speed requirement sequence according to the historical predicted temperature sequence and the historical expected temperature sequence; The adjusted temperature prediction model is called, and the target speed demand sequence, the current vehicle speed and the current ambient temperature are used to obtain a current predicted temperature sequence.

3. The method according to claim 2, characterized in that: The step of determining the target speed requirement sequence according to the historical predicted temperature sequence and the expected temperature sequence includes: Determining a target value according to the historical predicted temperature sequence and the expected temperature sequence; Determining an iteration result of a first iteration process according to the initial speed requirement sequence and the target value, and obtaining an iteration result of a current iteration process, wherein the iteration result includes a reference speed requirement sequence and a reference cost; When the current iteration process is not the Kth iteration process and the reference cost is greater than the preset cost, the iteration result of the next iteration process is determined according to the iteration result of the current iteration process, and the iteration result of the current iteration process is obtained again; When the current iteration process is the Kth iteration process or the reference cost is not greater than the preset cost, the reference speed requirement sequence in the iteration result of the current iteration process is determined as the target speed requirement sequence.

4. The method according to claim 3, characterized in that: The step of determining an iteration result of a first iteration process according to the initial speed requirement sequence and the target value includes: Determining a reference speed requirement sequence for a first iteration process according to the initial speed requirement sequence; Determining a reference cost of the first iteration process according to the reference speed requirement sequence of the first iteration process and the target value; According to the reference speed requirement sequence and the reference cost of the first iteration process, an iteration result of the first iteration process is obtained.

5. The method according to claim 3, characterized in that: Determining the iteration result of the next iteration process according to the iteration result of the current iteration process includes: Get the gradient sequence and target learning rate corresponding to the current iteration process; Calculating a rotation speed variation sequence according to the gradient sequence and the target learning rate; Determining a reference speed requirement sequence for a next iteration process according to the speed variation sequence and the reference speed requirement sequence for the current iteration process; determining a reference cost of a next iteration process according to a reference speed requirement sequence of a next iteration process; According to the reference speed requirement sequence and the reference cost of the next iteration process, the iteration result of the next iteration process is obtained.

6. The method according to claim 1, characterized in that: The step of adjusting the current temperature in the passenger compartment according to the current predicted temperature sequence includes: Determine the current speed requirement value according to the current predicted temperature sequence and the current expected temperature sequence; According to the current speed requirement value, the current speed of the compressor is adjusted to adjust the current temperature in the passenger compartment.

7. The method according to claim 1, characterized in that: The step of adjusting the temperature prediction model according to the historical predicted temperature sequence and the current passenger compartment temperature to obtain an adjusted temperature prediction model includes: In the historical predicted temperature sequence, obtaining the historical predicted temperature at the current time point; determining a loss value between the historical predicted temperature and the current passenger compartment temperature; The temperature prediction model is adjusted according to the loss value to obtain an adjusted temperature prediction model.

8. A passenger compartment temperature adjustment device, characterized in that: The device comprises: An acquisition unit, used to acquire the current ambient temperature of the vehicle, the current vehicle speed, the historical predicted temperature sequence output by the temperature prediction model at the previous time point, and the current passenger compartment temperature; A first adjustment unit, configured to adjust the temperature prediction model according to the historical predicted temperature sequence and the current passenger compartment temperature to obtain an adjusted temperature prediction model; A calling unit, used for calling the adjusted temperature prediction model, and obtaining a current predicted temperature sequence by using the historical predicted temperature sequence, the current vehicle speed and the current ambient temperature; The second adjustment unit is used to adjust the current passenger compartment temperature according to the current predicted temperature sequence.

9. A passenger compartment temperature adjustment device, characterized in that: include: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; at least one memory connected to the at least one bus, wherein the processor is configured to: Obtain the current ambient temperature of the vehicle, the current vehicle speed, the historical predicted temperature sequence output by the temperature prediction model at the previous time point, and the current passenger compartment temperature; Adjusting the temperature prediction model according to the historical predicted temperature sequence and the current passenger compartment temperature to obtain an adjusted temperature prediction model; Calling the adjusted temperature prediction model, and obtaining a current predicted temperature sequence using the historical predicted temperature sequence, the current vehicle speed, and the current ambient temperature; The current cabin temperature is adjusted based on the current predicted temperature sequence.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the passenger compartment temperature adjustment method according to any one of claims 1 to 7 is implemented.

Images