Electric vehicle heat pump air conditioner temperature control method, device, equipment and medium

Abstract

The present invention discloses a temperature control method, device, equipment and medium for heat pump air conditioner of electric vehicle. The method obtains the expected operating parameters through the ideal set temperature, actual ambient temperature, BP neural network model and PID controller, controls the compressor according to the expected operating parameters; obtains the actual operating parameters of the compressor and inputs them into the heat pump air conditioner model to obtain the actual output temperature; calculates the performance index parameter when the current system time meets the set conditions; if the performance index parameter does not meet the adaptation conditions, a new connection weight set is obtained by using a genetic algorithm to update the BP neural network model, and the actual ambient temperature is updated, and the above steps are repeated until the performance index parameter meets the adaptation conditions, so as to obtain the optimal BP neural network model to perform corresponding temperature control on the heat pump air conditioner of electric vehicle. The present invention effectively controls the temperature of the heat pump air conditioner based on the genetic algorithm, BP neural network and PID control algorithm, so that the control effect is more adaptable to environmental changes.

Description

Technical Field

[0001] The present invention relates to the technical field of heat pump air conditioners, and in particular to a temperature control method, device, equipment and medium for a heat pump air conditioner for an electric vehicle. Background Art

[0002] PID control (Proportional-Integral-Derivative Control) is one of the earliest developed control strategies. It is widely used in industrial process control due to its simple algorithm, good robustness and high reliability. Among them, the heat pump air conditioning system of electric vehicles has the characteristics of time-varying, nonlinear and hysteresis. The difficulty of using the classic PID control algorithm to adjust the temperature inside the car lies in the design of PID control parameters (i.e. proportional, integral and differential gain parameters), and the parameters cannot be adjusted online after they are determined, making its control effect unable to adapt to environmental changes. In addition, the BP neural network learning process is a process in which the error propagates backward while correcting the weights. The introduction of the neural network in BP-PID makes the algorithm training time longer, and the connection weights between the neurons in each layer of the neural network are difficult to determine, which limits the performance of the algorithm. Summary of the invention

[0003] The embodiments of the present invention provide a method, device, equipment and medium for controlling the temperature of an electric vehicle heat pump air conditioner, aiming to solve the problem in the prior art that it is difficult to design PID control parameters when using a PID control algorithm to adjust the temperature inside the electric vehicle.

[0004] In a first aspect, an embodiment of the present invention provides a method for controlling temperature of a heat pump air conditioner of an electric vehicle, comprising:

[0005] In response to the training instruction, an ideal set temperature and an actual ambient temperature corresponding to the training instruction are obtained, and a BP neural network model is constructed based on a preset initial connection weight set;

[0006] Obtaining an input parameter set based on the ideal set temperature and the actual ambient temperature, and inputting the input parameter set into the BP neural network model to obtain PID control parameters;

[0007] The PID control parameters are transmitted to a PID controller, and a compressor in a heat pump air conditioner of an electric vehicle is controlled according to the desired operating parameters output by the PID controller;

[0008] Acquiring actual operating parameters of the compressor, and inputting the actual operating parameters into a preset heat pump air conditioning model to output a corresponding actual output temperature;

[0009] If it is determined that the difference between the current system time and the system time corresponding to the training instruction is an integer multiple of the preset cycle length, the target operating parameters and the target output temperature are obtained, and the performance indicator parameters are obtained based on the ideal set temperature, the target output temperature and the target operating parameters; wherein the target operating parameters are the expected operating parameters output by the PID controller at the current system time; the target output temperature is the actual output temperature output by the heat pump air conditioning model at the current system time;

[0010] If it is determined that the performance indicator parameter does not meet the preset adaptation condition, all connection weights in the BP neural network model are optimized based on a genetic algorithm to obtain a new connection weight set;

[0011] The BP neural network model is updated using the new connection weight set, the actual ambient temperature is updated using the target output temperature, and the step of returning to the step of obtaining an input parameter set based on the ideal set temperature and the actual ambient temperature, and inputting the input parameter set into the BP neural network model to obtain PID control parameters is performed until the performance indicator parameters meet the adaptation conditions, and an optimal BP neural network model is obtained;

[0012] If a power-on command is received, the current ambient temperature is obtained in real time, and the electric vehicle heat pump air conditioner is temperature controlled accordingly based on the preset user set temperature, the current ambient temperature, the optimal BP neural network model and the PID controller.

[0013] In a second aspect, an embodiment of the present invention provides a temperature control device for an electric vehicle heat pump air conditioner, comprising:

[0014] A training instruction response unit, used to respond to the training instruction, obtain the ideal set temperature and the actual ambient temperature corresponding to the training instruction, and construct a BP neural network model based on a preset initial connection weight set;

[0015] A PID control parameter acquisition unit, used to obtain an input parameter set based on the ideal set temperature and the actual ambient temperature, and input the input parameter set into the BP neural network model to obtain PID control parameters;

[0016] A compressor control unit, used to transmit the PID control parameters to a PID controller, and control the compressor in the electric vehicle heat pump air conditioner according to the desired operating parameters output by the PID controller;

[0017] An air conditioning model output unit, used to obtain actual operating parameters of the compressor, and input the actual operating parameters into a preset heat pump air conditioning model to output a corresponding actual output temperature;

[0018] A performance indicator acquisition unit, for acquiring target operating parameters and target output temperature if it is determined that the difference between the current system time and the system time corresponding to the training instruction is an integer multiple of a preset cycle length, and obtaining performance indicator parameters based on the ideal set temperature, the target output temperature and the target operating parameters; wherein the target operating parameters are the expected operating parameters output by the PID controller at the current system time; and the target output temperature is the actual output temperature output by the heat pump air conditioning model at the current system time;

[0019] A network model optimization unit, configured to optimize all connection weights in the BP neural network model based on a genetic algorithm to obtain a new connection weight set if it is determined that the performance indicator parameter does not meet a preset adaptation condition;

[0020] an optimal model determination unit, configured to update the BP neural network model using the new connection weight set, update the actual ambient temperature using the target output temperature, and return to execute the step of obtaining an input parameter set based on the ideal set temperature and the actual ambient temperature, and inputting the input parameter set into the BP neural network model to obtain PID control parameters, until the performance indicator parameters meet the adaptation condition, and an optimal BP neural network model is obtained;

[0021] The temperature control unit is used to obtain the current ambient temperature in real time if a power-on command is received, and to perform corresponding temperature control on the electric vehicle heat pump air conditioner based on a preset user set temperature, the current ambient temperature, the optimal BP neural network model and the PID controller.

[0022] In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the electric vehicle heat pump air conditioning temperature control method of the first aspect mentioned above is implemented.

[0023] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the electric vehicle heat pump air conditioning temperature control method of the first aspect.

[0024] The embodiment of the present invention provides a temperature control method, device, equipment and medium for heat pump air conditioner of electric vehicle. The method obtains the expected operating parameters through the ideal set temperature, actual ambient temperature, BP neural network model and PID controller, controls the compressor according to the expected operating parameters; obtains the actual operating parameters of the compressor and inputs them into the heat pump air conditioner model to obtain the actual output temperature; calculates the performance index parameter when the current system time meets the set conditions; if the performance index parameter does not meet the adaptation conditions, a new connection weight set is obtained by genetic algorithm to update the BP neural network model, and the actual ambient temperature is updated, and the above steps are repeated until the performance index parameter meets the adaptation conditions, so as to obtain the optimal BP neural network model to perform corresponding temperature control on the heat pump air conditioner of electric vehicle. The present invention effectively controls the temperature of heat pump air conditioner based on genetic algorithm, BP neural network and PID control algorithm, makes the control effect more adaptable to environmental changes, and improves the accuracy of temperature control. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0026] Figure 1 A schematic flow chart of a method for controlling the temperature of an electric vehicle heat pump air conditioner according to an embodiment of the present invention;

[0027] Figure 2 A first framework diagram of a method for controlling temperature of a heat pump air conditioner in an electric vehicle provided by an embodiment of the present invention;

[0028] Figure 3 A second framework diagram of a method for controlling the temperature of an electric vehicle heat pump air conditioner provided by an embodiment of the present invention;

[0029] Figure 4 A schematic block diagram of a heat pump air conditioner temperature control device for an electric vehicle provided by an embodiment of the present invention;

[0030] Figure 5 A schematic block diagram of a computer device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0033] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0034] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0035] See also Figures 1 to 3 , Figure 1 A schematic flow chart of a method for controlling the temperature of an electric vehicle heat pump air conditioner according to an embodiment of the present invention; Figure 2 A first framework diagram of a method for controlling temperature of a heat pump air conditioner in an electric vehicle provided by an embodiment of the present invention; Figure 3 The second framework diagram of the electric vehicle heat pump air conditioner temperature control method provided by an embodiment of the present invention. The electric vehicle heat pump air conditioner temperature control method provided by an embodiment of the present invention includes steps S11 to S18.

[0036] S11. In response to a training instruction, an ideal set temperature and an actual ambient temperature corresponding to the training instruction are obtained, and a BP neural network model is constructed based on a preset initial connection weight set.

[0037] In this embodiment, the training instruction can be triggered by relevant personnel. When the training instruction is received, the ideal set temperature and the actual ambient temperature corresponding to the training instruction are obtained, and at the same time, the BP neural network model is constructed based on the preset initial connection weight set. Among them, the ideal set temperature can be set by relevant personnel, and the actual ambient temperature at this time refers to the ambient temperature collected at the system time corresponding to the training instruction.

[0038] S12. Obtain an input parameter set based on the ideal set temperature and the actual ambient temperature, and input the input parameter set into the BP neural network model to obtain PID control parameters.

[0039] In this embodiment, the input parameter set is obtained based on the ideal set temperature and the actual ambient temperature corresponding to the current moment. For details, see Figure 2, the ideal set temperature is recorded as T d (k), the actual ambient temperature is denoted as T(k), and the actual ambient temperature corresponds to the current moment, the difference between the ideal set temperature and the actual ambient temperature corresponding to the current moment is calculated, the temperature error value corresponding to the current moment is obtained, and the temperature error value corresponding to the current moment is used as the first error value; the temperature error value corresponding to the previous moment is obtained as the second error value, and the temperature error values ​​corresponding to the previous two moments are obtained as the third error value; wherein, it can also be understood that the second error value is the difference between the ideal set temperature and the actual ambient temperature corresponding to the previous moment, and the third error value is the difference between the ideal set temperature and the actual ambient temperature corresponding to the previous two moments. An input parameter set is obtained based on the first error value, the second error value and the third error value, wherein the input parameter set includes the first input parameter, the second input parameter and the third input parameter, the first error value is denoted as e(k), the second error value is denoted as e(k-1), and the third error value is denoted as e(k-2), then the first input parameter is e(k), the second input parameter is e(k)-e(k-1), and the third input parameter is e(k)-2e(k-1)+e(k-2).

[0040] After obtaining the input parameter set, the input parameter set is input into the input layer of the BP neural network model, and then the output layer of the BP neural network model outputs the PID control parameters. The BP neural network model has the ability of autonomous learning and can realize the nonlinear mapping of the model. The BP neural network is introduced to optimize the PID control parameters online in real time. Among them, the PID control parameters include the proportional gain parameter (K P )、Integral gain parameter(K I ) and the differential gain parameter (K D ).

[0041] S13, transmitting the PID control parameters to a PID controller, and controlling the compressor in the electric vehicle heat pump air conditioner according to the desired operating parameters output by the PID controller.

[0042] In this embodiment, the PID control parameters optimized by the BP neural network model are transmitted to the PID controller, and the PID controller calculates the desired operating parameters according to the PID control parameters, and then controls the compressor in the electric vehicle heat pump air conditioner according to the desired operating parameters.

[0043] In one embodiment, controlling the compressor in the electric vehicle heat pump air conditioner according to the desired operating parameters output by the PID controller includes:

[0044] Obtaining a PWM signal according to the desired operating parameters;

[0045] The compressor in the electric vehicle heat pump air conditioner is controlled according to the PWM signal.

[0046] In this embodiment, the desired operating parameters output by the PID controller are first converted into PWM signals, and then the PWM signals are sent to the compressor in the electric vehicle heat pump air conditioner to adjust the operating state of the compressor.

[0047] In one embodiment, obtaining a PWM signal according to the expected operating parameter includes:

[0048] If it is determined that the expected operating parameter is a negative value, obtaining a preset first duty cycle;

[0049] If it is determined that the expected operating parameter is a positive value, a second duty cycle is calculated according to the expected operating parameter and a preset duty cycle calculation strategy;

[0050] A corresponding PWM signal is obtained according to the first duty cycle or the second duty cycle.

[0051] More specifically, the formula corresponding to the duty cycle calculation strategy is D= [u d (k) / Umax]×100%; where D is the second duty cycle, u d (k) is the expected operating parameter, and Umax is the preset maximum operating parameter.

[0052] In this embodiment, the acquisition of the PWM signal is achieved by mapping the expected operating parameter output by the PID controller to the duty cycle. Specifically, if the expected operating parameter is determined to be a negative value, a preset first duty cycle is acquired, wherein the first duty cycle is 0%. If the expected operating parameter is determined to be a positive value, the second duty cycle is calculated based on the expected operating parameter and the preset duty cycle calculation strategy. After the first duty cycle or the second duty cycle is obtained, a PWM signal controller can be used to generate a corresponding PWM signal according to the first duty cycle or the second duty cycle.

[0053] S14, obtaining actual operating parameters of the compressor, and inputting the actual operating parameters into a preset heat pump air conditioning model to output a corresponding actual output temperature.

[0054] In this embodiment, the actual operating parameters of the compressor are obtained and input into a preset heat pump air conditioning model, so as to obtain the actual output temperature through the heat pump air conditioning model. The heat pump air conditioning model is an empirical model, which is a model with transfer function properties obtained by controlling an actual electric vehicle heat pump air conditioning, obtaining a series of data and analyzing the data.

[0055] In one embodiment, after step S14, the method further includes:

[0056] If it is determined that the difference between the current system time and the system time corresponding to the power-on instruction is not an integer multiple of the preset cycle length, the actual output temperature is used to update the actual ambient temperature, and the process returns to the step of obtaining an input parameter set based on the ideal set temperature and the actual ambient temperature, and inputting the input parameter set into the BP neural network model to obtain PID control parameters.

[0057] In this embodiment, it is determined whether the current system time satisfies the set condition, that is, it is determined whether the difference between the current system time and the system time corresponding to the power-on instruction is an integer multiple of the preset cycle time, so as to determine whether the current system time has reached the preset cycle target time. If it is determined that the difference between the current system time and the system time corresponding to the power-on instruction is not an integer multiple of the preset cycle time, it means that the current system time has not reached the preset cycle target time. At this time, it is necessary to update the actual ambient temperature using the actual output temperature output by the heat pump air conditioning model, and return to execute step S12, and then before the current system time has not reached the preset cycle target time, the heat pump air conditioning model is controlled by the current BP neural network model and the PID controller for the preset cycle time.

[0058] S15. If it is determined that the difference between the current system time and the system time corresponding to the training instruction is an integer multiple of the preset cycle length, the target operating parameters and the target output temperature are obtained, and the performance indicator parameters are obtained based on the ideal set temperature, the target output temperature and the target operating parameters; wherein the target operating parameters are the expected operating parameters output by the PID controller at the current system time; and the target output temperature is the actual output temperature output by the heat pump air conditioning model at the current system time.

[0059] In this embodiment, if it is determined that the difference between the current system time and the system time corresponding to the power-on instruction is an integer multiple of the preset cycle length, it means that the current system time has reached the preset cycle target time, then the expected operating parameters output by the PID controller at the current system time are obtained as the target operating parameters, the actual output temperature output by the heat pump air conditioning model at the current system time is obtained as the target output temperature, and the performance indicator parameters are obtained based on the ideal set temperature, the target output temperature and the target operating parameters, and it is determined whether the performance indicator parameters meet the preset adaptation conditions, so that when the current system time reaches the preset cycle target time and the performance indicator parameters do not meet the preset adaptation conditions, the connection weights in the BP neural network model are optimized, so that before the performance indicator parameters do not meet the preset adaptation conditions, the BP neural network model is periodically trained according to the preset cycle length.

[0060] In one embodiment, obtaining the performance indicator parameter based on the ideal set temperature, the target output temperature and the target operating parameter includes:

[0061] Calculating the difference between the ideal set temperature and the target output temperature to obtain a target temperature difference;

[0062] Get the preset performance indicator function;

[0063] The performance indicator parameter is calculated according to the target temperature difference value, the target operating parameter and the performance indicator function.

[0064] More specifically, the formula corresponding to the performance indicator function is J(T m ) = Q × e(T m ) 2 +R×u d (T m ) 2 ; Among them, J(T m ) is the performance index parameter, e(T m ) is the target temperature difference, u d (T m ) is the target operating parameter, Q is the preset first connection weight value, and R is the preset second connection weight value.

[0065] In this embodiment, the target temperature difference is obtained according to the ideal setting temperature and the target output temperature, wherein the target temperature difference is the difference between the ideal setting temperature and the target output temperature. Figure 2 , the current system time is T m , the target temperature difference is e(T m ), the target running parameter is u d (T m ), substitute the target temperature difference value and the target operating parameters into the preset performance index function, and the performance index parameters can be calculated, so as to select the optimal connection weights of the BP neural network model according to the performance index parameters. Among them, the performance index function provides a measure of system performance. The first connection weight value Q in the formula corresponding to the performance index function indicates the state weight, which defines the importance of the error variable in the performance index. The first connection weight value Q is used to punish the degree of deviation of the state from the target value. The second connection weight value R in the formula corresponding to the performance index function is used to control the weight of the input. The value of the second connection weight value R reflects the degree of punishment for the use of the control input.

[0066] S16: If it is determined that the performance indicator parameter does not meet the preset adaptation condition, all connection weights in the BP neural network model are optimized based on a genetic algorithm to obtain a new connection weight set.

[0067] In this embodiment, if it is determined that the performance indicator parameter does not meet the preset adaptation condition, it means that the connection weights in the BP neural network model at this time are not optimal, and all the connection weights in the BP neural network model need to be optimized based on the genetic algorithm to obtain a new connection weight set to be used in the next training of the BP neural network model. In one embodiment, the adaptation condition can be set to that the cumulative number of training times corresponding to the performance indicator parameter is less than or equal to the preset maximum number of training times, and the inverse of the performance indicator parameter is less than the preset adaptation value, that is, the adaptation condition can be set to m≤M and P(m)<P M , where m is the cumulative number of training times corresponding to the performance indicator parameter, M is the preset maximum number of training times, and P(m) is the reciprocal of the performance indicator parameter, that is, P(m)=1 / J(T m ), P M is the preset fitness value, P M It can be set according to the actual control effect. At the same time, m can be calculated according to the formula m=(t-t0) / T, where t is the current system time, t0 is the system time corresponding to the power-on command, and T is the preset cycle length. Therefore, if it is determined that m>M or P(m)>P M , it can be determined that the performance index parameter does not meet the preset adaptation conditions; if it is determined that m≤M and P(m)<P M , it can be determined that the performance index parameters meet the preset adaptation conditions.

[0068] More specifically, through the encoding, crossover and mutation operations in the genetic algorithm, a new set of connection weights to be used in the next training of the BP neural network model is obtained. First, the connection weights in the BP neural network model are converted into individual genotypes through encoding and form a population. Among them, the BP neural network model includes a number of input layer neurons, hidden layer neurons and output layer neurons. The connection weights in the BP neural network model include w ij and v jn , w ij is the connection weight between the input layer and the hidden layer in the BP neural network model, v jn is the connection weight between the hidden layer and the output layer in the BP neural network model, i is the index of the input layer neuron, j is the index of the hidden layer neuron, and n is the index of the output layer neuron. The encoding methods include real number encoding and binary encoding. Real number encoding means directly using real numbers to represent the connection weight and using a set of real number arrays to represent the genotype of an individual. For example, the genotype of an individual can be [w 11 , w 12 , …, v 21 , v 22,…]. Binary encoding means discretizing each connection weight and using a binary string to represent the genotype of an individual. For example, the genotype of an individual can be 110010. Then, a new set of connection weights is generated through crossover and mutation operations between individuals in the population. The crossover operation is to create a pair of new individuals. Usually, part of the chromosomes of the parent samples selected from the current generation are exchanged to create two new chromosomes representing the offspring. The purpose of the mutation operation is to periodically update the population randomly, which is achieved by randomly changing one or more chromosome values.

[0069] S17, using the new connection weight set to update the BP neural network model, using the target output temperature to update the actual ambient temperature, and returning to execute the step of obtaining an input parameter set based on the ideal set temperature and the actual ambient temperature, and inputting the input parameter set into the BP neural network model to obtain PID control parameters, until the performance indicator parameters meet the adaptation conditions, and the optimal BP neural network model is obtained.

[0070] In this embodiment, the BP neural network model is updated with a new set of connection weights to optimize the BP neural network model. At the same time, the target output temperature (i.e., the actual output temperature currently output by the heat pump air conditioning model) is used to update the actual ambient temperature. The process returns to step S12 and the updated BP neural network model and PID controller are used again to control the heat pump air conditioning model for a preset cycle duration to continuously perform periodic training on the BP neural network model until the calculated performance index parameters meet the adaptation conditions, and the optimal connection weights of the BP neural network model are selected to obtain the optimal BP neural network model.

[0071] S18. If a power-on instruction is received, the current ambient temperature is obtained in real time, and the electric vehicle heat pump air conditioner is temperature controlled accordingly based on the preset user set temperature, the current ambient temperature, the optimal BP neural network model and the PID controller.

[0072] In this embodiment, after the optimal BP neural network model is trained, when it is necessary to start the electric vehicle heat pump air conditioner for temperature control, the power-on command can be triggered by relevant personnel, so that when the power-on command is received, the electric vehicle heat pump air conditioner is subjected to corresponding temperature control according to the current ambient temperature, the user set temperature, the optimal BP neural network model and the PID controller obtained in real time. The PID control parameters output by the PID controller are optimized in real time using the optimal BP neural network model, which can solve the problem of poor adaptability of traditional PID control parameters and make the control effect more adaptable to environmental changes, thereby improving the accuracy of temperature control.

[0073] Specifically, firstly, the step of controlling the compressor in the electric vehicle heat pump air conditioner based on the preset user set temperature, the current ambient temperature, the optimal BP neural network model and the PID controller is performed, wherein the current ambient temperature can be acquired by the temperature sensor, see Figure 3 This step is similar to steps S12-S13 in the above embodiment. This step includes setting the temperature T* based on the user setting temperature d (k) and the current ambient temperature T*(k) to obtain the current input parameter set, and input the current input parameter set into the optimal BP neural network model to obtain the optimal PID control parameters; transmit the optimal PID control parameters to the PID controller, and according to the optimal operating parameter u* output by the PID controller d (k) Control the compressor in the electric vehicle heat pump air conditioner. Then, the electric vehicle heat pump air conditioner is controlled accordingly based on the operating parameters u*(k) of the compressor. The compressor is controlled by obtaining the optimal operating parameters through the optimal BP neural network model and the PID controller to adjust the compressor speed, and then the blower speed in the electric vehicle heat pump air conditioner is adjusted accordingly, thereby adjusting the cooling or heating capacity of the electric vehicle heat pump air conditioner, thereby effectively controlling the temperature of the electric vehicle heat pump air conditioner.

[0074] The present invention discloses a temperature control method for an electric vehicle heat pump air conditioner. Aiming at the time-varying, nonlinear and hysteresis characteristics of an electric vehicle heat pump air conditioner system, a BP neural network is introduced to optimize the PID control parameters output by a PID controller in real time. Meanwhile, a genetic algorithm is used to update the connection weights of the BP neural network. This can solve the problems of poor adaptability of traditional PID control parameters and difficulty in determining the connection weights of the BP neural network, so that the control effect can better adapt to environmental changes, the temperature of the heat pump air conditioner can be more effectively controlled, and the temperature control accuracy can be improved.

[0075] The embodiment of the present invention further provides an electric vehicle heat pump air conditioner temperature control device, which is used to execute any embodiment of the electric vehicle heat pump air conditioner temperature control method. Specifically, please refer to Figure 4 , Figure 4 A schematic block diagram of a heat pump air-conditioning temperature control device for an electric vehicle provided in an embodiment of the present invention. The heat pump air-conditioning temperature control device for an electric vehicle provided in an embodiment of the present invention includes a training instruction response unit 11, a PID control parameter acquisition unit 12, a compressor control unit 13, an air-conditioning model output unit 14, a performance indicator acquisition unit 15, a network model optimization unit 16, an optimal model determination unit 17 and a temperature control unit 18.

[0076] The training instruction response unit 11 is used to respond to the training instruction, obtain the ideal set temperature and the actual ambient temperature corresponding to the training instruction, and construct a BP neural network model based on a preset initial connection weight set.

[0077] In this embodiment, the training instruction can be triggered by relevant personnel. When the training instruction is received, the ideal set temperature and the actual ambient temperature corresponding to the training instruction are obtained, and at the same time, the BP neural network model is constructed based on the preset initial connection weight set. Among them, the ideal set temperature can be set by relevant personnel, and the actual ambient temperature at this time refers to the ambient temperature collected at the system time corresponding to the training instruction.

[0078] The PID control parameter acquisition unit 12 is used to obtain an input parameter set based on the ideal set temperature and the actual ambient temperature, and input the input parameter set into the BP neural network model to obtain PID control parameters.

[0079] In this embodiment, the input parameter set is obtained based on the ideal set temperature and the actual ambient temperature corresponding to the current moment. For details, see Figure 2 , the ideal set temperature is recorded as T d (k), the actual ambient temperature is denoted as T(k), and the actual ambient temperature corresponds to the current moment, the difference between the ideal set temperature and the actual ambient temperature corresponding to the current moment is calculated, the temperature error value corresponding to the current moment is obtained, and the temperature error value corresponding to the current moment is used as the first error value; the temperature error value corresponding to the previous moment is obtained as the second error value, and the temperature error values ​​corresponding to the previous two moments are obtained as the third error value; wherein, it can also be understood that the second error value is the difference between the ideal set temperature and the actual ambient temperature corresponding to the previous moment, and the third error value is the difference between the ideal set temperature and the actual ambient temperature corresponding to the previous two moments. An input parameter set is obtained based on the first error value, the second error value and the third error value, wherein the input parameter set includes the first input parameter, the second input parameter and the third input parameter, the first error value is denoted as e(k), the second error value is denoted as e(k-1), and the third error value is denoted as e(k-2), then the first input parameter is e(k), the second input parameter is e(k)-e(k-1), and the third input parameter is e(k)-2e(k-1)+e(k-2).

[0080] After obtaining the input parameter set, the input parameter set is input into the input layer of the BP neural network model, and then the output layer of the BP neural network model outputs the PID control parameters. The BP neural network model has the ability of autonomous learning and can realize the nonlinear mapping of the model. The BP neural network is introduced to optimize the PID control parameters online in real time. Among them, the PID control parameters include the proportional gain parameter (K P)、Integral gain parameter(K I ) and the differential gain parameter (K D ).

[0081] The compressor control unit 13 is used to transmit the PID control parameters to the PID controller, and control the compressor in the electric vehicle heat pump air conditioner according to the desired operating parameters output by the PID controller.

[0082] In this embodiment, the PID control parameters optimized by the BP neural network model are transmitted to the PID controller, and the PID controller calculates the desired operating parameters according to the PID control parameters, and then controls the compressor in the electric vehicle heat pump air conditioner according to the desired operating parameters.

[0083] In one embodiment, when the compressor control unit 13 executes the step of controlling the compressor in the electric vehicle heat pump air conditioner according to the desired operating parameters output by the PID controller, it is specifically used to:

[0084] Obtaining a PWM signal according to the desired operating parameters;

[0085] The compressor in the electric vehicle heat pump air conditioner is controlled according to the PWM signal.

[0086] In this embodiment, the desired operating parameters output by the PID controller are first converted into PWM signals, and then the PWM signals are sent to the compressor in the electric vehicle heat pump air conditioner to adjust the operating state of the compressor.

[0087] In one embodiment, when the compressor control unit 13 executes the step of obtaining a PWM signal according to the desired operating parameters, it is specifically configured to:

[0088] If it is determined that the expected operating parameter is a negative value, obtaining a preset first duty cycle;

[0089] If it is determined that the expected operating parameter is a positive value, a second duty cycle is calculated according to the expected operating parameter and a preset duty cycle calculation strategy;

[0090] A corresponding PWM signal is obtained according to the first duty cycle or the second duty cycle.

[0091] More specifically, the formula corresponding to the duty cycle calculation strategy is D= [u d (k) / Umax]×100%; where D is the second duty cycle, u d (k) is the expected operating parameter, and Umax is the preset maximum operating parameter.

[0092] In this embodiment, the acquisition of the PWM signal is achieved by mapping the expected operating parameter output by the PID controller to the duty cycle. Specifically, if the expected operating parameter is determined to be a negative value, a preset first duty cycle is acquired, wherein the first duty cycle is 0%. If the expected operating parameter is determined to be a positive value, the second duty cycle is calculated based on the expected operating parameter and the preset duty cycle calculation strategy. After the first duty cycle or the second duty cycle is obtained, a PWM signal controller can be used to generate a corresponding PWM signal according to the first duty cycle or the second duty cycle.

[0093] The air conditioning model output unit 14 is used to obtain the actual operating parameters of the compressor and input the actual operating parameters into a preset heat pump air conditioning model to output a corresponding actual output temperature.

[0094] In this embodiment, the actual operating parameters of the compressor are obtained and input into a preset heat pump air conditioning model, so as to obtain the actual output temperature through the heat pump air conditioning model. The heat pump air conditioning model is an empirical model, which is a model with transfer function properties obtained by controlling an actual electric vehicle heat pump air conditioning, obtaining a series of data and analyzing the data.

[0095] In one embodiment, the electric vehicle heat pump air conditioning temperature control device provided by the embodiment of the present invention further includes a circulation control unit, which is used to: after the air conditioning model output unit 14 executes the step of obtaining the actual operating parameters of the compressor and inputting the actual operating parameters into the preset heat pump air conditioning model to output the corresponding actual output temperature, the circulation control unit is used to:

[0096] If it is determined that the difference between the current system time and the system time corresponding to the power-on instruction is not an integer multiple of the preset cycle length, the actual output temperature is used to update the actual ambient temperature, and the process returns to the step of obtaining an input parameter set based on the ideal set temperature and the actual ambient temperature, and inputting the input parameter set into the BP neural network model to obtain PID control parameters.

[0097] In this embodiment, it is determined whether the current system time satisfies the set condition, that is, it is determined whether the difference between the current system time and the system time corresponding to the power-on instruction is an integer multiple of the preset cycle time, so as to determine whether the current system time has reached the preset cycle target time. If it is determined that the difference between the current system time and the system time corresponding to the power-on instruction is not an integer multiple of the preset cycle time, it means that the current system time has not reached the preset cycle target time. At this time, it is necessary to update the actual ambient temperature using the actual output temperature output by the heat pump air conditioning model, and return to execute step S12, and then before the current system time has not reached the preset cycle target time, the heat pump air conditioning model is controlled by the current BP neural network model and the PID controller for the preset cycle time.

[0098] The performance indicator acquisition unit 15 is used to obtain the target operating parameters and the target output temperature if it is determined that the difference between the current system time and the system time corresponding to the training instruction is an integer multiple of the preset cycle length, and obtain the performance indicator parameters based on the ideal set temperature, the target output temperature and the target operating parameters; wherein the target operating parameters are the expected operating parameters output by the PID controller at the current system time; and the target output temperature is the actual output temperature output by the heat pump air conditioning model at the current system time.

[0099] In this embodiment, if it is determined that the difference between the current system time and the system time corresponding to the power-on instruction is an integer multiple of the preset cycle length, it means that the current system time has reached the preset cycle target time, then the expected operating parameters output by the PID controller at the current system time are obtained as the target operating parameters, the actual output temperature output by the heat pump air conditioning model at the current system time is obtained as the target output temperature, and the performance indicator parameters are obtained based on the ideal set temperature, the target output temperature and the target operating parameters, and it is determined whether the performance indicator parameters meet the preset adaptation conditions, so that when the current system time reaches the preset cycle target time and the performance indicator parameters do not meet the preset adaptation conditions, the connection weights in the BP neural network model are optimized, so that before the performance indicator parameters do not meet the preset adaptation conditions, the BP neural network model is periodically trained according to the preset cycle length.

[0100] In one embodiment, when the performance indicator acquisition unit 15 executes the step of obtaining the performance indicator parameter based on the ideal set temperature, the target output temperature and the target operating parameter, it is specifically used to:

[0101] Calculating the difference between the ideal set temperature and the target output temperature to obtain a target temperature difference;

[0102] Get the preset performance indicator function;

[0103] The performance indicator parameter is calculated according to the target temperature difference value, the target operating parameter and the performance indicator function.

[0104] More specifically, the formula corresponding to the performance indicator function is J(T m ) = Q × e(T m ) 2 +R×u d (T m ) 2 ; Among them, J(T m ) is the performance index parameter, e(T m ) is the target temperature difference, u d (Tm ) is the target operating parameter, Q is the preset first connection weight value, and R is the preset second connection weight value.

[0105] In this embodiment, the target temperature difference is obtained according to the ideal setting temperature and the target output temperature, wherein the target temperature difference is the difference between the ideal setting temperature and the target output temperature. Figure 2 , the current system time is T m , the target temperature difference is e(T m ), the target running parameter is u d (T m ), substitute the target temperature difference value and the target operating parameters into the preset performance index function, and the performance index parameters can be calculated, so as to select the optimal connection weights of the BP neural network model according to the performance index parameters. Among them, the performance index function provides a measure of system performance. The first connection weight value Q in the formula corresponding to the performance index function indicates the state weight, which defines the importance of the error variable in the performance index. The first connection weight value Q is used to punish the degree of deviation of the state from the target value. The second connection weight value R in the formula corresponding to the performance index function is used to control the weight of the input. The value of the second connection weight value R reflects the degree of punishment for the use of the control input.

[0106] The network model optimization unit 16 is used to optimize all connection weights in the BP neural network model based on a genetic algorithm to obtain a new connection weight set if it is determined that the performance indicator parameter does not meet the preset adaptation condition.

[0107] In this embodiment, if it is determined that the performance indicator parameter does not meet the preset adaptation condition, it means that the connection weights in the BP neural network model at this time are not optimal, and all the connection weights in the BP neural network model need to be optimized based on the genetic algorithm to obtain a new connection weight set to be used in the next training of the BP neural network model. In one embodiment, the adaptation condition can be set to that the cumulative number of training times corresponding to the performance indicator parameter is less than or equal to the preset maximum number of training times, and the inverse of the performance indicator parameter is less than the preset adaptation value, that is, the adaptation condition can be set to m≤M and P(m)<P M , where m is the cumulative number of training times corresponding to the performance indicator parameter, M is the preset maximum number of training times, and P(m) is the reciprocal of the performance indicator parameter, that is, P(m)=1 / J(T m ), P M is the preset fitness value, P M It can be set according to the actual control effect. At the same time, m can be calculated according to the formula m=(t-t0) / T, where t is the current system time, t0 is the system time corresponding to the power-on command, and T is the preset cycle length. Therefore, if it is determined that m>M or P(m)>PM , it can be determined that the performance index parameter does not meet the preset adaptation conditions; if it is determined that m≤M and P(m)<P M , it can be determined that the performance index parameters meet the preset adaptation conditions.

[0108] More specifically, through the encoding, crossover and mutation operations in the genetic algorithm, a new set of connection weights to be used in the next training of the BP neural network model is obtained. First, the connection weights in the BP neural network model are converted into individual genotypes through encoding and form a population. Among them, the BP neural network model includes a number of input layer neurons, hidden layer neurons and output layer neurons. The connection weights in the BP neural network model include w ij and v jn , w ij is the connection weight between the input layer and the hidden layer in the BP neural network model, v jn is the connection weight between the hidden layer and the output layer in the BP neural network model, i is the index of the input layer neuron, j is the index of the hidden layer neuron, and n is the index of the output layer neuron. The encoding methods include real number encoding and binary encoding. Real number encoding means directly using real numbers to represent the connection weight and using a set of real number arrays to represent the genotype of an individual. For example, the genotype of an individual can be [w 11 , w 12 , …, v 21 , v 22 ,…]. Binary encoding means discretizing each connection weight and using a binary string to represent the genotype of an individual. For example, the genotype of an individual can be 110010. Then, a new set of connection weights is generated through crossover and mutation operations between individuals in the population. The crossover operation is to create a pair of new individuals. Usually, part of the chromosomes of the parent samples selected from the current generation are exchanged to create two new chromosomes representing the offspring. The purpose of the mutation operation is to periodically update the population randomly, which is achieved by randomly changing one or more chromosome values.

[0109] The optimal model determination unit 17 is used to update the BP neural network model using the new connection weight set, update the actual ambient temperature using the target output temperature, and return to execute the step of obtaining an input parameter set based on the ideal set temperature and the actual ambient temperature, and inputting the input parameter set into the BP neural network model to obtain PID control parameters, until the performance indicator parameters meet the adaptation conditions and the optimal BP neural network model is obtained.

[0110] In this embodiment, the BP neural network model is updated with a new set of connection weights to optimize the BP neural network model. At the same time, the target output temperature (i.e., the actual output temperature currently output by the heat pump air conditioning model) is used to update the actual ambient temperature. The process returns to step S12 and the updated BP neural network model and PID controller are used again to control the heat pump air conditioning model for a preset cycle duration to continuously perform periodic training on the BP neural network model until the calculated performance index parameters meet the adaptation conditions, and the optimal connection weights of the BP neural network model are selected to obtain the optimal BP neural network model.

[0111] The temperature control unit 18 is used to obtain the current ambient temperature in real time if a power-on command is received, and to perform corresponding temperature control on the electric vehicle heat pump air conditioner based on the preset user set temperature, the current ambient temperature, the optimal BP neural network model and the PID controller.

[0112] In this embodiment, after the optimal BP neural network model is trained, when it is necessary to start the electric vehicle heat pump air conditioner for temperature control, the power-on command can be triggered by relevant personnel, so that when the power-on command is received, the electric vehicle heat pump air conditioner is subjected to corresponding temperature control according to the current ambient temperature, the user set temperature, the optimal BP neural network model and the PID controller obtained in real time. The PID control parameters output by the PID controller are optimized in real time using the optimal BP neural network model, which can solve the problem of poor adaptability of traditional PID control parameters and make the control effect more adaptable to environmental changes, thereby improving the accuracy of temperature control.

[0113] Specifically, firstly, the step of controlling the compressor in the electric vehicle heat pump air conditioner based on the preset user set temperature, the current ambient temperature, the optimal BP neural network model and the PID controller is performed, wherein the current ambient temperature can be acquired by the temperature sensor, see Figure 3 This step is similar to steps S12-S13 in the above embodiment. This step includes setting the temperature T* based on the user setting temperature d (k) and the current ambient temperature T*(k) to obtain the current input parameter set, and input the current input parameter set into the optimal BP neural network model to obtain the optimal PID control parameters; transmit the optimal PID control parameters to the PID controller, and according to the optimal operating parameter u* output by the PID controller d(k) Control the compressor in the electric vehicle heat pump air conditioner. Then, the electric vehicle heat pump air conditioner is controlled accordingly based on the operating parameters u*(k) of the compressor. The compressor is controlled by obtaining the optimal operating parameters through the optimal BP neural network model and the PID controller to adjust the compressor speed, and then the blower speed in the electric vehicle heat pump air conditioner is adjusted accordingly, thereby adjusting the cooling or heating capacity of the electric vehicle heat pump air conditioner, thereby effectively controlling the temperature of the electric vehicle heat pump air conditioner.

[0114] The present invention discloses a temperature control device for an electric vehicle heat pump air conditioner, which is used to execute any embodiment of the aforementioned temperature control method for an electric vehicle heat pump air conditioner. In view of the time-varying, nonlinear and hysteresis characteristics of the electric vehicle heat pump air conditioner system, a BP neural network is introduced to optimize the PID control parameters output by the PID controller in real time. At the same time, the connection weights of the BP neural network are updated by a genetic algorithm. This can solve the problems of poor adaptability of traditional PID control parameters and difficulty in determining the connection weights of the BP neural network, so that the control effect can be more adaptable to environmental changes, the temperature of the heat pump air conditioner can be more effectively controlled, and the temperature control accuracy can be improved.

[0115] The electric vehicle heat pump air conditioner temperature control method can be implemented in the form of a computer program. The computer program can be used in Figure 5 Runs on the computer device shown.

[0116] See also Figure 5 , Figure 5 5 is a schematic block diagram of a computer device provided by an embodiment of the present invention. The computer device 500 includes a processor 502 , a memory and a network interface 505 connected via a device bus 501 , wherein the memory may include a storage medium 503 and an internal memory 504 .

[0117] The storage medium 503 can store an operating device 5031 and a computer program 5032. When the computer program 5032 is executed, the processor 502 can execute the electric vehicle heat pump air conditioner temperature control method.

[0118] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0119] The internal memory 504 provides an environment for the operation of the computer program 5032 in the storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute the electric vehicle heat pump air conditioning temperature control method.

[0120] The network interface 505 is used for network communication, such as providing data information transmission, etc. Those skilled in the art will understand that Figure 5The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device 500 to which the solution of the present invention is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0121] The processor 502 is used to run the computer program 5032 stored in the memory to implement the electric vehicle heat pump air conditioner temperature control method disclosed in the embodiment of the present invention.

[0122] Those skilled in the art will understand that Figure 5 The embodiments of the computer device shown in the figure do not constitute a limitation on the specific composition of the computer device. In other embodiments, the computer device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. For example, in some embodiments, the computer device may only include a memory and a processor. In such embodiments, the structure and function of the memory and the processor are the same as those of the embodiment of the present invention. Figure 5 The embodiments shown are consistent and will not be described again here.

[0123] It should be understood that in the embodiment of the present invention, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0124] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the electric vehicle heat pump air conditioner temperature control method disclosed in the embodiment of the present invention is implemented.

[0125] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the above-described equipment, devices and units can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. Those of ordinary skill in the art can appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0126] In the several embodiments provided by the present invention, it should be understood that the disclosed equipment, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. Units with the same function may also be combined into one unit. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices or units, or may be an electrical, mechanical or other form of connection.

[0127] 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 units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0128] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0129] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a backend server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), disk or optical disk and other media that can store program codes.

[0130] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for controlling the temperature of an electric vehicle heat pump air conditioner, characterized in that: include: In response to the training instruction, an ideal set temperature and an actual ambient temperature corresponding to the training instruction are obtained, and a BP neural network model is constructed based on a preset initial connection weight set; Obtaining an input parameter set based on the ideal set temperature and the actual ambient temperature, and inputting the input parameter set into the BP neural network model to obtain PID control parameters; The PID control parameters are transmitted to a PID controller, and a compressor in a heat pump air conditioner of an electric vehicle is controlled according to the desired operating parameters output by the PID controller; Acquiring actual operating parameters of the compressor, and inputting the actual operating parameters into a preset heat pump air conditioning model to output a corresponding actual output temperature; If it is determined that the difference between the current system time and the system time corresponding to the training instruction is an integer multiple of the preset cycle length, the target operating parameters and the target output temperature are obtained, and the performance indicator parameters are obtained based on the ideal set temperature, the target output temperature and the target operating parameters; wherein the target operating parameters are the expected operating parameters output by the PID controller at the current system time; the target output temperature is the actual output temperature output by the heat pump air conditioning model at the current system time; If it is determined that the performance indicator parameter does not meet the preset adaptation condition, all connection weights in the BP neural network model are optimized based on a genetic algorithm to obtain a new connection weight set; The BP neural network model is updated using the new connection weight set, the actual ambient temperature is updated using the target output temperature, and the step of returning to the step of obtaining an input parameter set based on the ideal set temperature and the actual ambient temperature, and inputting the input parameter set into the BP neural network model to obtain PID control parameters is performed until the performance indicator parameters meet the adaptation conditions, and an optimal BP neural network model is obtained; If a power-on command is received, the current ambient temperature is obtained in real time, and the temperature of the electric vehicle heat pump air conditioner is controlled accordingly based on the preset user set temperature, the current ambient temperature, the optimal BP neural network model and the PID controller; After obtaining the actual operating parameters of the compressor and inputting the actual operating parameters into a preset heat pump air conditioning model to output a corresponding actual output temperature, the method further includes: If it is determined that the difference between the current system time and the system time corresponding to the power-on instruction is not an integer multiple of the preset cycle length, the actual output temperature is used to update the actual ambient temperature, and the process returns to the step of obtaining an input parameter set based on the ideal set temperature and the actual ambient temperature, and inputting the input parameter set into the BP neural network model to obtain PID control parameters.

2. The electric vehicle heat pump air conditioning temperature control method according to claim 1, characterized in that: The method of controlling the compressor in the electric vehicle heat pump air conditioner according to the desired operating parameters output by the PID controller includes: Obtaining a PWM signal according to the desired operating parameters; The compressor in the electric vehicle heat pump air conditioner is controlled according to the PWM signal.

3. The electric vehicle heat pump air conditioner temperature control method according to claim 2, characterized in that: The obtaining of a PWM signal according to the expected operating parameter comprises: If it is determined that the expected operating parameter is a negative value, obtaining a preset first duty cycle; If it is determined that the expected operating parameter is a positive value, a second duty cycle is calculated according to the expected operating parameter and a preset duty cycle calculation strategy; A corresponding PWM signal is obtained according to the first duty cycle or the second duty cycle.

4. The electric vehicle heat pump air conditioner temperature control method according to claim 3, characterized in that: The formula corresponding to the duty cycle calculation strategy is D = [u d (k) / Umax]×100%; where D is the second duty cycle, u d (k) is the expected operating parameter, and Umax is the preset maximum operating parameter.

5. The electric vehicle heat pump air conditioner temperature control method according to claim 1, characterized in that: The obtaining of the performance indicator parameter based on the ideal set temperature, the target output temperature and the target operating parameter includes: Calculating the difference between the ideal set temperature and the target output temperature to obtain a target temperature difference; Get the preset performance indicator function; The performance indicator parameter is calculated according to the target temperature difference value, the target operating parameter and the performance indicator function.

6. The electric vehicle heat pump air conditioner temperature control method according to claim 5, characterized in that: The formula corresponding to the performance indicator function is J(T m ) = Q × e(T m ) 2 +R×u d (T m ) 2 ; Among them, J(T m ) is the performance index parameter, e(T m ) is the target temperature difference, u d (T m ) is the target operating parameter, Q is the preset first connection weight value, and R is the preset second connection weight value.

7. An electric vehicle heat pump air conditioner temperature control device, used to implement the electric vehicle heat pump air conditioner temperature control method as claimed in claim 1, characterized in that: include: A training instruction response unit, used to respond to the training instruction, obtain the ideal set temperature and the actual ambient temperature corresponding to the training instruction, and construct a BP neural network model based on a preset initial connection weight set; A PID control parameter acquisition unit, used to obtain an input parameter set based on the ideal set temperature and the actual ambient temperature, and input the input parameter set into the BP neural network model to obtain PID control parameters; A compressor control unit, used to transmit the PID control parameters to a PID controller, and control the compressor in the electric vehicle heat pump air conditioner according to the desired operating parameters output by the PID controller; An air conditioning model output unit, used to obtain actual operating parameters of the compressor, and input the actual operating parameters into a preset heat pump air conditioning model to output a corresponding actual output temperature; A performance indicator acquisition unit, for acquiring target operating parameters and target output temperature if it is determined that the difference between the current system time and the system time corresponding to the training instruction is an integer multiple of a preset cycle length, and obtaining performance indicator parameters based on the ideal set temperature, the target output temperature and the target operating parameters; wherein the target operating parameters are the expected operating parameters output by the PID controller at the current system time; and the target output temperature is the actual output temperature output by the heat pump air conditioning model at the current system time; A network model optimization unit, configured to optimize all connection weights in the BP neural network model based on a genetic algorithm to obtain a new connection weight set if it is determined that the performance indicator parameter does not meet a preset adaptation condition; an optimal model determination unit, configured to update the BP neural network model using the new connection weight set, update the actual ambient temperature using the target output temperature, and return to execute the step of obtaining an input parameter set based on the ideal set temperature and the actual ambient temperature, and inputting the input parameter set into the BP neural network model to obtain PID control parameters, until the performance indicator parameters meet the adaptation condition, and an optimal BP neural network model is obtained; The temperature control unit is used to obtain the current ambient temperature in real time if a power-on command is received, and to perform corresponding temperature control on the electric vehicle heat pump air conditioner based on a preset user set temperature, the current ambient temperature, the optimal BP neural network model and the PID controller.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the electric vehicle heat pump air conditioner temperature control method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the electric vehicle heat pump air conditioning temperature control method according to any one of claims 1 to 6.

Images