Intelligent water meter box body temperature self-adaptive dynamic regulation and control method

Abstract

The invention relates to the technical field of temperature regulation and control, and discloses an intelligent water meter box body temperature self-adaptive dynamic regulation and control method which comprises the following steps: monitoring the box body external environment temperature and the box body internal temperature of an intelligent water meter box in real time by using a high-precision temperature sensor; based on the temperature change track sequence, the intelligent water meter box body heating model and the self-learning optimal reward function, a self-adaptive temperature regulation and control strategy structural body is constructed, and parameter optimization is conducted; and self-adaptive temperature regulation and control strategy parameters needing to be adopted at present are obtained through calculation of the self-adaptive temperature regulation and control strategy structural body, and self-adaptive dynamic regulation and control are carried out. According to the method, the self-learning optimal reward function is constructed, evaluation of the battery control parameters selected at the current moment is achieved, the difference value of the internal temperature and the external environment temperature of the box body at the next moment is made to conform to a historical track, and parameter optimization is conducted on the self-adaptive temperature regulation and control strategy structure according to the self-learning optimal reward function at the current moment; and stable temperature regulation and control of the intelligent water meter box are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature adaptive control, and in particular to a method for adaptive dynamic control of the temperature of a smart water meter box. Background Art

[0002] With the widespread application of smart water meters in urban intelligent construction, people have higher and higher requirements for the performance and functions of smart water meters. As an important component of the smart water meter, the stability of the internal temperature of the smart water meter box directly affects the normal operation and life of the smart water meter. The traditional water meter box temperature control method usually adopts a static temperature setting method, which is difficult to adapt to the impact of external environmental temperature changes, resulting in large temperature fluctuations in the box, which can easily cause failure or damage to the smart water meter. In response to this problem, the present invention proposes a smart water meter box temperature adaptive dynamic control method. Through the adaptive dynamic control method, the internal temperature of the water meter box is adjusted in real time according to different external environmental temperature changes, and maintained within a stable range, effectively preventing the influence of excessively high or low temperatures on the smart water meter. Summary of the invention

[0003] In view of this, the present invention provides a method for adaptive dynamic control of the temperature of a smart water meter box, the purpose of which is to: 1) use the smart water meter box heating model to formally describe the electric heat conversion process, convert the adjusted battery control parameters into calorific values, and convert the calorific values ​​into the temperature transformation results of the smart water meter box, and use the trajectory difference between the external ambient temperature of the smart water meter box and the change trajectory sequence corresponding to the internal temperature of the box to construct the self-learning weight for updating the self-learning optimal reward function, select the self-learning weight that best matches the trajectory difference between the internal temperature of the box and the external ambient temperature at the current moment to update the self-learning optimal reward function at the current moment, and construct a reward basis function in combination with the Fourier basis to evaluate the battery control parameters selected at the current moment, where the reward value The higher the value, the more the selected battery control parameters will make the difference between the internal temperature of the box and the external ambient temperature at the next moment more consistent with the historical trajectory; 2) According to the self-learning optimal reward function at the current moment, the disturbance parameters corresponding to different battery control parameters are optimized to achieve disturbance update combined with the difference between the internal temperature of the box and the external ambient temperature trajectory at the current moment, to ensure the stability of the temperature of the smart water meter box before and after regulation. Different battery control parameters have different disturbance parameters, and the disturbance parameters will cause sudden changes in the battery control parameters. The greater the difference between the current temperature and the temperature at the next moment corresponding to the adjustment of the battery control parameters, the more severe the disturbance, which makes the temperature of the smart water meter box after adjusting the battery control parameters too different from the expected temperature, thereby achieving stable temperature regulation of the smart water meter box.

[0004] To achieve the above object, the present invention provides a method for adaptively and dynamically controlling the temperature of a smart water meter housing, comprising the following steps: S1: Constructing a smart water meter box heating model, wherein the smart water meter box heating model takes battery control parameters as variables, formally describes the electric heat conversion process, and outputs the conversion heat values ​​corresponding to different battery control parameters, wherein equivalent circuit modeling is the main implementation method for constructing the smart water meter box heating model; S2: Use high-precision temperature sensors to monitor the external ambient temperature and internal temperature of the smart water meter box in real time, and continuously compare the change trajectory sequences of the two box temperatures, construct a self-learning optimal reward function and perform self-learning updates, among which inverse reinforcement learning is the main implementation method for updating the self-learning optimal reward function; S3: Based on the change trajectory sequence of the two box temperatures, the smart water meter box heating model and the self-learning optimal reward function, an adaptive temperature control strategy structure is constructed, and parameters of the adaptive temperature control strategy structure are optimized according to the self-learning optimal reward function. The adaptive temperature control strategy structure takes the change trajectory sequence of the two box temperatures and the self-learning optimal reward function as input, and takes adaptive temperature control strategy parameters as output, wherein the adaptive temperature control strategy parameters are the battery control parameter control results of the battery in the smart water meter box; S4: The adaptive temperature control strategy structure is used to calculate the adaptive temperature control strategy parameters that need to be adopted at present, and the temperature of the smart water meter box is adaptively and dynamically controlled.

[0005] As a further improvement method of the present invention: Optionally, constructing a smart water meter box heating model in step S1 includes: A smart water meter box heating model is constructed. The smart water meter box heating model uses battery control parameters as variables, formally describes the electric heat conversion process, and outputs the conversion heat values ​​corresponding to different battery control parameters. Equivalent circuit modeling is the main implementation method for constructing the smart water meter box heating model. The constructed smart water meter box heating model is expressed in the form of: ; in: represents the heating model of the smart water meter box, Indicates the battery control parameters of the smart water meter box heating model, corresponding to the current value inside the battery, Indicates the battery control parameters of the battery in the smart water meter box Controlled conversion calorific value; Indicates the ohmic internal resistance of the battery. Indicates the polarization internal resistance of the battery; Indicates the temperature of the battery; in the embodiment of the present invention, set is 15 degrees Celsius; It represents the thermal entropy coefficient, which indicates the voltage change inside the battery for every unit increase in battery temperature.

[0006] Optionally, in step S2, a high-precision temperature sensor is used to monitor the external ambient temperature and the internal temperature of the smart water meter box in real time, and the change trajectory sequence of the two box temperatures is continuously compared, including: The high-precision temperature sensor is used to monitor the external ambient temperature and internal temperature of the smart water meter box in real time. The external ambient temperature of the box monitored by the high-precision temperature sensor at the current time t is The internal temperature of the box is ; The change trajectory sequences of the external ambient temperature and the internal temperature of the box at the current time t are: ; ; in: represents the change trajectory sequence of the external ambient temperature of the box at the current time t, Indicates time The monitored external ambient temperature of the box is always It represents a historical moment with n time intervals from the current moment t, where the duration of each time interval is , N represents the number of historical trajectory points in the change trajectory sequence; in the embodiment of the present invention, N is set to 15; represents the change trajectory sequence of the ambient temperature inside the box at the current time t, Indicates time The monitored ambient temperature inside the box; According to the change trajectory sequence of the external ambient temperature of the box and the internal temperature of the box at the current time t, the self-learning optimal reward function at the current time t is constructed and self-learning updates are performed.

[0007] Optionally, constructing a self-learning optimal reward function and performing self-learning update includes: Construct the self-learning optimal reward function at the current time t and perform self-learning update. The construction of the self-learning optimal reward function and the self-learning update process are: S21: Constructing reward basis function , where the input of the reward basis function is the change trajectory sequence of the external ambient temperature and the internal temperature of the box, and the output is the impact of the change trajectory sequence on the smart water meter box. Taking the change trajectory sequence of the external ambient temperature and the internal temperature of the box at the current time t as input, the reward basis function The output is: ; in: It means that the reward basis function takes the change trajectory sequence of the external ambient temperature and the internal temperature of the box at the current time t as input. The output result of represents the preset minimum reward basis function value, Indicates the preset minimum temperature threshold inside the smart water meter box. The preset maximum temperature threshold inside the smart water meter box; S22: construct a self-learning weight, and perform self-learning update on the self-learning weight, wherein the update formula of the self-learning weight is: ; in: Represents the self-learning weight at the current time t; represents an exponential function with a natural constant as base; represents the L1 norm; S23: Construct the self-learning optimal reward function at the current time t , where the input of the self-learning optimal reward function is the change trajectory sequence of the external ambient temperature and the internal temperature of the box. Taking the change trajectory sequence of the external ambient temperature and the internal temperature of the box at the current time t as input, the output result of the self-learning optimal reward function at the current time t is .

[0008] Optionally, in step S3, an adaptive temperature control strategy structure is constructed based on the change trajectory sequence of the two box temperatures, the smart water meter box heating model, and the self-learning optimal reward function, including: An adaptive temperature control strategy structure is constructed based on the change trajectory sequence of the two box temperatures, the smart water meter box heating model and the self-learning optimal reward function. The adaptive temperature control strategy structure takes the change trajectory sequence of the two box temperatures and the self-learning optimal reward function as input, and takes the adaptive temperature control strategy parameters calculated in combination with the smart water meter box heating model as output, wherein the adaptive temperature control strategy parameters are the battery control parameter control results of the battery in the smart water meter box; The adaptive temperature control strategy structure includes a self-learning training module, an external environment temperature prediction module, a control parameter selection module and an output module; The self-learning training module is used to receive the self-learning optimal reward function at the current moment obtained by self-learning update, and optimize the parameters in the adaptive temperature control strategy structure; The external environment temperature prediction module is used to receive the current moment external environment temperature change trajectory sequence of the box, predict the external environment temperature of the box at the next moment, and form the external environment temperature change trajectory sequence of the box at the next moment; The control parameter selection module is used to select the adaptive temperature control strategy parameters from the control parameter space so that the self-learning optimal reward function value corresponding to the two box temperature change trajectory sequences at the next moment after control reaches the maximum; The output module is used to output the selected adaptive temperature control strategy parameters; The self-learning training module optimizes the parameters of the adaptive temperature control strategy structure according to the self-learning optimal reward function at the current time t.

[0009] Optionally, the self-learning training module optimizes parameters of the adaptive temperature control strategy structure according to the self-learning optimal reward function at the current time t, including: The self-learning training module optimizes the parameters of the adaptive temperature control strategy structure according to the self-learning optimal reward function at the current time t, where the parameter optimization process is as follows: S31: Obtaining the control parameter space , where the control parameter space There are M kinds of battery control parameters. Represents the control parameter space The mth battery control parameter in; S32: Obtaining the optimized parameters at time t-1 : ; in: Indicates the mth battery control parameter The corresponding disturbance parameter; S33: Receive the temperature change trajectory sequence of the outside and inside of the box at the current time t , set the current iteration step of the change trajectory sequence to j, the maximum iteration step to J, and the initial value of j to 1; S34: Using the external environment temperature prediction module to predict the change trajectory sequence of the external environment temperature of the box at the current time t Perform the j-th step prediction to obtain the external ambient temperature of the box at time t+j , and the changing trajectory sequence of the external ambient temperature of the box at time t+j ; S35: From the control parameter space Select the battery control parameters as the adaptive temperature control strategy parameters at time t+j : ; ; ; in: represents the specific heat capacity of water, and V represents the mass of water in the smart water meter box; Indicates battery control parameters The corresponding conversion calorific value, represents the heating model of the smart water meter box, represents any battery control parameter in the regulation parameter space; Indicates battery control parameters The corresponding disturbance parameters; Indicates that battery control parameters are used As the battery control parameter of the smart water meter box at time t+j, the internal temperature of the smart water meter box at time t+j, Indicates battery-based control parameters The changing trajectory sequence of the internal temperature of the box at time t+j; Constitute the temperature variation sequence of the internal temperature of the box at time t+j; S36: Order , return to step S34 until a sequence of change trajectories of the external ambient temperature of the box and the internal temperature of the box from time t+1 to time t+J is obtained; S37: Construct a reward value function, wherein the input of the reward value function is the output result of the self-learning reward function at different times, the selected adaptive temperature control strategy parameters, and the disturbance parameters corresponding to the adaptive temperature control strategy parameters, and the output is the reward value of the selected adaptive temperature control strategy parameters for the stable temperature of the smart water meter box; S38: Optimize the parameters of the adaptive temperature control strategy structure based on the reward value function: ; ; in: Represents the learning rate parameter, Set to 0.02; represents the discount factor; It represents the sum of the self-learning optimal reward function values ​​of the change trajectory sequence of the J-step prediction of the external ambient temperature of the box and the internal temperature of the box at the current time t, Represents the self-learning optimal reward function value of the change trajectory sequence predicted in the jth step; Represents the adaptive temperature control strategy parameters at time t+j The corresponding disturbance parameter; S39: Using parameters to optimize results Construct the adaptive temperature control strategy structure at the current time t.

[0010] Optionally, in the step S34, the external environment temperature prediction module is used to predict the change trajectory sequence of the external environment temperature of the box at the current time t Make the j-th step prediction, including: S341: Obtain the change trajectory sequence of the external ambient temperature of the cabinet predicted in step j-1 ; In the embodiment of the present invention, the change trajectory sequence predicted in step j is composed of the real temperature and the predicted temperature; S342: Calculate the change trajectory sequence The mean , and calculate the change trajectory sequence The H-order covariance and autocorrelation function of , where the h-order covariance and autocorrelation function are: ; ; in: Represents a sequence of changing trajectories The h-th order covariance function of Represents a sequence of changing trajectories The h-th order autocorrelation function of <N-1; S343: Generate a change trajectory sequence Prediction parameters: ; in: The change trajectory sequence The p-order prediction parameter, ; S344: Predicting the ambient temperature outside the cabinet at time t+j based on the prediction parameters, wherein the prediction formula is: ; And based on the external ambient temperature of the box at time t+j, a change trajectory sequence of the external ambient temperature of the box at time t+j is constructed .

[0011] Optionally, in step S4, the adaptive temperature control strategy structure is used to calculate the adaptive temperature control strategy parameters that need to be currently adopted, and adaptive dynamic control is performed, including: The adaptive temperature control strategy structure obtained by parameter optimization in step S3 is used to calculate the adaptive temperature control strategy parameters that need to be taken at present, and the adaptive temperature control strategy parameters are used to adjust the conversion heat of the battery in the smart water meter box, and the temperature of the smart water meter box is adaptively and dynamically controlled. The selection process of the adaptive temperature control strategy parameters is as follows: S41: The external environment temperature prediction module receives the current external environment temperature change trajectory sequence of the cabinet , predict the external ambient temperature of the box at the next moment , forming a sequence of changes in the ambient temperature outside the box at the next moment In the embodiment of the present invention, the temperature change trajectory sequence of the external environment of the box The prediction process is consistent with step S342 to step S344; S42: The control parameter selection module selects the adaptive temperature control strategy parameters from the control parameter space : ; ; ; in: represents the specific heat capacity of water, and V represents the mass of water in the smart water meter box; Indicates the conversion heat value corresponding to the battery control parameter a, represents the intelligent water meter box heating model, a is any battery control parameter in the control parameter space; Represents the disturbance parameter corresponding to the battery control parameter a in the current adaptive temperature control strategy structure; Indicates that the battery control parameter a is used as the battery control parameter of the smart water meter box at time t+1, and the internal temperature of the smart water meter box at time t+1, It represents the change trajectory sequence of the internal temperature of the box at time t+1 based on the battery control parameter a; S43: The output module outputs the selected adaptive temperature control strategy parameters .

[0012] In order to solve the above problem, the present invention provides an electronic device, the electronic device comprising: A memory storing at least one instruction; Communication interface, enabling electronic equipment to communicate; and The processor executes the instructions stored in the memory to implement the above-mentioned method for adaptively controlling the temperature of the smart water meter box.

[0013] In order to solve the above problem, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned smart water meter box temperature adaptive dynamic control method.

[0014] Compared with the prior art, the present invention proposes a method for adaptively controlling the temperature of a smart water meter housing, which has the following advantages: First, this scheme proposes a temperature-controlled reward function and a self-learning update method to construct the self-learning optimal reward function at the current time t and perform self-learning update. The construction and self-learning update process of the self-learning optimal reward function are as follows: Construct the reward basis function , where the input of the reward basis function is the change trajectory sequence of the external ambient temperature and the internal temperature of the box, and the output is the impact of the change trajectory sequence on the smart water meter box. Taking the change trajectory sequence of the external ambient temperature and the internal temperature of the box at the current time t as input, the reward basis function The output is: ; in: It means that the reward basis function takes the change trajectory sequence of the external ambient temperature and the internal temperature of the box at the current time t as input. The output result of represents the preset minimum reward basis function value, Indicates the preset minimum temperature threshold inside the smart water meter box. The maximum temperature threshold inside the preset smart water meter box is set; a self-learning weight is constructed, and the self-learning weight is updated by self-learning, wherein the update formula of the self-learning weight is: ; in: Represents the self-learning weight at the current time t; represents an exponential function with a natural constant as base; Represents the L1 norm; constitutes the self-learning optimal reward function at the current time t , where the input of the self-learning optimal reward function is the change trajectory sequence of the external ambient temperature and the internal temperature of the box. Taking the change trajectory sequence of the external ambient temperature and the internal temperature of the box at the current time t as input, the output result of the self-learning optimal reward function at the current time t is . This scheme uses the smart water meter box heating model to formally describe the electrothermal conversion process, converts the adjusted battery control parameters into calorific values, and converts the calorific values ​​into the temperature transformation results of the smart water meter box. The trajectory difference between the external ambient temperature of the smart water meter box and the internal temperature of the box is used to construct the self-learning weights for updating the self-learning optimal reward function. The self-learning weights that best match the current moment's internal temperature and external ambient temperature trajectory difference are selected to update the current moment's self-learning optimal reward function, and the reward basis function is constructed in combination with the Fourier basis to evaluate the battery control parameters selected at the current moment. The higher the reward value, the more the selected battery control parameters will make the difference between the internal temperature of the box and the external ambient temperature at the next moment more consistent with the historical trajectory.

[0015] At the same time, this scheme proposes an adaptive temperature control method, which uses the adaptive temperature control strategy structure obtained by parameter optimization to calculate the adaptive temperature control strategy parameters that need to be taken at present, and uses the adaptive temperature control strategy parameters to adjust the conversion heat of the battery in the smart water meter box, and adaptively and dynamically control the temperature of the smart water meter box. The selection process of the adaptive temperature control strategy parameters is as follows: the external environment temperature prediction module receives the current box external environment temperature change trajectory sequence , predict the external ambient temperature of the box at the next moment , forming a sequence of changes in the ambient temperature outside the box at the next moment ; The control parameter selection module selects the adaptive temperature control strategy parameters from the control parameter space : ; ; ; in: represents the specific heat capacity of water, and V represents the mass of water in the smart water meter box; Indicates the conversion heat value corresponding to the battery control parameter a, represents the intelligent water meter box heating model, a is any battery control parameter in the control parameter space; Represents the disturbance parameter corresponding to the battery control parameter a in the current adaptive temperature control strategy structure; Indicates that the battery control parameter a is used as the battery control parameter of the smart water meter box at time t+1, and the internal temperature of the smart water meter box at time t+1, Represents the change trajectory sequence of the internal temperature of the box at time t+1 based on the battery control parameter a; the output module outputs the adaptive temperature control strategy parameters screened . According to the self-learning optimal reward function at the current moment, the disturbance parameters corresponding to different battery control parameters are optimized to achieve disturbance update combined with the difference between the internal temperature of the box and the external ambient temperature trajectory at the current moment, ensuring the stability of the temperature of the smart water meter box before and after regulation. Different battery control parameters have different disturbance parameters, and the disturbance parameters will cause sudden changes in the battery control parameters. The greater the difference between the current temperature and the temperature at the next moment corresponding to the adjustment of the battery control parameters, the more severe the disturbance, which makes the temperature of the smart water meter box after adjusting the battery control parameters too different from the expected temperature, and realizes stable temperature regulation of the smart water meter box. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of a flow chart of a method for adaptively and dynamically controlling the temperature of a smart water meter box provided by an embodiment of the present invention; Figure 2 A schematic diagram of the structure of an electronic device for implementing a method for adaptively dynamic temperature control of a smart water meter housing provided by an embodiment of the present invention.

[0017] In the figure: 1 electronic device, 10 processor, 11 memory, 12 program, 13 communication interface.

[0018] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0019] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0020] The embodiment of the present application provides a method for adaptively controlling the temperature of a smart water meter housing. The execution subject of the method for adaptively controlling the temperature of a smart water meter housing includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for adaptively controlling the temperature of a smart water meter housing can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0021] Embodiment 1: S1: Construct a smart water meter box heating model, which uses battery control parameters as variables, formally describes the electric heat conversion process, and outputs the conversion heat value corresponding to different battery control parameters.

[0022] The smart water meter box heating model is constructed in step S1, including: A smart water meter box heating model is constructed. The smart water meter box heating model uses battery control parameters as variables, formally describes the electric heat conversion process, and outputs the conversion heat values ​​corresponding to different battery control parameters. Equivalent circuit modeling is the main implementation method for constructing the smart water meter box heating model. The constructed smart water meter box heating model is expressed in the form of: ; in: represents the heating model of the smart water meter box, Indicates the battery control parameters of the smart water meter box heating model, corresponding to the current value inside the battery, Indicates the battery control parameters of the battery in the smart water meter box Controlled conversion calorific value; Indicates the ohmic internal resistance of the battery. Indicates the polarization internal resistance of the battery; Indicates the temperature of the battery; in the embodiment of the present invention, set is 15 degrees Celsius; It represents the thermal entropy coefficient, which indicates the voltage change inside the battery for every unit increase in battery temperature.

[0023] S2: Use high-precision temperature sensors to monitor the external ambient temperature and internal temperature of the smart water meter box in real time, and continuously compare the change trajectory sequences of the two box temperatures to construct a self-learning optimal reward function and perform self-learning updates.

[0024] In step S2, a high-precision temperature sensor is used to monitor the external ambient temperature and the internal temperature of the smart water meter box in real time, and the change trajectory sequence of the two box temperatures is continuously compared, including: The high-precision temperature sensor is used to monitor the external ambient temperature and internal temperature of the smart water meter box in real time. The external ambient temperature of the box monitored by the high-precision temperature sensor at the current time t is The internal temperature of the box is ; The change trajectory sequences of the external ambient temperature and the internal temperature of the box at the current time t are: ; ; in: represents the change trajectory sequence of the external ambient temperature of the box at the current time t, Indicates time The monitored external ambient temperature of the box is always It represents a historical moment with n time intervals from the current moment t, where the duration of each time interval is , N represents the number of historical trajectory points in the change trajectory sequence; in the embodiment of the present invention, N is set to 15; represents the change trajectory sequence of the ambient temperature inside the box at the current time t, Indicates time The monitored ambient temperature inside the box; According to the change trajectory sequence of the external ambient temperature of the box and the internal temperature of the box at the current time t, the self-learning optimal reward function at the current time t is constructed and self-learning updates are performed.

[0025] The self-learning optimal reward function at the current time t is constructed and self-learning updated, wherein the construction of the self-learning optimal reward function and the self-learning update process are: S21: Constructing reward basis function , where the input of the reward basis function is the change trajectory sequence of the external ambient temperature and the internal temperature of the box, and the output is the impact of the change trajectory sequence on the smart water meter box. Taking the change trajectory sequence of the external ambient temperature and the internal temperature of the box at the current time t as input, the reward basis function The output is: ; in: It means that the reward basis function takes the change trajectory sequence of the external ambient temperature and the internal temperature of the box at the current time t as input. The output result of represents the preset minimum reward basis function value, Indicates the preset minimum temperature threshold inside the smart water meter box. The preset maximum temperature threshold inside the smart water meter box; S22: construct a self-learning weight, and perform self-learning update on the self-learning weight, wherein the update formula of the self-learning weight is: ; in: Represents the self-learning weight at the current time t; represents an exponential function with a natural constant as base; represents the L1 norm; S23: Construct the self-learning optimal reward function at the current time t , where the input of the self-learning optimal reward function is the change trajectory sequence of the external ambient temperature and the internal temperature of the box. Taking the change trajectory sequence of the external ambient temperature and the internal temperature of the box at the current time t as input, the output result of the self-learning optimal reward function at the current time t is .

[0026] S3: Based on the change trajectory sequence of the two box temperatures, the smart water meter box heating model and the self-learning optimal reward function, an adaptive temperature control strategy structure is constructed, and the parameters of the adaptive temperature control strategy structure are optimized according to the self-learning optimal reward function.

[0027] In the step S3, an adaptive temperature control strategy structure is constructed based on the change trajectory sequence of the two box temperatures, the smart water meter box heating model and the self-learning optimal reward function, including: An adaptive temperature control strategy structure is constructed based on the change trajectory sequence of the two box temperatures, the smart water meter box heating model and the self-learning optimal reward function. The adaptive temperature control strategy structure takes the change trajectory sequence of the two box temperatures and the self-learning optimal reward function as input, and takes the adaptive temperature control strategy parameters calculated in combination with the smart water meter box heating model as output, wherein the adaptive temperature control strategy parameters are the battery control parameter control results of the battery in the smart water meter box; The adaptive temperature control strategy structure includes a self-learning training module, an external environment temperature prediction module, a control parameter selection module and an output module; The self-learning training module is used to receive the self-learning optimal reward function at the current moment obtained by self-learning update, and optimize the parameters in the adaptive temperature control strategy structure; The external environment temperature prediction module is used to receive the current moment external environment temperature change trajectory sequence of the box, predict the external environment temperature of the box at the next moment, and form the external environment temperature change trajectory sequence of the box at the next moment; The control parameter selection module is used to select the adaptive temperature control strategy parameters from the control parameter space so that the self-learning optimal reward function value corresponding to the two box temperature change trajectory sequences at the next moment after control reaches the maximum; The output module is used to output the selected adaptive temperature control strategy parameters; The self-learning training module optimizes the parameters of the adaptive temperature control strategy structure according to the self-learning optimal reward function at the current time t.

[0028] The self-learning training module optimizes the parameters of the adaptive temperature control strategy structure according to the self-learning optimal reward function at the current time t, including: The self-learning training module optimizes the parameters of the adaptive temperature control strategy structure according to the self-learning optimal reward function at the current time t, where the parameter optimization process is as follows: S31: Obtaining the control parameter space , where the control parameter space There are M kinds of battery control parameters. Represents the control parameter space The mth battery control parameter in; S32: Obtaining the optimized parameters at time t-1 : ; in: Indicates the mth battery control parameter The corresponding disturbance parameter; S33: Receive the temperature change trajectory sequence of the outside and inside of the box at the current time t , set the current iteration step of the change trajectory sequence to j, the maximum iteration step to J, and the initial value of j to 1; S34: Using the external environment temperature prediction module to predict the change trajectory sequence of the external environment temperature of the box at the current time t Perform the j-th step prediction to obtain the external ambient temperature of the box at time t+j , and the changing trajectory sequence of the external ambient temperature of the box at time t+j ; S35: From the control parameter space Select the battery control parameters as the adaptive temperature control strategy parameters at time t+j : ; ; ; in: represents the specific heat capacity of water, and V represents the mass of water in the smart water meter box; Indicates battery control parameters The corresponding conversion calorific value, represents the heating model of the smart water meter box, represents any battery control parameter in the regulation parameter space; Indicates battery control parameters The corresponding disturbance parameters; Indicates that battery control parameters are used As the battery control parameter of the smart water meter box at time t+j, the internal temperature of the smart water meter box at time t+j, Indicates battery-based control parameters The changing trajectory sequence of the internal temperature of the box at time t+j; Constitute the temperature variation sequence of the internal temperature of the box at time t+j; S36: Order , return to step S34 until a sequence of change trajectories of the external ambient temperature of the box and the internal temperature of the box from time t+1 to time t+J is obtained; S37: Construct a reward value function, wherein the input of the reward value function is the output result of the self-learning reward function at different times, the selected adaptive temperature control strategy parameters, and the disturbance parameters corresponding to the adaptive temperature control strategy parameters, and the output is the reward value of the selected adaptive temperature control strategy parameters for the stable temperature of the smart water meter box; S38: Optimize the parameters of the adaptive temperature control strategy structure based on the reward value function: ; ; in: Represents the learning rate parameter, Set to 0.02; represents the discount factor; It represents the sum of the self-learning optimal reward function values ​​of the change trajectory sequence of the J-step prediction of the external ambient temperature of the box and the internal temperature of the box at the current time t, Represents the self-learning optimal reward function value of the change trajectory sequence predicted in the jth step; Represents the adaptive temperature control strategy parameters at time t+j The corresponding disturbance parameter; S39: Using parameters to optimize results Construct the adaptive temperature control strategy structure at the current time t.

[0029] In the step S34, the external environment temperature prediction module is used to predict the change trajectory sequence of the external environment temperature of the box at the current time t Make the j-th step prediction, including: S341: Obtain the change trajectory sequence of the external ambient temperature of the cabinet predicted in step j-1 ; In the embodiment of the present invention, the change trajectory sequence predicted in step j is composed of the real temperature and the predicted temperature; S342: Calculate the change trajectory sequence The mean , and calculate the change trajectory sequence The H-order covariance and autocorrelation function of , where the h-order covariance and autocorrelation function are: ; ; in: Represents a sequence of changing trajectories The h-th order covariance function of Represents a sequence of changing trajectories The h-th order autocorrelation function of <N-1; S343: Generate a change trajectory sequence Prediction parameters: ; in: The change trajectory sequence The p-order prediction parameter, ; S344: Predicting the ambient temperature outside the cabinet at time t+j based on the prediction parameters, wherein the prediction formula is: ; And based on the external ambient temperature of the box at time t+j, a change trajectory sequence of the external ambient temperature of the box at time t+j is constructed .

[0030] S4: The adaptive temperature control strategy structure is used to calculate the adaptive temperature control strategy parameters that need to be adopted at present, and the temperature of the smart water meter box is adaptively and dynamically controlled.

[0031] In the step S4, the adaptive temperature control strategy structure is used to calculate the adaptive temperature control strategy parameters that need to be currently adopted, and adaptive dynamic control is performed, including: The adaptive temperature control strategy structure obtained by parameter optimization in step S3 is used to calculate the adaptive temperature control strategy parameters that need to be taken at present, and the adaptive temperature control strategy parameters are used to adjust the conversion heat of the battery in the smart water meter box, and the temperature of the smart water meter box is adaptively and dynamically controlled. The selection process of the adaptive temperature control strategy parameters is as follows: S41: The external environment temperature prediction module receives the current external environment temperature change trajectory sequence of the cabinet , predict the external ambient temperature of the box at the next moment , forming a sequence of changes in the ambient temperature outside the box at the next moment In the embodiment of the present invention, the temperature change trajectory sequence of the external environment of the box The prediction process is consistent with step S342 to step S344; S42: The control parameter selection module selects the adaptive temperature control strategy parameters from the control parameter space : ; ; ; in: represents the specific heat capacity of water, and V represents the mass of water in the smart water meter box; Indicates the conversion heat value corresponding to the battery control parameter a, represents the intelligent water meter box heating model, a is any battery control parameter in the control parameter space; Represents the disturbance parameter corresponding to the battery control parameter a in the current adaptive temperature control strategy structure; Indicates that the battery control parameter a is used as the battery control parameter of the smart water meter box at time t+1, and the internal temperature of the smart water meter box at time t+1, It represents the change trajectory sequence of the internal temperature of the box at time t+1 based on the battery control parameter a; S43: The output module outputs the selected adaptive temperature control strategy parameters .

[0032] Embodiment 2: like Figure 2 , which is a schematic diagram of the structure of an electronic device for implementing a method for adaptively dynamic temperature control of a smart water meter housing provided by an embodiment of the present invention.

[0033] The electronic device 1 may include a processor 10 , a memory 11 , a communication interface 13 and a bus, and may also include a computer program stored in the memory 11 and executable on the processor 10 , such as a program 12 .

[0034] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), etc. equipped on the electronic device 1. Further, the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 11 may not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the program 12, etc., but also be used to temporarily store data that has been output or is to be output.

[0035] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (such as the program 12 for realizing the adaptive dynamic control of the temperature of the intelligent water meter box), and calls the data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0036] The communication interface 13 may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices, and to achieve connection and communication between internal components of the electronic device.

[0037] The bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0038] Figure 2 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 2 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0039] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0040] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0041] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0042] The program 12 stored in the memory 11 in the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve: Construct a smart water meter box heating model; Use high-precision temperature sensors to monitor the external ambient temperature and internal temperature of the smart water meter box in real time, and continuously compare the change trajectory sequences of the two box temperatures to construct a self-learning optimal reward function and perform self-learning updates; Based on the change trajectory sequence of the two box temperatures, the smart water meter box heating model and the self-learning optimal reward function, an adaptive temperature control strategy structure is constructed, and the parameters of the adaptive temperature control strategy structure are optimized according to the self-learning optimal reward function. The adaptive temperature control strategy structure is used to calculate the adaptive temperature control strategy parameters that need to be taken at present, and the temperature of the smart water meter box is adaptively and dynamically controlled.

[0043] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figure 1 to Figure 2 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0044] It should be noted that the serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. And the terms "including", "comprising" or any other variants thereof in this article are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "including a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0045] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0046] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for adaptive dynamic control of the temperature of a smart water meter box, characterized in that: The method comprises: S1: constructing a smart water meter box heating model, wherein the smart water meter box heating model takes the battery control parameters as variables, formally describes the electric heat conversion process, and outputs the conversion heat values ​​corresponding to different battery control parameters; S2: Use a high-precision temperature sensor to monitor the external ambient temperature and internal temperature of the smart water meter box in real time, and continuously compare the change trajectory sequences of the two box temperatures to construct a self-learning optimal reward function and perform self-learning updates; S3: Based on the change trajectory sequence of the two box temperatures, the smart water meter box heating model and the self-learning optimal reward function, an adaptive temperature control strategy structure is constructed, and parameters of the adaptive temperature control strategy structure are optimized according to the self-learning optimal reward function. The adaptive temperature control strategy structure takes the change trajectory sequence of the two box temperatures and the self-learning optimal reward function as input, and takes adaptive temperature control strategy parameters as output, wherein the adaptive temperature control strategy parameters are the battery control parameter control results of the battery in the smart water meter box; S4: The adaptive temperature control strategy structure is used to calculate the adaptive temperature control strategy parameters that need to be adopted at present, and the temperature of the smart water meter box is adaptively and dynamically controlled.

2. A method for adaptively controlling the temperature of a smart water meter housing as claimed in claim 1, characterized in that: The smart water meter box heating model is constructed in step S1, including: A smart water meter box heating model is constructed. The smart water meter box heating model uses the battery control parameters as variables, formally describes the electric heat conversion process, and outputs the conversion heat values ​​corresponding to different battery control parameters. The constructed smart water meter box heating model is expressed as: ； in: represents the heating model of the smart water meter box, Indicates the battery control parameters of the smart water meter box heating model, corresponding to the current value inside the battery, Indicates the battery control parameters of the battery in the smart water meter box Controlled conversion calorific value; Indicates the ohmic internal resistance of the battery. Indicates the polarization internal resistance of the battery; Indicates the temperature of the battery; It represents the thermal entropy coefficient, which indicates the voltage change inside the battery for every unit increase in battery temperature.

3. The method for adaptively controlling the temperature of a smart water meter housing according to claim 1, characterized in that: In step S2, a high-precision temperature sensor is used to monitor the external ambient temperature and the internal temperature of the smart water meter box in real time, and the change trajectory sequence of the two box temperatures is continuously compared, including: The high-precision temperature sensor is used to monitor the external ambient temperature and internal temperature of the smart water meter box in real time. The external ambient temperature of the box monitored by the high-precision temperature sensor at the current time t is The internal temperature of the box is ; The change trajectory sequences of the external ambient temperature and the internal temperature of the box at the current time t are: ； ； in: represents the change trajectory sequence of the external ambient temperature of the box at the current time t, Indicates time The monitored external ambient temperature of the box is always It represents a historical moment with n time intervals from the current moment t, where the duration of each time interval is , N represents the number of historical trajectory points in the change trajectory sequence; represents the change trajectory sequence of the ambient temperature inside the box at the current time t, Indicates time The monitored ambient temperature inside the box; According to the change trajectory sequence of the external ambient temperature of the box and the internal temperature of the box at the current time t, the self-learning optimal reward function at the current time t is constructed and self-learning updates are performed.

4. A method for adaptively controlling the temperature of a smart water meter housing as claimed in claim 3, characterized in that: The self-learning optimal reward function is constructed and self-learning updates are performed, including: Construct the self-learning optimal reward function at the current time t and perform self-learning update. The construction of the self-learning optimal reward function and the self-learning update process are: S21: Constructing reward basis function , where the input of the reward basis function is the change trajectory sequence of the external ambient temperature and the internal temperature of the box, and the output is the impact of the change trajectory sequence on the smart water meter box. Taking the change trajectory sequence of the external ambient temperature and the internal temperature of the box at the current time t as input, the reward basis function The output is: ； in: It means that the reward basis function takes the change trajectory sequence of the external ambient temperature and the internal temperature of the box at the current time t as input. The output result of represents the preset minimum reward basis function value, Indicates the preset minimum temperature threshold inside the smart water meter box. The preset maximum temperature threshold inside the smart water meter box; S22: construct a self-learning weight, and perform self-learning update on the self-learning weight, wherein the update formula of the self-learning weight is: ； in: Represents the self-learning weight at the current time t; represents an exponential function with a natural constant as base; represents the L1 norm; S23: Construct the self-learning optimal reward function at the current time t , where the input of the self-learning optimal reward function is the change trajectory sequence of the external ambient temperature and the internal temperature of the box. Taking the change trajectory sequence of the external ambient temperature and the internal temperature of the box at the current time t as input, the output result of the self-learning optimal reward function at the current time t is .

5. The method for adaptively controlling the temperature of a smart water meter housing according to claim 1, characterized in that: In the step S3, an adaptive temperature control strategy structure is constructed based on the change trajectory sequence of the two box temperatures, the smart water meter box heating model and the self-learning optimal reward function, including: An adaptive temperature control strategy structure is constructed based on the change trajectory sequence of the two box temperatures, the smart water meter box heating model and the self-learning optimal reward function. The adaptive temperature control strategy structure takes the change trajectory sequence of the two box temperatures and the self-learning optimal reward function as input, and takes the adaptive temperature control strategy parameters calculated in combination with the smart water meter box heating model as output, wherein the adaptive temperature control strategy parameters are the battery control parameter control results of the battery in the smart water meter box; The adaptive temperature control strategy structure includes a self-learning training module, an external environment temperature prediction module, a control parameter selection module and an output module; The self-learning training module is used to receive the self-learning optimal reward function at the current moment obtained by self-learning update, and optimize the parameters in the adaptive temperature control strategy structure; The external environment temperature prediction module is used to receive the current moment external environment temperature change trajectory sequence of the box, predict the external environment temperature of the box at the next moment, and form the external environment temperature change trajectory sequence of the box at the next moment; The control parameter selection module is used to select the adaptive temperature control strategy parameters from the control parameter space so that the self-learning optimal reward function value corresponding to the two box temperature change trajectory sequences at the next moment after control reaches the maximum; The output module is used to output the selected adaptive temperature control strategy parameters; The self-learning training module optimizes the parameters of the adaptive temperature control strategy structure according to the self-learning optimal reward function at the current time t.

6. A method for adaptively controlling the temperature of a smart water meter housing as claimed in claim 5, characterized in that: The self-learning training module optimizes the parameters of the adaptive temperature control strategy structure according to the self-learning optimal reward function at the current time t, including: The self-learning training module optimizes the parameters of the adaptive temperature control strategy structure according to the self-learning optimal reward function at the current time t, where the parameter optimization process is as follows: S31: Obtaining the control parameter space , where the control parameter space There are M kinds of battery control parameters. Represents the control parameter space The mth battery control parameter in; S32: Obtaining the optimized parameters at time t-1 : ； in: Indicates the mth battery control parameter The corresponding disturbance parameter; S33: Receive the temperature change trajectory sequence of the outside and inside of the box at the current time t , set the current iteration step of the change trajectory sequence to j, the maximum iteration step to J, and the initial value of j to 1; S34: Using the external environment temperature prediction module to predict the change trajectory sequence of the external environment temperature of the box at the current time t Perform the j-th step prediction to obtain the external ambient temperature of the box at time t+j , and the changing trajectory sequence of the external ambient temperature of the box at time t+j ; S35: From the control parameter space Select the battery control parameters as the adaptive temperature control strategy parameters at time t+j : ； ； ； in: represents the specific heat capacity of water, and V represents the mass of water in the smart water meter box; Indicates battery control parameters The corresponding conversion calorific value, represents the heating model of the smart water meter box, represents any battery control parameter in the regulation parameter space; Indicates battery control parameters The corresponding disturbance parameters; Indicates that battery control parameters are used As the battery control parameter of the smart water meter box at time t+j, the internal temperature of the smart water meter box at time t+j, Indicates battery-based control parameters The changing trajectory sequence of the internal temperature of the box at time t+j; The temperature variation sequence of the internal temperature of the box at time t+j is formed; S36: Order , return to step S34 until a sequence of change trajectories of the external ambient temperature of the box and the internal temperature of the box from time t+1 to time t+J is obtained; S37: Construct a reward value function, wherein the input of the reward value function is the output result of the self-learning reward function at different times, the selected adaptive temperature control strategy parameters, and the disturbance parameters corresponding to the adaptive temperature control strategy parameters, and the output is the reward value of the selected adaptive temperature control strategy parameters for the stable temperature of the smart water meter box; S38: Optimize the parameters of the adaptive temperature control strategy structure based on the reward value function: ; ; in: Represents the learning rate parameter, Set to 0.02; represents the discount factor; It represents the sum of the self-learning optimal reward function values ​​of the change trajectory sequence of the J-step prediction of the external ambient temperature of the box and the internal temperature of the box at the current time t, Represents the self-learning optimal reward function value of the change trajectory sequence predicted in the jth step; Represents the adaptive temperature control strategy parameters at time t+j The corresponding disturbance parameter; S39: Using parameters to optimize results Construct the adaptive temperature control strategy structure at the current time t.

7. A method for adaptively controlling the temperature of a smart water meter housing as claimed in claim 6, characterized in that: In the step S34, the external environment temperature prediction module is used to predict the change trajectory sequence of the external environment temperature of the box at the current time t Make the j-th step prediction, including: S341: Obtain the change trajectory sequence of the external ambient temperature of the cabinet predicted in step j-1 ; S342: Calculate the change trajectory sequence The mean , and calculate the change trajectory sequence The H-order covariance and autocorrelation function of , where the h-order covariance and autocorrelation function are: ； ； in: Represents a sequence of changing trajectories The h-th order covariance function of Represents a sequence of changing trajectories The h-th order autocorrelation function of <N-1; S343: Generate a change trajectory sequence Prediction parameters: ； in: The change trajectory sequence The p-order prediction parameter, ; S344: Predicting the ambient temperature outside the cabinet at time t+j based on the prediction parameters, wherein the prediction formula is: ； And based on the external ambient temperature of the box at time t+j, a change trajectory sequence of the external ambient temperature of the box at time t+j is constructed .

8. A method for adaptively controlling the temperature of a smart water meter housing as claimed in claim 6, characterized in that: In the step S4, the adaptive temperature control strategy structure is used to calculate the adaptive temperature control strategy parameters that need to be currently adopted, and adaptive dynamic control is performed, including: The adaptive temperature control strategy structure obtained by parameter optimization in step S3 is used to calculate the adaptive temperature control strategy parameters that need to be taken at present, and the adaptive temperature control strategy parameters are used to adjust the conversion heat of the battery in the smart water meter box, and the temperature of the smart water meter box is adaptively and dynamically controlled. The selection process of the adaptive temperature control strategy parameters is as follows: S41: The external environment temperature prediction module receives the current external environment temperature change trajectory sequence of the cabinet , predict the external ambient temperature of the box at the next moment , forming a sequence of changes in the ambient temperature outside the box at the next moment ; S42: The control parameter selection module selects the adaptive temperature control strategy parameters from the control parameter space : ； ； ； in: represents the specific heat capacity of water, and V represents the mass of water in the smart water meter box; Indicates the conversion heat value corresponding to the battery control parameter a, represents the intelligent water meter box heating model, a is any battery control parameter in the control parameter space; Represents the disturbance parameter corresponding to the battery control parameter a in the current adaptive temperature control strategy structure; Indicates that the battery control parameter a is used as the battery control parameter of the smart water meter box at time t+1, and the internal temperature of the smart water meter box at time t+1, It represents the change trajectory sequence of the internal temperature of the box at time t+1 based on the battery control parameter a; S43: The output module outputs the selected adaptive temperature control strategy parameters .

Images