AI energy-saving control method and system for heat exchange module

Abstract

The present application relates to the field of heat dissipation technology, and provides an AI energy-saving control method and system for a heat exchange module. The heat exchange module is used to dissipate heat for the compressor of an air conditioner. The method includes obtaining the operating parameter information of the air conditioner and the environmental parameter information of the operating environment in real time during the operation of the air conditioner, and inputting the operating parameter information and the environmental parameter information into a target coolant flow rate prediction model to obtain a predicted coolant flow rate value, and controlling the coolant flow rate in the heat exchange module based on the predicted coolant flow rate value. This method provides an intelligent, efficient, and energy-saving heat exchange module control method by introducing artificial intelligence technology, which not only improves the cooling efficiency and system stability, reduces energy consumption and maintenance costs, but also significantly enhances the overall performance and user experience of the air conditioner, and has broad application prospects and significant technical advantages.

Description

Technical Field

[0001] The present application relates to the field of heat dissipation technology, and in particular to an AI energy-saving control method and system for a heat exchange module. Background Art

[0002] During the operation of the air conditioner, a large amount of heat is generated by the compressor. If the compressor is not effectively dissipated, the air conditioner performance will decline and even the service life of the air conditioner will be affected.

[0003] Traditional compressor cooling systems mainly rely on mechanical control, such as constant fan speed or preset coolant flow rate, to maintain the compressor within a suitable operating temperature range. However, with the diversification and complexity of air-conditioning application scenarios, a single cooling control strategy is difficult to adapt to different operating conditions and environmental changes. For example, under extreme climatic conditions, traditional cooling systems may not be able to adjust the cooling intensity in time, causing the compressor to overheat, thereby affecting the performance of the air conditioner and even causing safety hazards. At the same time, overcooling will also lead to energy waste. Therefore, there is an urgent need for a technical means that can intelligently sense and dynamically adjust the cooling strategy to improve cooling efficiency, reduce energy consumption, and enhance the overall performance and user experience of the air conditioner. Summary of the invention

[0004] The present application provides an AI energy-saving control method and system for a heat exchange module to solve the problems raised by the above background technology.

[0005] In a first aspect, the present application provides an AI energy-saving control method for a heat exchange module, wherein the heat exchange module is used to dissipate heat for a compressor of an air conditioner, and the method comprises:

[0006] Acquire the operating parameter threshold interval information of the air conditioner and the environmental parameter threshold interval information of the operating environment of the air conditioner; wherein the operating parameter threshold interval information includes parameter threshold intervals of multiple operating parameters, and the environmental parameter threshold interval information includes parameter threshold intervals of multiple environmental parameters;

[0007] A training data set is constructed based on the operating parameter threshold interval information and the environmental parameter threshold interval information; the training data set includes a plurality of matching relationships, the matching relationship is a matching relationship between operating state information and a coolant flow rate, and the operating state information includes operating parameter information and environmental parameter information;

[0008] Determine the number of model parameters of a preset neural network model, randomly extract the number of matching relationships in the training data set to form a training set, and determine the matching relationships in the training data set other than the training set as a verification set;

[0009] Training a preset neural network model based on the training set to obtain an initial coolant flow rate prediction model;

[0010] Based on a preset genetic optimization algorithm, the model parameters of the initial coolant flow rate prediction model are optimized through the verification set to obtain a target coolant flow rate prediction model;

[0011] During the operation of the air conditioner, the operating parameter information of the air conditioner and the environmental parameter information of the operating environment are obtained in real time, and the operating parameter information and the environmental parameter information are input into the target coolant flow rate prediction model to obtain the coolant flow rate prediction value, and the coolant flow rate in the heat exchange module is controlled based on the coolant flow rate prediction value.

[0012] In a possible implementation manner, the constructing a training data set based on the operating parameter threshold interval information and the environmental parameter threshold interval information includes:

[0013] For each of the parameter threshold intervals, extracting a plurality of parameter values ​​in the parameter threshold interval based on a preset step size to obtain a parameter value set corresponding to the parameter threshold interval, wherein the parameter value set includes endpoint values ​​of the parameter threshold interval;

[0014] Cartesian product operations are performed on each of the parameter value sets to obtain a plurality of operation status information; the operation status information includes operation parameter information and environment parameter information;

[0015] For each piece of the operating status information, the coolant flow rate corresponding to the operating status information is obtained, and a matching relationship between the operating status information and the coolant flow rate is constructed; each of the matching relationships constitutes the training data set.

[0016] In a possible implementation, the obtaining the coolant flow rate corresponding to the operating status information includes:

[0017] placing the indoor unit of the air conditioner in an indoor environment corresponding to the environmental parameter information of the operating state information, placing the outdoor unit of the air conditioner in an outdoor environment corresponding to the environmental parameter information of the operating state information, controlling the air conditioner to operate for a preset time according to the operating parameter information of the operating state information, and obtaining the temperature corresponding to the compressor of the air conditioner in real time during the operation of the air conditioner to obtain a temperature sequence;

[0018] Obtaining the temperature difference between the end temperature and the start temperature of the temperature sequence;

[0019] Obtaining the mass and specific heat capacity of the compressor in a database;

[0020] Multiplying the temperature difference, the mass and the specific heat capacity to obtain the heat generated by the compressor within the preset time period;

[0021] The coolant flow rate is determined based on the heating value.

[0022] In a possible implementation, determining the coolant flow rate based on the heat generation includes:

[0023] Dividing the heat output by the preset time length, obtaining the heating efficiency of the compressor corresponding to the operating state information;

[0024] Determining whether the heating efficiency is greater than a preset heating efficiency;

[0025] If so, the heat dissipation efficiency of the heat exchange module is obtained by subtracting the preset heat dissipation efficiency from the heat dissipation efficiency, and the coolant flow rate is determined based on the heat dissipation efficiency.

[0026] In a possible implementation, the preset genetic optimization algorithm is used to optimize the model parameters of the initial coolant flow rate prediction model through the verification set to obtain the target coolant flow rate prediction model, including:

[0027] For each matching relationship in the validation set, inputting the operating status information of the matching relationship into the initial coolant flow rate prediction model to obtain a coolant flow rate prediction value, and obtaining an absolute value of a difference between the coolant flow rate prediction value and the coolant flow rate corresponding to the matching relationship;

[0028] Compare each of the absolute values ​​with a preset absolute value respectively, and when any of the absolute values ​​is greater than the preset absolute value, perform mutation processing on the model parameters of the initial coolant flow rate prediction model based on a preset mutation algorithm to obtain a first-generation population, wherein the first-generation population includes a plurality of first-generation individuals;

[0029] For each of the first-generation individuals, the model parameters of the initial coolant flow rate prediction model are updated using the first-generation individuals to obtain a first intermediate coolant flow rate prediction model, and whether the prediction accuracy of the first intermediate coolant flow rate prediction model is qualified;

[0030] If there are multiple qualified first intermediate coolant flow rate prediction models, determine any qualified first intermediate coolant flow rate prediction model as the target coolant flow rate prediction model;

[0031] If the prediction accuracy of each of the first intermediate coolant flow rate prediction models is unqualified, obtaining a prediction accuracy coefficient of the first intermediate coolant flow rate prediction model for each of the first intermediate coolant flow rate prediction models;

[0032] Determining a target first intermediate coolant flow rate prediction model based on the prediction accuracy coefficients of each of the first intermediate coolant flow rate prediction models, wherein the prediction accuracy coefficient of the target first intermediate coolant flow rate prediction model is the largest;

[0033] Based on a preset mutation algorithm, a model parameter of the target first intermediate coolant flow rate prediction model is mutated to obtain a second generation population, wherein the second generation population includes a plurality of second generation individuals;

[0034] For each of the second-generation individuals, the model parameters of the initial coolant flow rate prediction model are updated using the second-generation individuals to obtain a second intermediate coolant flow rate prediction model, and whether the prediction accuracy of the second intermediate coolant flow rate prediction model is qualified;

[0035] If there are multiple qualified second intermediate coolant flow rate prediction models, any qualified second intermediate coolant flow rate prediction model is determined as the target coolant flow rate prediction model.

[0036] In a possible implementation, the determining whether the prediction accuracy of the first intermediate coolant flow rate prediction model is qualified includes:

[0037] For each matching relationship in the validation set, inputting the operation status information of the matching relationship into the first intermediate coolant flow rate prediction model to obtain a coolant flow rate prediction value, and obtaining an absolute value of a difference between the coolant flow rate prediction value and the coolant flow rate corresponding to the matching relationship;

[0038] Comparing each of the absolute values ​​with a preset absolute value respectively;

[0039] If any of the absolute values ​​is greater than the preset absolute value, it is determined that the prediction accuracy of the first intermediate coolant flow rate prediction model is qualified;

[0040] If each of the absolute values ​​is not greater than the preset absolute value, it is determined that the prediction accuracy of the first intermediate coolant flow rate prediction model is unqualified.

[0041] In a possible implementation, obtaining the prediction accuracy coefficient of the first intermediate coolant flow rate prediction model includes:

[0042] For each matching relationship in the validation set, inputting the operation status information of the matching relationship into the first intermediate coolant flow rate prediction model to obtain a coolant flow rate prediction value, and obtaining an absolute value of a difference between the coolant flow rate prediction value and the coolant flow rate corresponding to the matching relationship, and determining that the matching relationship is a target matching relationship when the absolute value is greater than a preset absolute value;

[0043] The absolute values ​​corresponding to the target matching relationships are added together to obtain the sum of the absolute values, and the ratio of the sum of the absolute values ​​to the number of the target matching relationships is determined as the prediction accuracy coefficient.

[0044] In a second aspect, the present application provides an AI energy-saving control system for a heat exchange module, wherein the heat exchange module is used to dissipate heat for a compressor of an air conditioner, and the system includes:

[0045] An acquisition module, used to acquire operating parameter threshold interval information of the air conditioner and environmental parameter threshold interval information of the operating environment of the air conditioner; wherein the operating parameter threshold interval information includes parameter threshold intervals of multiple operating parameters, and the environmental parameter threshold interval information includes parameter threshold intervals of multiple environmental parameters;

[0046] A construction module, configured to construct a training data set based on the operating parameter threshold interval information and the environmental parameter threshold interval information; the training data set includes a plurality of matching relationships, wherein the matching relationship is a matching relationship between operating state information and a coolant flow rate, and the operating state information includes operating parameter information and environmental parameter information;

[0047] A determination module, used to determine the number of model parameters of a preset neural network model, randomly extract the matching relationships of the number in the training data set to form a training set, and determine the matching relationships in the training data set other than the training set as a verification set;

[0048] A training module, used for training a preset neural network model based on the training set to obtain an initial coolant flow rate prediction model;

[0049] An optimization module, configured to optimize the model parameters of the initial coolant flow rate prediction model through the verification set based on a preset genetic optimization algorithm to obtain a target coolant flow rate prediction model;

[0050] A control module is used to obtain the operating parameter information of the air conditioner and the environmental parameter information of the operating environment in real time during the operation of the air conditioner, and input the operating parameter information and the environmental parameter information into the target coolant flow rate prediction model to obtain the coolant flow rate prediction value, and control the coolant flow rate in the heat exchange module based on the coolant flow rate prediction value.

[0051] The present application provides an AI energy-saving control method and system for a heat exchange module, wherein the heat exchange module is used to dissipate heat for a compressor of an air conditioner, and the method comprises: obtaining operating parameter threshold interval information of the air conditioner and environmental parameter threshold interval information of an operating environment of the air conditioner; wherein the operating parameter threshold interval information comprises parameter threshold intervals of a plurality of operating parameters, and the environmental parameter threshold interval information comprises parameter threshold intervals of a plurality of environmental parameters; constructing a training data set based on the operating parameter threshold interval information and the environmental parameter threshold interval information; the training data set comprises a plurality of matching relationships, wherein the matching relationship is a matching relationship between operating status information and a coolant flow rate, and the operating status information comprises operating parameter information and environmental parameter information; determining the number of model parameters of a preset neural network model, Randomly extract the number of matching relationships in the training data set to form a training set, and determine the matching relationships in the training data set other than the training set as a verification set; train the preset neural network model based on the training set to obtain an initial coolant flow rate prediction model; optimize the model parameters of the initial coolant flow rate prediction model through the verification set based on a preset genetic optimization algorithm to obtain a target coolant flow rate prediction model; during the operation of the air conditioner, obtain the operating parameter information of the air conditioner and the environmental parameter information of the operating environment in real time, and input the operating parameter information and the environmental parameter information into the target coolant flow rate prediction model to obtain a coolant flow rate prediction value, and control the coolant flow rate in the heat exchange module based on the coolant flow rate prediction value. This method introduces artificial intelligence technology to provide an intelligent, efficient and energy-saving heat exchange module control method for the shortcomings of traditional air conditioning cooling systems in diversified application scenarios. This method not only improves cooling efficiency and system stability, reduces energy consumption and maintenance costs, but also significantly enhances the overall performance and user experience of the air conditioner, and has broad application prospects and significant technical advantages. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] 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.

[0053] Figure 1 A schematic diagram of a flow chart of an AI energy-saving control method for a heat exchange module provided in an embodiment of the present application;

[0054] Figure 2 A schematic block diagram of the structure of the AI ​​energy-saving control system of the heat exchange module provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] 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.

[0056] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0057] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0058] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0059] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0060] See also Figure 1 , Figure 1 A schematic diagram of a flow chart of an AI energy-saving control method for a heat exchange module provided in an embodiment of the present application, wherein the heat exchange module is used to dissipate heat for a compressor of an air conditioner, such as Figure 1 As shown, the AI ​​energy-saving control method of the heat exchange module provided in the embodiment of the present application includes steps S1 to S5.

[0061] Step S1, obtaining operating parameter threshold interval information of the air conditioner and environmental parameter threshold interval information of the operating environment of the air conditioner; wherein the operating parameter threshold interval information includes parameter threshold intervals of multiple operating parameters, and the environmental parameter threshold interval information includes parameter threshold intervals of multiple environmental parameters.

[0062] Specifically, the operating parameter threshold interval information and the environmental parameter threshold interval information are obtained through the production specification information of the air conditioner, the operating parameters include but are not limited to wind speed, set temperature, and operating mode, and the environmental parameters include but are not limited to temperature, humidity, and light intensity.

[0063] Step S2, constructing a training data set based on the operating parameter threshold interval information and the environmental parameter threshold interval information; the training data set includes multiple matching relationships, the matching relationship is a matching relationship between operating status information and coolant flow rate, and the operating status information includes operating parameter information and environmental parameter information.

[0064] Specifically, step S2 includes the following steps:

[0065] For each of the parameter threshold intervals, a plurality of parameter values ​​are extracted from the parameter threshold interval based on a preset step size to obtain a parameter value set corresponding to the parameter threshold interval, wherein the parameter value set includes endpoint values ​​of the parameter threshold interval; it can be understood that the parameter threshold interval includes an environmental parameter threshold interval and an operating parameter threshold interval;

[0066] Cartesian product operations are performed on each of the parameter value sets to obtain a plurality of operation status information; the operation status information includes operation parameter information and environment parameter information;

[0067] For each piece of the operating status information, the coolant flow rate corresponding to the operating status information is obtained, and a matching relationship between the operating status information and the coolant flow rate is constructed; each of the matching relationships constitutes the training data set.

[0068] It can be understood that the method for constructing the training data set described above ensures that the training data set contains various possible combinations of operating parameters and environmental parameters by extracting multiple parameter values ​​based on a preset step size within each parameter threshold interval, including the endpoint values ​​of the interval. This comprehensive parameter sampling method effectively avoids data blind spots, so that the target coolant flow rate prediction model obtained by subsequent training can show good prediction capabilities under a wide range of working conditions.

[0069] Wherein, obtaining the coolant flow rate corresponding to the operating status information comprises the following steps:

[0070] placing the indoor unit of the air conditioner in an indoor environment corresponding to the environmental parameter information of the operating state information, placing the outdoor unit of the air conditioner in an outdoor environment corresponding to the environmental parameter information of the operating state information, controlling the air conditioner to operate for a preset time according to the operating parameter information of the operating state information, and obtaining the temperature corresponding to the compressor of the air conditioner in real time during the operation of the air conditioner to obtain a temperature sequence;

[0071] Obtaining the temperature difference between the end temperature and the start temperature of the temperature sequence;

[0072] Obtaining the mass and specific heat capacity of the compressor in a database;

[0073] Multiplying the temperature difference, the mass and the specific heat capacity to obtain the heat generated by the compressor within the preset time period;

[0074] The coolant flow rate is determined based on the heating value.

[0075] Wherein, determining the coolant flow rate based on the heat generation comprises the following steps:

[0076] Dividing the heat output by the preset time length, obtaining the heating efficiency of the compressor corresponding to the operating state information;

[0077] Determining whether the heating efficiency is greater than a preset heating efficiency;

[0078] If so, the heat dissipation efficiency of the heat exchange module is obtained by subtracting the preset heat dissipation efficiency from the heat dissipation efficiency, and the coolant flow rate is determined based on the heat dissipation efficiency; it should be noted that when the heat dissipation efficiency is not greater than the preset heat dissipation efficiency, the compressor can be cooled by radiation heat dissipation during the operation of the air conditioner. At this time, it is not necessary to cool the compressor by the heat exchange module. In order to save energy consumption of the heat exchange module, the coolant flow rate is determined to be 0;

[0079] If so, the heat dissipation efficiency of the heat exchange module is obtained by subtracting the preset heat dissipation efficiency from the heat dissipation efficiency, and the coolant flow rate is determined based on the heat dissipation efficiency; specifically, the method for determining the coolant flow rate based on the heat dissipation efficiency is to obtain the heat dissipation model of the heat exchange module in the specification information of the heat exchange module, and input the heat dissipation power into the heat dissipation model to determine the coolant flow rate. It can be understood that when the heat dissipation efficiency is the preset heat dissipation efficiency, the compressor can be cooled by radiation heat dissipation. In this step, when the heat dissipation efficiency is greater than the preset heat dissipation efficiency, the heat dissipation efficiency of the heat exchange module is obtained by subtracting the preset heat dissipation efficiency from the heat dissipation efficiency, and the coolant flow rate is determined based on the heat dissipation efficiency, which can achieve effective heat dissipation of the compressor while reducing the energy consumption of the heat dissipation module as much as possible.

[0080] Step S3, determining the number of model parameters of the preset neural network model, randomly extracting the number of matching relationships in the training data set to form a training set, and determining the matching relationships in the training data set except the training set as a verification set.

[0081] Step S4: training a preset neural network model based on the training set to obtain an initial coolant flow rate prediction model.

[0082] Specifically, for each matching relationship in the training set, the operating status information corresponding to the matching relationship is used as the input of the preset neural network model, and the coolant flow rate corresponding to the matching relationship is used as the output of the preset neural network model to train the preset neural network model to obtain the initial coolant flow rate prediction model.

[0083] Step S5: Based on a preset genetic optimization algorithm, the model parameters of the initial coolant flow rate prediction model are optimized through the verification set to obtain a target coolant flow rate prediction model.

[0084] Specifically, step S5 includes the following steps:

[0085] For each matching relationship in the validation set, inputting the operating status information of the matching relationship into the initial coolant flow rate prediction model to obtain a coolant flow rate prediction value, and obtaining an absolute value of a difference between the coolant flow rate prediction value and the coolant flow rate corresponding to the matching relationship;

[0086] Compare each of the absolute values ​​with a preset absolute value respectively, and when any of the absolute values ​​is greater than the preset absolute value, perform mutation processing on the model parameters of the initial coolant flow rate prediction model based on a preset mutation algorithm to obtain a first-generation population, wherein the first-generation population includes a plurality of first-generation individuals;

[0087] For each of the first-generation individuals, the model parameters of the initial coolant flow rate prediction model are updated using the first-generation individuals to obtain a first intermediate coolant flow rate prediction model, and whether the prediction accuracy of the first intermediate coolant flow rate prediction model is qualified;

[0088] If there are multiple qualified first intermediate coolant flow rate prediction models, determine any qualified first intermediate coolant flow rate prediction model as the target coolant flow rate prediction model;

[0089] If the prediction accuracy of each of the first intermediate coolant flow rate prediction models is unqualified, obtaining a prediction accuracy coefficient of the first intermediate coolant flow rate prediction model for each of the first intermediate coolant flow rate prediction models;

[0090] Determining a target first intermediate coolant flow rate prediction model based on the prediction accuracy coefficients of each of the first intermediate coolant flow rate prediction models, wherein the prediction accuracy coefficient of the target first intermediate coolant flow rate prediction model is the largest;

[0091] Based on a preset mutation algorithm, a model parameter of the target first intermediate coolant flow rate prediction model is mutated to obtain a second generation population, wherein the second generation population includes a plurality of second generation individuals;

[0092] For each of the second-generation individuals, the model parameters of the initial coolant flow rate prediction model are updated using the second-generation individuals to obtain a second intermediate coolant flow rate prediction model, and whether the prediction accuracy of the second intermediate coolant flow rate prediction model is qualified;

[0093] If there are multiple qualified second intermediate coolant flow rate prediction models, any qualified second intermediate coolant flow rate prediction model is determined as the target coolant flow rate prediction model.

[0094] Wherein, judging whether the prediction accuracy of the first intermediate coolant flow rate prediction model is qualified comprises the following steps:

[0095] For each matching relationship in the validation set, inputting the operation status information of the matching relationship into the first intermediate coolant flow rate prediction model to obtain a coolant flow rate prediction value, and obtaining an absolute value of a difference between the coolant flow rate prediction value and the coolant flow rate corresponding to the matching relationship;

[0096] Comparing each of the absolute values ​​with a preset absolute value respectively;

[0097] If any of the absolute values ​​is greater than the preset absolute value, it is determined that the prediction accuracy of the first intermediate coolant flow rate prediction model is qualified;

[0098] If each of the absolute values ​​is not greater than the preset absolute value, it is determined that the prediction accuracy of the first intermediate coolant flow rate prediction model is unqualified.

[0099] Wherein, obtaining the prediction accuracy coefficient of the first intermediate coolant flow rate prediction model comprises the following steps:

[0100] For each matching relationship in the validation set, inputting the operation status information of the matching relationship into the first intermediate coolant flow rate prediction model to obtain a coolant flow rate prediction value, and obtaining an absolute value of a difference between the coolant flow rate prediction value and the coolant flow rate corresponding to the matching relationship, and determining that the matching relationship is a target matching relationship when the absolute value is greater than a preset absolute value;

[0101] The absolute values ​​corresponding to the target matching relationships are added together to obtain the sum of the absolute values, and the ratio of the sum of the absolute values ​​to the number of the target matching relationships is determined as the prediction accuracy coefficient.

[0102] It can be understood that step S5 optimizes the model parameters of the initial coolant flow rate prediction model through the verification set based on a preset genetic optimization algorithm to obtain a target coolant flow rate prediction model, thereby improving the prediction accuracy of the target coolant flow rate prediction model.

[0103] Step S6: During the operation of the air conditioner, the operating parameter information of the air conditioner and the environmental parameter information of the operating environment are obtained in real time, and the operating parameter information and the environmental parameter information are input into the target coolant flow rate prediction model to obtain a coolant flow rate prediction value, and the coolant flow rate in the heat exchange module is controlled based on the coolant flow rate prediction value; it should be noted that the environmental parameter information refers to the environmental parameter information of the environment where the outdoor unit of the air conditioner is located.

[0104] The method provided in this embodiment introduces artificial intelligence technology to provide an intelligent, efficient and energy-saving heat exchange module control method for the shortcomings of traditional air conditioning cooling systems in various application scenarios. This method not only improves cooling efficiency and system stability, reduces energy consumption and maintenance costs, but also significantly enhances the overall performance and user experience of the air conditioner, and has broad application prospects and significant technical advantages.

[0105] See also Figure 2 , Figure 2 A schematic block diagram of the structure of an AI energy-saving control system 100 of a heat exchange module provided in an embodiment of the present application, wherein the heat exchange module is used to dissipate heat for a compressor of an air conditioner, such as Figure 2 As shown, the AI ​​energy-saving control system 100 of the heat exchange module provided in the embodiment of the present application includes:

[0106] The acquisition module 110 is used to obtain the operating parameter threshold interval information of the air conditioner and the environmental parameter threshold interval information of the operating environment of the air conditioner; wherein the operating parameter threshold interval information includes parameter threshold intervals of multiple operating parameters, and the environmental parameter threshold interval information includes parameter threshold intervals of multiple environmental parameters.

[0107] The construction module 120 is used to construct a training data set based on the operating parameter threshold interval information and the environmental parameter threshold interval information; the training data set includes multiple matching relationships, the matching relationship is a matching relationship between operating status information and coolant flow rate, and the operating status information includes operating parameter information and environmental parameter information.

[0108] The determination module 130 is used to determine the number of model parameters of the preset neural network model, randomly extract the matching relationships of the number in the training data set to form a training set, and determine the matching relationships in the training data set except the training set as a verification set.

[0109] The training module 140 is used to train the preset neural network model based on the training set to obtain an initial coolant flow rate prediction model.

[0110] The optimization module 150 is used to optimize the model parameters of the initial coolant flow rate prediction model through the verification set based on a preset genetic optimization algorithm to obtain a target coolant flow rate prediction model.

[0111] The control module 160 is used to obtain the operating parameter information of the air conditioner and the environmental parameter information of the operating environment in real time during the operation of the air conditioner, and input the operating parameter information and the environmental parameter information into the target coolant flow rate prediction model to obtain the coolant flow rate prediction value, and control the coolant flow rate in the heat exchange module based on the coolant flow rate prediction value.

[0112] It should be noted that technicians in the relevant technical field can clearly understand that for the convenience and conciseness of description, the specific working process of the system and each module described above can refer to the process in the aforementioned AI energy-saving control method embodiment of the heat exchange module, and will not be repeated here.

[0113] The above is only a specific implementation of the present application, but the protection scope of the present application 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 in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. An AI energy-saving control method for a heat exchange module, characterized in that: The heat exchange module is used to dissipate heat for a compressor of an air conditioner, and the method comprises: Acquire the operating parameter threshold interval information of the air conditioner and the environmental parameter threshold interval information of the operating environment of the air conditioner; wherein the operating parameter threshold interval information includes parameter threshold intervals of multiple operating parameters, and the environmental parameter threshold interval information includes parameter threshold intervals of multiple environmental parameters; A training data set is constructed based on the operating parameter threshold interval information and the environmental parameter threshold interval information; the training data set includes a plurality of matching relationships, the matching relationship is a matching relationship between operating state information and a coolant flow rate, and the operating state information includes operating parameter information and environmental parameter information; Determine the number of model parameters of a preset neural network model, randomly extract the number of matching relationships in the training data set to form a training set, and determine the matching relationships in the training data set other than the training set as a verification set; Training a preset neural network model based on the training set to obtain an initial coolant flow rate prediction model; Based on a preset genetic optimization algorithm, the model parameters of the initial coolant flow rate prediction model are optimized through the verification set to obtain a target coolant flow rate prediction model; During the operation of the air conditioner, the operating parameter information of the air conditioner and the environmental parameter information of the operating environment are obtained in real time, and the operating parameter information and the environmental parameter information are input into the target coolant flow rate prediction model to obtain a coolant flow rate prediction value, and the coolant flow rate in the heat exchange module is controlled based on the coolant flow rate prediction value; Wherein, constructing a training data set based on the operating parameter threshold interval information and the environmental parameter threshold interval information includes: For each of the parameter threshold intervals, extracting a plurality of parameter values ​​in the parameter threshold interval based on a preset step size to obtain a parameter value set corresponding to the parameter threshold interval, wherein the parameter value set includes endpoint values ​​of the parameter threshold interval; Cartesian product operations are performed on each of the parameter value sets to obtain a plurality of operation status information; the operation status information includes operation parameter information and environment parameter information; For each piece of the operating status information, the coolant flow rate corresponding to the operating status information is obtained, and a matching relationship between the operating status information and the coolant flow rate is constructed; each of the matching relationships constitutes the training data set.

2. The AI ​​energy-saving control method of the heat exchange module according to claim 1 is characterized in that: The obtaining of the coolant flow rate corresponding to the operating status information includes: placing the indoor unit of the air conditioner in an indoor environment corresponding to the environmental parameter information of the operating state information, placing the outdoor unit of the air conditioner in an outdoor environment corresponding to the environmental parameter information of the operating state information, controlling the air conditioner to operate for a preset time according to the operating parameter information of the operating state information, and obtaining the temperature corresponding to the compressor of the air conditioner in real time during the operation of the air conditioner to obtain a temperature sequence; Obtaining the temperature difference between the end temperature and the start temperature of the temperature sequence; Obtaining the mass and specific heat capacity of the compressor in a database; Multiplying the temperature difference, the mass and the specific heat capacity to obtain the heat generated by the compressor within the preset time period; The coolant flow rate is determined based on the heating value.

3. The AI ​​energy-saving control method of the heat exchange module according to claim 2 is characterized in that: The step of determining the coolant flow rate based on the heat generation comprises: Dividing the heat output by the preset time length, obtaining the heating efficiency of the compressor corresponding to the operating state information; Determining whether the heating efficiency is greater than a preset heating efficiency; If so, the heat dissipation efficiency of the heat exchange module is obtained by subtracting the preset heat dissipation efficiency from the heat dissipation efficiency, and the coolant flow rate is determined based on the heat dissipation efficiency.

4. The AI ​​energy-saving control method of the heat exchange module according to claim 1, characterized in that: The preset genetic optimization algorithm is used to optimize the model parameters of the initial coolant flow rate prediction model through the verification set to obtain the target coolant flow rate prediction model, including: For each matching relationship in the validation set, inputting the operating status information of the matching relationship into the initial coolant flow rate prediction model to obtain a coolant flow rate prediction value, and obtaining an absolute value of a difference between the coolant flow rate prediction value and the coolant flow rate corresponding to the matching relationship; Compare each of the absolute values ​​with a preset absolute value respectively, and when any of the absolute values ​​is greater than the preset absolute value, perform mutation processing on the model parameters of the initial coolant flow rate prediction model based on a preset mutation algorithm to obtain a first-generation population, wherein the first-generation population includes a plurality of first-generation individuals; For each of the first-generation individuals, the model parameters of the initial coolant flow rate prediction model are updated using the first-generation individuals to obtain a first intermediate coolant flow rate prediction model, and whether the prediction accuracy of the first intermediate coolant flow rate prediction model is qualified; If there are multiple qualified first intermediate coolant flow rate prediction models, determine any qualified first intermediate coolant flow rate prediction model as the target coolant flow rate prediction model; If the prediction accuracy of each of the first intermediate coolant flow rate prediction models is unqualified, obtaining a prediction accuracy coefficient of the first intermediate coolant flow rate prediction model for each of the first intermediate coolant flow rate prediction models; Determining a target first intermediate coolant flow rate prediction model based on the prediction accuracy coefficients of each of the first intermediate coolant flow rate prediction models, wherein the prediction accuracy coefficient of the target first intermediate coolant flow rate prediction model is the largest; Based on a preset mutation algorithm, a model parameter of the target first intermediate coolant flow rate prediction model is mutated to obtain a second generation population, wherein the second generation population includes a plurality of second generation individuals; For each of the second-generation individuals, the model parameters of the initial coolant flow rate prediction model are updated using the second-generation individuals to obtain a second intermediate coolant flow rate prediction model, and whether the prediction accuracy of the second intermediate coolant flow rate prediction model is qualified; If there are multiple qualified second intermediate coolant flow rate prediction models, any qualified second intermediate coolant flow rate prediction model is determined as the target coolant flow rate prediction model.

5. The AI ​​energy-saving control method of the heat exchange module according to claim 4 is characterized in that: The determining whether the prediction accuracy of the first intermediate coolant flow rate prediction model is qualified includes: For each matching relationship in the validation set, inputting the operation status information of the matching relationship into the first intermediate coolant flow rate prediction model to obtain a coolant flow rate prediction value, and obtaining an absolute value of a difference between the coolant flow rate prediction value and the coolant flow rate corresponding to the matching relationship; Comparing each of the absolute values ​​with a preset absolute value respectively; If any of the absolute values ​​is greater than the preset absolute value, it is determined that the prediction accuracy of the first intermediate coolant flow rate prediction model is qualified; If each of the absolute values ​​is not greater than the preset absolute value, it is determined that the prediction accuracy of the first intermediate coolant flow rate prediction model is unqualified.

6. The AI ​​energy-saving control method of the heat exchange module according to claim 4, characterized in that: The obtaining of the prediction accuracy coefficient of the first intermediate coolant flow rate prediction model comprises: For each matching relationship in the validation set, inputting the operation status information of the matching relationship into the first intermediate coolant flow rate prediction model to obtain a coolant flow rate prediction value, and obtaining an absolute value of a difference between the coolant flow rate prediction value and the coolant flow rate corresponding to the matching relationship, and determining that the matching relationship is a target matching relationship when the absolute value is greater than a preset absolute value; The absolute values ​​corresponding to the target matching relationships are added together to obtain the sum of the absolute values, and the ratio of the sum of the absolute values ​​to the number of the target matching relationships is determined as the prediction accuracy coefficient.

7. An AI energy-saving control system for a heat exchange module, characterized in that: The heat exchange module is used to dissipate heat for the compressor of the air conditioner. The system includes: An acquisition module, used to acquire operating parameter threshold interval information of the air conditioner and environmental parameter threshold interval information of the operating environment of the air conditioner; wherein the operating parameter threshold interval information includes parameter threshold intervals of multiple operating parameters, and the environmental parameter threshold interval information includes parameter threshold intervals of multiple environmental parameters; A construction module, configured to construct a training data set based on the operating parameter threshold interval information and the environmental parameter threshold interval information; the training data set includes a plurality of matching relationships, wherein the matching relationship is a matching relationship between operating state information and a coolant flow rate, and the operating state information includes operating parameter information and environmental parameter information; A determination module, used to determine the number of model parameters of a preset neural network model, randomly extract the matching relationships of the number in the training data set to form a training set, and determine the matching relationships in the training data set other than the training set as a verification set; A training module, used for training a preset neural network model based on the training set to obtain an initial coolant flow rate prediction model; An optimization module, configured to optimize the model parameters of the initial coolant flow rate prediction model through the verification set based on a preset genetic optimization algorithm to obtain a target coolant flow rate prediction model; a control module, configured to obtain, in real time during the operation of the air conditioner, operating parameter information of the air conditioner and environmental parameter information of the operating environment, input the operating parameter information and the environmental parameter information into the target coolant flow rate prediction model, obtain a coolant flow rate prediction value, and control the coolant flow rate in the heat exchange module based on the coolant flow rate prediction value; Wherein, constructing a training data set based on the operating parameter threshold interval information and the environmental parameter threshold interval information includes: For each of the parameter threshold intervals, extracting a plurality of parameter values ​​in the parameter threshold interval based on a preset step size to obtain a parameter value set corresponding to the parameter threshold interval, wherein the parameter value set includes endpoint values ​​of the parameter threshold interval; Cartesian product operations are performed on each of the parameter value sets to obtain a plurality of operation status information; the operation status information includes operation parameter information and environment parameter information; For each piece of the operating status information, the coolant flow rate corresponding to the operating status information is obtained, and a matching relationship between the operating status information and the coolant flow rate is constructed; each of the matching relationships constitutes the training data set.

Images