Air conditioner design parameter evaluation method and device, electronic equipment and storage medium

Abstract

The invention relates to an air conditioner design parameter evaluation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a first design parameter of an air conditioner, inputting the first design parameter into an evaluation index model, and generating a first comfort evaluation index of the first design parameter, the evaluation index model is used for determining a comfort evaluation index corresponding to the design parameter based on a mapping relation between the design parameter and the comfort evaluation index, and evaluating the first comfort evaluation index based on a multi-target genetic algorithm to generate a parameter evaluation result of the first design parameter. Therefore, optimization of the comfort evaluation index is achieved through the multi-target genetic algorithm, the design parameters are evaluated according to the comfort evaluation index, and the advantages and disadvantages of the air conditioner design scheme are distinguished based on comfort.

Description

Technical Field

[0001] The present disclosure relates to the technical field of air conditioners, and particularly to an evaluation method, device, electronic device and storage medium for air conditioner design parameters. Background Art

[0002] Air conditioners have become one of the essential devices in modern family daily life, which can create a more comfortable indoor environment and improve the quality of life. However, in an air-conditioned room, there are sometimes situations where the room temperature is effectively controlled but the user comfort is not good, which is closely related to the air flow organization in the air-conditioned room. Adjusting the air supply parameters and forms to improve the air flow organization in the air-conditioned room is a common means and method for creating a comfortable air-conditioning environment at present. Among them, the air supply parameters and forms are relatively important, which determine the indoor air flow characteristics and also determine the air flow trajectory near the return air area. Therefore, reasonably selecting the air supply type and setting the air supply parameters can avoid uncomfortable air flow and flow dead zones indoors, thereby creating a more comfortable air-conditioning environment. Summary of the Invention

[0003] To overcome the problems existing in the related art, the present disclosure provides an evaluation method, device, electronic device and storage medium for air conditioner design parameters.

[0004] According to the first aspect of the embodiments of the present disclosure, an evaluation method for air conditioner design parameters is provided, including:

[0005] Obtain a first design parameter of the air conditioner;

[0006] Input the first design parameter into an evaluation index model to generate a first comfort evaluation index of the first design parameter, where the evaluation index model is used to determine the comfort evaluation index corresponding to the design parameter based on the mapping relationship between the design parameter and the comfort evaluation index;

[0007] Evaluate the first comfort evaluation index based on a multi-objective genetic algorithm to generate a parameter evaluation result of the first design parameter.

[0008] Optionally, the evaluating the first comfort evaluation index based on a multi-objective genetic algorithm to generate a parameter evaluation result of the first design parameter includes:

[0009] Generate initial population data of the multi-objective genetic algorithm according to the first comfort evaluation index;

[0010] Use the initial population data as the first population data and determine a first objective function of the first population data;

[0011] In the case that the first objective function does not meet the preset convergence condition, determine the first fitness value of the first comfort evaluation index on the first objective function;

[0012] Screen from the first comfort evaluation index according to the first fitness value to generate the second population data;

[0013] Determine the second objective function of the second population data;

[0014] In the case that the second objective function meets the preset convergence condition, generate the parameter evaluation result according to the second population data and the first comfort evaluation index.

[0015] Optionally, evaluating the first comfort evaluation index based on the multi-objective genetic algorithm to generate the parameter evaluation result of the first design parameter includes:

[0016] Perform normalization processing on the first comfort evaluation index to generate normalized data;

[0017] Obtain the preset matrix scale of the comfort evaluation index;

[0018] According to the preset matrix scale, determine the evaluation weight value of the comfort evaluation index through the analytic hierarchy process (AHP) algorithm;

[0019] Generate the parameter evaluation result according to the normalized data and the evaluation weight value.

[0020] Optionally, the first comfort evaluation index includes multiple comfort evaluation indexes, and evaluating the first comfort evaluation index based on the multi-objective genetic algorithm to generate the parameter evaluation result of the first design parameter includes:

[0021] Obtain the evaluation weight values of the multiple comfort evaluation indexes;

[0022] Perform weighted averaging on the multiple comfort evaluation indexes based on the scoring weight values to generate the comprehensive scoring data of the first set parameter;

[0023] Use the comprehensive scoring data as the reference evaluation result.

[0024] Optionally, evaluating the first comfort evaluation index based on the multi-objective genetic algorithm to generate the parameter evaluation result of the first design parameter includes:

[0025] Evaluate the first comfort evaluation index based on the multi-objective genetic algorithm to generate the frontier solution set data;

[0026] Obtain the optimal comfort evaluation index of the air conditioner;

[0027] According to the distance between the frontier solution set data and the optimal comfort evaluation index, the closeness between the first comfort evaluation index and the optimal comfort evaluation index is determined by the TOPSIS algorithm;

[0028] Take the closeness as the parameter evaluation result.

[0029] Optionally, the determining the closeness between the first comfort evaluation index and the optimal comfort evaluation index by the TOPSIS algorithm includes:

[0030] Obtain the evaluation weight value of the comfort evaluation index;

[0031] Based on the evaluation weight value, determine the first evaluation score of the first comfort evaluation index and determine the second evaluation score of the optimal comfort evaluation index;

[0032] Determine the closeness according to the first evaluation score and the second evaluation score.

[0033] Optionally, the determining the closeness between the first comfort evaluation index and the optimal comfort evaluation index by the TOPSIS algorithm includes:

[0034] Obtain the preset matrix scale of the comfort evaluation index;

[0035] According to the preset matrix scale, determine the evaluation weight value of the comfort evaluation index by the Analytic Hierarchy Process (AHP) algorithm;

[0036] Based on the evaluation weight value, determine the first evaluation score of the first comfort evaluation index and determine the second evaluation score of the optimal comfort evaluation index;

[0037] Determine the closeness according to the first evaluation score and the second evaluation score.

[0038] Optionally, the evaluation index model is trained and generated in the following manner;

[0039] Obtain the second design parameter of the air conditioner and the second comfort evaluation index corresponding to the second design parameter;

[0040] Perform data expansion on the first design parameter to generate multiple design parameters;

[0041] Based on a preset Computational Fluid Dynamics (CFD) simulation module, perform simulation on the multiple design parameters to generate multiple comfort evaluation indexes corresponding to the multiple design parameters;

[0042] Using the multiple design parameters and the multiple comfort evaluation indexes as a data training set for model training, training an initial machine learning model to generate the evaluation index model.

[0043] Optionally, based on a preset computational fluid dynamics (CFD) simulation module, simulating the multiple design parameters to generate multiple comfort evaluation indexes corresponding to the multiple design parameters, including:

[0044] Simulating the second design parameter based on the CFD simulation module to generate a simulation result corresponding to the second design parameter;

[0045] When the error between the simulation result and the second comfort evaluation index is less than a preset error range, simulating the multiple design parameters based on the CFD simulation module to generate the multiple comfort evaluation indexes.

[0046] Optionally, the first design parameter includes multiple groups of design parameters, and the parameter evaluation result includes multiple parameter evaluation results. The method includes:

[0047] Determining, according to the multiple parameter evaluation results, the design parameter with the optimal parameter evaluation result from the multiple groups of design parameters as the target design parameter of the air conditioner.

[0048] According to a second aspect of the embodiments of the present disclosure, there is provided an air conditioner design parameter evaluation device, including:

[0049] An acquisition module configured to acquire the first design parameter of the air conditioner;

[0050] A generation module configured to input the first design parameter into an evaluation index model to generate a first comfort evaluation index of the first design parameter, where the evaluation index model is used to determine a comfort evaluation index corresponding to a design parameter based on a mapping relationship between the design parameter and the comfort evaluation index;

[0051] An execution module configured to evaluate the first comfort evaluation index based on a multi-objective genetic algorithm to generate a parameter evaluation result of the first design parameter.

[0052] According to a third aspect of the embodiments of the present disclosure, there is provided an electronic device, including:

[0053] A processor;

[0054] A memory for storing instructions executable by the processor;

[0055] Wherein, the processor is configured to execute the executable instructions to implement the steps of the air conditioner design parameter evaluation method according to any one of the first aspects of the present disclosure.

[0056] According to a fourth aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium, on which computer program instructions are stored, and when the program instructions are executed by a processor, the steps of the air conditioner design parameter evaluation method provided in the first aspect of the present disclosure are implemented.

[0057] The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects:

[0058] In the above manner, the first design parameter of the air conditioner is obtained, the first design parameter is input into the evaluation index model, and the first comfort evaluation index of the first design parameter is generated. The evaluation index model is used to determine the comfort evaluation index corresponding to the design parameter based on the mapping relationship between the design parameter and the comfort evaluation index, and the first comfort evaluation index is evaluated based on the multi-objective genetic algorithm to generate the parameter evaluation result of the first design parameter. Thus, the optimization of the comfort evaluation index is realized through the multi-objective genetic algorithm, and the design parameter is evaluated according to the comfort evaluation index to distinguish the advantages and disadvantages of the air conditioner design scheme based on comfort.

[0059] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure.

[0061] Figure 1 is a flowchart of a method for evaluating air conditioner design parameters shown according to an exemplary embodiment.

[0062] Figure 2 is a flowchart of a method for constructing an evaluation index model shown according to an exemplary embodiment.

[0063] Figure 3 is a schematic diagram of a multi-objective optimization mapping relationship shown according to an exemplary embodiment.

[0064] Figure 4 is a flowchart of a machine learning - multi-objective genetic algorithm shown according to an exemplary embodiment.

[0065] Figure 5 is a flowchart of a method for evaluating air conditioner design parameters shown according to an exemplary embodiment.

[0066] Figure 6 is a block diagram of a device for evaluating air conditioner design parameters shown according to an exemplary embodiment.

[0067] Figure 7 It is a block diagram of an electronic device 700 shown according to an exemplary embodiment. Detailed implementation manners

[0068] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0069] It should be noted that all actions of obtaining signals, information, or data in the present disclosure are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where it is located and with the authorization given by the owner of the corresponding device.

[0070] Air conditioners have become one of the essential devices in modern family daily life, which can create a more comfortable indoor environment for users and improve the quality of life. However, in an air-conditioned room, sometimes the room temperature is effectively controlled, but the user's comfort experience in the room is not good. At this time, the user's comfort is related to the air flow organization in the air-conditioned room. Adjusting the air supply parameters and air supply forms of the air conditioner to improve the air flow organization in the air-conditioned room is a common means and method for creating a comfortable air-conditioning environment at present. Among them, the air supply parameters and air supply forms are relatively important, which determine the indoor air flow characteristics and also determine the air flow trajectory near the return air area. Therefore, reasonably selecting the air supply type and setting the air supply parameters can avoid uncomfortable air flows indoors and avoid the occurrence of air flow dead zones indoors, thereby creating a more comfortable air-conditioning environment for users.

[0071] Then, there are many design parameters of the air conditioner. In the related art, the factors affecting the indoor thermal environment of the air conditioner mainly include the structural design of the air conditioner, system control parameters, the operating characteristics of the air conditioner, and the current environmental parameters, etc. Among them, the structural design of the air conditioner can be divided into the structural design of refrigeration system components such as evaporators and condensers, the structural design of heating system components such as warm air blowers and radiators, and the structural design of air conditioner air supply outlets and return air outlets, etc. It is necessary for the various design structures of the air conditioner to cooperate with each other to generate an overall air conditioner design scheme that meets the user's comfort requirements.

[0072] In the related art, in order to select the optimal design solution that meets the user's comfort requirements from multiple design solutions, the present invention proposes a method for rating the design solution of an air conditioner based on data driving. Machine learning training and prediction are carried out through machine learning methods, and multi-objective optimization is realized by combining a multi-objective genetic algorithm with relevant evaluation methods. By establishing a multi-objective optimization model, the room comfort evaluation index under different air conditioner design solutions can be calculated conveniently and efficiently. Through the multiple evaluation results corresponding to multiple design solutions under the corresponding multi-objective evaluation method, the preferred design of the air conditioner is output, providing theoretical guidance for the scientific design of room air conditioners and saving time and resource investment.

[0073] Figure 1 is a flowchart of a method for evaluating air conditioner design parameters shown according to an exemplary embodiment, as Figure 1 shown, this method is used in a terminal and includes the following steps.

[0074] In step S11, the first design parameter of the air conditioner is obtained.

[0075] Exemplarily, in this embodiment, the influence of the optimization and combination of structural design, system control, operating characteristics, and environmental parameters on the indoor thermal environment is considered in the air conditioner design stage. A database is formed based on test data and simulation data, a corresponding model is established through machine learning methods, and then solved by a multi-objective genetic algorithm to obtain the evaluation parameters of the air conditioner design solution. The comfort evaluation index of the air conditioner in the room under different design parameters is output through different multi-objective evaluation methods. Through the comprehensive evaluation result of the above indexes, the air conditioner design parameter with the optimal comprehensive evaluation result is selected as the final design solution of the air conditioner, so as to realize the multi-objective optimal design of the air conditioner.

[0076] This embodiment is applied to a terminal. The terminal comprehensively evaluates the input first design parameter based on the comfort of the user corresponding to the air conditioner, and obtains the parameter evaluation result corresponding to the first design parameter. The first design parameter is the design parameter of the air conditioner, and the design parameter may include the structural design parameter of the air conditioner, the system control parameter of the air conditioner, the operating characteristic parameter of the air conditioner, and the environmental parameter of the installation scenario applicable to the air conditioner, etc. The environmental parameter may include the environmental area, the installation position information of the air conditioner in the environment, the environmental space range information, etc.

[0077] In step S12, the first design parameter is input into the evaluation index model to generate the first comfort evaluation index of the first design parameter. The evaluation index model is used to determine the comfort evaluation index corresponding to the design parameter based on the mapping relationship between the design parameter and the comfort evaluation index.

[0078] Exemplarily, an evaluation index model is configured in the terminal of this embodiment. The evaluation index model can determine the comfort evaluation index corresponding to the design parameter based on the mapping relationship between the design parameter and the comfort evaluation index. Input the first design parameter obtained in the above steps into the evaluation index model, so as to generate the first comfort evaluation index of the first design parameter. In this embodiment, the evaluation index model is a trained machine learning model, and the initial machine learning model can be trained through multiple groups of design parameters and the comfort evaluation indexes corresponding to each group of design parameters, so that the machine learning model determines the mapping relationship between the design parameter and the comfort evaluation index, and then based on this mapping relationship, determine the first comfort evaluation index corresponding to the first design parameter.

[0079] Among them, the comfort evaluation indexes include temperature fluctuation, temperature uniformity, vertical air temperature difference, draft feeling index, predicted mean vote, air distribution characteristic index, etc.

[0080] Optionally, in some embodiments, the evaluation index model is trained and generated in the following manner:

[0081] Obtain the second design parameter of the air conditioner;

[0082] Perform data expansion on the first design parameter to generate multiple design parameters;

[0083] Based on a preset computational fluid dynamics (CFD) simulation module, perform simulation on multiple design parameters to generate multiple comfort evaluation indexes corresponding to the multiple design parameters;

[0084] Use the multiple design parameters and the multiple comfort evaluation indexes as the data training set for model training, and train the initial machine learning model to generate the evaluation index model.

[0085] Exemplarily, use the initial preset design parameter of the air conditioner as the second design parameter. After manufacturing the air conditioner prototype based on the second design parameter, measure the comfort evaluation index of the air conditioner prototype under the second design parameter in the enthalpy difference chamber. Exemplarily, debug the air conditioner prototype to work normally in the enthalpy difference chamber based on the second design parameter, and measure multiple comfort evaluation indexes such as temperature fluctuation, temperature uniformity, vertical air temperature difference, draft feeling index, predicted mean vote, air distribution characteristic index, etc. in the enthalpy difference chamber to generate the second comfort evaluation index corresponding to the second design parameter.

[0086] Data expansion is performed on the second design parameter to generate multiple design parameters. Part of the design range in the second design parameter can be modified to obtain new design parameters. For example, the evaporator fin spacing in the second design parameter is [1.2, 1.4]. Modify this evaporator fin spacing and set the spacing to [1.0, 1.5], thereby obtaining new design parameters. It should be noted that in this embodiment, a change threshold needs to be set for each design parameter during the data expansion of the second design parameter, and the data expansion range needs to be controlled within the range of the set change threshold to avoid unreasonable data expansion.

[0087] Exemplarily, in this embodiment, based on a preset data expansion rule, the initial design parameters of the air conditioner are expanded to propose multiple design parameters of the air conditioner, as shown in the following table, generating 1 - 10 air conditioner design parameter schemes:

[0088]

[0089]

[0090] The multiple design parameters generated by the expansion are simulated through CFD (Computational Fluid Dynamics software) software to simulate the air flow conditions of different air conditioners in the enthalpy difference chamber under different design parameters. Based on the comfort evaluation index, this air flow condition is evaluated to generate the comfort evaluation index corresponding to each design parameter. The multiple design parameters and multiple comfort evaluation indexes are used as the data training set for model training to train the initial machine learning model, thereby generating an evaluation index model. Exemplarily, the initial machine learning model can be selected from models applicable to multi-dimensional thermal comfort prediction according to the actual design requirements of the air conditioner. The initial machine learning model includes, but is not limited to: SVM (Support Vector Machine model), BP (Backpropagation Neural Network model), discrete wavelet transform model, Bayesian network model, decision tree model, random forest model, MLR (Multiple Linear Regression model), SVR (Support Vector Regression model), etc.

[0091] Optionally, in some embodiments, the above step "Based on a preset CFD simulation module of fluid mechanics, perform simulation on multiple design parameters to generate multiple comfort evaluation indexes corresponding to the multiple design parameters" includes:

[0092] Simulate the second design parameter based on the CFD simulation module to generate the simulation result corresponding to the second design parameter;

[0093] Obtain the second comfort evaluation index corresponding to the second design parameter;

[0094] When the error between the simulation result and the second comfort evaluation index is less than the preset error range, simulate multiple design parameters based on the CFD simulation module to generate multiple comfort evaluation indexes.

[0095] Exemplarily, in this embodiment, to ensure the accuracy of the model training data set, it is necessary to verify the relevant setting parameters of the CFD simulation module to ensure the accuracy of the CFD simulation module. Simulate the second design parameter based on the CFD simulation module to generate the simulation result of the second design parameter, and obtain the second comfort evaluation index determined by measuring the air conditioner manufactured based on the second design parameter in the enthalpy difference chamber. Compare the second comfort evaluation index with the simulation result. When the error between the simulation result and the second comfort evaluation index is less than the preset error range, it means that the relevant setting parameters of the CFD simulation module are reasonable, and the design parameters can be simulated based on the currently set CFD simulation module to generate multiple comfort evaluation indexes corresponding to multiple design parameters.

[0096] Exemplarily, Figure 2 is a flowchart of a method for constructing an evaluation index model shown according to an exemplary embodiment. As Figure 2 shown, the machine learning method can be selected from methods applicable to multi-dimensional thermal comfort prediction modeling according to specific requirements, including but not limited to: models such as support vector machine (SVM), BP neural network, discrete wavelet transform, Bayesian network, decision tree, random forest, multiple linear regression (MLR), and support vector regression (SVR). The specific steps are as follows:

[0097] First, produce an air conditioner prototype according to the typical design parameters, and obtain the test data of the air conditioner prototype under the typical design parameters in the enthalpy difference chamber (a test chamber built based on the air enthalpy difference method to measure the refrigeration and heating capacities of air conditioners) as the basic data.

[0098] Then, a simulation model corresponding to the prototype is established through CFD simulation software, and the simulation results are output. If the error between the prototype test results and the simulation results is within 5%, the simulation is considered accurate and feasible. Then, the simulation data under different design parameters are output through the CFD software as extended data. The basic data and the extended data are used as the original data set, and the example data is shown in Table 1. A database is established based on the original data set, and the data is preprocessed to obtain data that conforms to the machine learning model, and the characteristic variables are selected. The comfort evaluation index is output through the training data, and the implicit mapping relationship between the design parameters and the comfort index is mined, and then the corresponding model is established.

[0099] In step S13, the first comfort evaluation index is evaluated based on the multi-objective genetic algorithm to generate a parameter evaluation result of the first design parameter.

[0100] Exemplarily, in this embodiment, the first comfort evaluation index generated in the above steps is evaluated according to the multi-objective genetic algorithm to generate a parameter evaluation result of the first design parameter. The parameter evaluation result can be a specific numerical value. The larger the corresponding numerical value, the higher the evaluation value of the first design parameter. The air conditioner manufactured based on the first design parameter can bring a more comfortable use experience to the user. Exemplarily, the multi-objective genetic algorithm includes, but is not limited to: NSGA (Non-dominated Sorting Genetic Algorithm)-II, NSGA-III, PAES (Pareto Archived Evolution Strategy, Pareto optimization evolutionary strategy algorithm), SPEA (Strength Pareto Evolutionary Algorithm, Pareto strength evolutionary algorithm) 2, MOCell (Multi-Objective Cellular Evolutionary Algorithm, multi-objective cell evolutionary algorithm), and other multi-objective genetic algorithms.

[0101] Optionally, in some embodiments, the above step S13 includes:

[0102] Generate the initial population data of the multi-objective genetic algorithm according to the first comfort evaluation index;

[0103] Take the initial population data as the first population data and determine the first objective function of the first population data;

[0104] In the case that the first objective function does not meet the preset convergence condition, determine the first fitness value of the first comfort evaluation index on the first objective function;

[0105] Screen from the first comfort evaluation index according to the first fitness value to generate the second population data;

[0106] Determine the second objective function of the second population data;

[0107] When the second objective function meets the preset convergence condition, generate a parameter evaluation result according to the second population data and the first comfort evaluation index.

[0108] Exemplarily, in this embodiment, according to the first comfort evaluation index, a group of individuals is randomly generated as the initial population data, and the initial population data is used as the first population data for population inheritance and population splitting. Before performing genetic splitting on the first population data, determine the first objective function of the first population data, and judge the objective function. If the objective function meets the preset convergence condition, then output the first population data, and generate a parameter evaluation result according to the first population data; if the objective function does not meet the preset convergence condition, then determine the first fitness value of the first comfort evaluation index on the first objective function, and screen the first comfort evaluation index according to the first fitness value to generate the second population data. That is, genetic operations are performed on the first comfort evaluation index based on the first fitness value to generate a new population. Determine the second objective function of the second population data, and judge whether the second objective function meets the convergence condition. If the second objective function meets the convergence condition, then output the second population data, and generate a parameter evaluation result based on the second population data; if the second objective function does not meet the convergence condition, then perform genetic iteration on the second population data again until the objective function corresponding to the generated new population meets the convergence condition, and output the new population data that meets the convergence condition.

[0109] Exemplarily, in some embodiments, before evaluating the first comfort evaluation index based on the multi-objective genetic algorithm, data preprocessing is first performed on the first comfort evaluation index. For example, data normalization and one-hot encoding processing are performed to make each feature variable in the same data magnitude and each state is independently stored. Then, based on the multi-objective genetic algorithm, the data index is evaluated using three parts: initializing the population, updating the population, and selection operation, to generate a parameter evaluation result of the design parameters.

[0110] Optionally, in some embodiments, the above step S13 includes:

[0111] Obtain the evaluation weight values of multiple comfort evaluation indexes;

[0112] Perform weighted averaging on multiple comfort evaluation indexes based on the scoring weight values to generate comprehensive scoring data of the first set of parameters;

[0113] Use the comprehensive scoring data as the reference evaluation result.

[0114] Exemplarily, the linear weighted method can be used to evaluate the first comfort evaluation index. A weight is set for each target through the linear weighted algorithm, and multiple targets are converted into a single target for solution, and then the optimal solution under this weight can be obtained. As shown in the following table, it is the reference table for the refrigeration comfort level score.

[0115]

[0116] Based on the above-mentioned level score reference table, a comprehensive evaluation is carried out on the corresponding indicators to obtain the score values of each indicator. Then, a weighted average is performed on each indicator to obtain the comprehensive score, and the star rating is determined according to this comprehensive score. Exemplarily, the following table shows the linear weighted evaluation weights of each comfort indicator:

[0117] Evaluation index Evaluation weight / % Predicted average thermal sensation index 30 Draft sensation index 15 Temperature fluctuation 15 Temperature uniformity 10 Vertical air temperature difference 20 Air distribution characteristic index 10

[0118] Multiply the parameter values of each evaluation index item in the above comfort evaluation index reference table by the corresponding evaluation weight to obtain the score values of each evaluation index, and then add the score values of each evaluation index to obtain the parameter evaluation result corresponding to this design parameter. Based on this parameter evaluation result, the comfort score of the design parameter is determined. Exemplarily, after determining the parameter evaluation value of the design parameter, the following weighted evaluation star rating table can be referred to evaluate the pros and cons of the design parameter.

[0119]

[0120]

[0121] Perform a weighted average on each indicator to obtain the comprehensive score, and determine the star rating according to the comprehensive score. The five-star result is used as the optimization range. When changing the weight of each target, a corresponding set of optimal solutions can be obtained. By changing multiple weight matching schemes, the Pareto optimal solution set of a multi-objective optimization problem can be obtained. For Schemes 1-10, the evaluation results using the linear weighted method are shown in the following table. Among them, the optimal design is that the fin pitch of the evaporator is 1.20 mm, the outer diameter of the tube is 6.00 mm, the tube pitch is 22.00 mm, the air supply speed is 3.5 m / s, the set temperature is 24 °C, the air deflector angle is 120°, and the swing blade angle is 0°, and the score is 4.68.

[0122]

[0123] Optionally, in some embodiments, the above step S13 includes:

[0124] Perform normalization processing on the first comfort evaluation index to generate normalized data;

[0125] Obtain the preset matrix scale of the comfort evaluation index;

[0126] According to the preset matrix scale, the evaluation weight value of the comfort evaluation index is determined by the Analytic Hierarchy Process (AHP) algorithm;

[0127] Based on the normalized data and the evaluation weight value, the parameter evaluation result is generated.

[0128] Exemplarily, in this embodiment, the AHP method is used to divide the multi-objective optimization problem of the complex system into an ordered hierarchical structure, and the importance order weights of the elements at each level are determined by quantifying the decision-making thinking process. First, the first comfort evaluation index is normalized to generate normalized comfort evaluation index data, and then the preset matrix scale of the comfort evaluation index is obtained. Exemplarily, the following table shows a matrix scale division table proposed in this embodiment:

[0129] Scale Meaning 1 Objective functions are equally important 3 i is slightly more important than j 5 i is significantly more important than j 7 i is very much more important than j 8 i is extremely more important than j 2、4、6 Mid-value of the two-sided scale Reciprocal Objective functions are interchanged

[0130] According to this preset matrix scale, the evaluation weight value of the comfort evaluation index is determined by the AHP algorithm. Exemplarily, when calculating the weights by the AHP method, a judgment matrix needs to be established, and the establishment of the judgment matrix needs to refer to the corresponding scale, as shown in the above matrix scale division table. Using the AHP method for evaluation, the total sorting weight of the scheme layer with respect to the target layer is obtained. After comprehensively considering the above factors, the optimal design parameters are output as the evaluation result of the AHP. Exemplarily, the following table shows an evaluation weight distribution table of the AHP method:

[0131] Evaluation index Weight value Importance ranking Predicted average thermal sensation index 0.309 1 Draft sensation index 0.142 4 Temperature fluctuation 0.158 3 Temperature uniformity 0.118 5 Vertical air temperature difference 0.189 2 Air distribution characteristic index 0.084 6

[0132] According to the weight values of each evaluation index determined by the AHP method, the parameter evaluation result values of each design parameter are calculated, and the design parameter with the largest parameter evaluation result value is selected from multiple parameter evaluation result values as the optimal design parameter of the air conditioner.

[0133] Optionally, in some embodiments, the first design parameter includes multiple groups of design parameters, and the parameter evaluation result includes multiple parameter evaluation results. After the above step S13, the method further includes:

[0134] According to multiple parameter evaluation results, the design parameter with the optimal parameter evaluation result is determined from multiple groups of design parameters as the target design parameter of the air conditioner.

[0135] Exemplarily, through the above method, multiple groups of design parameters corresponding to the air conditioner can be evaluated to generate multiple parameter evaluation results corresponding to multiple groups of design parameters. The designers of the air conditioner can select the target design parameter corresponding to the optimal parameter evaluation result from multiple parameter evaluation results to design the air conditioner, providing theoretical guidance for the scientific design of the air conditioner and saving time and resource investment.

[0136] Exemplarily, Figure 3It is a schematic diagram of a multi-objective optimization mapping relationship shown according to an exemplary embodiment. As Figure 3 shown, the input parameters are design parameters such as structural design, system control, operating characteristics, and environmental parameters. Among them, the structural design can be divided into the structural design of refrigeration system components such as evaporators and condensers, and the structural design of air outlets such as supply air outlets and return air outlets. The system control is divided into control strategies, set temperatures, etc.; the operating characteristics are divided into air supply characteristics, system energy efficiency, etc.; the environmental parameters are divided into room structural layout, air conditioner installation location, etc. The air supply parameters have a greater impact on the thermal environment of the air-conditioned room. Therefore, in the implementation case, the air deflector angle and the swing blade angle in the air outlet structure parameters are taken into consideration. The evaluation indicators are the temperature fluctuation, temperature uniformity, vertical air temperature difference, draft feeling index, and predicted mean vote specified in the corresponding implementation standards. For example, this implementation standard is GB / T 33658. And the air distribution characteristics index specified in the ASHRAE 113 implementation standard; the evaluation method is the relevant evaluation methods applicable to multi-objective optimization problems, including the linear weighted method, the TOPSIS method, and the AHP method; the optimization result is the optimal design parameters of the output air conditioner.

[0137] For example, Figure 4 It is a flowchart of a machine learning - multi-objective genetic algorithm shown according to an exemplary embodiment. As Figure 4 described, various machine learning models and multi-objective genetic algorithms can be adopted. Among them, the machine learning model can be selected according to the data set scale, robustness, etc.

[0138] In the process of establishing the machine learning model, first, data preprocessing is performed, such as data normalization and one-hot encoding, so that each feature variable is at the same order of magnitude and each state is independently stored;

[0139] After the data preprocessing is completed, it is divided into a training set and a test set according to a certain ratio (such as 7:3, 8:2, etc.) for model training. First, each hyperparameter is adjusted one by one and the corresponding better results are found. Finally, a set of hyperparameter combinations with the best prediction results is obtained. Through tuning, a machine learning model with the smallest error can be obtained. After obtaining the machine learning model, the multi-objective genetic algorithm is used for solving. The main framework for the multi-objective genetic algorithm to achieve optimization is divided into three parts: initializing the population, updating the population, and selection operation. Through the combination of the machine learning model and the multi-objective genetic algorithm, the multi-objective optimization of different design parameters can be achieved.

[0140] In the above manner, the first design parameters of the air conditioner are obtained, and the first design parameters are input into the evaluation index model to generate the first comfort evaluation index of the first design parameters. The evaluation index model is used to determine the comfort evaluation index corresponding to the design parameters based on the mapping relationship between the design parameters and the comfort evaluation index, and evaluate the first comfort evaluation index based on the multi-objective genetic algorithm to generate the parameter evaluation result of the first design parameters. Thus, the optimization of the comfort evaluation index is realized through the multi-objective genetic algorithm, and the design parameters are evaluated according to the comfort evaluation index to distinguish the advantages and disadvantages of the air conditioner design scheme based on comfort.

[0141] Figure 5 is a flowchart of a method for evaluating the design parameters of an air conditioner shown according to an exemplary embodiment, as Figure 5 shown, this method is applied to the terminal, and the above step S13 may include the following steps.

[0142] Step S131: Evaluate the first comfort evaluation index based on the multi-objective genetic algorithm to generate the frontier solution set data.

[0143] Step S132: Obtain the optimal comfort evaluation index of the air conditioner.

[0144] Step S133: According to the distance between the frontier solution set data and the optimal comfort evaluation index, determine the closeness between the first comfort evaluation index and the optimal comfort evaluation index through the TOPSIS algorithm.

[0145] Step S134: Take the closeness as the parameter evaluation result.

[0146] Exemplarily, in this embodiment, the first comfort evaluation index generated in the above steps is evaluated based on the multi-objective genetic algorithm to obtain the frontier solution set data of the comfort evaluation index. After obtaining the optimal comfort evaluation index of the air conditioner, calculate the distance between the frontier solution set data and the optimal comfort evaluation index, determine the closeness between the first comfort evaluation index and the optimal comfort evaluation index through the TOPSIS algorithm, and take this closeness as the parameter evaluation result of the first comfort evaluation index.

[0147] Exemplarily, by using the TOPSIS method to evaluate the frontier solution set obtained by the multi-objective genetic algorithm, a design parameter combination with the optimal comprehensive effect can be obtained. Based on the optimization effects of different objectives of the frontier solution set, the optimal design parameter combination is screened to meet different design requirements, so as to realize the design decision on the tendency of the target requirements. Exemplarily, the specific steps of comfort evaluation by the TOPSIS method are as follows:

[0148] S1. Establish an initial judgment matrix;

[0149] S2. Standardize the decision matrix;

[0150] S3. Establish a weighted standardized decision matrix;

[0151] S4. Calculate the closeness degree of the evaluation object.

[0152] The TOPSIS algorithm calculates the score and conducts a ranking evaluation by evaluating the distance between the evaluation frontier solution set and the ideal solution. The method for calculating the closeness degree of the evaluation object can be calculated by the following formula:

[0153]

[0154] where S i is the final score of each evaluation solution. The value of this S i ranges from [0, 1]. The closer the value of S i is to 1, the better the corresponding parameter evaluation solution; are the distances between the i-th evaluation solution and the positive ideal solution and the negative ideal solution respectively; z ij is the normalized weighted matrix; are the positive ideal solution and the negative ideal solution respectively; ω j is the weight of the j-th evaluation index; D i is the i-th evaluation solution.

[0155] Exemplarily, in this embodiment, the preset index relative importance ranking selected is: predicted average thermal sensation index > vertical air temperature difference > draft sensation index = temperature fluctuation > temperature uniformity = air distribution characteristic index. The evaluation results of the TOPSIS algorithm are shown in the following table:

[0156]

[0157] where the closeness degree S i The larger it is, the closer it is to the ideal plan. Therefore, the optimal design evaluated by the TOPSIS method is Plan 1: evaporator fin pitch 1.20 mm, tube outer diameter 6.00 mm, tube pitch 22.00 mm, air supply speed 3.5 m / s, set temperature 24 °C, air deflector angle 120°, and swing blade angle 0°, and the corresponding closeness degree is 0.8143.

[0158] Optionally, in some embodiments, the above step S133 includes:

[0159] Obtain the evaluation weight value of the comfort evaluation index;

[0160] Based on the evaluation weight value, determine the first evaluation score of the first comfort evaluation index and determine the second evaluation score of the optimal comfort evaluation index;

[0161] Determine the closeness based on the first evaluation score and the second evaluation score.

[0162] Exemplarily, in this embodiment, the first comfort evaluation index includes multiple comfort evaluation indexes, and the corresponding optimal comfort evaluation index also includes multiple comfort evaluation indexes. Based on the influence degree of each comfort evaluation index on the overall comfort, an evaluation weight value is set for each comfort evaluation index. According to the evaluation weight value, the first evaluation score is obtained by weighted averaging each comfort evaluation index of the first comfort evaluation index, and the second evaluation score is obtained by weighted averaging each comfort evaluation index of the optimal comfort evaluation index. Calculate the distance between the first evaluation score and the second evaluation score, so as to determine the closeness value of the first design parameter.

[0163] Optionally, in some embodiments, the above step S133 includes:

[0164] Obtain the preset matrix scale of the comfort evaluation index;

[0165] According to the preset matrix scale, determine the evaluation weight value of the comfort evaluation index through the Analytic Hierarchy Process (AHP) algorithm;

[0166] Based on the evaluation weight value, determine the first evaluation score of the first comfort evaluation index and the second evaluation score of the optimal comfort evaluation index;

[0167] Determine the closeness based on the first evaluation score and the second evaluation score.

[0168] Exemplarily, in this embodiment, the AHP algorithm is used to determine the evaluation weight value of each comfort evaluation index in the process of performing the TOPSIS algorithm. The calculation method of the weight value distribution based on the AHP algorithm can refer to the above embodiment and will not be elaborated here. According to the evaluation weight value, determine the first evaluation score of the first comfort evaluation index and the second evaluation score of the optimal comfort evaluation index. Calculate the distance between the first evaluation score and the second evaluation score, so as to determine the closeness value of the first design parameter.

[0169] Exemplarily, in some embodiments, the evaluation weights of each comfort evaluation parameter can also be set to be the same, that is, no weight analysis is performed on each comfort evaluation parameter, and the first comfort evaluation index is directly evaluated through the TOPSIS algorithm, so as to generate the parameter evaluation result of the first design parameter.

[0170] Through the above method, the evaluation method is expanded and comprehensively evaluated. A comprehensive evaluation model is constructed based on the TOSIS and AHP algorithms. The AHP method is used to calculate the weight value of each index, and then the TOSIS algorithm is used to calculate the relative closeness, so as to realize the comprehensive evaluation of the comfort evaluation index and improve the evaluation accuracy of the design parameter.

[0171] Figure 6 It is a block diagram of an air conditioner design parameter evaluation device shown according to an exemplary embodiment. Referring to Figure 6 , the device 100 includes an acquisition module 110, a generation module 120, and an execution module 130.

[0172] The acquisition module 110 is configured to acquire the first design parameter of the air conditioner;

[0173] The generation module 120 is configured to input the first design parameter into the evaluation index model to generate the first comfort evaluation index of the first design parameter. The evaluation index model is used to determine the comfort evaluation index corresponding to the design parameter based on the mapping relationship between the design parameter and the comfort evaluation index;

[0174] The execution module 130 is configured to evaluate the first comfort evaluation index based on a multi-objective genetic algorithm to generate a parameter evaluation result of the first design parameter.

[0175] Optionally, the execution module 130 is configured to:

[0176] Generate initial population data of the multi-objective genetic algorithm according to the first comfort evaluation index;

[0177] Use the initial population data as the first population data and determine the first objective function of the first population data;

[0178] In the case where the first objective function does not meet the preset convergence condition, determine the first fitness value of the first comfort evaluation index on the first objective function;

[0179] Screen according to the first fitness value from the first comfort evaluation index to generate the second population data;

[0180] Determine the second objective function of the second population data;

[0181] In the case where the second objective function meets the preset convergence condition, generate a parameter evaluation result according to the second population data and the first comfort evaluation index.

[0182] Optionally, the execution module 130 is configured to:

[0183] Perform normalization processing on the first comfort evaluation index to generate normalized data;

[0184] Obtain the preset matrix scale of the comfort evaluation index;

[0185] According to the preset matrix scale, determine the evaluation weight value of the comfort evaluation index through the analytic hierarchy process (AHP) algorithm;

[0186] Generate a parameter evaluation result based on the normalized data and evaluation weight values.

[0187] Optionally, the execution module 130 is configured to:

[0188] Obtain the evaluation weight values of multiple comfort evaluation indicators;

[0189] Perform weighted averaging on multiple comfort evaluation indicators based on the scoring weight values to generate comprehensive scoring data for the first set of parameters;

[0190] Use the comprehensive scoring data as the reference evaluation result.

[0191] Optionally, the execution module 130 includes:

[0192] A generation sub-module, configured to evaluate the first comfort evaluation indicator based on a multi-objective genetic algorithm to generate frontier solution set data;

[0193] An acquisition sub-module, configured to obtain the optimal comfort evaluation indicator of the air conditioner;

[0194] A determination sub-module, configured to determine the closeness between the first comfort evaluation indicator and the optimal comfort evaluation indicator through the TOPSIS algorithm according to the distance between the frontier solution set data and the optimal comfort evaluation indicator;

[0195] An execution sub-module, configured to use the closeness as the parameter evaluation result.

[0196] Optionally, the determination sub-module is configured to:

[0197] Obtain the evaluation weight values of the comfort evaluation indicators;

[0198] Based on the evaluation weight values, determine the first evaluation score of the first comfort evaluation indicator and determine the second evaluation score of the optimal comfort evaluation indicator;

[0199] Determine the closeness according to the first evaluation score and the second evaluation score.

[0200] Optionally, the determination sub-module is configured to:

[0201] Obtain the preset matrix scale of the comfort evaluation indicators;

[0202] According to the preset matrix scale, determine the evaluation weight values of the comfort evaluation indicators through the Analytic Hierarchy Process (AHP) algorithm;

[0203] Based on the evaluation weight values, determine the first evaluation score of the first comfort evaluation indicator and determine the second evaluation score of the optimal comfort evaluation indicator;

[0204] Determine the closeness based on the first evaluation score and the second evaluation score.

[0205] Optionally, the evaluation index model is trained and generated in the following manner;

[0206] Obtain the second design parameter of the air conditioner;

[0207] Perform data expansion on the first design parameter to generate multiple design parameters;

[0208] Based on a preset computational fluid dynamics (CFD) simulation module, perform simulation on multiple design parameters to generate multiple comfort evaluation indexes corresponding to the multiple design parameters;

[0209] Use the multiple design parameters and the multiple comfort evaluation indexes as the data training set for model training, and train the initial machine learning model to generate the evaluation index model.

[0210] Optionally, based on a preset computational fluid dynamics (CFD) simulation module, perform simulation on multiple design parameters to generate multiple comfort evaluation indexes corresponding to the multiple design parameters, including:

[0211] Perform simulation on the second design parameter based on the CFD simulation module to generate a simulation result corresponding to the second design parameter;

[0212] Obtain the second comfort evaluation index corresponding to the second design parameter;

[0213] When the error between the simulation result and the second comfort evaluation index is less than the preset error range, perform simulation on multiple design parameters based on the CFD simulation module to generate multiple comfort evaluation indexes.

[0214] Optionally, the first design parameter includes multiple groups of design parameters, and the parameter evaluation result includes multiple parameter evaluation results. The device further includes a determination module, which is configured to:

[0215] According to the multiple parameter evaluation results, determine the design parameter with the optimal parameter evaluation result from the multiple groups of design parameters as the target design parameter of the air conditioner.

[0216] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0217] The present disclosure also provides a computer-readable storage medium, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the air conditioner design parameter evaluation method provided by the present disclosure are implemented.

[0218] Figure 7It is a block diagram of an electronic device 700 shown according to an exemplary embodiment. For example, the electronic device 700 can be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0219] Referring Figure 7 , the electronic device 700 may include one or more of the following components: a processing component 702, a memory 704, a power supply component 706, a multimedia component 707, an audio component 710, an input / output interface 712, a sensor component 714, and a communication component 716.

[0220] The processing component 702 generally controls the overall operation of the electronic device 700, such as operations associated with display, telephone calls, data communication, camera operations, and recording operations. The processing component 702 may include one or more processors 720 to execute instructions to complete all or part of the steps of the above methods. In addition, the processing component 702 may include one or more modules to facilitate the interaction between the processing component 702 and other components. For example, the processing component 702 may include a multimedia module to facilitate the interaction between the multimedia component 707 and the processing component 702.

[0221] The memory 704 is configured to store various types of data to support the operation of the electronic device 700. Examples of these data include instructions for any application or method operating on the electronic device 700, contact data, phone book data, messages, pictures, videos, etc. The memory 704 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disk.

[0222] The power supply component 706 provides power to various components of the electronic device 700. The power supply component 706 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 700.

[0223] The multimedia component 707 includes a screen that provides an output interface between the electronic device 700 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can sense not only the boundaries of a touch or swipe action but also detect the duration and pressure associated with the touch or swipe operation. In some embodiments, the multimedia component 707 includes a front camera and / or a rear camera. When the electronic device 700 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each of the front camera and the rear camera can be a fixed optical lens system or have a focal length and optical zoom capabilities.

[0224] The audio component 710 is configured to output and / or input audio signals. For example, the audio component 710 includes a microphone (MIC) that is configured to receive external audio signals when the electronic device 700 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals can be further stored in the memory 704 or transmitted via the communication component 716. In some embodiments, the audio component 710 further includes a speaker for outputting audio signals.

[0225] The input / output interface 712 provides an interface between the processing component 702 and a peripheral interface module, which can be a keyboard, a click wheel, buttons, etc. These buttons can include but are not limited to: a home button, a volume button, a power button, and a lock button.

[0226] The sensor component 714 includes one or more sensors for providing an assessment of the various aspects of the status of the electronic device 700. For example, the sensor component 714 can detect the on / off state of the electronic device 700, the relative positioning of components, such as the display and the keypad of the electronic device 700. The sensor component 714 can also detect a change in the position of the electronic device 700 or a component of the electronic device 700, the presence or absence of user contact with the electronic device 700, the orientation or acceleration / deceleration of the electronic device 700, and the temperature change of the electronic device 700. The sensor component 714 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor component 714 can also include a light sensor, such as a CMOS or a CCD image sensor, for use in imaging applications. In some embodiments, the sensor component 714 can further include an acceleration sensor, a gyro sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0227] The communication component 716 is configured to facilitate communication between the electronic device 700 and other devices in a wired or wireless manner. The electronic device 700 can access a communication standard-based wireless network, such as WiFi, 2G, or 3G, or a combination thereof. In an exemplary embodiment, the communication component 716 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 716 further includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0228] In an exemplary embodiment, the electronic device 700 can be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the above-described air conditioner design parameter evaluation method.

[0229] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 704 including instructions, and the above instructions can be executed by a processor 720 of the electronic device 700 to complete the above-described air conditioner design parameter evaluation method. For example, the non-transitory computer-readable storage medium can be a ROM, Random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0230] In addition to being an independent electronic device, the above-mentioned device can also be a part of an independent electronic device. For example, in one embodiment, the device can be an integrated circuit (IC) or a chip. The integrated circuit can be a single IC or a collection of multiple ICs. The chip can include, but is not limited to, the following types: GPU (Graphics Processing Unit), CPU (Central Processing Unit), FPGA (Field Programmable Gate Array), DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), SOC (System on Chip), etc. The above-mentioned integrated circuit or chip can be used to execute executable instructions (or code) to implement the above-mentioned air conditioner design parameter evaluation method. The executable instructions can be stored in the integrated circuit or chip, or obtained from other devices or equipment. For example, the integrated circuit or chip includes a processor, a memory, and an interface for communicating with other devices. The executable instructions can be stored in the memory and, when executed by the processor, implement the above-mentioned air conditioner design parameter evaluation method. Or, the integrated circuit or chip can receive the executable instructions through the interface and transmit them to the processor for execution to implement the above-mentioned air conditioner design parameter evaluation method.

[0231] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program that can be executed by a programmable device, and the computer program has a code portion for executing the above-mentioned air conditioner design parameter evaluation method when executed by the programmable device.

[0232] Those skilled in the art will readily think of other embodiments of the present disclosure after considering the specification and practicing the present disclosure. The present disclosure aims to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the following claims.

[0233] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. An evaluation method for the design parameters of an air conditioner, characterized in that, it includes: Obtain the first design parameter of the air conditioner; Input the first design parameter into the evaluation index model to generate the first comfort evaluation index of the first design parameter. The evaluation index model is used to determine the comfort evaluation index corresponding to the design parameter based on the mapping relationship between the design parameter and the comfort evaluation index; Evaluate the first comfort evaluation index based on the multi-objective genetic algorithm to generate the parameter evaluation result of the first design parameter.

2. The method according to claim 1, characterized in that, The evaluating the first comfort evaluation index based on the multi-objective genetic algorithm to generate the parameter evaluation result of the first design parameter includes: Generate the initial population data of the multi-objective genetic algorithm according to the first comfort evaluation index; Take the initial population data as the first population data and determine the first objective function of the first population data; In the case that the first objective function does not meet the preset convergence condition, determine the first fitness value of the first comfort evaluation index on the first objective function; Screen from the first comfort evaluation index according to the first fitness value to generate the second population data; Determine the second objective function of the second population data; In the case that the second objective function meets the preset convergence condition, generate the parameter evaluation result according to the second population data and the first comfort evaluation index.

3. The method according to claim 1, characterized in that, The evaluating the first comfort evaluation index based on the multi-objective genetic algorithm to generate the parameter evaluation result of the first design parameter includes: Perform normalization processing on the first comfort evaluation index to generate normalized data; Obtain the preset matrix scale of the comfort evaluation index; Determine the evaluation weight value of the comfort evaluation index through the Analytic Hierarchy Process (AHP) algorithm according to the preset matrix scale; Generate the parameter evaluation result according to the normalized data and the evaluation weight value.

4. The method according to claim 1, characterized in that, The first comfort evaluation index includes multiple comfort evaluation indexes. The evaluating the first comfort evaluation index based on the multi-objective genetic algorithm to generate the parameter evaluation result of the first design parameter includes: Obtain the evaluation weight values of the multiple comfort evaluation indexes; Perform weighted averaging on the multiple comfort evaluation indexes based on the scoring weight values to generate the comprehensive scoring data of the first set parameter; Take the comprehensive scoring data as the reference evaluation result.

5. The method according to claim 1, characterized in that, The evaluating the first comfort evaluation index based on the multi-objective genetic algorithm to generate the parameter evaluation result of the first design parameter includes: Evaluate the first comfort evaluation index based on the multi-objective genetic algorithm to generate the frontier solution set data; Obtain the optimal comfort evaluation index of the air conditioner; According to the distance between the frontier solution set data and the optimal comfort evaluation index, determine the closeness between the first comfort evaluation index and the optimal comfort evaluation index through the TOPSIS algorithm; Take the closeness as the parameter evaluation result.

6. The method according to claim 5, wherein, the determining the closeness between the first comfort evaluation index and the optimal comfort evaluation index through the TOPSIS algorithm includes: obtain the evaluation weight value of the comfort evaluation index; based on the evaluation weight value, determine the first evaluation score of the first comfort evaluation index and determine the second evaluation score of the optimal comfort evaluation index; determine the closeness according to the first evaluation score and the second evaluation score.

7. The method according to claim 5, wherein, the determining the closeness between the first comfort evaluation index and the optimal comfort evaluation index through the TOPSIS algorithm includes: obtain the preset matrix scale of the comfort evaluation index; according to the preset matrix scale, determine the evaluation weight value of the comfort evaluation index through the Analytic Hierarchy Process (AHP) algorithm; based on the evaluation weight value, determine the first evaluation score of the first comfort evaluation index and determine the second evaluation score of the optimal comfort evaluation index; determine the closeness according to the first evaluation score and the second evaluation score.

8. The method according to any one of claims 1-7, wherein, the evaluation index model is trained and generated in the following manner; obtain the second design parameter of the air conditioner; perform data expansion on the first design parameter to generate multiple design parameters; based on a preset Computational Fluid Dynamics (CFD) simulation module, perform simulation on the multiple design parameters to generate multiple comfort evaluation indexes corresponding to the multiple design parameters; use the multiple design parameters and the multiple comfort evaluation indexes as the data training set for model training, and train an initial machine learning model to generate the evaluation index model.

9. The method according to claim 8, wherein, the performing simulation on the multiple design parameters based on the preset Computational Fluid Dynamics (CFD) simulation module to generate multiple comfort evaluation indexes corresponding to the multiple design parameters includes: perform simulation on the second design parameter based on the CFD simulation module to generate a simulation result corresponding to the second design parameter; obtain the second comfort evaluation index corresponding to the second design parameter; when the error between the simulation result and the second comfort evaluation index is less than a preset error range, perform simulation on the multiple design parameters based on the CFD simulation module to generate the multiple comfort evaluation indexes.

10. The method according to claim 1, wherein, the first design parameter includes multiple groups of design parameters, the parameter evaluation result includes multiple parameter evaluation results, and the method includes: Based on the evaluation results of the multiple parameters, determine the design parameters with the optimal parameter evaluation results from the multiple groups of design parameters as the target design parameters of the air conditioner.

11. An air conditioner design parameter evaluation device, characterized in that, the device includes: an acquisition module configured to acquire the first design parameters of the air conditioner; a generation module configured to input the first design parameters into an evaluation index model to generate a first comfort evaluation index of the first design parameters, and the evaluation index model is used to determine the comfort evaluation index corresponding to the design parameters based on the mapping relationship between the design parameters and the comfort evaluation index; an execution module configured to evaluate the first comfort evaluation index based on a multi-objective genetic algorithm to generate a parameter evaluation result of the first design parameters.

12. An electronic device, characterized in that, it includes: a processor; a memory for storing instructions executable by the processor; wherein, the processor is configured to execute the executable instructions to implement the steps of the air conditioner design parameter evaluation method according to any one of claims 1-10.

13. A computer-readable storage medium, on which computer program instructions are stored, characterized in that, when the program instructions are executed by a processor, the steps of the air conditioner design parameter evaluation method according to any one of claims 1-10 are implemented.

Images