Method and system for testing energy efficiency of electric kettle

Abstract

The invention discloses an electric kettle energy efficiency test method and system. The method comprises the steps of obtaining initial data, heat preservation time and power consumption of an electric kettle; obtaining energy efficiency data according to the initial data and the power consumption, obtaining heat preservation data based on the heat preservation time, and performing causal analysis on the initial data to obtain influence data; performing clustering analysis on the heat preservation data through the energy efficiency data to obtain a loss factor, and establishing an electric kettle energy efficiency test model based on the loss factor, the influence data and the energy efficiency data; and optimizing the electric kettle energy efficiency test model by adopting a sparrow search algorithm, inputting to-be-tested data into the electric kettle energy efficiency test model, and outputting a test result. The invention not only provides a scientific and systematic method for the energy efficiency test of the electric kettle, but also makes an important contribution to the promotion of energy conservation and emission reduction and sustainable development through the automatic test process.

Description

Technical Field

[0001] The present invention relates to the technical field of energy efficiency testing of household appliances, and in particular to an energy efficiency testing method and system for an electric kettle. Background Art

[0002] With the growing global demand for energy and the strengthening of environmental protection awareness, energy efficiency testing of household appliances has gradually become the focus of attention of consumers and manufacturers. As one of the common household appliances, the energy efficiency of electric kettles directly affects the energy consumption and usage costs of users. However, the traditional energy efficiency testing methods of electric kettles have many shortcomings: the testing process is cumbersome, inefficient, and it is difficult to accurately evaluate the energy efficiency performance of electric kettles under different usage conditions. In addition, most of the existing technologies ignore the potential impact of environmental factors on energy efficiency and lack accurate evaluation of the performance of electric kettles in actual use environments. Therefore, it is particularly important to develop an efficient and accurate energy efficiency testing method and system for electric kettles to meet the market demand for energy-saving products and provide consumers with a reliable basis for purchase. Summary of the invention

[0003] The purpose of the present invention is to provide a method and system for testing the energy efficiency of an electric kettle.

[0004] To achieve the above object, the present invention is implemented according to the following technical solutions:

[0005] The present invention comprises the following steps:

[0006] Get the initial data, heat preservation time and power consumption of the electric kettle;

[0007] Obtain energy efficiency data based on the initial data and power consumption, obtain insulation data based on the insulation time, and perform causal analysis on the initial data to obtain impact data;

[0008] Performing cluster analysis on the heat preservation data through the energy efficiency data to obtain a loss factor, and establishing an electric kettle energy efficiency test model based on the loss factor, the impact data and the energy efficiency data;

[0009] The electric kettle energy efficiency test model is optimized by using a sparrow search algorithm, and the data to be tested is input into the electric kettle energy efficiency test model to output a test result.

[0010] Furthermore, the method for obtaining the initial data, heat preservation time and power consumption of the electric kettle includes:

[0011] The initial data includes ambient temperature, rated volume, initial water temperature, initial depth of water and initial mass. After the electric kettle heats the rated volume of pure water to boiling and turns off the power, the time it takes to maintain the boiling water temperature and the time it takes to drop to the target temperature is taken as the insulation time. The power consumption is the power consumed from heating the water to the initial temperature to boiling and then turning off the power.

[0012] Furthermore, the method for obtaining energy efficiency data according to the initial data and power consumption includes:

[0013] The calculation formula for energy efficiency data is:

[0014]

[0015] Where E is the energy efficiency data of the electric kettle, C is the specific heat capacity of water, G is the mass of water, T0 is the initial water temperature, T is the boiling water temperature, λ is the heating method revision coefficient, a is a constant, and Q is the power consumption.

[0016] Furthermore, a method for obtaining insulation data based on the insulation time includes:

[0017] The calculation formula of thermal insulation coefficient is:

[0018]

[0019] where k d is the insulation coefficient, T env is the ambient temperature data, T ref is the reference temperature, T d is the current water temperature, including the target water temperature and boiling water temperature. The target water temperature is 80°C. Δt is the insulation time corresponding to the current water temperature. ΔT is the change in water temperature. α is the ambient temperature influencing factor. β and γ are the time change rate influencing factors. The insulation coefficient that maintains the boiling water temperature and drops to the target water temperature is used as the insulation data.

[0020] Furthermore, the method of performing causal analysis on the initial data to obtain the influencing data includes:

[0021] The regression model is established using the initial data as feature data and the energy efficiency data as predicted values. The predicted values ​​are:

[0022]

[0023] in is the predicted value of the tth decision tree, f is the decision tree, v i is the i-th leaf node of the decision tree, corresponding to the i-th feature data, I is the sample set of i in the t-th decision tree, w i is the weight vector, the regularized loss function of the regression model:

[0024]

[0025] in represents the loss function of the kth feature data, which is the cross entropy loss, n is the number of feature data, T is the number of leaf nodes, γ is the regularization parameter, λ is the coefficient of the L2 regularization term, and wj is the weight of leaf node j, the split gain of the decision tree:

[0026]

[0027] Among them I L and I R are the sample sets of the left subtree and the right subtree after the decision tree splits, ζ is the penalty coefficient, is the first-order derivative, representing the gradient, represents the second-order derivative,

[0028] The feature data is selected based on the splitting gain, and the feature data whose splitting gain is greater than a preset gain threshold is used as the influencing data.

[0029] Furthermore, the method of obtaining the loss factor by clustering the insulation data through the energy efficiency data includes:

[0030] Use the insulation data to form data points and cluster the data points:

[0031] The local density is:

[0032]

[0033] where d k (x i ,x j ) is the data point x i and x j The Euclidean distance between the two, d is the dimension of the data point, k is a constant, indicating the number of nearest neighbors considered, kNN(x i ) is x i The nearest neighbor set of , the average density of the cluster is:

[0034]

[0035] in is the average density of cluster l, N(l) is the number of data points in cluster l,

[0036] Calculate the local average energy efficiency data of the data point and the average energy efficiency data within the cluster to obtain the loss factor:

[0037]

[0038] Where S i is the loss factor of the ith insulation data, and the local average energy efficiency data is The local average energy efficiency data is p i is the energy efficiency data corresponding to the i-th insulation data, p max is the maximum energy efficiency data, pmin This is the minimum energy efficiency data.

[0039] Furthermore, a method for establishing an electric kettle energy efficiency test model based on the loss factor, the impact data and the energy efficiency data comprises:

[0040] Through EM method training, the Gaussian mixture model is obtained:

[0041]

[0042] Where p(x,y) is a Gaussian mixture model, x and y are feature indices in X and Y respectively, X is the impact data and loss factor, Y is the energy efficiency data set, and a e is the weight of the e-th Gaussian component, E is the number of Gaussian components, N(ν e ,Φ e ) is ν e and Φ e Gaussian distribution, ν e is the mean vector of the e-th Gaussian component, Φ e is the covariance matrix of the e-th Gaussian component,

[0043] Decomposition ν e and Φ e :

[0044]

[0045] Where T represents the transpose of the matrix, Φ e,YX is the covariance between X and Y in the e-th Gaussian component,

[0046] The conditional probability distribution of the output of the Gaussian mixture regression model:

[0047]

[0048] Where h represents the mixing coefficient, I e (x) is the regularization term covariance matrix,

[0049] The expected output of the Gaussian mixture regression model is:

[0050]

[0051] The trained Gaussian mixture regression model is used as the electric kettle energy efficiency test model.

[0052] Furthermore, the method of optimizing the electric kettle energy efficiency test model by using a sparrow search algorithm comprises:

[0053] The sparrow search algorithm is used to optimize the hyperparameters of the electric kettle energy efficiency test model. The position update formula of the discoverer in the sparrow search algorithm is:

[0054]

[0055] in represents the position of the i-th sparrow in the j-th dimension in the d+1-th iteration, It represents the position of the i-th sparrow in the j-th dimension in the d-th iteration, t(N) is a random number generated by t distribution with N degrees of freedom, N represents the current iteration number, η is the fitness weight, η=1-d / N max , N max is the maximum number of iterations, L is the j-dimensional unit row vector, used for direction adjustment when updating the position, and S T Represent the warning value and safety value respectively.

[0056] The follower's position update formula is:

[0057]

[0058] in represents the position of the sparrow with the lowest fitness in the dth iteration, is the position with the best fitness controlled by the discoverer at the d+1th iteration, A1 is a d-dimensional row vector, and the elements in A1 are only 1 and -1. is the transpose of A1, n is the total number of sparrows,

[0059] Scout position update formula:

[0060]

[0061] in is the position of the sparrow with the highest fitness in the dth iteration, G is a random number between -1 and 1, δ is a random number that obeys the standard normal distribution, ε is a constant close to 0, and f i represents the individual fitness value, f best and f u The best and worst fitness in the current population,

[0062] In each iteration, the best sparrow individual is selected according to the fitness value, and the best sparrow individual is perturbed according to the tangent flight mechanism:

[0063] Y d+1 =Y d +S step tanθ

[0064] Where S step is the step length, θ is the angle in the tangent flight perturbation mechanism, θ is from 0 to Increase,

[0065] Iterate and update the sparrow position until the maximum number of iterations is reached.

[0066] An electric kettle energy efficiency testing system, characterized by comprising:

[0067] The acquisition module obtains the initial data, heat preservation time and power consumption of the electric kettle;

[0068] a calculation module, obtaining energy efficiency data according to the initial data and the power consumption, obtaining heat preservation data based on the heat preservation time, performing causal analysis on the initial data to obtain influence data, performing cluster analysis on the heat preservation data through the energy efficiency data to obtain a loss factor, and establishing an electric kettle energy efficiency test model based on the loss factor, the influence data and the energy efficiency data;

[0069] An optimization module, which uses a sparrow search algorithm to optimize the electric kettle energy efficiency test model;

[0070] The output module inputs the data to be tested into the electric kettle energy efficiency test model to output the test results.

[0071] The beneficial effects of the present invention are:

[0072] The present invention significantly improves the accuracy of the electric kettle energy efficiency test by integrating multi-source observation data and adopting advanced data analysis technology. The testing method of the present invention helps the electric kettle meet higher environmental protection and energy efficiency standards and promotes the development of green energy products. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 The present invention is a flowchart of the steps of an electric kettle energy efficiency testing method and system. DETAILED DESCRIPTION

[0074] The present invention is further described below by means of specific embodiments. The illustrative embodiments and descriptions of the present invention are used to explain the present invention but are not intended to limit the present invention.

[0075] The present invention provides an electric kettle energy efficiency testing method and system, comprising the following steps:

[0076] like Figure 1 As shown, in this embodiment, the following steps are included:

[0077] Get the initial data, heat preservation time and power consumption of the electric kettle;

[0078] In the actual evaluation, the relative humidity was 55% and the atmospheric pressure was 101.325 kPa. Three electric kettles with a capacity of 1.5 liters were selected for testing. The three groups of ambient temperature, initial water temperature, initial depth, initial mass and power consumption of the three electric kettles were as follows: Group 1, kettle 1, [20℃, 18℃, 200 mm, 1.5 kg, 0.17 kw·h], kettle 2, [20, 18, 210, 1.5, 0.18], kettle 3, [20, 18, 220, 1.5, 0.19]; Group 2, kettle 1, [25, 22, 180, 1.2, 0.13], kettle 2, [25, 22, 190, 1.2, 0.14], kettle 3, [25 , 22, 200, 1.2, 0.15]; 3 groups, pot 1, [30, 28, 150, 1, 0.12], pot 2, [30, 28, 160, 1, 0.13], pot 3, [30, 28, 170, 1, 0.13]; the holding time is: group 1, ambient temperature 20°C, pot 1, [45s, 8 minutes], pot 2, [47, 8.5], pot 3, [50, 9]; group 2, 25°C, pot 1, [46, 8.1], pot 2, [48, 8.6], pot 3, [51, 9.1]; group 2, 30°C, pot 1, [47, 8.2], pot 2, [49, 8.7], pot 3, [52, 9.2];

[0079] Obtain energy efficiency data based on the initial data and power consumption, obtain insulation data based on the insulation time, and perform causal analysis on the initial data to obtain impact data;

[0080] In the actual evaluation, the boiling water temperature is 100°C, the heating method revision coefficient is 1, and the energy efficiency data are: Group 1, pot 1, 0.90, pot 2, 0.85, pot 3, 0.82; Group 2, pot 1, 0.86, pot 2, 0.84, pot 3, 0.83; Group 3, pot 1, 0.86, pot 2, 0.8, pot 3, 0.8; The insulation data are: Group 1, 20°C, pot 1, [5.51, 2.75], pot 2, [6.01, 3], pot 3, [6.51, 3.25]; 2 groups, 25℃, pot 1, [5.52, 2.77], pot 2, [6.02, 3.02], pot 3, [6.52, 3.27]; 2 groups, 30℃, pot 1, [5.53, 2.79], pot 2, [6.03, 3.04], pot 3, [6.53, 3.29];

[0081] Influencing data include ambient temperature, initial water temperature and initial mass;

[0082] Performing cluster analysis on the heat preservation data through the energy efficiency data to obtain a loss factor, and establishing an electric kettle energy efficiency test model based on the loss factor, the impact data and the energy efficiency data;

[0083] In the actual evaluation, the loss factors are: Group 1, pot 1, 0.88, pot 2, 0.83, pot 3, 0.8; Group 2, pot 1, 0.83, pot 2, 0.82, pot 3, 0.81; Group 3, pot 1, 0.84, pot 2, 0.78, pot 3, 0.77;

[0084] The electric kettle energy efficiency test model is optimized by using a sparrow search algorithm, and the data to be tested is input into the electric kettle energy efficiency test model to output a test result.

[0085] In this embodiment, the method for obtaining the initial data, heat preservation time and power consumption of the electric kettle includes:

[0086] The initial data includes ambient temperature, rated volume, initial water temperature, initial depth of water and initial mass. After the electric kettle heats the rated volume of pure water to boiling and turns off the power, the time it takes to maintain the boiling water temperature and the time it takes to drop to the target temperature is taken as the insulation time. The power consumption is the power consumed from heating the water to the initial temperature to boiling and then turning off the power.

[0087] In this embodiment, the method for obtaining energy efficiency data according to the initial data and power consumption includes:

[0088] The calculation formula for energy efficiency data is:

[0089]

[0090] Where E is the energy efficiency data of the electric kettle, C is the specific heat capacity of water, G is the mass of water, T0 is the initial water temperature, T is the boiling water temperature, λ is the heating method revision coefficient, a is a constant, and Q is the power consumption.

[0091] In this embodiment, the method for obtaining the insulation data based on the insulation time includes:

[0092] The calculation formula of thermal insulation coefficient is:

[0093]

[0094] where k d is the insulation coefficient, T env is the ambient temperature data, T ref is the reference temperature, T d is the current water temperature, including the target water temperature and boiling water temperature. The target water temperature is 80°C. Δt is the insulation time corresponding to the current water temperature. ΔT is the change in water temperature. α is the ambient temperature influencing factor. β and γ are the time change rate influencing factors. The insulation coefficient that maintains the boiling water temperature and drops to the target water temperature is used as the insulation data.

[0095] In this embodiment, the method of performing causal analysis on the initial data to obtain the influencing data includes:

[0096] The regression model is established using the initial data as feature data and the energy efficiency data as predicted values. The predicted values ​​are:

[0097]

[0098] in is the predicted value of the tth decision tree, f is the decision tree, v i is the i-th leaf node of the decision tree, corresponding to the i-th feature data, I is the sample set of i in the t-th decision tree, w i is the weight vector, the regularized loss function of the regression model:

[0099]

[0100] in represents the loss function of the kth feature data, which is the cross entropy loss, n is the number of feature data, T is the number of leaf nodes, γ is the regularization parameter, λ is the coefficient of the L2 regularization term, and w j is the weight of leaf node j, the split gain of the decision tree:

[0101]

[0102] Among them I L and I R are the sample sets of the left subtree and the right subtree after the decision tree splits, ζ is the penalty coefficient, is the first-order derivative, representing the gradient, represents the second-order derivative,

[0103] The feature data is selected based on the splitting gain, and the feature data whose splitting gain is greater than a preset gain threshold is used as the influencing data.

[0104] In this embodiment, the method of obtaining the loss factor by clustering the insulation data through the energy efficiency data includes:

[0105] Use the insulation data to form data points and cluster the data points:

[0106] The local density is:

[0107]

[0108] where d k (x i ,x j ) is the data point x i and x j The Euclidean distance between the two, d is the dimension of the data point, k is a constant, indicating the number of nearest neighbors considered, kNN(x i ) is x iThe nearest neighbor set of , the average density of the cluster is:

[0109]

[0110] in is the average density of cluster l, N(l) is the number of data points in cluster l,

[0111] Calculate the local average energy efficiency data of the data point and the average energy efficiency data within the cluster to obtain the loss factor:

[0112]

[0113] Where S i is the loss factor of the ith insulation data, and the local average energy efficiency data is The local average energy efficiency data is p i is the energy efficiency data corresponding to the i-th insulation data, p max is the maximum energy efficiency data, p min This is the minimum energy efficiency data.

[0114] In this embodiment, the method for establishing the electric kettle energy efficiency test model based on the loss factor, the impact data and the energy efficiency data includes:

[0115] Through EM method training, the Gaussian mixture model is obtained:

[0116]

[0117] Where p(x,y) is a Gaussian mixture model, x and y are feature indices in X and Y respectively, X is the impact data and loss factor, Y is the energy efficiency data set, and a e is the weight of the e-th Gaussian component, E is the number of Gaussian components, N(ν e ,Φ e ) is ν e and Φ e Gaussian distribution, ν e is the mean vector of the e-th Gaussian component, Φ e is the covariance matrix of the e-th Gaussian component,

[0118] Decomposition ν e and Φ e :

[0119]

[0120] Where T represents the transpose of the matrix, Φ e,YX is the covariance between X and Y in the e-th Gaussian component,

[0121] The conditional probability distribution of the output of the Gaussian mixture regression model:

[0122]

[0123] Where h represents the mixing coefficient, I e (x) is the regularization term covariance matrix,

[0124] The expected output of the Gaussian mixture regression model is:

[0125]

[0126] The trained Gaussian mixture regression model is used as the electric kettle energy efficiency test model.

[0127] In this embodiment, the method of optimizing the electric kettle energy efficiency test model by using the sparrow search algorithm includes:

[0128] The sparrow search algorithm is used to optimize the hyperparameters of the electric kettle energy efficiency test model. The position update formula of the discoverer in the sparrow search algorithm is:

[0129]

[0130] in represents the position of the i-th sparrow in the j-th dimension in the d+1-th iteration, It represents the position of the i-th sparrow in the j-th dimension in the d-th iteration, t(N) is a random number generated by t distribution with N degrees of freedom, N represents the current iteration number, η is the fitness weight, η=1-d / N max , N max is the maximum number of iterations, L is the j-dimensional unit row vector, used for direction adjustment when updating the position, and S T Represent the warning value and safety value respectively.

[0131] The follower's position update formula is:

[0132]

[0133] in represents the position of the sparrow with the lowest fitness in the dth iteration, is the position with the best fitness controlled by the discoverer at the d+1th iteration, A1 is a d-dimensional row vector, and the elements in A1 are only 1 and -1. is the transpose of A1, n is the total number of sparrows,

[0134] Scout position update formula:

[0135]

[0136] in is the position of the sparrow with the highest fitness in the dth iteration, G is a random number between -1 and 1, δ is a random number that obeys the standard normal distribution, ε is a constant close to 0, and f i represents the individual fitness value, f best and f u The best and worst fitness in the current population,

[0137] In each iteration, the best sparrow individual is selected according to the fitness value, and the best sparrow individual is perturbed according to the tangent flight mechanism:

[0138] Y d+1 =Y d +S step tanθ

[0139] Where S step is the step length, θ is the angle in the tangent flight perturbation mechanism, θ is from 0 to Increase,

[0140] Iterate and update the sparrow position until the maximum number of iterations is reached.

[0141] An electric kettle energy efficiency testing system, characterized by comprising:

[0142] The acquisition module obtains the initial data, heat preservation time and power consumption of the electric kettle;

[0143] a calculation module, obtaining energy efficiency data according to the initial data and the power consumption, obtaining heat preservation data based on the heat preservation time, performing causal analysis on the initial data to obtain influence data, performing cluster analysis on the heat preservation data through the energy efficiency data to obtain a loss factor, and establishing an electric kettle energy efficiency test model based on the loss factor, the influence data and the energy efficiency data;

[0144] An optimization module, which uses a sparrow search algorithm to optimize the electric kettle energy efficiency test model;

[0145] The output module inputs the data to be tested into the electric kettle energy efficiency test model to output the test results.

[0146] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for testing the energy efficiency of an electric kettle, characterized in that: The following steps are involved: Get the initial data, heat preservation time and power consumption of the electric kettle; Obtain energy efficiency data based on the initial data and power consumption, obtain insulation data based on the insulation time, and perform causal analysis on the initial data to obtain impact data; Performing cluster analysis on the heat preservation data through the energy efficiency data to obtain a loss factor, and establishing an electric kettle energy efficiency test model based on the loss factor, the impact data and the energy efficiency data; The electric kettle energy efficiency test model is optimized by using a sparrow search algorithm, and the data to be tested is input into the electric kettle energy efficiency test model to output a test result.

2. The method for testing the energy efficiency of an electric kettle according to claim 1, characterized in that: The method for obtaining the initial data, heat preservation time and power consumption of the electric kettle includes: The initial data includes ambient temperature, rated volume, initial water temperature, initial depth of water and initial mass. After the electric kettle heats the rated volume of pure water to boiling and turns off the power, the time it takes to maintain the boiling water temperature and the time it takes to drop to the target temperature is taken as the insulation time. The power consumption is the power consumed from heating the water to the initial temperature to boiling and then turning off the power.

3. The method for testing the energy efficiency of an electric kettle according to claim 1, characterized in that: The method for obtaining energy efficiency data according to the initial data and power consumption includes: The calculation formula for energy efficiency data is: Where E is the energy efficiency data of the electric kettle, C is the specific heat capacity of water, G is the mass of water, T0 is the initial water temperature, T is the boiling water temperature, λ is the heating method revision coefficient, a is a constant, and Q is the power consumption.

4. The method for testing the energy efficiency of an electric kettle according to claim 1, characterized in that: The method for obtaining the insulation data based on the insulation time comprises: The calculation formula of thermal insulation coefficient is: where k d is the insulation coefficient, T env is the ambient temperature data, T ref is the reference temperature, T d is the current water temperature, including the target water temperature and boiling water temperature. The target water temperature is 80°C. Δt is the insulation time corresponding to the current water temperature. ΔT is the change in water temperature. α is the ambient temperature influencing factor. β and γ are the time change rate influencing factors. The insulation coefficient that maintains the boiling water temperature and drops to the target water temperature is used as the insulation data.

5. The method for testing the energy efficiency of an electric kettle according to claim 1, characterized in that: The method of performing causal analysis on the initial data to obtain the impact data comprises: The regression model is established using the initial data as feature data and the energy efficiency data as predicted values. The predicted values ​​are: in is the predicted value of the tth decision tree, f is the decision tree, v i is the i-th leaf node of the decision tree, corresponding to the i-th feature data, I is the sample set of i in the t-th decision tree, w i is the weight vector, the regularized loss function of the regression model: in represents the loss function of the kth feature data, which is the cross entropy loss, n is the number of feature data, T is the number of leaf nodes, γ is the regularization parameter, λ is the coefficient of the L2 regularization term, and w j is the weight of leaf node j, the split gain of the decision tree: Among them I L and I R are the sample sets of the left subtree and the right subtree after the decision tree splits, ζ is the penalty coefficient, is the first-order derivative, representing the gradient, represents the second-order derivative, The feature data is selected based on the splitting gain, and the feature data whose splitting gain is greater than a preset gain threshold is used as the influencing data.

6. The method for testing the energy efficiency of an electric kettle according to claim 1, characterized in that: The method for obtaining a loss factor by clustering the insulation data through the energy efficiency data includes: Use the insulation data to form data points and cluster the data points: The local density is: where d k (x i , x j ) is the data point x i and x j The Euclidean distance between the two, d is the dimension of the data point, k is a constant, indicating the number of nearest neighbors considered, kNN(x i ) is X i The nearest neighbor set of , the average density of the cluster is: in is the average density of cluster l, N(l) is the number of data points in cluster l, Calculate the local average energy efficiency data of the data point and the average energy efficiency data within the cluster to obtain the loss factor: Where S i is the loss factor of the ith insulation data, and the local average energy efficiency data is The local average energy efficiency data is p i is the energy efficiency data corresponding to the ith insulation data, p max is the maximum energy efficiency data, p min This is the minimum energy efficiency data.

7. The method for testing the energy efficiency of an electric kettle according to claim 1, characterized in that: The method for establishing an electric kettle energy efficiency test model based on the loss factor, the impact data and the energy efficiency data comprises: Through EM method training, the Gaussian mixture model is obtained: Where p(x, y) is a Gaussian mixture model, x and y are feature indices in X and Y respectively, X is the impact data and loss factor, Y is the energy efficiency data set, and a e is the weight of the e-th Gaussian component, E is the number of Gaussian components, N(v e , Φ e ) is v e and Φ e Gaussian distribution, v e is the mean vector of the e-th Gaussian component, Φ e is the covariance matrix of the e-th Gaussian component, Decomposition e and Φ e : Where T represents the transpose of the matrix, Φ e，YX is the covariance between X and Y in the e-th Gaussian component, The conditional probability distribution of the output of the Gaussian mixture regression model: Where h represents the mixing coefficient, I e (X) is the regularization term covariance matrix, The expected output of the Gaussian mixture regression model is: The trained Gaussian mixture regression model is used as the electric kettle energy efficiency test model.

8. The method for testing the energy efficiency of an electric kettle according to claim 1, characterized in that: The method for optimizing the electric kettle energy efficiency test model by using a sparrow search algorithm comprises: The sparrow search algorithm is used to optimize the hyperparameters of the electric kettle energy efficiency test model. The position update formula of the discoverer in the sparrow search algorithm is: in represents the position of the i-th sparrow in the j-th dimension in the d+1-th iteration, It represents the position of the i-th sparrow in the j-th dimension in the d-th iteration, t(N) is a random number generated by t distribution with N degrees of freedom, N represents the current iteration number, η is the fitness weight, η=1-d / N max , N max is the maximum number of iterations, L is the j-dimensional unit row vector, used for direction adjustment when updating the position, and S T Represent the warning value and safety value respectively. The follower's position update formula is: in represents the position of the sparrow with the lowest fitness in the dth iteration, is the position with the best fitness controlled by the discoverer at the d+1th iteration, A1 is a d-dimensional row vector, and the elements in A1 are only 1 and -1. is the transpose of A1, n is the total number of sparrows, Scout position update formula: in is the position of the sparrow with the highest fitness in the dth iteration, G is a random number between -1 and 1, 6 is a random number that obeys the standard normal distribution, ε is a constant close to 0, fi represents the individual fitness value, and f best and f u The best and worst fitness in the current population, In each iteration, the best sparrow individual is selected according to the fitness value, and the best sparrow individual is perturbed according to the tangent flight mechanism: Y d+1 =Y d +S step ·tanθ Where S step is the step length, θ is the angle in the tangent flight perturbation mechanism, θ is from 0 to Increase, Iterate and update the sparrow position until the maximum number of iterations is reached.

9. An electric kettle energy efficiency testing system, characterized in that: include: The acquisition module obtains the initial data, heat preservation time and power consumption of the electric kettle; a calculation module, obtaining energy efficiency data according to the initial data and the power consumption, obtaining heat preservation data based on the heat preservation time, performing causal analysis on the initial data to obtain influence data, performing cluster analysis on the heat preservation data through the energy efficiency data to obtain a loss factor, and establishing an electric kettle energy efficiency test model based on the loss factor, the influence data and the energy efficiency data; An optimization module, which uses a sparrow search algorithm to optimize the electric kettle energy efficiency test model; The output module inputs the data to be tested into the electric kettle energy efficiency test model to output the test results.

Images