Electric water heater protection control system based on clustering processing

Abstract

The invention discloses an electric water heater protection control system based on clustering processing. The system comprises a data acquisition module, a basic clustering generation module, an optimal fuzzy matrix learning module, a sample screening module, an optimization strategy design module and a protection control module. The invention belongs to the field of data processing, and particularly relates to an electric water heater protection control system based on clustering processing, according to the scheme, by introducing a joint target of a physical space Euclidean distance and entropy regularization, misjudgment on a real fault boundary is reduced; a physical distance penalty term is introduced, so that the sensitivity to real fault state change is improved; the fault-tolerant capability of the sensor noise and the boundary state is enhanced through fuzzy neighbors; noise and fault points are eliminated in combination with fuzzy similarity and outlier degree, and all-directional anomaly filtering is carried out; the risk of equipment failure is reduced; and the hyper-parameter is adjusted by combining the random coefficient and the difference information, so that a good protection control effect can be realized under different working conditions.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and specifically refers to an electric water heater protection control system based on clustering processing. Background Art

[0002] The electric water heater protection control system is a combination of a series of functional modules and technologies in the electric water heater to ensure safe use, stable operation, and extend the service life of the device. However, the general electric water heater protection control system has problems such as severe fluctuations in the single division result and increased misjudgment rate due to sensor measurement noise and operating state boundaries; the general electric water heater protection control system has problems such as improper identification of outlier data in the operating data of the electric water heater, difficulty in detecting short-term sudden abnormal conditions, resulting in poor protection control effect of the electric water heater. Summary of the Invention

[0003] In view of the above situation, to overcome the defects of the prior art, the present invention provides an electric water heater protection control system based on clustering processing. Aiming at the problems of severe fluctuations in the single division result and increased misjudgment rate due to sensor measurement noise and operating state boundaries in the general electric water heater protection control system, this solution reduces the misjudgment of the true fault boundary by introducing the joint objective of physical space Euclidean distance and entropy regularization; introduces a physical distance penalty term to improve the sensitivity to the change of the true fault state and reduce misjudgment; enhances the fault tolerance of sensor noise and boundary states through fuzzy neighbors, reducing the risk of false alarms and missed alarms; aiming at the problems of improper identification of outlier data in the operating data of the electric water heater, difficulty in detecting short-term sudden abnormal conditions, resulting in poor protection control effect of the electric water heater in the general electric water heater protection control system, this solution combines fuzzy similarity and outlier degree to eliminate noise and fault points, and conducts comprehensive anomaly filtering; not only alarms for single-point anomalies, but also captures rare working conditions based on state transition probability, reducing the risk of equipment failure; combines random coefficients and differential information to adjust hyperparameters to ensure good protection control effect under different working conditions.

[0004] The technical solution adopted by the present invention is as follows: The electric water heater protection control system based on clustering processing provided by the present invention includes a data acquisition module, a basic clustering generation module, an optimal fuzzy matrix learning module, a sample screening module, an optimization strategy design module, and a protection control module;

[0005] The data acquisition module acquires the operating data of the heating element of the electric water heater and constructs an electric water heater sample set;

[0006] The basic clustering generation module runs K-means clustering in parallel, generates a basic clustering result for the electric water heater sample set, and constructs a co-association matrix;

[0007] The optimal fuzzy matrix learning module constructs an initial fuzzy co - association matrix based on the co - association matrix, and through alternating optimization and iterative learning, obtains the optimal fuzzy co - association matrix, and gets the preliminary clustering result of the electric water heater sample set;

[0008] The sample screening module calculates the sample outlier degree based on the preliminary clustering result of the electric water heater sample set to eliminate outliers, and statistically calculates the state transition probability of the clustering labels to trigger a rare anomaly warning, and gets the screened clustering result;

[0009] The optimization strategy design module optimizes the screened clustering result to obtain the final clustering result of the electric water heater sample set;

[0010] The protection control module performs protection control on the real - time collected operation data of the electric water heater based on the final clustering result.

[0011] Furthermore, the data acquisition module synchronously samples the historical sensor signals of the heating element of the electric water heater at a fixed sampling frequency to form a historical time - series data set; linearly normalizes each dimension according to the maximum range; divides the time - series data set according to the window length w and the step size s to obtain the electric water heater sample set, and assigns the operation mode to the electric water heater sample set as a label, and the label does not participate in the dimension operation.

[0012] Furthermore, the basic clustering generation module runs the K - means m times in parallel on the electric water heater sample set to obtain m basic clustering results; constructs a co - association matrix; each basic clustering gets a co - association matrix. For the k - th basic clustering result, construct the co - association matrix , and the formula used is: ; where is the matrix element, i and j are the matrix row and column indices; is the label; and are the i - th sample and the j - th sample in the electric water heater sample set respectively; constructs a hard similarity mark between the sample pairs in the electric water heater sample set.

[0013] Furthermore, the optimal fuzzy matrix learning module specifically includes the following content:

[0014] Initial fuzzy co - association matrix; based on the co - association matrix, obtain the initial fuzzy co - association matrix according to the average strategy, and the formula used is: ; where is the initial fuzzy co - association matrix;

[0015] Alternating optimization overall objective; under the conditions of satisfying the fuzzy index r and the rank constraint, jointly minimize, and the overall objective is expressed as: ; ; where , is the Laplacian matrix, and controls the balance between the difference from the original measurement and entropy regularization; is the weight of the k-th basic clustering result in the final fusion; is an element in the current fuzzy co-association matrix S; i and j are the row and column indices of the matrix; rank(·) is the rank of the matrix; n is the total number of samples; c is the total number of clusters; is to take the diagonal;

[0016] Equivalent transformation; with the help of the Lagrange multiplier , decompose the overall objective and combine the spectral structure matrix F to obtain an equivalent objective, and the formula used is: ; ; where, F is the spectral structure matrix composed of the smallest c eigenvectors; Tr(·) is the trace of the matrix; I is the identity matrix; T is the matrix transpose;

[0017] Alternating three-step iteration; repeat the following three steps until convergence. After convergence, obtain the fuzzy co-association matrix, and directly extract c cluster numbers from the connected components of the fuzzy co-association matrix; the cluster number indicates which cluster the sample belongs to; take the label with the largest number in the same cluster as the cluster label; obtain the preliminary clustering result of the electric water heater sample set: (1) Update F, extract the low-dimensional spectral embedding of the latest similarity graph, and the formula used is: , F takes the smallest c eigenvectors; (2) Update S, combine the physical distance, spectral distance, and basic co-association information to adjust the sample similarity in the electric water heater sample set; after writing the sub-problem in quadratic form, solve it independently row by row in a closed form, which is equivalent to: ; ; where, and are the row vectors of F; is an element of the co-association matrix ; (3) Update the weight, dynamically allocate the importance of each basic clustering according to the current fusion result, and the formula used is: ; where, t is the index of the basic clustering; is the co-association matrix obtained from the t-th basic clustering.

[0018] Furthermore, the sample screening module screens the preliminary clustering result to obtain a screened clustering result; the screening process is: for the clustering members, calculate the outlier degree of the electric water heater samples using the elements of the fuzzy matrix, and the formula used is: ; when When is marked as abnormal data and deleted; and early warning detection of abnormal working conditions is carried out, a state transition probability matrix P is constructed, and for the cluster labels obtained by each iteration of the electric water heater samples, the state transition frequency is counted. The formula used is: ; If , a rare abnormal alarm is triggered; where is the sample outlier degree, is the outlier threshold; is the k-th cluster; is an element of the state transition probability matrix; is the number of times the statistical sample transfers from cluster label u to cluster label g in all iterations; is the number of times the statistical sample transfers from cluster label u to all other cluster labels in all iterations; is the transfer threshold.

[0019] Furthermore, the optimization strategy design module sets a label ratio B. For screening the clustering results, let the minimum ratio of the label with the largest number in the cluster to all labels in the cluster be D. If D is less than B, it means that the current clustering result of the electric water heater sample set is not ideal, and optimization is carried out; Optimization content: Based on the number of runs m, the fuzzy index r, the balance parameter and , the label ratio D, the window length w, and the step size s, a search space is established; The genetic algorithm is used for parameter optimization, and D obtained based on the position of the genetic individual is used as the individual fitness value; The crossover operator is changed, and the random coefficient and the difference information are combined to enhance diversity. The binary encoding of the parent is converted to decimal, and arithmetic crossover and differential mutation are performed. The specific operation formula used is: ; ; where and are the decimal values of the parent chromosomes; and are the decimal values of the generated offspring chromosomes; ; ; Then the offspring are mapped back to the binary encoding and returned to the genetic algorithm for optimization; Until there is an individual whose obtained D is not less than B, the final clustering result of the corresponding electric water heater sample set at this time is returned to the protection control module.

[0020] Furthermore, based on the final clustering result, the protection control module collects the operation data of the electric water heater in real time, distributes the operation data of the electric water heater collected in real time based on the minimum distance principle, uses the cluster label as the label of the operation data of the electric water heater collected in real time, and pre-defines the operation modes corresponding to each label; According to the label trigger control strategy, the protection control of the electric water heater is realized.

[0021] The beneficial effects achieved by the present invention using the above solution are as follows:

[0022] (1) Aiming at the problems existing in the general electric water heater protection control system, such as the sensor measurement noise and the operation state boundary leading to severe fluctuations in the single division result and an increase in the misjudgment rate, this solution reduces the misjudgment of the true fault boundary by introducing the joint objective of the Euclidean distance in physical space and entropy regularization; introduces a physical distance penalty term to improve the sensitivity to the change of the true fault state and reduce misjudgment; enhances the fault tolerance of sensor noise and boundary states through fuzzy neighbors, reducing the risks of false alarms and missed alarms.

[0023] (2) Aiming at the problems existing in the general electric water heater protection control system, such as improper identification of outlier data in the operation data of the electric water heater and difficulty in detecting short-term sudden abnormal working conditions, resulting in poor protection control effect of the electric water heater, this solution combines fuzzy similarity and outlier degree to eliminate noise and fault points for all-round abnormal filtering; not only alarms for single-point abnormalities, but also captures rare working conditions based on the state transition probability, reducing the risk of equipment failure; combines random coefficients and difference information to adjust hyperparameters to ensure good protection control effects under different working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a schematic flowchart of the electric water heater protection control system based on clustering processing provided by the present invention;

[0025] Figure 2 It is a schematic flowchart of the optimal fuzzy matrix learning module.

[0026] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, but do not constitute a limitation to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments; based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present invention.

[0028] In the description of the present invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", etc. indicating the orientation or position relationship are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention.

[0029] Example 1. Refer to Figure 1 , the electric water heater protection control system based on clustering processing provided by the present invention includes a data acquisition module, a basic clustering generation module, an optimal fuzzy matrix learning module, a sample screening module, an optimization strategy design module, and a protection control module;

[0030] The data acquisition module collects the operation data of the heating element of the electric water heater, constructs a sample set of the electric water heater; and sends the data to the basic clustering generation module;

[0031] The basic clustering generation module runs K-means clustering in parallel, generates a basic clustering result for the sample set of the electric water heater, and constructs a co-association matrix; and sends the data to the optimal fuzzy matrix learning module;

[0032] The optimal fuzzy matrix learning module constructs an initial fuzzy co-association matrix based on the co-association matrix, and through alternating optimization and iterative learning, obtains the optimal fuzzy co-association matrix to obtain a preliminary clustering result of the sample set of the electric water heater; and sends the data to the sample screening module;

[0033] The sample screening module calculates the sample outlier degree based on the preliminary clustering result of the sample set of the electric water heater to eliminate outliers, and statistically calculates the state transition probability of the clustering label to trigger a rare anomaly warning to obtain a screened clustering result; and sends the data to the optimization strategy design module;

[0034] The optimization strategy design module optimizes the screened clustering result to obtain the final clustering result of the sample set of the electric water heater; and sends the data to the protection control module;

[0035] The protection control module performs protection control on the operation data of the electric water heater collected in real time based on the final clustering result.

[0036] Example 2. Refer to Figure 1 , based on the above example, the data acquisition module synchronously samples the historical sensor signals of the temperature, current, voltage, water pressure, and flow rate of the heating element of the electric water heater at a fixed sampling frequency to form a historical time series data set; linearly normalizes each dimension according to the maximum range to reduce the influence of dimension; divides the time series data set according to the window length w and the step size s to obtain a sample set of the electric water heater to enhance real-time performance and diversity, and assigns an operation mode as a label to the sample set of the electric water heater, and the label does not participate in dimension operations.

[0037] Example 3. Refer to Figure 1, this embodiment is based on the above embodiment. The basic clustering generation module runs K-means m times in parallel on the electric water heater sample set to obtain m basic clustering results. Each basic clustering result represents the division of samples in the electric water heater sample set belonging to different operating states, and uses a random k value to enhance the adaptability to the number of faults; constructs a co-association matrix; each basic clustering obtains a co-association matrix. For the k-th basic clustering result, construct a co-association matrix , and the formula used is: ; where is the matrix element, and i and j are the matrix row and column indices; is the label; and are the i-th sample and the j-th sample in the electric water heater sample set respectively; construct a hard similarity label between samples in the electric water heater sample set.

[0038] Embodiment 4, refer to Figure 1 and Figure 2 , this embodiment is based on the above embodiment. The optimal fuzzy matrix learning module specifically includes the following content:

[0039] Initial fuzzy co-association matrix; obtain the initial fuzzy co-association matrix based on the co-association matrix according to the average strategy, and the formula used is: ; where is the initial fuzzy co-association matrix; by taking the average of the basic clustering results, the error influence of a single clustering of the electric water heater sample set is initially reduced;

[0040] Alternately optimize the overall objective; under the conditions of satisfying the fuzzy index r and rank constraint, jointly minimize, introduce the Euclidean distance from the physical space. If the actual measurement values of two sensor samples are quite different, they should not be considered in a similar state. The overall objective is expressed as: ; ; where , is the Laplacian matrix, and control the balance between the difference from the original measurement and entropy regularization; is the weight of the k-th basic clustering result in the final fusion; is the element in the current fuzzy co-association matrix S; i and j are the matrix row and column indices; rank(·) is the rank of the matrix; n is the total number of samples; is to take the diagonal; c is the total number of clusters; is to ensure that the Laplacian matrix exactly has c zero eigenvalues, so as to obtain c connected components, corresponding to c clusters; the first term fuses multiple partitions and suppresses the single clustering error; the second term introduces the measured physical distance. If the sensor measurement values are significantly different, then for The penalty increases, enhancing the sensitivity to real state changes and reducing misjudgments; the third term adaptively adjusts the importance weights; while taking into account the consistency of multiple electric water heater sample clusterings, the differences in real measurements, and weight adaptivity;

[0041] Equivalent transformation; with the help of Lagrange multipliers , decompose the overall objective and combine it with the spectral structure matrix F to obtain an equivalent objective. The formula used is: ; ; where F is the spectral structure matrix composed of the smallest c eigenvectors of ; Tr(·) is the trace of the matrix; I is the identity matrix; T is the matrix transpose;

[0042] Alternating three-step iteration; repeat the following three steps until convergence. After convergence, obtain the fuzzy co-association matrix, and directly extract the c cluster numbers from the connected components of the fuzzy co-association matrix; the cluster number indicates which cluster the sample belongs to; take the label with the largest number in the same cluster as the cluster label; obtain the preliminary clustering result of the electric water heater sample set: (1) Update F, extract the low-dimensional spectral embedding of the latest similarity graph, and the formula used is: , and F takes the smallest c eigenvectors; (2) Update S, combine physical distance, spectral distance, and basic co-association information to finely adjust the sample similarity in the electric water heater sample set; after writing the sub-problem in quadratic form, solve it independently and closed-form row by row, which is equivalent to: ; ; where and are the row vectors of F; is an element of the co-association matrix ; (3) Update the weights, dynamically allocate the importance of each basic clustering according to the current fusion result, and the formula used is: ; where t is the index of the basic clustering; is the co-association matrix obtained from the t-th basic clustering; each step of iteration has a closed-form and efficient solution, which is suitable for real-time operation of the microcontroller; the fuzzy neighbors determined by r, the entropy term, and the weights enhance the fault tolerance ability to sensor noise and boundary states; the rank constraint ensures exactly c stable states are separated, avoiding false alarms of redundant categories.

[0043] By performing the above operations, aiming at the problems of large fluctuations in the single-division results and increased misjudgment rate caused by sensor measurement noise and operating state boundaries in the general electric water heater protection control system, this solution reduces the misjudgment of the true fault boundary by introducing the joint objective of Euclidean distance in physical space and entropy regularization; introduces a physical distance penalty term to improve the sensitivity to changes in the true fault state and reduce misjudgment; and reduces the risks of false alarms and missed alarms by enhancing the fault tolerance of sensor noise and boundary states through fuzzy neighbors.

[0044] Example Five. Refer to Figure 1 , based on the above example, the sample screening module screens the preliminary clustering results to obtain the screened clustering results. The screening process is as follows: for the clustering members, the outlier degree of the electric water heater samples is calculated using the fuzzy matrix elements, and the formula used is: ; when , mark as abnormal data and delete it; and perform early warning detection for abnormal working conditions. A state transition probability matrix P is constructed, and for the cluster labels obtained for the electric water heater samples in each iteration, the state transition frequency is statistically calculated, and the formula used is: ; if , trigger a rare abnormal alarm; where is the outlier degree of the sample, is the outlier threshold; is the kth cluster; is the element of the state transition probability matrix; is the number of times the statistical sample transfers from cluster label u to cluster label g in all iterations; is the number of times the statistical sample transfers from cluster label u to all other cluster labels in all iterations; is the transition threshold.

[0045] Example Six. Refer to Figure 1 , based on the above example, the optimization strategy design module sets the label ratio B. Let the minimum ratio of the label with the largest number in the cluster to all the labels in the cluster for the screened clustering results be D. If D is less than B, it indicates that the current clustering result of the electric water heater sample set is not ideal, and optimization is performed. Optimization content: Based on the number of runs m, the fuzzy index r, the balance parameter and , the label ratio D, the window length w, and the step size s, a search space is established; a genetic algorithm is used for parameter optimization, and D obtained based on the position of the genetic individual is used as the individual fitness value; the crossover operator is changed, and the diversity is enhanced by combining the random coefficient and the difference information. The binary coding of the parent generation is converted to decimal, and arithmetic crossover and differential mutation are performed, which can introduce more exploration while retaining the information of the parent generation, so as to more effectively search the solution space. The specific operation formula used is: ; ; wherein, and are the decimal values of the parental chromosomes; and are the decimal values of the generated offspring chromosomes; ; ; Then map the offspring back to the binary encoding and return it to the genetic algorithm for optimization; until there is an individual whose D is not less than B, return the final clustering result of the corresponding electric water heater sample set to the protection control module.

[0046] By performing the above operations, for the problem that the general electric water heater protection control system has improper identification of outlier data in the electric water heater operation data and is difficult to detect short-term sudden abnormal working conditions, resulting in poor protection control effect of the electric water heater, this solution combines fuzzy similarity and outlier degree to eliminate noise and fault points, and conducts all-round abnormal filtering; it not only alarms for single-point abnormalities, but also captures rare working conditions based on the state transition probability, reducing the risk of equipment failure; combines random coefficients and difference information to adjust hyperparameters to ensure good protection control effects under different working conditions.

[0047] Example Seven, refer to Figure 1 , based on the above example, the protection control module, based on the final clustering result, real-time collects the electric water heater operation data, distributes the real-time collected electric water heater operation data based on the minimum distance principle, uses the cluster label as the label of the real-time collected electric water heater operation data, and pre-defines the operation modes corresponding to each label; triggers the control strategy according to the label to achieve the protection control of the electric water heater; the clustering result is directly mapped to the control strategy; the operation modes corresponding to the clustering labels are expressed as: ; The execution signals are in sequence: normal heating (l = 1), maintaining the heating operation; heating warning (l = 3), the buzzer prompts and the UI displays the risk of current overload; heat preservation standby (l = 2), turning off the main heating element and maintaining it with low power consumption; electric leakage fault (l = 4), immediately cutting off the power supply of the heating circuit, opening the safety valve, beeping an alarm and notifying remotely; dry burning protection (l = 5), turning off the heating element, detecting the water flow and performing necessary cooling treatment.

[0048] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention.

[0049] The above description of the present invention and its implementation manners is not restrictive. What is shown in the drawings is only one of the implementation manners of the present invention, and the actual structure is not limited thereto. Generally speaking, if those of ordinary skill in the art are inspired by it and design, without creative efforts, structural manners and embodiments similar to the technical solution without departing from the purpose of the present invention, they shall fall within the protection scope of the present invention.

Claims

1. Electric water heater protection control system based on clustering processing, characterized in that: The system includes a data acquisition module, a basic clustering generation module, an optimal fuzzy matrix learning module, a sample screening module, an optimization strategy design module, and a protection control module; The data acquisition module collects the operation data of the electric water heater heating element and constructs an electric water heater sample set; The basic clustering generation module runs the K-means clustering in parallel, generates a basic clustering result for the electric water heater sample set, and constructs a co-association matrix; The optimal fuzzy matrix learning module constructs an initial fuzzy co-association matrix based on the co-association matrix, and through alternating optimization and iterative learning, obtains the optimal fuzzy co-association matrix to get a preliminary clustering result of the electric water heater sample set; The sample screening module calculates the sample outlier degree based on the preliminary clustering result of the electric water heater sample set, eliminates the outliers, and statistically calculates the state transition probability of the clustering labels, triggers a rare anomaly warning, and obtains a screened clustering result; The optimization strategy design module optimizes the screened clustering result to obtain the final clustering result of the electric water heater sample set; The protection control module performs protection control on the real-time collected electric water heater operation data based on the final clustering result.

2. The electric water heater protection control system based on clustering processing according to claim 1, wherein: The optimal fuzzy matrix learning module specifically includes the following content: Initial fuzzy co-association matrix; Obtain the initial fuzzy co-association matrix based on the co-association matrix according to the average strategy; Alternating optimization overall objective; Under the conditions of satisfying the fuzzy index r and rank constraint, jointly minimize; Equivalent transformation; with the help of Lagrange multipliers , decompose the overall objective and combine it with the spectral structure matrix F to obtain an equivalent objective; Alternating three-step iteration.

3. The electric water heater protection control system based on clustering processing according to claim 2, characterized in that: The alternating three-step iteration is to repeat the following three steps until convergence. After convergence, obtain the fuzzy co-association matrix, and directly extract c cluster numbers from the connected components of the fuzzy co-association matrix; The cluster number indicates which cluster the sample belongs to; Take the label with the largest number in the same cluster as the cluster label; Obtain the preliminary clustering result of the electric water heater sample set: (1) Update F and extract the low-dimensional spectral embedding of the latest similarity graph; (2) Update S, combine the physical distance, spectral distance, and basic co-association information to adjust the sample similarity in the electric water heater sample set; After writing the sub-problem in quadratic form, solve it independently and in a closed form row by row; (3) Update the weights and dynamically allocate the importance of each basic clustering according to the current fusion result.

4. The electric water heater protection control system based on clustering processing according to claim 3, characterized in that: The sample screening module screens the preliminary clustering results to obtain the screened clustering results. The screening process is as follows: for the clustering members, the outlier degree of the electric water heater samples is calculated using the fuzzy matrix elements, and the formula used is: ; when , is marked as abnormal data and deleted; And perform early warning detection for abnormal working conditions, construct the state transition probability matrix P, and count the state transition frequencies for the cluster labels obtained in each iteration of the electric water heater samples. The formula used is: ; If , trigger a rare abnormal alarm; where is the sample outlier degree, is the outlier threshold; is the k-th cluster; is the element of the state transition probability matrix; is the number of times the statistical sample transfers from cluster label u to cluster label g in all iterations; is the number of times the statistical sample transfers from cluster label u to all other cluster labels in all iterations; is the transfer threshold.

5. The electric water heater protection control system based on clustering processing according to claim 4, wherein: The optimization strategy design module sets the label ratio B. For screening the clustering results, let the minimum ratio of the label with the largest number in the cluster to all labels in the cluster be D. If D is less than B, it indicates that the current clustering result of the electric water heater sample set is not ideal, and optimization is carried out. The optimization content: Based on the number of runs m, the fuzzy index r, the balance parameter and , a search space is established based on the label ratio D, the window length w, and the step size s; the genetic algorithm is used for parameter optimization, and D obtained based on the position of the genetic individual is used as the individual fitness value; the crossover operator is changed, and the random coefficient and the difference information are combined to enhance the diversity. The binary coding of the parent generation is converted into decimal, and arithmetic crossover and differential mutation are carried out. The specific operation formula is as follows: ； ； Among them, and are the decimal values of the parental chromosomes; and are the decimal values of the generated offspring chromosomes; ; ; Then map the offspring back to binary encoding and return it for genetic algorithm optimization; until there is an individual whose D is not less than B, return the final clustering result of the corresponding electric water heater sample set to the protection control module.

6. The electric water heater protection control system based on clustering processing according to claim 5, characterized in that: The basic clustering generation module runs the K-means m times in parallel on the electric water heater sample set to obtain m basic clustering results; Construct a co - association matrix; each basic clustering results in a co - association matrix. For the k - th basic clustering result, construct the co - association matrix .

7. The electric water heater protection control system based on clustering processing according to claim 6, characterized in that: The data acquisition module synchronously samples the historical sensor signals of the electric water heater heating element at a fixed sampling frequency to form a historical time series data set; Linearly normalize each dimension according to the maximum range; Divide the time series data set according to the window length w and step size s to obtain the electric water heater sample set, and assign the operation mode as a label to the electric water heater sample set. The label does not participate in the dimension operation.

8. The electric water heater protection control system based on clustering processing according to claim 7, characterized in that: The protection control module, based on the final clustering result, real-time collects the electric water heater operation data, distributes the real-time collected electric water heater operation data based on the minimum distance principle, uses the cluster label as the label of the real-time collected electric water heater operation data, and pre-defines the operation modes corresponding to each label; Triggers the control strategy according to the label to achieve the protection control of the electric water heater.

Images