Wireless control method for split heating rod with self-cleaning function

Abstract

The present invention relates to the field of heating rod control technology, and in particular to a method for wirelessly controlling a split heating rod with a self-cleaning function. The method comprises: obtaining historical cleaning records representing different historical self-cleaning processes of a split heating rod to be controlled, determining target factor weights under the dimensions of cleaning time, cleaning temperature, cleaning energy consumption, and cleaning degree; determining a standard cleaning time and a standard cleaning temperature; determining an objective function based on the target factor weights under different dimensions, as well as the standard cleaning time and the standard cleaning temperature; solving the objective function through a simulated annealing algorithm, and controlling and adjusting the split heating rod to be controlled based on an optimal combination solution; correcting the disturbance range in the solution obtained by the simulated annealing algorithm; and correcting the disturbance probability of each combination solution in the solution obtained by the simulated annealing algorithm. The present invention realizes the control of the split heating rod and improves the rationality of the optimal screening of the cleaning time and cleaning temperature.

Description

Technical Field

[0001] The present invention relates to the technical field of heating rod control, and in particular to a wireless control method for a split heating rod with a self-cleaning function. Background Art

[0002] A split heating rod is a detachable heating device whose control section and heating section are often designed separately. During use, simply place the heating module into the pot and place the control section on the table. Since scale and impurities may accumulate on the heating rod after long-term use, especially in hard water environments, these deposits often affect heating efficiency and device life. To solve this problem, split heating rods are usually equipped with a self-cleaning function. During the self-cleaning process, the heating rod often needs to be heated to a certain temperature to complete the cleaning. However, if the cleaning temperature is too high or too low, or the cleaning time is too long or too short, it may affect the cleaning effect. Therefore, controlling the split heating rod and adjusting its cleaning time and temperature to the optimal level is the key to ensuring efficient cleaning, equipment safety, and energy saving. A simulated annealing algorithm is generally used to determine the optimal cleaning time and cleaning temperature for a split heating rod.

[0003] In existing simulated annealing algorithms, the objective function often requires customized modeling based on the specific optimization problem. During this process, expert evaluation methods are often used to assign weights to each of the multiple factors influencing the overall goal, ultimately weighting the overall objective function. However, the influencing factors involved in different systems often vary, and relying on expert evaluation to determine weights can be detrimental to improving optimization results due to subjective factors. This can lead to poor rationality in selecting the optimal cleaning time and temperature.

[0004] Secondly, in the existing simulated annealing algorithm, when the "temperature" drops, the process of perturbing the current solution and randomly generating new candidate solutions within the perturbation range is the core of the algorithm to find the global optimal solution. Specifically, it is necessary to define the perturbation range within the neighborhood of the current solution, and then perform iterative optimization by randomly selecting solutions within the perturbation range. However, since the perturbation range is not clearly defined, and the probability of randomly selecting each solution within the range is equal, if some solutions within the perturbation range cause drastic changes in energy consumption, it may cause serious damage to the split heating rod. Therefore, not all solutions within the perturbation range are equally feasible. Therefore, using random desirability as the perturbation probability of the solution may lead to poor rationality in the optimal screening of cleaning time and cleaning temperature. Summary of the Invention

[0005] In order to solve the technical problem of poor rationality in optimal screening of cleaning time and cleaning temperature, the present invention proposes a wireless control method for a split heating rod with a self-cleaning function.

[0006] In a first aspect, the present invention provides a wireless control method for a split-type heating rod with a self-cleaning function, the method comprising:

[0007] Obtain historical cleaning records representing different historical self-cleaning processes of the split heating rod to be controlled, and determine the target factor weights under the cleaning time dimension, cleaning temperature dimension, cleaning energy consumption dimension, and cleaning degree dimension based on all historical cleaning records;

[0008] Determine the standard cleaning time and standard cleaning temperature based on the target factor weights under the cleaning energy consumption dimension and the cleaning degree dimension, as well as the cleaning time and cleaning temperature in all historical cleaning records;

[0009] Determine the objective function based on the weights of the target factors under the cleaning time dimension, cleaning temperature dimension, cleaning energy consumption dimension and cleaning degree dimension, as well as the standard cleaning time and standard cleaning temperature;

[0010] The simulated annealing algorithm is used to solve the objective function and obtain the optimal combination solution. Based on the cleaning time and cleaning temperature in the optimal combination solution, the split heating rod to be controlled is controlled and adjusted.

[0011] When solving the objective function through the simulated annealing algorithm, the importance of control in the cleaning time dimension and the cleaning temperature dimension is determined according to all historical cleaning records, and based on all the control importance, the disturbance range in the simulated annealing algorithm solution is corrected; according to the target factor weights in the cleaning time dimension and the cleaning temperature dimension, the disturbance probability of each combination solution in the simulated annealing algorithm solution is corrected.

[0012] In conjunction with the first aspect above, in one possible implementation, determining the target factor weights under the cleaning time dimension, the cleaning temperature dimension, the cleaning energy consumption dimension, and the cleaning degree dimension based on all historical cleaning records includes:

[0013] Based on the differences between each cleaning time and the average cleaning time, the differences between each cleaning temperature and the average cleaning temperature, the differences between each cleaning energy consumption and the average cleaning energy consumption, and the differences between each cleaning degree and the average cleaning degree in all historical cleaning records, the target factor weights under the cleaning time dimension, cleaning temperature dimension, cleaning energy consumption dimension and cleaning degree dimension are determined.

[0014] In combination with the first aspect above, in one possible implementation, the simultaneous formula corresponding to the weights of the target factors in the cleaning time dimension, the cleaning temperature dimension, the cleaning energy consumption dimension, and the cleaning degree dimension is:

[0015]

[0016] Among them, w1 is the target factor weight under the cleaning time dimension; w2 is the target factor weight under the cleaning temperature dimension; w3 is the target factor weight under the cleaning energy consumption dimension; w4 is the target factor weight under the cleanliness degree dimension; N is the number of historical cleaning records; i is the sequence number of the historical cleaning record; || is the absolute value function; t i is the normalized value of the cleaning time in the i-th historical cleaning record; μ1 is the mean of the normalized values ​​of the cleaning time in all historical cleaning records; T i is the normalized value of the cleaning temperature in the i-th historical cleaning record; μ2 is the mean of the normalized values ​​of the cleaning temperature in all historical cleaning records; E i is the normalized value of the cleaning energy consumption in the i-th historical cleaning record; μ3 is the mean of the normalized values ​​of the cleaning energy consumption in all historical cleaning records; C i is the normalized value of the cleanliness level in the i-th historical cleaning record; μ4 is the mean of the normalized values ​​of the cleanliness level in all historical cleaning records.

[0017] In conjunction with the first aspect above, in one possible implementation, determining the standard cleaning time and standard cleaning temperature based on the target factor weights under the cleaning energy consumption dimension and the cleaning degree dimension, as well as the cleaning time and cleaning temperature in all historical cleaning records, includes:

[0018] Determine the cleaning effect factor corresponding to each historical cleaning record based on the target factor weights under the cleaning energy consumption dimension and the cleaning degree dimension, as well as the cleaning energy consumption and cleaning degree in each historical cleaning record;

[0019] Determine the standard cleaning time based on the cleaning effect factors corresponding to all historical cleaning records and the cleaning time in all historical cleaning records;

[0020] The standard cleaning temperature is determined based on the cleaning effect factors corresponding to all historical cleaning records and the cleaning degrees in all historical cleaning records.

[0021] In combination with the first aspect above, in a possible implementation, the formulas corresponding to the cleaning effect factors corresponding to the standard cleaning time, the standard cleaning temperature, and the historical cleaning records are respectively:

[0022]

[0023] Where t is the standard cleaning time; T is the standard cleaning temperature; N is the number of historical cleaning records; i is the sequence number of the historical cleaning record; A i is the cleaning effect factor corresponding to the i-th historical cleaning record; A is the cumulative value of the cleaning effect factors corresponding to all historical cleaning records; t i is the normalized value of the cleaning time in the i-th historical cleaning record; T iis the normalized value of the cleaning temperature in the i-th historical cleaning record; w3 is the target factor weight under the cleaning energy consumption dimension; w4 is the target factor weight under the cleaning degree dimension; E i is the normalized value of the cleaning energy consumption in the i-th historical cleaning record; ε is a pre-set hyperparameter greater than 0; C i is the normalized value of the cleanliness level in the i-th historical cleaning record.

[0024] In combination with the first aspect above, in a possible implementation, the formula corresponding to the objective function is:

[0025] F(t v , T v )=w1×F 1v +w2×F 2v +w3×F 3v -w4×F 4v ;

[0026] F 1v =(t v -t) 2 ;

[0027] F 2v =(T v -T) 2 ;

[0028]

[0029] B i，v =exp(-(w1×|t v -t i |+w2×|T v -T i |));

[0030] Among them, F(t v , T v ) is the function value of the objective function under the vth combination solution; v is the sequence number of the combination solution of the objective function; t v and T v The vth combined solution of the objective function, t v is the normalized value of the cleaning time in the vth combined solution of the objective function, T v is the normalized value of the cleaning temperature in the vth combined solution of the objective function; w1 is the target factor weight under the cleaning time dimension; w2 is the target factor weight under the cleaning temperature dimension; w3 is the target factor weight under the cleaning energy consumption dimension; w4 is the target factor weight under the cleaning degree dimension; F 1v 、F 2v 、F 3v and F 4vare the indicators associated with the cleaning time dimension, cleaning temperature dimension, cleaning energy consumption dimension, and cleaning degree dimension under the vth combination solution; t is the standard cleaning time; T is the standard cleaning temperature; N is the number of historical cleaning records; i is the sequence number of the historical cleaning record; B i，v is the similarity between the i-th historical cleaning record and the v-th combination solution; B v is the cumulative value of the similarity between all historical cleaning records and the vth combined solution; E i is the normalized value of cleaning energy consumption in the i-th historical cleaning record; C i is the normalized value of the cleanliness level in the i-th historical cleaning record; exp() is the natural exponential function; || is the absolute value function; t i is the normalized value of the cleaning time in the i-th historical cleaning record; T i is the normalized value of the cleaning temperature in the i-th historical cleaning record.

[0031] In conjunction with the first aspect above, in one possible implementation, determining the importance of control in the cleaning time dimension and the cleaning temperature dimension based on all historical cleaning records includes:

[0032] Determine the importance of regulation under the cleaning time dimension based on historical cleaning records with the same cleaning time;

[0033] Similarly, based on the historical cleaning records with the same cleaning temperature, the importance of regulation under the cleaning temperature dimension is determined.

[0034] In conjunction with the first aspect above, in a possible implementation, determining the importance of regulation in the cleaning time dimension based on historical cleaning records with the same cleaning time includes:

[0035] According to the historical cleaning records under the same cleaning time, the formula for determining the local optimal factor under the cleaning time is:

[0036] Among them, Lt a is the local optimal factor under the a-th cleaning time; a is the sequence number of different cleaning times in all historical cleaning records; || is the absolute value function; PCCs(TX a , CX a ) is TX a and CX a Pearson correlation coefficient between TX a is the time series of cleaning temperatures in all historical cleaning records where the cleaning time is equal to the a-th cleaning time; CX a is a time series consisting of the cleaning degrees of all historical cleaning records whose cleaning time is equal to the a-th cleaning time; ε1 is a pre-set hyperparameter greater than 0;

[0037] Determine the local optimal factor under the cleaning time in each historical cleaning record as the target contribution factor corresponding to each historical cleaning record;

[0038] The product of the cleaning time in each historical cleaning record and its corresponding target contribution factor is determined to determine the correction time corresponding to each historical cleaning record;

[0039] The product of the cleaning energy consumption in each historical cleaning record and its corresponding target contribution factor is determined to determine the corrected energy consumption corresponding to each historical cleaning record;

[0040] The product of the cleaning degree in each historical cleaning record and its corresponding target contribution factor is determined to determine the correction degree corresponding to each historical cleaning record;

[0041] Based on the time series consisting of the correction time of all historical cleaning records, the time series consisting of the correction energy consumption of all historical cleaning records, and the time series consisting of the correction degree of all historical cleaning records, the formula for determining the importance of control in the cleaning time dimension is:

[0042] γ1=w1×(w3×GP(XtX,XEX)+w4×GP(XtX,XCX)); where γ1 is the importance of regulation under the cleaning time dimension; w1 is the target factor weight under the cleaning time dimension; w3 is the target factor weight under the cleaning energy consumption dimension; w4 is the target factor weight under the cleaning degree dimension; GP(XtX,XEX) is the normalized value of the Pearson correlation coefficient between XtX and XEX; GP(XtX,XCX) is the normalized value of the Pearson correlation coefficient between XtX and XCX; XtX is the time series consisting of the correction time corresponding to all historical cleaning records; XEX is the time series consisting of the correction energy consumption corresponding to all historical cleaning records; XCX is the time series consisting of the correction degree corresponding to all historical cleaning records.

[0043] In combination with the first aspect above, in a possible implementation, the formula corresponding to the disturbance range in the solution of the modified simulated annealing algorithm is:

[0044]

[0045] Among them, st v,L+1，1 is the minimum value of the corrected perturbation range of the cleaning time in the L+1 candidate solution of the vth combination solution in the simulated annealing algorithm; st v,L+1，2 is the maximum value of the corrected perturbation range of the cleaning time in the L+1th candidate solution of the vth combination solution in the simulated annealing algorithm; sT v，L+1，1is the minimum value of the corrected perturbation range of the clean temperature in the L+1th candidate solution of the vth combination solution in the simulated annealing algorithm; sT v，L+1，2 is the maximum value of the corrected perturbation range of the clean temperature in the L+1th candidate solution of the vth combination solution in the simulated annealing algorithm; v is the serial number of the combination solution of the objective function; L is the serial number of the candidate solution of the vth combination solution; t v，L is the normalized value of the cleaning time in the Lth candidate solution of the vth combination solution; T v，L is the normalized value of the cleaning temperature in the Lth candidate solution of the vth combination solution; γ1 is the control importance under the cleaning time dimension; γ2 is the control importance under the cleaning temperature dimension; and is a hyperparameter; w1 is the target factor weight under the cleaning time dimension; w2 is the target factor weight under the cleaning temperature dimension.

[0046] In combination with the first aspect above, in a possible implementation, the formula corresponding to the perturbation probability of the combined solution in the modified simulated annealing algorithm is:

[0047] k v，L+1 =exp(-(w1×|Et v -Et v,L |+w2×|ET v -ET v，L |)); where k v,L+1 is the perturbation probability of the vth combination solution within the overall perturbation range of the L+1th candidate solution; v is the serial number of the combination solution of the objective function; L is the serial number of the candidate solution of the vth combination solution; exp() is the natural exponential function; w1 is the target factor weight under the cleaning time dimension; || is the absolute value function; Et v is the mean of the cleaning energy consumption in all historical cleaning records whose cleaning time is equal to the cleaning time in the vth combination solution; Et v，L is the mean of the cleaning energy consumption in all historical cleaning records whose cleaning time is equal to the cleaning time in the Lth candidate solution of the vth combination solution; w2 is the target factor weight under the cleaning temperature dimension; ET v is the mean cleaning energy consumption in all historical cleaning records where the cleaning temperature is equal to the cleaning temperature in the vth combined solution; ET v，L It is the mean of the cleaning energy consumption in all historical cleaning records where the cleaning temperature is equal to the cleaning temperature in the Lth candidate solution of the vth combined solution.

[0048] In a second aspect, the present invention provides a split-type wireless control system for heating rods with a self-cleaning function, the system comprising:

[0049] An acquisition and determination module is used to obtain historical cleaning records representing different historical self-cleaning processes of the split heating rod to be controlled, and determine the target factor weights under the cleaning time dimension, cleaning temperature dimension, cleaning energy consumption dimension, and cleaning degree dimension based on all historical cleaning records;

[0050] A time and temperature determination module is used to determine the standard cleaning time and standard cleaning temperature based on the target factor weights under the cleaning energy consumption dimension and the cleaning degree dimension, as well as the cleaning time and cleaning temperature in all historical cleaning records;

[0051] An objective function determination module is used to determine an objective function based on the weights of target factors under the cleaning time dimension, the cleaning temperature dimension, the cleaning energy consumption dimension, and the cleaning degree dimension, as well as the standard cleaning time and the standard cleaning temperature;

[0052] The solution control and adjustment module is used to solve the objective function through a simulated annealing algorithm to obtain an optimal combination solution, and control and adjust the split heating rod to be controlled based on the cleaning time and cleaning temperature in the optimal combination solution.

[0053] In a third aspect, a server is provided, comprising a memory and a processor. The memory is configured to store executable program code, and the processor is configured to call and execute the executable program code from the memory, so that the device executes the method of the first aspect or any possible implementation of the first aspect.

[0054] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0055] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation of the first aspect.

[0056] The present invention has the following beneficial effects:

[0057] The wireless control method for a split-type heating rod with a self-cleaning function of the present invention realizes the control of a split-type heating rod, solves the technical problem of poor rationality of the optimal screening of cleaning time and cleaning temperature, and improves the rationality of the optimal screening of cleaning time and cleaning temperature. Specifically, the present invention quantifies the weights of different target factors relatively objectively by analyzing multiple historical cleaning records, that is, the weights of target factors under the dimensions of cleaning time, cleaning temperature, cleaning energy consumption, and cleaning degree, and quantifies the standard cleaning time and standard cleaning temperature, thereby improving the rationality of the objective function setting, and further improving the rationality of the subsequent optimal screening of cleaning time and cleaning temperature. Secondly, when solving the objective function through the simulated annealing algorithm, the disturbance range and disturbance probability are adaptively corrected, which can reduce the acquisition of incomprehension to a certain extent, thereby improving the rationality of the subsequent optimal screening of cleaning time and cleaning temperature. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0059] Figure 1 This is a flow chart of the wireless control method of the split heating rod with self-cleaning function of the present invention;

[0060] Figure 2 This is a schematic diagram of the structure of a split-type wireless control system for a heating rod with a self-cleaning function according to the present invention;

[0061] Figure 3 The figure is a structural diagram of a computer device of the present invention. DETAILED DESCRIPTION

[0062] To further illustrate the technical means and effects employed by the present invention to achieve its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementations, structures, features, and effects of the technical solutions proposed by the present invention. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0063] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0064] refer to Figure 1, shows the process of some embodiments of the wireless control method of a split-type heating rod with a self-cleaning function according to the present invention. The wireless control method of a split-type heating rod with a self-cleaning function comprises the following steps:

[0065] Step S1, obtain historical cleaning records representing different historical self-cleaning processes of the split heating rod to be controlled, and determine the target factor weights under the cleaning time dimension, cleaning temperature dimension, cleaning energy consumption dimension and cleaning degree dimension based on all historical cleaning records.

[0066] The split heating rod to be controlled can be a self-cleaning split heating rod with adjustable cleaning temperature and time. The split heating rod consists of a lower heating template and an upper control template. The heating template is responsible for generating heat, while the control template includes control functions such as temperature adjustment and timing. In actual use, it is often sufficient to simply place the heating module into the pot and immerse the heating template in the desired medium, while the control template remains outside the pot. Historical self-cleaning processes represent past cleaning processes of the split heating rod. Historical cleaning records may include: cleaning time, cleaning temperature, cleaning energy consumption, and cleaning degree. The cleaning time in the historical cleaning record can be the total duration of the historical self-cleaning process. The cleaning temperature in the historical cleaning record can be the cleaning temperature set during the historical self-cleaning process. The cleaning energy consumption in the historical cleaning record can be the total electrical energy consumed during the historical self-cleaning process. The cleaning degree indicates the cleaning condition after the completion of the historical self-cleaning process; a higher value indicates a better cleaning effect. The method for obtaining the cleanliness level can be: after the historical self-cleaning process is completed, an infrared image or RGB (Red Green Blue, color mode) image of the split heating rod is collected, and the staff observes the collected image and scores the cleanliness of the split heating rod from 0 to 10. The higher the score, the better the cleaning effect, and the score is used as the cleanliness level.

[0067] As an example, the target factor weights under the cleaning time dimension, cleaning temperature dimension, cleaning energy consumption dimension and cleaning degree dimension can be determined based on the differences between each cleaning time and the average cleaning time, the differences between each cleaning temperature and the average cleaning temperature, the differences between each cleaning energy consumption and the average cleaning energy consumption, and the differences between each cleaning degree and the average cleaning degree in all historical cleaning records.

[0068] For example, the simultaneous formulas for determining the weights of the target factors under the cleaning time dimension, cleaning temperature dimension, cleaning energy consumption dimension, and cleaning degree dimension can be:

[0069]

[0070] Where w1 is the target factor weight under the cleaning time dimension. w2 is the target factor weight under the cleaning temperature dimension. w3 is the target factor weight under the cleaning energy consumption dimension. w4 is the target factor weight under the cleanliness level dimension. N is the number of historical cleaning records. i is the sequence number of the historical cleaning record. || is the absolute value function. t i is the normalized value of the cleaning time in the i-th historical cleaning record. μ1 is the mean of the normalized values ​​of the cleaning time in all historical cleaning records. i is the normalized value of the cleaning temperature in the i-th historical cleaning record. μ2 is the mean of the normalized values ​​of the cleaning temperature in all historical cleaning records. E i is the normalized value of the cleaning energy consumption in the i-th historical cleaning record. μ3 is the mean of the normalized values ​​of the cleaning energy consumption in all historical cleaning records. i is the normalized value of the cleanliness level in the i-th historical cleaning record. μ4 is the mean of the normalized values ​​of the cleanliness level in all historical cleaning records.

[0071] It should be noted that in practice, if a small change in a dimension can trigger significant changes in other factors, then that dimension should be given a higher weight. For example, if a small change in cleaning time can trigger significant changes in other factors, then the cleaning time dimension should be given a higher weight. The weights of other influencing factors are often different as well, with higher weights indicating higher availability. i -μ1| can characterize the fluctuation of historical cleaning time. |T i -μ2| can represent the fluctuation of historical clean energy consumption. |E i -μ3| can represent the fluctuation of historical clean energy consumption. |C i -μ4| can represent the fluctuation of historical cleanliness. Therefore, w1, w2, w3, and w4 can represent the weights of the cleaning time dimension, cleaning temperature dimension, cleaning energy consumption dimension, and cleanliness dimension, respectively.

[0072] Step S2: determining the standard cleaning time and standard cleaning temperature based on the target factor weights under the cleaning energy consumption dimension and the cleaning degree dimension, as well as the cleaning time and cleaning temperature in all historical cleaning records.

[0073] It should be noted that the standard cleaning time may represent the minimum cleaning time required to meet the cleaning requirements, that is, a relatively suitable cleaning time. The standard cleaning temperature may represent a relatively suitable cleaning temperature to meet the cleaning requirements.

[0074] As an example, this step may include the following steps:

[0075] In the first step, the cleaning effect factor corresponding to each historical cleaning record is determined based on the target factor weights under the cleaning energy consumption dimension and the cleaning degree dimension, as well as the cleaning energy consumption and cleaning degree in each historical cleaning record.

[0076] The second step is to determine the standard cleaning time based on the cleaning effect factors corresponding to all historical cleaning records and the cleaning time in all historical cleaning records.

[0077] The third step is to determine the standard cleaning temperature based on the cleaning effect factors corresponding to all historical cleaning records and the cleaning degrees in all historical cleaning records.

[0078] For example, the formulas for determining the cleaning effect factors corresponding to the standard cleaning time, standard cleaning temperature, and historical cleaning records may be:

[0079]

[0080] Where t is the standard cleaning time. T is the standard cleaning temperature. N is the number of historical cleaning records. i is the sequence number of the historical cleaning record. i is the cleaning effect factor corresponding to the i-th historical cleaning record. A is the cumulative value of the cleaning effect factors corresponding to all historical cleaning records. i T is the normalized value of the cleaning time in the i-th historical cleaning record. i is the normalized value of the cleaning temperature in the i-th historical cleaning record. w3 is the target factor weight under the cleaning energy consumption dimension. w4 is the target factor weight under the cleaning degree dimension. E i is the normalized value of the cleaning energy consumption in the i-th historical cleaning record. ε is a pre-set hyperparameter greater than 0, for example, ε can be 1. i is the normalized value of the cleanliness level in the i-th historical cleaning record.

[0081] It should be noted that, taking the minimum cleaning time as an example, it is necessary to find the minimum cleaning time required while ensuring the cleaning energy consumption is low and the cleaning degree is optimal. To this end, historical cleaning records can be used for availability weighting. If the historical cleaning records are low in cleaning energy consumption, that is, In the larger case, the higher the degree of cleanliness, that is, C i If the value is higher, then this record contributes more to determining the minimum cleaning time, indicating that its availability is higher. However, since the weight coefficients of cleaning energy consumption and cleaning degree are different, these two factors can be weighted. In order to comprehensively consider these two factors, a weighted index can be obtained using the weight coefficient, so that The higher the value, the higher the availability of cleaning time for the minimum cleaning time. This is to ensure that the weighted sum of the availability of all historical cleaning records is 1. Therefore, t can represent a relatively suitable cleaning time. Similarly, T can represent a relatively suitable cleaning temperature.

[0082] Step S3: determining the objective function according to the target factor weights under the cleaning time dimension, the cleaning temperature dimension, the cleaning energy consumption dimension and the cleaning degree dimension, as well as the standard cleaning time and the standard cleaning temperature.

[0083] As an example, the formula for determining the objective function may be:

[0084] F(t v , T v )=w1×F 1v +w2×F 2v +w3×F 3v -w4×F 4v ;

[0085] F 1v =(t v -t) 2 ;

[0086] F 2v =(T v -T) 2 ;

[0087]

[0088] B i，v =exp(-(w1×|t v -t i |+w2×|T v -T i |));

[0089] Among them, F(t v , T v ) is the function value of the objective function under the vth combination solution. v is the serial number of the combination solution of the objective function. v and T v The vth combined solution of the objective function. v T is the normalized value of the cleaning time in the vth combined solution of the objective function. v is the normalized value of the cleaning temperature in the vth combined solution of the objective function. w1 is the target factor weight under the cleaning time dimension. w2 is the target factor weight under the cleaning temperature dimension. w3 is the target factor weight under the cleaning energy consumption dimension. w4 is the target factor weight under the cleaning degree dimension. F 1v 、F 2v 、F 3v and F 4vare the indicators associated with the cleaning time dimension, cleaning temperature dimension, cleaning energy consumption dimension, and cleaning degree dimension under the vth combination solution. t is the standard cleaning time. T is the standard cleaning temperature. N is the number of historical cleaning records. i is the sequence number of the historical cleaning record. B i，v is the similarity between the i-th historical cleaning record and the v-th combined solution. v It is the cumulative value of the similarity between all historical cleaning records and the vth combined solution. i C is the normalized value of cleaning energy consumption in the i-th historical cleaning record. i is the normalized value of the cleanliness level in the i-th historical cleaning record. exp() is the natural exponential function. || is the absolute value function. i T is the normalized value of the cleaning time in the i-th historical cleaning record. i is the normalized value of the cleaning temperature in the i-th historical cleaning record.

[0090] It should be noted that when F 1v The smaller it is, the closer the cleaning time in the vth combination solution is to the relatively suitable cleaning time. 2v The smaller it is, the closer the cleaning temperature in the vth combination solution is to the relatively suitable cleaning temperature. In actual practice, the more suitable the cleaning time and cleaning temperature are, the more energy consumption should be minimized, resource consumption should be reduced, energy efficiency should be improved, and the cleaning degree should be improved. v -t i |+w2×|T v -T i The smaller the value of |, the more similar the cleaning time and temperature in the vth combination solution are to the cleaning time and temperature in the ith historical cleaning record, which means the higher the availability of the ith historical cleaning record for the vth combination solution. 3v It can represent the overall clean energy consumption under the vth combination solution. 4v It can characterize the overall cleanliness of the v-th combination solution. Therefore, when F(t v , T v ) is smaller, it often means that the vth combination solution is more likely to be the optimal solution, and it often means that the cleaning time and cleaning temperature in the vth combination solution are more likely to be the optimal cleaning time and optimal cleaning temperature.

[0091] Step S4, solving the objective function through a simulated annealing algorithm to obtain an optimal combination solution, and controlling and adjusting the split heating rod to be controlled based on the cleaning time and cleaning temperature in the optimal combination solution.

[0092] It should be noted that during the self-cleaning process of the split heating rod to be controlled, the cleaning time of the split heating rod to be controlled can be set to the cleaning time in the optimal combination solution, and the cleaning temperature of the split heating rod to be controlled can be set to the cleaning temperature in the optimal combination solution to achieve control and adjustment of the split heating rod to be controlled.

[0093] As an example, when solving the objective function by using the simulated annealing algorithm, the following steps may be included:

[0094] The first step is to determine the importance of control under the cleaning time dimension and cleaning temperature dimension based on all historical cleaning records. This can include the following sub-steps:

[0095] The first sub-step, based on historical cleaning records with the same cleaning time, determines the importance of control under the cleaning time dimension, may include the following steps:

[0096] First, based on the historical cleaning records under the same cleaning time, the formula corresponding to the local optimal factor under the cleaning time can be determined as follows:

[0097] Among them, Lt a is the local optimal factor under the a-th cleaning time. a is the sequence number of different cleaning times in all historical cleaning records. || is the absolute value function. PCCs(TX a , CX a ) is TX a and CX a Pearson correlation coefficient between TX a It is the time series of cleaning temperatures in all historical cleaning records where the cleaning time is equal to the a-th cleaning time. a is a time series of the cleaning degrees of all historical cleaning records whose cleaning time is equal to the a-th cleaning time. ε1 is a pre-set hyperparameter greater than 0, for example, ε1 can be 1.

[0098] It should be noted that in actual situations, if a large change in cleaning temperature does not cause a change in the cleaning degree within a certain cleaning time, it often means that cleaning has probably been completed within that cleaning time, that is, the cleaning may have reached the optimal level at this time. a , CX a )| is larger, it often indicates that the cleaning temperature and the cleaning degree at the a-th cleaning time are more correlated, and it often indicates that the cleaning degree at the a-th cleaning time is more likely to change with the cleaning temperature. a The larger it is, the more likely it is that the a-th cleaning time is to reach the local optimal cleaning time.

[0099] Next, the local optimal factor under the cleaning time in each historical cleaning record is determined as the target contribution factor corresponding to each historical cleaning record.

[0100] Then, the product of the cleaning time in each historical cleaning record and its corresponding target contribution factor is determined as the correction time corresponding to each historical cleaning record.

[0101] Furthermore, the product of the cleaning energy consumption in each historical cleaning record and its corresponding target contribution factor is determined as the corrected energy consumption corresponding to each historical cleaning record.

[0102] Next, the product of the cleaning degree in each historical cleaning record and its corresponding target contribution factor is determined as the correction degree corresponding to each historical cleaning record.

[0103] Finally, based on the time series consisting of the correction time of all historical cleaning records, the time series consisting of the correction energy consumption of all historical cleaning records, and the time series consisting of the correction degree of all historical cleaning records, the formula for determining the control importance under the cleaning time dimension can be:

[0104] γ1 = w1 × (w3 × GP(XtX, XEX) + w4 × GP(XtX, XCX)); where γ1 is the control importance under the cleaning time dimension. w1 is the target factor weight under the cleaning time dimension. w3 is the target factor weight under the cleaning energy consumption dimension. w4 is the target factor weight under the cleaning degree dimension. GP(XtX, XEX) is the normalized Pearson correlation coefficient between XtX and XEX. GP(XtX, XCX) is the normalized Pearson correlation coefficient between XtX and XCX. XtX is the time series consisting of the correction times corresponding to all historical cleaning records. XEX is the time series consisting of the correction energy consumption corresponding to all historical cleaning records. XCX is the time series consisting of the correction degrees corresponding to all historical cleaning records.

[0105] It should be noted that, in practice, the more positive the correlation between cleaning time and cleaning energy consumption, and the more positive the correlation between cleaning time and cleanliness, the more likely cleaning time is to play a significant role in the control process. Generally speaking, historical cleaning records with high local optimal factors contribute more to the Pearson correlation coefficient, while historical cleaning records with low local optimal factors contribute less to the Pearson correlation coefficient. The target factor weight represents the weight of the corresponding dimension. Therefore, a larger γ1 indicates that cleaning time is more likely to play a significant role in the control process.

[0106] In the second sub-step, similarly, the importance of regulation under the cleaning temperature dimension is determined based on historical cleaning records with the same cleaning temperature.

[0107] It should be noted that the method for obtaining the importance of regulation under the cleaning temperature dimension can be the same as the method for obtaining the importance of regulation under the cleaning time dimension. Specifically, when determining the importance of regulation under the cleaning temperature dimension, the cleaning temperature and cleaning time can be regarded as cleaning time and cleaning temperature, respectively, and the first step included in step S4 is executed as an example. The regulation importance obtained at this time is the regulation importance under the cleaning temperature dimension.

[0108] It should be noted that when the importance of regulation under the cleaning temperature dimension is greater, it often means that the cleaning temperature is more likely to occupy an important position in the regulation process.

[0109] In the second step, based on the importance of all controls, the perturbation range in the simulated annealing algorithm solution is corrected.

[0110] For example, the formula corresponding to the perturbation range in the modified simulated annealing algorithm solution can be:

[0111]

[0112]

[0113] Among them, st v,L+1，1 It is the minimum value of the corrected perturbation range of the cleaning time in the L+1th candidate solution of the vth combination solution in the simulated annealing algorithm. Candidate solution is also called neighborhood solution. v,L+1，2 sT is the maximum value of the corrected perturbation range of the cleaning time in the L+1th candidate solution of the vth combination solution in the simulated annealing algorithm. v，L+1，1 sT is the minimum value of the corrected perturbation range of the clean temperature in the L+1th candidate solution of the vth combination solution in the simulated annealing algorithm. v，L+1，2 is the maximum value of the corrected perturbation range of the clean temperature in the L+1th candidate solution of the vth combination solution in the simulated annealing algorithm. v is the serial number of the combination solution of the objective function. L is the serial number of the candidate solution of the vth combination solution. v，L T is the normalized value of the cleaning time in the Lth candidate solution of the vth combined solution. v，L is the normalized value of the cleaning temperature in the Lth candidate solution of the vth combination solution. γ1 is the control importance under the cleaning time dimension. γ2 is the control importance under the cleaning temperature dimension. and is a hyperparameter. w1 is the target factor weight under the cleaning time dimension. w2 is the target factor weight under the cleaning temperature dimension.

[0114] It should be noted that the perturbation range of dimensions with higher regulation importance often needs to be relatively increased, while the perturbation range of dimensions with lower regulation importance should often be relatively reduced. v,L+1,1 ,st v,L+1,2 ] can characterize the final perturbation range of the cleaning time in the L+1 candidate solution of the vth combination solution in the simulated annealing algorithm solution. [sT v，L+1，1 , sT v，L+1，2 ] can characterize the final perturbation range of the cleaning temperature in the L+1th candidate solution of the vth combined solution in the simulated annealing algorithm solution.

[0115] In the third step, the perturbation probability of each combined solution in the simulated annealing algorithm is corrected according to the target factor weights under the cleaning time dimension and the cleaning temperature dimension.

[0116] For example, the formula corresponding to the perturbation probability of the combined solution in the modified simulated annealing algorithm can be:

[0117] k v，L+1 =exp(-(w1×|Et v -Et v,L |+w2×|ET v -ET v，L |)); where k v,L+1 is the perturbation probability of the vth combination solution within the overall perturbation range of the L+1th candidate solution, which indicates the selectability of the vth combination solution within the perturbation range of the L+1th candidate solution. v is the serial number of the combination solution of the objective function. L is the serial number of the candidate solution of the vth combination solution. exp() is the natural exponential function. w1 is the target factor weight under the cleaning time dimension. || is the absolute value function. Et v Et is the mean of the cleaning energy consumption in all historical cleaning records whose cleaning time is equal to the cleaning time in the vth combined solution. v，L is the mean of the cleaning energy consumption in all historical cleaning records whose cleaning time is equal to the cleaning time in the Lth candidate solution of the vth combination solution. w2 is the target factor weight under the cleaning temperature dimension. ET v ET is the average cleaning energy consumption in all historical cleaning records where the cleaning temperature is equal to the cleaning temperature in the vth combined solution. v,L It is the mean of the cleaning energy consumption in all historical cleaning records where the cleaning temperature is equal to the cleaning temperature in the Lth candidate solution of the vth combined solution.

[0118] It should be noted that in actual situations, when the current solution is perturbed, a new solution is usually randomly selected within the perturbation range. Generally speaking, the random desirability of each solution within the perturbation range is the same. However, if certain perturbations cause drastic changes in energy consumption, it may cause serious damage to the split heating rod. The materials used for heating rods usually have specific temperature resistance ranges and durability limits. If the energy consumption fluctuates too much, especially frequent heating and cooling cycles, it will accelerate the aging and fatigue of the material. Repeated thermal cycles at high temperatures may cause changes in material properties, such as fatigue of metals or embrittlement of plastics, which will significantly reduce the durability of the heating rod and may even lead to structural failure in extreme cases. Therefore, in order to avoid damage to the heating rod due to excessive energy consumption fluctuations, the desirability of solutions within the perturbation range should be adjusted. Specifically, solutions with smaller energy consumption changes within the perturbation range should have higher desirability, thereby reducing potential harm to the heating rod and improving the selectivity of the solution. |Et v -Et v,L |It can represent the energy consumption change between the cleaning time in the vth combined solution and the cleaning time in the Lth candidate solution within the perturbation range of the L+1th candidate solution. |ET v -ET v,L | can represent the energy consumption change between the clean temperature in the vth combined solution and the clean temperature in the Lth candidate solution within the perturbation range of the L+1th candidate solution. Therefore, k v,L+1 It can characterize the desirability of the vth combined solution within the perturbation range of the L+1th candidate solution. The larger its value is, the more desirable it is.

[0119] Optionally, the specific steps of solving the objective function by using a simulated annealing algorithm to obtain the optimal combination solution may include:

[0120] The first step is initialization. Specifically, set the initial solution: randomly select an initial solution, which includes the cleaning time and cleaning temperature. Set the initial "temperature": select a high initial "temperature". Set the termination "temperature": set a low "temperature". When the "temperature" drops to this value, the algorithm stops iterating. Set the "temperature" decay strategy: a linear decay strategy can be used.

[0121] The second step is to generate neighborhood solutions. Specifically, according to the previously determined perturbation range, a new neighborhood solution is generated according to the perturbation probability of each solution.

[0122] The third step is to calculate the quality of the solution. Specifically, the objective function value of the current solution and the neighborhood solution, namely "energy", can be calculated through the previous steps.

[0123] The fourth step is to accept or reject the neighboring solution. Specifically, if the neighboring solution is better than the current solution, that is, the objective function value is smaller, then the neighboring solution is accepted as the new current solution. If the neighboring solution is worse than the current solution, then the neighboring solution is accepted with a certain probability (Metropolis criterion).

[0124] The fifth step is to reduce the “temperature”. Specifically, the “temperature” is reduced according to the preset linear attenuation strategy.

[0125] The sixth step is to check the termination condition. Specifically, when the "temperature" drops to the termination "temperature", the algorithm stops and outputs the current solution as the final optimized solution.

[0126] The seventh step is to return the optimal solution. Specifically, at the time of termination, the currently found optimal solution is returned as the determined optimal cleaning temperature and cleaning time of the split heating rod.

[0127] Optionally, after the optimal cleaning time and cleaning temperature are determined by the simulated annealing algorithm, wireless control technology can be used to achieve self-cleaning of the split heating rod. First, the optimal cleaning time and temperature settings are transmitted to the control unit of the heating rod through a wireless communication module (such as Wi-Fi or Bluetooth). The temperature sensor in the heating rod monitors the current temperature in real time and adjusts the heater according to the received instructions to ensure that heating is within the set temperature range. The control system starts the heating process according to the set cleaning time and automatically maintains a stable temperature. During the cleaning process, the system will continue to monitor the temperature and time, and feed back real-time data to the user device through the wireless network. The user can check the progress or adjust the parameters at any time. When the cleaning time is reached, the system will automatically stop heating and complete the self-cleaning process. Through this wireless control method, the user can complete the automatic cleaning of the heating rod without manual intervention, which improves the degree of automation and ease of use of the equipment to a certain extent.

[0128] refer to Figure 2 Based on the same inventive concept as the above method embodiment, the present invention provides a wireless control system for a split heating rod with a self-cleaning function. The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the wireless control method for a split heating rod with a self-cleaning function may specifically include:

[0129] An acquisition and determination module 201 is configured to acquire historical cleaning records representing different historical self-cleaning processes of the split heating rod to be controlled, and determine target factor weights under the cleaning time dimension, the cleaning temperature dimension, the cleaning energy consumption dimension, and the cleaning degree dimension based on all historical cleaning records;

[0130] The time and temperature determination module 202 is used to determine the standard cleaning time and standard cleaning temperature based on the target factor weights under the cleaning energy consumption dimension and the cleaning degree dimension, as well as the cleaning time and cleaning temperature in all historical cleaning records;

[0131] An objective function determination module 203 is configured to determine an objective function based on the weights of the target factors under the cleaning time dimension, the cleaning temperature dimension, the cleaning energy consumption dimension, and the cleaning degree dimension, as well as the standard cleaning time and the standard cleaning temperature;

[0132] The solution control and adjustment module 204 is used to solve the objective function through a simulated annealing algorithm to obtain an optimal combination solution, and control and adjust the split heating rod to be controlled based on the cleaning time and cleaning temperature in the optimal combination solution.

[0133] Figure 3 FIG. 1 is a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. For example, Figure 3 As shown, the computer device 300 includes: a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302, wherein when the processor 302 executes the computer program 303, the computer device can execute any one of the aforementioned wireless control methods for split heating rods with self-cleaning function.

[0134] Based on the same inventive concept as the above-described method embodiments, the present invention provides a server comprising a memory and a processor. The memory is configured to store executable program code, and the processor is configured to retrieve and execute the executable program code from the memory, thereby enabling the device to perform any of the above-described methods for wirelessly controlling a split-type heating rod with a self-cleaning function.

[0135] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer program product, which includes: computer program code, which, when running on a computer, enables the computer to execute any one of the above-mentioned wireless control methods for a split heating rod with a self-cleaning function.

[0136] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer executes any one of the above-mentioned wireless control methods for a split heating rod with a self-cleaning function.

[0137] In summary, compared with the prior art of assigning weights to each target factor through expert evaluation methods and weighting the objective function of each factor to obtain the overall objective function, the present invention first clarifies the target factors of the system, and determines the weight of each target factor through historical record data, and generates an objective function that is more suitable for the current problem to evaluate the target value of each cleaning time and cleaning temperature combination.

[0138] Secondly, in the prior art, when a new solution is randomly selected each time a disturbance occurs, the disturbance range is not clearly specified, and not all solutions within the disturbance range are desirable. The present invention determines the importance of regulating the cleaning time dimension and the cleaning temperature dimension in the disturbance space, and combines the "temperature" at this time to obtain a clear disturbance range. Then, the desirability of each solution within the disturbance range is determined by the energy consumption change between the current solution and the solution within the disturbance range. Finally, the new solution is selected based on the desirability. To a certain extent, the acquisition of inappropriate solutions can be reduced, thereby improving the rationality of the subsequent optimal screening of cleaning time and cleaning temperature.

[0139] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A wireless control method for a split type heating rod with a self-cleaning function, characterized in that: The following steps are involved: Obtain historical cleaning records representing different historical self-cleaning processes of the split heating rod to be controlled, and determine the target factor weights under the cleaning time dimension, cleaning temperature dimension, cleaning energy consumption dimension, and cleaning degree dimension based on all historical cleaning records; Determine the standard cleaning time and standard cleaning temperature based on the target factor weights under the cleaning energy consumption dimension and the cleaning degree dimension, as well as the cleaning time and cleaning temperature in all historical cleaning records; Determine the objective function based on the weights of the target factors under the cleaning time dimension, cleaning temperature dimension, cleaning energy consumption dimension and cleaning degree dimension, as well as the standard cleaning time and standard cleaning temperature; The simulated annealing algorithm is used to solve the objective function and obtain the optimal combination solution. Based on the cleaning time and cleaning temperature in the optimal combination solution, the split heating rod to be controlled is controlled and adjusted. When solving the objective function using the simulated annealing algorithm, the importance of controls in the cleaning time and cleaning temperature dimensions is determined based on all historical cleaning records, and the perturbation range in the simulated annealing algorithm solution is corrected based on all the control importances. According to the target factor weights under the cleaning time dimension and the cleaning temperature dimension, the disturbance probability of each combination solution in the simulated annealing algorithm is corrected; The formula corresponding to the objective function is: F(t v ,T v )=w1×F 1v +w2×F 2v +w3×F 3v -w4×F 4v ; F 1v =(t v -t) 2 ; F 2v =(T v -T) 2 ; B i,v =exp(-(w1×|t v -t i |+w2×|T v -T i |)); Among them, F(t v ,T v ) is the function value of the objective function under the vth combination solution; v is the sequence number of the combination solution of the objective function; t v and T v The vth combined solution of the objective function, t v is the normalized value of the cleaning time in the vth combined solution of the objective function, T v is the normalized value of the cleaning temperature in the vth combined solution of the objective function; w1 is the target factor weight under the cleaning time dimension; w2 is the target factor weight under the cleaning temperature dimension; w3 is the target factor weight under the cleaning energy consumption dimension; w4 is the target factor weight under the cleaning degree dimension; F 1v 、F 2v 、F 3v and F 4v are the indicators associated with the cleaning time dimension, cleaning temperature dimension, cleaning energy consumption dimension, and cleaning degree dimension under the vth combination solution; t is the standard cleaning time; T is the standard cleaning temperature; N is the number of historical cleaning records; i is the sequence number of the historical cleaning record; B i,v is the similarity between the i-th historical cleaning record and the v-th combination solution; B v is the cumulative value of the similarity between all historical cleaning records and the vth combined solution; E i is the normalized value of cleaning energy consumption in the i-th historical cleaning record; C i is the normalized value of the cleanliness level in the i-th historical cleaning record; exp() is the natural exponential function; || is the absolute value function; t i is the normalized value of the cleaning time in the i-th historical cleaning record; T i is the normalized value of the cleaning temperature in the i-th historical cleaning record.

2. A wireless control method for a split type heating rod with a self-cleaning function according to claim 1, characterized in that: The weights of target factors under the cleaning time dimension, cleaning temperature dimension, cleaning energy consumption dimension, and cleaning degree dimension are determined based on all historical cleaning records, including: Based on the differences between each cleaning time and the average cleaning time, the differences between each cleaning temperature and the average cleaning temperature, the differences between each cleaning energy consumption and the average cleaning energy consumption, and the differences between each cleaning degree and the average cleaning degree in all historical cleaning records, the target factor weights under the cleaning time dimension, cleaning temperature dimension, cleaning energy consumption dimension and cleaning degree dimension are determined.

3. The wireless control method for a split type heating rod with a self-cleaning function according to claim 2, characterized in that: The simultaneous formulas corresponding to the target factor weights under the cleaning time dimension, cleaning temperature dimension, cleaning energy consumption dimension, and cleaning degree dimension are as follows: Among them, w1 is the target factor weight under the cleaning time dimension; w2 is the target factor weight under the cleaning temperature dimension; w3 is the target factor weight under the cleaning energy consumption dimension; w4 is the target factor weight under the cleanliness degree dimension; N is the number of historical cleaning records; i is the sequence number of the historical cleaning record; || is the absolute value function; t i is the normalized value of the cleaning time in the i-th historical cleaning record; μ1 is the mean of the normalized values ​​of the cleaning time in all historical cleaning records; T i is the normalized value of the cleaning temperature in the i-th historical cleaning record; μ2 is the mean of the normalized values ​​of the cleaning temperature in all historical cleaning records; E i is the normalized value of the cleaning energy consumption in the i-th historical cleaning record; μ3 is the mean of the normalized values ​​of the cleaning energy consumption in all historical cleaning records; C i is the normalized value of the cleanliness level in the i-th historical cleaning record; μ4 is the mean of the normalized values ​​of the cleanliness level in all historical cleaning records.

4. The wireless control method for a split type heating rod with a self-cleaning function according to claim 1, characterized in that: The standard cleaning time and standard cleaning temperature are determined based on the target factor weights under the cleaning energy consumption dimension and the cleaning degree dimension, as well as the cleaning time and cleaning temperature in all historical cleaning records, including: Determine the cleaning effect factor corresponding to each historical cleaning record based on the target factor weights under the cleaning energy consumption dimension and the cleaning degree dimension, as well as the cleaning energy consumption and cleaning degree in each historical cleaning record; Determine the standard cleaning time based on the cleaning effect factors corresponding to all historical cleaning records and the cleaning time in all historical cleaning records; The standard cleaning temperature is determined based on the cleaning effect factors corresponding to all historical cleaning records and the cleaning degrees in all historical cleaning records.

5. The wireless control method for a split type heating rod with a self-cleaning function according to claim 4, characterized in that: The formulas for the cleaning effect factors corresponding to the standard cleaning time, standard cleaning temperature, and historical cleaning records are: Where t is the standard cleaning time; T is the standard cleaning temperature; N is the number of historical cleaning records; i is the sequence number of the historical cleaning record; A i is the cleaning effect factor corresponding to the i-th historical cleaning record; A is the cumulative value of the cleaning effect factors corresponding to all historical cleaning records; t i is the normalized value of the cleaning time in the i-th historical cleaning record; T i is the normalized value of the cleaning temperature in the i-th historical cleaning record; w3 is the target factor weight under the cleaning energy consumption dimension; w4 is the target factor weight under the cleaning degree dimension; E i is the normalized value of the cleaning energy consumption in the i-th historical cleaning record; ε is a pre-set hyperparameter greater than 0; C i is the normalized value of the cleanliness level in the i-th historical cleaning record.

6. The wireless control method for a split type heating rod with a self-cleaning function according to claim 1, characterized in that: The importance of control under the cleaning time dimension and cleaning temperature dimension is determined based on all historical cleaning records, including: Determine the importance of regulation under the cleaning time dimension based on historical cleaning records with the same cleaning time; Similarly, based on the historical cleaning records with the same cleaning temperature, the importance of regulation under the cleaning temperature dimension is determined.

7. The wireless control method for a split type heating rod with a self-cleaning function according to claim 6, characterized in that: Determining the importance of regulation under the cleaning time dimension based on historical cleaning records with the same cleaning time includes: According to the historical cleaning records under the same cleaning time, the formula for determining the local optimal factor under the cleaning time is: Among them, Lt a is the local optimal factor under the a-th cleaning time; a is the sequence number of different cleaning times in all historical cleaning records; || is the absolute value function; PCCs(TX a ,CX a ) is TX a and CX a Pearson correlation coefficient between TX a is the time series of cleaning temperatures in all historical cleaning records where the cleaning time is equal to the a-th cleaning time; CX a is a time series consisting of the cleaning degrees of all historical cleaning records whose cleaning time is equal to the a-th cleaning time; ε1 is a pre-set hyperparameter greater than 0; Determine the local optimal factor under the cleaning time in each historical cleaning record as the target contribution factor corresponding to each historical cleaning record; The product of the cleaning time in each historical cleaning record and its corresponding target contribution factor is determined to determine the correction time corresponding to each historical cleaning record; The product of the cleaning energy consumption in each historical cleaning record and its corresponding target contribution factor is determined to determine the corrected energy consumption corresponding to each historical cleaning record; The product of the cleaning degree in each historical cleaning record and its corresponding target contribution factor is determined to determine the correction degree corresponding to each historical cleaning record; Based on the time series consisting of the correction time of all historical cleaning records, the time series consisting of the correction energy consumption of all historical cleaning records, and the time series consisting of the correction degree of all historical cleaning records, the formula for determining the importance of control in the cleaning time dimension is: γ1=w1×(w3×GP(XtX,XEX)+w4×GP(XtX,XCX)); where γ1 is the importance of regulation under the cleaning time dimension; w1 is the target factor weight under the cleaning time dimension; w3 is the target factor weight under the cleaning energy consumption dimension; w4 is the target factor weight under the cleaning degree dimension; GP(XtX,XEX) is the normalized value of the Pearson correlation coefficient between XtX and XEX; GP(XtX,XCX) is the normalized value of the Pearson correlation coefficient between XtX and XCX; XtX is the time series consisting of the correction time corresponding to all historical cleaning records; XEX is the time series consisting of the correction energy consumption corresponding to all historical cleaning records; XCX is the time series consisting of the correction degree corresponding to all historical cleaning records.

8. The wireless control method for a split type heating rod with a self-cleaning function according to claim 1, characterized in that: The formula corresponding to the perturbation range in the modified simulated annealing algorithm is: Among them, st v,L+1,1 is the minimum value of the corrected perturbation range of the cleaning time in the L+1 candidate solution of the vth combination solution in the simulated annealing algorithm; st v,L+1,2 is the maximum value of the corrected perturbation range of the cleaning time in the L+1th candidate solution of the vth combination solution in the simulated annealing algorithm; sT v,L+1,1 is the minimum value of the corrected perturbation range of the clean temperature in the L+1th candidate solution of the vth combination solution in the simulated annealing algorithm; sT v,L+1,2 is the maximum value of the corrected perturbation range of the clean temperature in the L+1th candidate solution of the vth combination solution in the simulated annealing algorithm; v is the serial number of the combination solution of the objective function; L is the serial number of the candidate solution of the vth combination solution; t v,L is the normalized value of the cleaning time in the Lth candidate solution of the vth combination solution; T v,L is the normalized value of the cleaning temperature in the Lth candidate solution of the vth combination solution; γ1 is the control importance under the cleaning time dimension; γ2 is the control importance under the cleaning temperature dimension; and is a hyperparameter; w1 is the target factor weight under the cleaning time dimension; w2 is the target factor weight under the cleaning temperature dimension.

9. The wireless control method for a split type heating rod with a self-cleaning function according to claim 1, characterized in that: The formula corresponding to the perturbation probability of the combined solution in the modified simulated annealing algorithm is: k v,L+1 =exp(-(w1×|Et v -Et v,L |+w2×|ET v -ET v,L |)); where k v,L+1 is the perturbation probability of the vth combination solution within the overall perturbation range of the L+1th candidate solution; v is the serial number of the combination solution of the objective function; L is the serial number of the candidate solution of the vth combination solution; exp() is the natural exponential function; w1 is the target factor weight under the cleaning time dimension; || is the absolute value function; Et v is the mean of the cleaning energy consumption in all historical cleaning records whose cleaning time is equal to the cleaning time in the vth combination solution; Et v,L is the mean of the cleaning energy consumption in all historical cleaning records whose cleaning time is equal to the cleaning time in the Lth candidate solution of the vth combination solution; w2 is the target factor weight under the cleaning temperature dimension; ET v is the mean cleaning energy consumption in all historical cleaning records where the cleaning temperature is equal to the cleaning temperature in the vth combined solution; ET v,L It is the mean of the cleaning energy consumption in all historical cleaning records where the cleaning temperature is equal to the cleaning temperature in the Lth candidate solution of the vth combined solution.

Images