Electric water heater quick heating control method and system driven by user habit analysis and electric water heater

Abstract

The invention relates to an electric water heater instant heating control method and system driven by user habit analysis and an electric water heater, and relates to the field of intelligent control, and the method comprises the steps that when an instant heating command signal does not comprise an instant heating specified temperature, specified temperature habit analysis is conducted, and an instant heating temperature target interval is obtained; when the instant heating command signal does not comprise the instant heating appointed duration, appointed duration habit analysis is carried out, and a heating constraint time zone is obtained; electric water heater heating power time sequence information is randomly configured in the heating constraint time zone, the electric water heater heating power time sequence information, the water body initial temperature information and the cavity water level information are input into the temperature prediction model to be analyzed, and water body temperature time sequence information is obtained; and when the end point moment temperature belongs to the instant heating temperature target interval, electric water heater instant heating control is conducted according to the electric water heater heating power time sequence information. The technical problem that in the prior art, due to the fact that an electric water heater is low in operation intelligence degree, the individualized requirement of a user cannot be met is solved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a method and system for controlling rapid heating of an electric water heater driven by user habit analysis, and an electric water heater. Background Art

[0002] In traditional electric water heater technology, users need to manually set the heating temperature and heating time when using the electric water heater. However, users need to repeat the settings every time they use the electric water heater, which is cumbersome and troublesome to use. In addition, the existing operation method of the electric water heater has obvious limitations, especially for children and the elderly, who may not be familiar with how to set the heating temperature and heating time, resulting in low comfort in using the electric water heater.

[0003] Although there are currently electric water heaters with automatic heating, they all use a unified control mode for heating and cannot meet the user's individual needs for manual control.

[0004] In summary, how to achieve automatic control of electric water heaters that meets the personalized needs of users has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present invention aims to solve the technical problem in the prior art that the electric water heater has a low degree of intelligent operation, resulting in the inability to meet the individual needs of users. An electric water heater rapid heating control method, system and electric water heater driven by user habit analysis are provided to solve the problem.

[0006] The technical solution of the present invention to solve the above technical problems is as follows:

[0007] In a first aspect, the present invention provides a method for controlling rapid heating of an electric water heater driven by user habit analysis, comprising: receiving a rapid heating command signal; when the rapid heating command signal does not include a specified rapid heating temperature, performing a specified temperature habit analysis on the user's historical rapid heating log to obtain a rapid heating temperature target range; when the rapid heating command signal does not include a specified rapid heating duration, performing a specified duration habit analysis on the user's historical rapid heating log to obtain a heating constraint time zone; randomly configuring the heating power timing information of the electric water heater in the heating constraint time zone, inputting the heating power timing information of the electric water heater, the initial temperature information of the water body and the water level information in the cavity into a temperature prediction model for analysis to obtain the water body temperature timing information; when the temperature at the end moment of the water body temperature timing information belongs to the rapid heating temperature target range, performing rapid heating control of the electric water heater according to the heating power timing information of the electric water heater.

[0008] In a second aspect, the present invention provides an electric water heater rapid heating control system driven by user habit analysis, comprising: a signal receiving module for receiving a rapid heating command signal; a temperature habit analysis module for, when the rapid heating command signal does not include a specified rapid heating temperature, performing a specified temperature habit analysis on the user's historical rapid heating log to obtain a rapid heating temperature target range; a duration habit analysis module for, when the rapid heating command signal does not include a specified rapid heating duration, performing a specified duration habit analysis on the user's historical rapid heating log to obtain a heating constraint time zone; a water body temperature prediction module for randomly configuring the electric water heater heating power timing information in the heating constraint time zone, inputting the electric water heater heating power timing information, the water body initial temperature information and the water level information in the cavity into a temperature prediction model for analysis to obtain the water body temperature timing information; a task execution module for, when the temperature at the end moment of the water body temperature timing information belongs to the rapid heating temperature target range, performing rapid heating control of the electric water heater according to the electric water heater heating power timing information.

[0009] In a third aspect, the present invention provides an electric water heater, comprising: a memory for storing a computer software program; a processor for reading and executing the computer software program, thereby implementing the electric water heater rapid heating control method driven by user habit analysis as described in the first aspect.

[0010] In a fourth aspect, the present invention provides a non-transitory computer-readable storage medium, in which a computer software program is stored. When the computer software program is executed by a processor, the electric water heater rapid heating control method driven by user habit analysis described in the first aspect is implemented.

[0011] The beneficial effects of the present invention are as follows: after receiving a quick heating command signal, if there is no quick heating specified temperature and quick heating specified duration, the user's heating habits are analyzed according to the user's historical quick heating log, and the heating temperature and duration are automatically set. Then, based on the automatically set quick heating temperature target interval and heating constraint time zone, the heating power timing is optimized in combination with the temperature prediction model, and a technical solution for quick heating control of the electric water heater is obtained based on the heating power timing information of the electric water heater. By analyzing the user's historical quick heating log, the electric water heater can learn and predict the user's heating habits, and then use the temperature prediction model based on the heating habits to automatically configure the heating parameters and realize automatic quick heating control, ultimately achieving the technical effect of personalized heating control of the electric water heater. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A schematic flow chart of a method for controlling rapid heating of an electric water heater driven by user habit analysis provided by the present invention;

[0013] Figure 2 A schematic diagram of the structure of the electric water heater rapid heating control system driven by user habit analysis provided by the present invention;

[0014] Figure 3 A schematic diagram of the structure of the electric water heater provided by the present invention;

[0015] Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0016] In the accompanying drawings, the components represented by the reference numerals are described as follows:

[0017] Electric water heater 500 , memory 510 , processor 520 , first computer program 511 , computer readable storage medium 600 , second computer program 611 . DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0019] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0020] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0021] Embodiment 1:

[0022] like Figure 1 As shown, the embodiment of the present invention provides a method for controlling the rapid heating of an electric water heater driven by user habit analysis, comprising the steps of:

[0023] S10: receiving a rapid heating command signal;

[0024] Specifically, the quick heating command signal refers to the instruction issued by the user to the electric water heater, requiring it to start the quick heating mode in order to quickly heat the water to a suitable temperature. This signal may be input through physical buttons, touch screens, voice commands, or remote control (such as smartphone applications). The quick heating command signal may include the quick heating specified temperature and quick heating specified time directly specified by the user, or may not include these parameters.

[0025] In this step, the control system of the electric water heater needs to be able to recognize and analyze the quick heating command signal from the user; if the user does not specify a specific heating temperature and duration, the control system will automatically infer these parameters based on the user's historical usage data. The purpose of this step is to start the quick heating process and determine whether further user habit analysis is needed to complete the setting of heating parameters. It is the prerequisite for realizing personalized quick heating control and ensures that the electric water heater can perform subsequent heating operations according to the user's instructions or habits.

[0026] S20: When the quick heating command signal does not include a quick heating designated temperature, analyzing the user's historical quick heating logs for designated temperature habits to obtain a quick heating temperature target range;

[0027] Specifically, the specified temperature habit analysis refers to the process by which the electric water heater system analyzes the temperature data set by the user when using the electric water heater in the past. By analyzing the user's historical quick heating log, the system can identify the user's preferred temperature setting mode; the quick heating temperature target range refers to a temperature range based on the user's habit analysis. This range reflects the water temperature range that the user usually hopes to achieve in the quick heating mode.

[0028] When the user issues a quick-heat command signal but does not specify a specific temperature, the electric water heater system will automatically perform a specified temperature habit analysis, specifically: collecting and analyzing the user's historical quick-heat log data, including the water temperatures set by the user at different times and in different situations, and through data mining technology, identifying the water temperature range most commonly used by the user, thereby determining the quick-heat temperature target range.

[0029] For example, suppose a user usually likes to set the water temperature to 40℃ when taking a bath in the morning, but prefers 42℃ in the evening. The electric water heater system analyzes the user's quick heating logs in the past few months and finds that there is a significant difference in the water temperature settings in the morning and at night. Therefore, when the user issues a quick heating command signal in the morning without specifying a temperature, the system automatically sets the target temperature range to around 40℃, and to around 42℃ in the evening, thereby providing users with a more personalized and comfortable bathing experience.

[0030] The role of this step in the entire solution is to achieve personalized temperature control, so that the electric water heater can automatically provide the appropriate water temperature according to the user's habits without the need for manual input by the user each time. This not only improves the user experience, but also makes the operation of the electric water heater more intelligent and convenient.

[0031] S30: When the quick heating command signal does not include a specified quick heating time, performing a specified time habit analysis on the user's historical quick heating log to obtain a heating constraint time zone;

[0032] Specifically, designated time habit analysis refers to the process by which the electric water heater system analyzes the heating time data set by the user when using the electric water heater in the past. By analyzing the user's historical rapid heating log, the system can identify the user's preferred heating time setting mode. The heating constraint time zone refers to a time range based on user habit analysis, which reflects the maximum time limit that the user usually wants to complete heating in the rapid heating mode.

[0033] When the user issues a quick heating command signal but does not specify a specific heating duration, the electric water heater system will automatically perform a specified duration habit analysis. This process involves collecting and analyzing the user's historical quick heating log data, including the heating duration set by the user at different times and in different situations. Through data mining and pattern recognition technology, the system can identify the heating duration range most frequently used by the user, thereby determining the heating constraint time zone.

[0034] For example, suppose a user usually starts the electric water heater for heating 30 minutes before taking a bath, but wants the electric water heater to complete heating within 10 minutes when washing vegetables. The electric water heater system analyzes the user's quick heating logs for the past few months and finds that there is a significant difference in the heating time for taking a bath and washing vegetables. Therefore, when the user issues a quick heating command signal when preparing to take a bath without specifying the duration, the system will automatically set the heating constraint time zone to about 30 minutes, and to about 10 minutes when preparing to wash vegetables, thereby providing users with a more personalized and timely hot water supply.

[0035] The role of this step in the entire solution is to achieve personalized heating time control, so that the electric water heater can automatically provide appropriate heating time according to the user's habits without the user having to manually input it every time. This not only improves the user experience, but also makes the operation of the electric water heater more intelligent and convenient.

[0036] S40: randomly configuring the heating power time series information of the electric water heater in the heating constraint time zone, inputting the heating power time series information of the electric water heater, the initial temperature information of the water body and the water level information in the cavity into the temperature prediction model for analysis, and obtaining the water body temperature time series information;

[0037] Specifically, the heating power timing information refers to the heating power settings of the electric water heater at different time points during the heating process. Randomly configuring the heating power timing information within the heating constraint time zone means that the system will randomly set the size and change pattern of the heating power within the range that meets the user's heating time habits; the temperature prediction model is a mathematical model used to predict the change of water temperature of an electric water heater under given heating power, initial water temperature and water level in the cavity. The input of the model includes heating power timing information, initial water temperature information and water level in the cavity, and the output is the predicted water temperature timing information.

[0038] For example, suppose a user usually wants the water temperature to rise from 20°C to 40°C within 15 minutes when taking a shower in the morning, and from 25°C to 42°C within 30 minutes at night. The electric water heater system determines the heating constraint time zone and water temperature timing information by analyzing the user's historical rapid heating log. When the user sends a rapid heating command signal in the morning, the system will randomly configure a heating power timing so that the water temperature rises from 20°C to 40°C within 15 minutes. The temperature prediction model will predict the timing changes of the water temperature based on this configuration to ensure that the heating process meets the user's habits.

[0039] The role of this step in the entire plan is to ensure that the electric water heater can accurately control the temperature changes of the water body according to the user's habits and needs through the analysis of the temperature prediction model, thereby providing a more comfortable and personalized user experience.

[0040] S50: When the temperature at the end moment of the water body temperature time series information belongs to the rapid heating temperature target interval, the electric water heater is rapidly heated according to the heating power time series information of the electric water heater.

[0041] Specifically, the end-point temperature of the water body temperature time series information refers to the temperature value of the last time point in the water body temperature time series information output by the temperature prediction model. This temperature value is the expected temperature of the water body at the end of the electric water heater heating process.

[0042] When the temperature at the end moment of the water body temperature timing information belongs to the rapid heating temperature target range, the electric water heater will perform the heating operation according to the pre-configured heating power timing information to ensure that the water body temperature reaches a value within the rapid heating temperature target range when the heating ends.

[0043] After the temperature prediction model analyzes the water temperature time series information, the electric water heater system will check whether the temperature at the end of this time series information belongs to the rapid heating temperature target range. If it does, it means that the predicted heating result meets the user's personalized needs. The system will perform rapid heating control according to the configured heating power time series information, that is, perform the heating operation according to the power setting in this time series information. Through the analysis of the temperature prediction model and the configuration of the heating power time series information, the electric water heater can accurately control the heating process so that the water temperature reaches the user's expected temperature range at the end of heating, ensuring that the heating result of the electric water heater meets the user's personalized temperature needs, thereby providing a more comfortable and personalized user experience.

[0044] For example, suppose a user usually wants the water temperature to rise from 20°C to 40°C within 15 minutes when taking a shower in the morning, and from 25°C to 42°C within 30 minutes at night. The electric water heater system determines the rapid heating temperature target range by analyzing the user's historical rapid heating log. When the user sends a rapid heating command signal in the morning, the system configures a heating power sequence so that the water temperature rises from 20°C to 40°C within 15 minutes. The water temperature sequence information predicted by the temperature prediction model shows that the water temperature is 40°C at the end of heating, which belongs to the rapid heating temperature target range. Therefore, the electric water heater will perform rapid heating control according to this heating power sequence to ensure that the water temperature reaches 40°C within 15 minutes to meet the user's personalized needs.

[0045] Furthermore, the step of constructing the temperature prediction model in step S40 includes:

[0046] S41: Obtaining basic information of the electric water heater, wherein the basic information of the electric water heater includes the model of the electric water heater and the service time of the electric water heater;

[0047] S42: collecting the electric water heater heating power record time series information, water body initial temperature record information, cavity water level record information and water body temperature monitoring record time series information that meet the electric water heater model and the service life of the electric water heater, and setting it as a temperature prediction model construction data set;

[0048] S43: Using the water body temperature monitoring record time series information as supervision, the electric water heater heating power record time series information, the water body initial temperature record information, and the cavity water level record information as input data, the temperature prediction model is retrieved to construct a data set to train the temperature prediction model.

[0049] Specifically, the basic information of electric water heaters refers to the model and service time of the electric water heaters. This information is crucial to understanding the performance and aging degree of the electric water heaters. The model may affect the heating efficiency and power characteristics of the electric water heater, while the service time may affect its aging status and performance degradation; the heating power record time series information refers to the historical records of the heating power of the electric water heater at different time points. These data reflect the heating behavior of the electric water heater; the water body initial temperature record information and the cavity water level record information refer to the water body temperature and water level when the electric water heater starts heating, respectively. These initial conditions have a direct impact on the heating process and the final temperature; the water body temperature monitoring record time series information refers to the records of monitoring the water body temperature during the heating process. These data are used as supervision signals for model training to guide the model to learn how to predict future water body temperatures.

[0050] The steps of building a temperature prediction model are the key to achieving accurate and rapid heating control. First, it is necessary to collect basic information about the electric water heater, including the model and service time. This information helps to understand the performance characteristics and aging status of the electric water heater. Then, based on this basic information, the corresponding heating power record time series information, water body initial temperature record information, cavity water level record information, and water body temperature monitoring record time series information are collected. These data constitute the data set for the construction of the temperature prediction model.

[0051] Using the water temperature monitoring record time series information as the supervisory signal, and the electric water heater heating power record time series information, water body initial temperature record information, and cavity water level record information as input data, the temperature prediction model is trained from the constructed data set. This model can learn the relationship between the input data and the supervisory signal, thereby predicting the future water temperature under given heating power, initial temperature, and water level conditions.

[0052] For example, assume that an electric water heater model is X and has been in service for 5 years. The system first collects the heating power, initial water temperature, water level and temperature monitoring data of the electric water heater of model X and in service for 5 years. Then, use these data to train a temperature prediction model so that it can accurately predict the water temperature at the end of heating based on the input heating power, initial water temperature and water level. When the user issues a quick heating command signal, the system will use this trained model to predict the water temperature change under different heating power timings, and select a heating power timing that meets the user's quick heating temperature target range to perform heating, ensuring that the electric water heater can quickly and accurately reach the user's desired water temperature.

[0053] Further, taking the water body temperature monitoring record time series information as supervision, taking the electric water heater heating power record time series information, the water body initial temperature record information, and the cavity water level record information as input data, the temperature prediction model is retrieved to build a data set to train the temperature prediction model, step S43 includes the steps of:

[0054] S431: Construct unit model loss function:

[0055]

[0056] Among them, L represents the temperature prediction loss function, ξ represents the standard deviation coefficient, T i Represents the temperature prediction value at the i-th moment, T i0 represents the temperature monitoring value at the i-th moment, ΔT represents the temperature deviation threshold, and N represents the total number of moments in the time zone;

[0057] S432: according to the unit model loss function, taking the water body temperature monitoring record time series information as supervision, taking the electric water heater heating power record time series information, the water body initial temperature record information, and the cavity water level record information as input data, calling the temperature prediction model to construct a data set, and training a plurality of LSTM neural network temperature prediction unit models;

[0058] S433: Integrate the several LSTM neural network temperature prediction unit models to obtain the temperature prediction model.

[0059] Specifically, the unit model loss function refers to a mathematical function used to evaluate the performance of a single temperature prediction model, which measures the difference between the model prediction value and the actual value. The loss function is a key tool for optimizing model parameters in machine learning. The unit model loss function of the embodiment of the present application is in the following form: The loss function includes temperature prediction loss and standard deviation coefficient to ensure that the model can not only accurately predict the temperature but also capture the uncertainty of temperature changes; the LSTM neural network is a special recurrent neural network that is good at processing and predicting important events with long intervals and delays in time series data.

[0060] Using the water temperature monitoring record time series information as the supervisory signal, and the electric water heater heating power record time series information, water body initial temperature record information, and cavity water level record information as input data, several LSTM neural network temperature prediction unit models are trained from the constructed data set. LSTM is selected for its advantages in processing time series data, especially in capturing long-term dependencies. After training, these LSTM unit models are integrated to obtain the final temperature prediction model. The purpose of the integration is to improve the accuracy and robustness of the prediction by combining the prediction results of multiple models and reduce the possible overfitting problem of a single model.

[0061] Further, the plurality of LSTM neural network temperature prediction unit models are integrated to obtain the temperature prediction model, and step S433 includes the following steps:

[0062] S4331: Obtaining a plurality of temperature prediction time series information of the plurality of LSTM neural network temperature prediction unit models;

[0063] S4332: performing a central trend analysis on the temperature values ​​at the first moment of the plurality of temperature prediction time series information to obtain a temperature integration value at the first moment;

[0064] S4333: performing a central trend analysis on the temperature values ​​at the Mth moment of the plurality of temperature prediction time series information to obtain a temperature integration value at the Mth moment;

[0065] S4334: Sort the temperature integration value at the first moment to the temperature integration value at the Mth moment by time, and set them as output data of the temperature prediction model.

[0066] Specifically, several temperature prediction time series information refer to the output data of each unit model; the first moment temperature integration value refers to the result of mean analysis on the remaining concentrated data after outlier data are deleted from several first moment temperature values ​​of several temperature prediction time series information; the Mth moment temperature integration value refers to the result of mean analysis on the remaining concentrated data after outlier data are deleted from several Mth moment temperature values ​​of several temperature prediction time series information, and the temperature integration values ​​of all moments obtained are arranged in chronological order to form the final output data of the temperature prediction model.

[0067] Preferably, the detailed strategy of the central trend analysis is, taking the determination of the temperature integration value at the first moment as an example: sorting a number of first moment temperature values ​​from small to large to obtain a first moment temperature value sequence; calculating the result of multiplying one quarter by the total number of temperature values ​​at the first moment and rounding up to obtain a first serial number; extracting the result of multiplying three quarters by the total number of temperature values ​​at the first moment and rounding down to obtain a second serial number, calculating the difference between the second serial number temperature value and the first serial number temperature value in the first moment temperature value sequence, and setting it as the extreme value; calculating the first serial number temperature value minus 1.5 times the extreme value to obtain the lower limit temperature; calculating the second serial number temperature value plus 1.5 times the extreme value to obtain the upper limit temperature; extracting a set of temperatures greater than or equal to the lower limit temperature and less than or equal to the upper limit temperature from a number of first moment temperature values, finding the average, and setting it as the first moment temperature integration value.

[0068] Furthermore, the heating power time series information of the electric water heater is randomly configured in the heating constraint time zone, and the heating power time series information of the electric water heater, the initial temperature information of the water body and the water level information in the cavity are input into the temperature prediction model for analysis to obtain the water body temperature time series information, which also includes step S60. Step S60 includes the steps of:

[0069] S61: randomly configuring the heating power timing information of the first electric water heater according to the heating constraint time zone;

[0070] S62: Calculate the variance value of the heating power time series information of the first electric water heater and set it as a first fluctuation coefficient;

[0071] S63: Calculate the variance of the power standard deviation at adjacent moments of the heating power time series information of the first electric water heater, and set it as a second fluctuation coefficient;

[0072] S64: inputting the first fluctuation coefficient and the second fluctuation coefficient into a binary model of the life impact of the electric water heater to generate a binary value of the life impact;

[0073] S65: when the lifespan impact binary value is equal to 1, updating the heating power timing information of the first electric water heater and executing a loop;

[0074] S66: When the lifespan impact binary value is equal to 0, the first electric water heater heating power timing information is set as the electric water heater heating power timing information.

[0075] Specifically, the first electric water heater heating power timing information refers to a set of initial heating power settings randomly configured for the electric water heater within the heating constraint time zone, which changes over time and is used to control the heating process; the first fluctuation coefficient refers to the variance value of the heating power timing information, which reflects the amplitude of the power change; the second fluctuation coefficient refers to the variance value of the power standard deviation of the above adjacent moments, which is used to evaluate the consistency of the power change; the "life impact binary model" is a model that evaluates the impact of the heating power configuration on the life of the electric water heater based on the fluctuation coefficient and outputs a binary value (0 or 1). The life impact binary value is the output of the life impact binary model, indicating whether the heating power configuration has a negative impact on the life of the electric water heater (1 means there is an impact and needs to be adjusted; 0 means no impact and it is acceptable).

[0076] The first fluctuation coefficient and the second fluctuation coefficient are used as inputs to enter the life impact binary model. The model generates a binary value based on the input fluctuation coefficient to determine whether the current heating power timing information will affect the life of the electric water heater. If the life impact binary value is equal to 1, it means that the current heating power timing information may damage the life of the electric water heater. The heating power timing information of the first electric water heater needs to be updated and the loop is re-executed until a suitable configuration is found. If the binary value is equal to 0, it means that the current configuration has no negative impact on the life, and the heating power timing information can be accepted.

[0077] By dynamically adjusting the heating power timing information and evaluating its impact on life, the heating strategy can be optimized and the service life of the electric water heater can be extended while ensuring the user experience.

[0078] Further, the first fluctuation coefficient and the second fluctuation coefficient are input into the binary model of the life impact of the electric water heater to generate a binary value of the life impact. Step S64 includes the following steps:

[0079] S641: Setting a first fluctuation coefficient threshold interval and a second fluctuation coefficient threshold interval;

[0080] S642: When the first fluctuation coefficient belongs to the first fluctuation coefficient threshold interval, and the second fluctuation coefficient belongs to the second fluctuation coefficient threshold interval, the lifespan impact binary value is equal to 0;

[0081] S643: Otherwise, the lifespan impact binary value is equal to 1.

[0082] Specifically, the first fluctuation coefficient threshold interval and the second fluctuation coefficient threshold interval refer to the safety range or ideal range set for the first fluctuation coefficient and the second fluctuation coefficient. These intervals are determined based on the design parameters and historical service data of the electric water heater to evaluate the potential impact of heating power changes on the life of the electric water heater.

[0083] If the first fluctuation coefficient and the second fluctuation coefficient are both within their respective threshold ranges, it means that the heating power change is within a safe range. At this time, the generated life impact binary value is equal to 0, indicating that the current heating power configuration has no negative impact on the life of the electric water heater; if any fluctuation coefficient exceeds the corresponding threshold range, it means that the heating power change may damage the life of the electric water heater. At this time, the generated life impact binary value is equal to 1, indicating that the heating power configuration needs to be adjusted.

[0084] Exemplarily, assume that the first fluctuation coefficient threshold interval of the electric water heater is [0.1, 0.3], and the second fluctuation coefficient threshold interval is [0.05, 0.2]. If the calculated first fluctuation coefficient of the heating power timing information is 0.2, and the second fluctuation coefficient is 0.15, both within their respective threshold intervals, then the life impact binary value is equal to 0, indicating that this heating power configuration is safe. If any coefficient exceeds the threshold interval, for example, the first fluctuation coefficient is 0.4, then the life impact binary value is equal to 1, and the heating power configuration needs to be readjusted to ensure that the life of the electric water heater is not affected. By setting a reasonable fluctuation coefficient threshold interval and evaluating the life impact binary value, the heating power configuration can be dynamically adjusted to balance the relationship between rapid heating demand and equipment life, extend the service life of the electric water heater, and ensure the long-term interests of users.

[0085] Further, the first fluctuation coefficient threshold interval and the second fluctuation coefficient threshold interval are set, and step S641 includes the steps of:

[0086] S6412: Get service data of electric water heater;

[0087] S6413: According to the service data of the electric water heater, a plurality of first fluctuation coefficient record values, a plurality of second fluctuation coefficient record values ​​and a plurality of electric water heater life record values ​​corresponding to each other are counted;

[0088] S6414: extracting a first fluctuation coefficient record value set and a second fluctuation coefficient record value set whose life record values ​​of the electric water heaters are greater than or equal to a life threshold value from the plurality of first fluctuation coefficient record values ​​and the plurality of second fluctuation coefficient record values;

[0089] S6415: Count the non-outlier distribution intervals of the first fluctuation coefficient record value set and the second fluctuation coefficient record value set respectively, and set the first fluctuation coefficient threshold interval and the second fluctuation coefficient threshold interval.

[0090] Specifically, the service data of electric water heaters refers to the data collected during the actual use of electric water heaters, including the operating parameters and performance indicators of electric water heaters; the first fluctuation coefficient record value and the second fluctuation coefficient record value refer to the actual record values ​​of the fluctuation coefficient calculated based on the heating power time series information during the service period of the electric water heater; the life record value of the electric water heater refers to the record of the actual service life or durability index of the electric water heater during the service period. The non-outlier distribution interval refers to the range of concentrated distribution of data points after removing outliers or outliers in statistical analysis. This range can better reflect the general trend and stability of the data.

[0091] The detailed steps are as follows: collect data generated by the actual use of the electric water heater, including heating power timing information, service life, etc., extract the corresponding first fluctuation coefficient record value, second fluctuation coefficient record value and electric water heater life record value from the service data, and filter out the corresponding fluctuation coefficient record values ​​whose electric water heater life record values ​​are greater than or equal to the preset life threshold value from the above record values ​​to form two sets; perform statistical analysis on the filtered fluctuation coefficient record value sets, exclude outliers, and determine the concentrated distribution interval of non-outlier points; set the non-outlier point distribution interval as the threshold interval of the first fluctuation coefficient and the second fluctuation coefficient, and these intervals will be used to evaluate the impact of the new heating power timing information on the life of the electric water heater.

[0092] By analyzing the actual service data, the threshold range can be set more accurately, making the control strategy of the electric water heater more in line with the actual usage and improving the reliability and effectiveness of the control strategy.

[0093] The electric water heater rapid heating control method driven by user habit analysis provided by the embodiment of the present invention has at least the following technical effects:

[0094] 1. After receiving the quick heating command signal, if there is no specified quick heating temperature and quick heating duration, the user's heating habits are analyzed according to the user's historical quick heating log, and the heating temperature and duration are automatically set. Then, based on the automatically set quick heating temperature target interval and heating constraint time zone, the heating power timing is optimized in combination with the temperature prediction model, and the heating power timing information of the electric water heater is obtained to obtain a technical solution for quick heating control of the electric water heater. By analyzing the user's historical quick heating log, the electric water heater can learn and predict the user's heating habits, and then use the temperature prediction model based on the heating habits to automatically configure the heating parameters and realize automatic quick heating control, ultimately achieving the technical effect of personalized heating control of the electric water heater.

[0095] 2. By setting a reasonable fluctuation coefficient threshold range and evaluating the binary value of life impact, the heating power configuration can be dynamically adjusted to balance the relationship between rapid heating demand and equipment life, thereby extending the service life of the electric water heater and ensuring the long-term interests of users.

[0096] 3. By analyzing the actual service data, the threshold range can be set more accurately, making the control strategy of the electric water heater more in line with the actual usage and improving the reliability and effectiveness of the control strategy.

[0097] Embodiment 2:

[0098] like Figure 2 As shown, based on the same inventive concept of the electric water heater rapid heating control method driven by user habit analysis provided in Example 1, the embodiment of the present invention also provides an electric water heater rapid heating control system driven by user habit analysis, including:

[0099] A signal receiving module, used for receiving a rapid heating command signal;

[0100] A temperature habit analysis module, for performing a specified temperature habit analysis on the user's historical quick heating logs to obtain a quick heating temperature target range when the quick heating command signal does not include a quick heating specified temperature;

[0101] A duration habit analysis module, configured to perform a specified duration habit analysis on the user's historical quick heating logs to obtain a heating constraint time zone when the quick heating command signal does not include a specified quick heating duration;

[0102] A water body temperature prediction module, used for randomly configuring the electric water heater heating power time series information in the heating constraint time zone, inputting the electric water heater heating power time series information, water body initial temperature information and cavity water level information into a temperature prediction model for analysis, and obtaining the water body temperature time series information;

[0103] The task execution module is used to perform rapid heating control of the electric water heater according to the heating power timing information of the electric water heater when the temperature at the end moment of the water body temperature timing information belongs to the rapid heating temperature target interval.

[0104] Furthermore, the steps of constructing the temperature prediction model include:

[0105] Obtaining basic information of the electric water heater, wherein the basic information of the electric water heater includes the model of the electric water heater and the service time of the electric water heater;

[0106] Collect the heating power record time series information of the electric water heater that meets the electric water heater model and the service time of the electric water heater, the water body initial temperature record information, the cavity water level record information and the water body temperature monitoring record time series information, and set it as the temperature prediction model construction data set;

[0107] The water body temperature monitoring record time series information is used as supervision, the electric water heater heating power record time series information, the water body initial temperature record information, and the cavity water level record information are used as input data, and the temperature prediction model is retrieved to construct a data set to train the temperature prediction model.

[0108] Further, taking the water body temperature monitoring record time series information as supervision, taking the electric water heater heating power record time series information, the water body initial temperature record information, and the cavity water level record information as input data, calling the temperature prediction model to construct a data set to train the temperature prediction model, including:

[0109] Construct the unit model loss function:

[0110]

[0111] Among them, L represents the temperature prediction loss function, ξ represents the standard deviation coefficient, T i Represents the temperature prediction value at the i-th moment, T i0 represents the temperature monitoring value at the i-th moment, ΔT represents the temperature deviation threshold, and N represents the total number of moments in the time zone;

[0112] According to the unit model loss function, taking the water body temperature monitoring record time series information as supervision, taking the electric water heater heating power record time series information, the water body initial temperature record information, and the cavity water level record information as input data, calling the temperature prediction model to build a data set, and training several LSTM neural network temperature prediction unit models;

[0113] The several LSTM neural network temperature prediction unit models are integrated to obtain the temperature prediction model.

[0114] Furthermore, the plurality of LSTM neural network temperature prediction unit models are integrated to obtain the temperature prediction model, including:

[0115] Obtaining a plurality of temperature prediction time series information of the plurality of LSTM neural network temperature prediction unit models;

[0116] Performing a central trend analysis on the temperature values ​​at the first moment of the plurality of temperature prediction time series information to obtain a temperature integration value at the first moment;

[0117] Until a central trend analysis is performed on the temperature values ​​at the Mth moment of the plurality of temperature prediction time series information to obtain a temperature integration value at the Mth moment;

[0118] The temperature integration value at the first moment to the temperature integration value at the Mth moment are sorted according to time and set as output data of the temperature prediction model.

[0119] Furthermore, the heating power time series information of the electric water heater is randomly configured in the heating constraint time zone, and the heating power time series information of the electric water heater, the initial temperature information of the water body and the water level information in the cavity are input into the temperature prediction model for analysis to obtain the water body temperature time series information, which also includes:

[0120] Randomly configure the heating power timing information of the first electric water heater according to the heating constraint time zone;

[0121] Calculate the variance value of the heating power time series information of the first electric water heater and set it as a first fluctuation coefficient;

[0122] Calculate the variance value of the power standard deviation at adjacent moments of the heating power time series information of the first electric water heater, and set it as the second fluctuation coefficient;

[0123] Inputting the first fluctuation coefficient and the second fluctuation coefficient into a binary model of the life impact of the electric water heater to generate a binary value of the life impact;

[0124] When the life impact binary value is equal to 1, the heating power timing information of the first electric water heater is updated and executed in a loop;

[0125] When the life impact binary value is equal to 0, the first electric water heater heating power timing information is set as the electric water heater heating power timing information.

[0126] Furthermore, the first fluctuation coefficient and the second fluctuation coefficient are input into a binary model of the life impact of the electric water heater to generate a binary value of the life impact, including:

[0127] Setting a first fluctuation coefficient threshold interval and a second fluctuation coefficient threshold interval;

[0128] When the first fluctuation coefficient belongs to the first fluctuation coefficient threshold interval, and the second fluctuation coefficient belongs to the second fluctuation coefficient threshold interval, the lifespan impact binary value is equal to 0;

[0129] Otherwise, the lifetime impact binary value is equal to 1.

[0130] Furthermore, setting the first fluctuation coefficient threshold interval and the second fluctuation coefficient threshold interval includes:

[0131] Obtain service data of electric water heaters;

[0132] According to the service data of the electric water heater, a number of first fluctuation coefficient record values, a number of second fluctuation coefficient record values ​​and a number of electric water heater life record values ​​corresponding to each other are counted;

[0133] Extracting a first fluctuation coefficient record value set and a second fluctuation coefficient record value set of the plurality of electric water heater life record values ​​greater than or equal to the life threshold value from the plurality of first fluctuation coefficient record values ​​and the plurality of second fluctuation coefficient record values;

[0134] The non-outlier distribution intervals of the first fluctuation coefficient record value set and the second fluctuation coefficient record value set are respectively counted, and the first fluctuation coefficient threshold interval and the second fluctuation coefficient threshold interval are set.

[0135] Embodiment three:

[0136] See also Figure 3 , Figure 3 Schematic diagram of an electric water heater provided in an embodiment of the present invention. Figure 3 As shown, the embodiment of the present invention provides an electric water heater 500, including a memory 510, a processor 520, and a first computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the first computer program 511, the following steps are implemented:

[0137] Receive a rapid heating command signal;

[0138] When the quick heating command signal does not include a quick heating designated temperature, a designated temperature habit analysis is performed on the user's historical quick heating log to obtain a quick heating temperature target range;

[0139] When the quick heating command signal does not include a specified quick heating time, performing a specified time habit analysis on the user's historical quick heating log to obtain a heating constraint time zone;

[0140] Randomly configure the electric water heater heating power time series information in the heating constraint time zone, input the electric water heater heating power time series information, water body initial temperature information and cavity water level information into the temperature prediction model for analysis, and obtain the water body temperature time series information;

[0141] When the temperature at the end moment of the water body temperature time series information belongs to the rapid heating temperature target interval, the electric water heater rapid heating control is performed according to the electric water heater heating power time series information.

[0142] Embodiment 4:

[0143] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 600, on which a second computer program 611 is stored. When the second computer program 611 is executed by a processor, the following steps are implemented:

[0144] Receive a rapid heating command signal;

[0145] When the quick heating command signal does not include a quick heating designated temperature, a designated temperature habit analysis is performed on the user's historical quick heating log to obtain a quick heating temperature target range;

[0146] When the quick heating command signal does not include a specified quick heating time, performing a specified time habit analysis on the user's historical quick heating log to obtain a heating constraint time zone;

[0147] Randomly configure the electric water heater heating power time series information in the heating constraint time zone, input the electric water heater heating power time series information, water body initial temperature information and cavity water level information into the temperature prediction model for analysis, and obtain the water body temperature time series information;

[0148] When the temperature at the end moment of the water body temperature time series information belongs to the rapid heating temperature target interval, the electric water heater rapid heating control is performed according to the electric water heater heating power time series information.

[0149] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0150] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0151] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0152] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0153] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0154] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0155] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A method for controlling rapid heating of an electric water heater driven by user habit analysis, characterized in that: include: Receive a rapid heating command signal; When the quick heating command signal does not include a quick heating designated temperature, a designated temperature habit analysis is performed on the user's historical quick heating log to obtain a quick heating temperature target range; When the quick heating command signal does not include a specified quick heating time, performing a specified time habit analysis on the user's historical quick heating log to obtain a heating constraint time zone; Randomly configure the electric water heater heating power time series information in the heating constraint time zone, input the electric water heater heating power time series information, water body initial temperature information and cavity water level information into the temperature prediction model for analysis, and obtain the water body temperature time series information; When the temperature at the end moment of the water body temperature time series information belongs to the rapid heating temperature target interval, the electric water heater rapid heating control is performed according to the electric water heater heating power time series information.

2. The method according to claim 1, characterized in that The steps of constructing the temperature prediction model include: Obtaining basic information of the electric water heater, wherein the basic information of the electric water heater includes the model of the electric water heater and the service time of the electric water heater; Collect the heating power record time series information of the electric water heater that meets the electric water heater model and the service time of the electric water heater, the water body initial temperature record information, the cavity water level record information and the water body temperature monitoring record time series information, and set it as the temperature prediction model construction data set; The water body temperature monitoring record time series information is used as supervision, the electric water heater heating power record time series information, the water body initial temperature record information, and the cavity water level record information are used as input data, and the temperature prediction model is retrieved to construct a data set to train the temperature prediction model.

3. The method according to claim 2, characterized in that Taking the water body temperature monitoring record time series information as supervision, taking the electric water heater heating power record time series information, the water body initial temperature record information, and the cavity water level record information as input data, calling the temperature prediction model to build a data set to train the temperature prediction model, including: Construct the unit model loss function: Among them, L represents the temperature prediction loss function, ξ represents the standard deviation coefficient, T i Represents the temperature prediction value at the i-th moment, T i0 represents the temperature monitoring value at the i-th moment, ΔT represents the temperature deviation threshold, and N represents the total number of moments in the time zone; According to the unit model loss function, taking the water body temperature monitoring record time series information as supervision, taking the electric water heater heating power record time series information, the water body initial temperature record information, and the cavity water level record information as input data, calling the temperature prediction model to build a data set, and training several LSTM neural network temperature prediction unit models; The several LSTM neural network temperature prediction unit models are integrated to obtain the temperature prediction model.

4. The method according to claim 3, characterized in that Integrating the plurality of LSTM neural network temperature prediction unit models to obtain the temperature prediction model includes: Obtaining a plurality of temperature prediction time series information of the plurality of LSTM neural network temperature prediction unit models; Performing a central trend analysis on the temperature values ​​at the first moment of the plurality of temperature prediction time series information to obtain a temperature integration value at the first moment; Until a central trend analysis is performed on the temperature values ​​at the Mth moment of the plurality of temperature prediction time series information to obtain a temperature integration value at the Mth moment; The temperature integration value at the first moment to the temperature integration value at the Mth moment are sorted according to time and set as output data of the temperature prediction model.

5. The method according to claim 1, characterized in that The heating power time series information of the electric water heater is randomly configured in the heating constraint time zone, and the heating power time series information of the electric water heater, the initial temperature information of the water body and the water level information in the cavity are input into the temperature prediction model for analysis to obtain the water body temperature time series information, and further comprising: Randomly configure the heating power timing information of the first electric water heater according to the heating constraint time zone; Calculate the variance value of the heating power time series information of the first electric water heater and set it as a first fluctuation coefficient; Calculate the variance value of the power standard deviation at adjacent moments of the heating power time series information of the first electric water heater, and set it as the second fluctuation coefficient; Inputting the first fluctuation coefficient and the second fluctuation coefficient into a binary model of the life impact of the electric water heater to generate a binary value of the life impact; When the life impact binary value is equal to 1, the heating power timing information of the first electric water heater is updated and executed in a loop; When the life impact binary value is equal to 0, the first electric water heater heating power timing information is set as the electric water heater heating power timing information.

6. The method according to claim 5, characterized in that Inputting the first fluctuation coefficient and the second fluctuation coefficient into the life impact binary model of the electric water heater to generate a life impact binary value, including: Setting a first fluctuation coefficient threshold interval and a second fluctuation coefficient threshold interval; When the first fluctuation coefficient belongs to the first fluctuation coefficient threshold interval, and the second fluctuation coefficient belongs to the second fluctuation coefficient threshold interval, the lifespan impact binary value is equal to 0; Otherwise, the lifetime impact binary value is equal to 1.

7. The method according to claim 6, characterized in that Setting a first fluctuation coefficient threshold interval and a second fluctuation coefficient threshold interval includes: Obtain service data of electric water heaters; According to the service data of the electric water heater, a number of first fluctuation coefficient record values, a number of second fluctuation coefficient record values ​​and a number of electric water heater life record values ​​corresponding to each other are counted; Extracting a first fluctuation coefficient record value set and a second fluctuation coefficient record value set of the plurality of electric water heater life record values ​​greater than or equal to the life threshold value from the plurality of first fluctuation coefficient record values ​​and the plurality of second fluctuation coefficient record values; The non-outlier distribution intervals of the first fluctuation coefficient record value set and the second fluctuation coefficient record value set are respectively counted, and the first fluctuation coefficient threshold interval and the second fluctuation coefficient threshold interval are set.

8. The electric water heater rapid heating control system driven by user habit analysis is characterized by: include: A signal receiving module, used for receiving a rapid heating command signal; A temperature habit analysis module, for performing a specified temperature habit analysis on the user's historical quick heating logs to obtain a quick heating temperature target range when the quick heating command signal does not include a quick heating specified temperature; A duration habit analysis module, configured to perform a specified duration habit analysis on the user's historical quick heating logs to obtain a heating constraint time zone when the quick heating command signal does not include a specified quick heating duration; A water body temperature prediction module, used for randomly configuring the electric water heater heating power time series information in the heating constraint time zone, inputting the electric water heater heating power time series information, water body initial temperature information and cavity water level information into a temperature prediction model for analysis, and obtaining the water body temperature time series information; The task execution module is used to perform rapid heating control of the electric water heater according to the heating power timing information of the electric water heater when the temperature at the end moment of the water body temperature timing information belongs to the rapid heating temperature target interval.

9. An electric water heater, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the electric water heater rapid heating control method driven by user habit analysis as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, the electric water heater rapid heating control method driven by user habit analysis as described in any one of claims 1 to 7 is implemented.

Images