Temperature control method and device for electric water heater, computer equipment and storage medium
Through the combination of adaptive fuzzy neural network and temperature sensor array, the problem of inaccurate water temperature control of traditional electric water heaters is solved, and precise water temperature control is achieved in complex environments, ensuring the safety and comfort of infants and young children's bathing.
Patent Information
- Application Number
- CN202411040695.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
During the heating process, traditional electric water heaters are prone to hot and cold, making it difficult to achieve accurate constant temperature control in complex environments, especially for infants and young children.
Adaptive fuzzy neural network is used to combine temperature sensor arrays and Kalman filters to obtain the temperature control impact information of the electric water heater, including water temperature and environmental information, generate control signals through fuzzy inference, and adjust the operating status of the electric water heater to achieve the accuracy of the water temperature at the outlet. control.
The precise control of water temperature is achieved in complex environments, avoiding violent fluctuations in water temperature, ensuring the safety and comfort of water temperature when infants and young children are bathing, and enhancing the adaptability and control accuracy of the electric water heater.
Smart Images

Figure CN118915851A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of water heaters, and in particular to a temperature control method, device, computer equipment and storage medium for an electric water heater. Background Art
[0002] Infants and young children have delicate and sensitive skin, and are very sensitive to changes in water temperature. During the heating process of traditional electric water heaters, the water temperature often fluctuates, which is a challenge for bathing infants and young children. Therefore, infant bathing usually uses a relatively constant water temperature. At present, most of the constant temperature technologies on the market use a single temperature control method, such as simple temperature sensor monitoring, or adjusting the water temperature by mixing cold and hot water. These technologies are difficult to cope with various complex situations in actual use, such as changes in water pressure, unstable water flow rate, etc., which will affect the constant temperature effect. How to achieve precise temperature control in a complex use environment and ensure that the water temperature is always within a safe and comfortable range is a technical problem that needs to be solved urgently. Summary of the invention
[0003] The purpose of the embodiments of the present application is to provide a method, device, computer equipment and storage medium for controlling the temperature of an electric water heater, so as to achieve constant temperature control when bathing infants and young children.
[0004] In order to solve the above technical problems, the embodiment of the present application provides a temperature control method for an electric water heater, which adopts the following technical solution:
[0005] Acquire temperature control influencing information of the electric water heater, wherein the temperature control influencing information includes water temperature information and environmental information, wherein the water temperature information includes water inlet water temperature, water outlet water temperature, temperature deviation and water temperature fluctuation trend of the electric water heater, and the environmental information includes water pressure and environmental temperature of the electric water heater;
[0006] Inputting the temperature control influence information into an adaptive fuzzy neural network, so as to perform fuzzy reasoning according to various factors in the temperature control influence information through the adaptive fuzzy neural network to obtain control information;
[0007] generating a control signal according to the control information;
[0008] The operating state of the electric water heater is adjusted according to the control signal to control the water temperature at the water outlet to a target temperature.
[0009] Further, when obtaining the temperature deviation, the step of obtaining the temperature control influence information of the electric water heater includes:
[0010] The temperature value of each measuring point in the electric water heater is collected by a temperature sensor array, wherein the temperature sensor array comprises a plurality of temperature sensors arranged in the electric water heater, and the collected temperature value comprises the water temperature at the water outlet of the electric water heater;
[0011] Obtaining the first weight corresponding to each temperature value according to the position of each measuring point, wherein the water temperature at the water outlet has the largest first weight;
[0012] Taking a weighted average of the temperature values to obtain an average water temperature of the electric water heater;
[0013] Based on the average water temperature and a preset target water temperature, a temperature deviation of the electric water heater is calculated.
[0014] Further, when obtaining the water temperature fluctuation trend, the step of obtaining the temperature control influence information of the electric water heater includes:
[0015] Collecting the temperature values of each measuring point in the electric water heater at multiple time points by means of a temperature sensor array, wherein the temperature sensor array comprises multiple temperature sensors arranged in the electric water heater;
[0016] Inputting the temperature values of each measuring point at multiple time points into a Kalman filter for data fusion filtering to obtain a fused temperature sequence;
[0017] calculating a derivative index of the fusion temperature series;
[0018] The fused temperature sequence and the derived index are determined as the water temperature fluctuation trend of the electric water heater.
[0019] Furthermore, after the step of obtaining the temperature control influence information of the electric water heater, the method further includes:
[0020] When the temperature deviation is greater than a preset temperature difference threshold, a temperature difference alarm notification is triggered; or,
[0021] When the temperature deviation exists for a time greater than a preset time threshold, a maintenance alarm notification is triggered.
[0022] Furthermore, the adaptive fuzzy neural network includes a fuzzification layer, a rule layer, a normalization layer and an output layer. The step of performing fuzzy reasoning according to various factors in the temperature control influence information by the adaptive fuzzy neural network to obtain control information includes:
[0023] Performing fuzzy processing on various factors in the temperature control influencing information through the fuzzification layer to obtain fuzzy representation parameters of the various factors;
[0024] Determine the control rules corresponding to each fuzzy representation parameter through the rule layer, and obtain the rule output corresponding to each control rule;
[0025] Acquiring the second weight of each control rule at the normalization layer, and calculating the weighted output according to the second weight of each control rule and the rule output thereof;
[0026] The weighted output is defuzzified at the output layer to obtain control information.
[0027] Furthermore, the step of obtaining the second weight of each control rule at the normalization layer and calculating the weighted output according to the second weight of each control rule and its rule output includes:
[0028] Calculating the activation degree of each control rule according to the membership degree of each fuzzy representation parameter to each control rule;
[0029] Acquiring, at the normalization layer, a second weight of each of the control rules;
[0030] Calculating the effective weight of each control rule according to the activation degree of each control rule and its second weight;
[0031] The weighted output is calculated based on the effective weights of the control rules and their rule outputs.
[0032] Further, after the step of adjusting the operating state of the electric water heater according to the control signal, the method further includes:
[0033] The adaptive fuzzy neural network is reinforced learned according to a reward function to adjust a second weight of a control rule and a rule output, wherein the reward function is constructed based on temperature deviation, energy consumption and water temperature fluctuation trend.
[0034] In order to solve the above technical problems, the embodiment of the present application also provides a temperature control device for an electric water heater, which adopts the following technical solution:
[0035] An information acquisition module, used to acquire temperature control influence information of the electric water heater, wherein the temperature control influence information includes water temperature information and environmental information, wherein the water temperature information includes water inlet water temperature, water outlet water temperature, temperature deviation and water temperature fluctuation trend of the electric water heater, and the environmental information includes water pressure and environmental temperature of the electric water heater;
[0036] An information input module, used for inputting the temperature control influence information into an adaptive fuzzy neural network, so as to perform fuzzy reasoning according to various factors in the temperature control influence information through the adaptive fuzzy neural network to obtain control information;
[0037] A signal generating module, used for generating a control signal according to the control information;
[0038] The state adjustment module is used to adjust the operating state of the electric water heater according to the control signal to control the water temperature at the water outlet to a target temperature.
[0039] In order to solve the above technical problems, an embodiment of the present application also provides a computer device, which includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the electric water heater temperature control method as described above are implemented.
[0040] In order to solve the above technical problems, an embodiment of the present application further provides a computer-readable storage medium, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor, the steps of the electric water heater temperature control method as described above are implemented.
[0041] Compared with the prior art, the embodiments of the present application mainly have the following beneficial effects: obtaining temperature control influencing information of the electric water heater, including water temperature information and environmental information, the water temperature information including the water temperature at the water inlet of the electric water heater, the water temperature at the water outlet, the temperature deviation and the water temperature fluctuation trend, which helps to have a more comprehensive understanding of the temperature condition of the electric water heater; the environmental information includes the water pressure and ambient temperature of the electric water heater, and incorporating external factors into the control system can avoid temperature fluctuations caused by environmental changes; the temperature control influencing information is input into an adaptive fuzzy neural network, and the adaptive fuzzy neural network performs fuzzy reasoning based on various factors in the temperature control influencing information, adapts and responds to various complex environments, and generates accurate control information; a control signal that can act on the electric water heater is generated based on the control information, the operating state of the electric water heater is adjusted based on the control signal, the water temperature at the water outlet is controlled to the target temperature, and in situations where environmental conditions change and precise temperature control is required, the water temperature is controlled more comprehensively and accurately to avoid drastic fluctuations in the water temperature. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0043] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;
[0044] Figure 2 is a flow chart of an embodiment of a method for controlling the temperature of an electric water heater according to the present application;
[0045] Figure 3 is a structural schematic diagram of an embodiment of a temperature control device for an electric water heater according to the present application;
[0046] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION
[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.
[0048] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0049] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.
[0050] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.
[0051] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.
[0052] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.
[0053] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .
[0054] It should be noted that the electric water heater temperature control method provided in the embodiment of the present application is generally executed by a terminal device, and accordingly, the electric water heater temperature control device is generally arranged in the terminal device.
[0055] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.
[0056] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for controlling the temperature of an electric water heater according to the present application. The method for controlling the temperature of an electric water heater comprises the following steps:
[0057] Step S201, obtaining temperature control influencing information of the electric water heater, the temperature control influencing information including water temperature information and environmental information, the water temperature information including the water inlet water temperature, the water outlet water temperature, the temperature deviation and the water temperature fluctuation trend of the electric water heater, and the environmental information including the water pressure and the ambient temperature of the electric water heater.
[0058] In this embodiment, the electric water heater temperature control method is executed on the electronic device (eg Figure 1 The terminal device shown in the figure can communicate with the server through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.
[0059] Specifically, the temperature control influencing information of the electric water heater may be obtained through a sensor provided in the electric water heater. The temperature control influencing information is information that affects the temperature control of the electric water heater, and includes water temperature information and environmental information.
[0060] Among them, water temperature information is information related to the temperature of water, which may include the water temperature at the water inlet, the water temperature at the water outlet, the temperature deviation and the water temperature fluctuation trend. The water temperature at the water inlet refers to the initial temperature of the water entering the electric water heater. The water temperature at the water outlet refers to the final temperature of the water flowing out of the electric water heater, which is the temperature actually experienced by the user. Usually, electric water heaters do not have a separate device to monitor the water temperature at the water outlet, but the present application specifically sets a temperature sensor at the water outlet to monitor the water temperature at the water outlet. The temperature deviation refers to the difference between the current water temperature of the electric water heater and the preset target temperature, which reflects the temperature control accuracy. The water temperature fluctuation trend refers to the water temperature change pattern or trend of the electric water heater, providing dynamic information about water temperature changes.
[0061] Environmental information is information related to the environment in which the electric water heater is used, and can include water pressure and ambient temperature. Water pressure refers to the water pressure level in the electric water heater, which affects the water flow rate and heating efficiency. Ambient temperature refers to the temperature of the environment in which the electric water heater is located, which can affect the heat dissipation and energy consumption of the electric water heater.
[0062] In electric water heaters for infant bathing, environmental factors may also include water quality factors, water flow, heater load and power supply stability. Among them, water quality factors refer to water hardness, mineral content, etc., which will affect heating efficiency and water temperature stability. Water flow refers to the flow rate of water affecting heating time and temperature distribution. Heater load refers to the power load of the electric heater currently in use, which may affect control accuracy. Power supply stability refers to voltage fluctuations that may affect the performance of the heating element and water temperature control.
[0063] Step S202, inputting the temperature control influence information into the adaptive fuzzy neural network, so as to perform fuzzy reasoning according to various factors in the temperature control influence information through the adaptive fuzzy neural network to obtain control information.
[0064] Specifically, the acquired temperature control influence information is input into a pre-built adaptive fuzzy neural network. The adaptive fuzzy neural network combines fuzzy logic and artificial neural network. It has the ability of fuzzy logic system to easily interpret and process uncertain data, and also has the learning and adaptive ability of neural network. Fuzzy logic is a multi-valued logic that can handle black-and-white fuzzy information. In traditional binary logic systems, a statement can only be completely true or completely false. However, in the real world, many problems are not so simple and clear. For example, temperature can be "high", "very high" or "relatively high". Fuzzy logic allows these fuzzy descriptions and uses membership functions to convert input data into fuzziness between 0 and 1.
[0065] Adaptive fuzzy neural networks usually include an input layer, a fuzzification layer, a rule layer, a normalization layer, and an output layer. The input layer is used to receive input data and represents different input variables. The fuzzification layer converts the input data into fuzzy sets and calculates the membership of the input variables through membership functions. In the rule layer, each neuron corresponds to a fuzzy rule, which can be learned from expert knowledge or data, and each rule corresponds to a combination of fuzzy input variables. For example, a rule can be "If the inlet water temperature is high and the outlet water temperature is low, then increase the heating power." The rule layer can calculate the activation (or matching degree) of each rule based on the membership of the input data. In the normalization layer, the output of the fuzzy rules is normalized to ensure that the total output is consistent. The output layer combines all normalized outputs, usually by weighted average or other methods to obtain the final system output. The output layer converts the normalized results into specific output values. This step usually includes a defuzzification process to map the fuzzy output back to a specific value. The result of the output layer is the final control signal of the system, such as adjusting the heating power, regulating the water flow, etc.
[0066] Adaptive fuzzy neural networks have adaptive capabilities, which are achieved through learning algorithms, such as gradient descent, which help the network adjust the parameters of the membership function (such as the shape and location of the membership function) and the weights of the fuzzy rules to better fit the training data.
[0067] Based on adaptive fuzzy neural networks, fuzzy logic can effectively handle imprecise and uncertain information, which is particularly important in control systems. The learning mechanism of neural networks enables the system to adjust its own structure and parameters according to data, enhancing the system's adaptability and accuracy. Fuzzy rules and membership functions provide an explanatory framework for system behavior, making the system's decision-making process more transparent and understandable.
[0068] The adaptive fuzzy neural network can perform fuzzy reasoning according to different temperature control factors (such as water temperature, environmental information, etc.), realize intelligent reasoning and control information generation, and achieve precise control of water temperature.
[0069] Step S203: Generate a control signal according to the control information.
[0070] Specifically, the control information is the result of fuzzy reasoning, indicating how to control the electric water heater, such as adjusting the heating power, controlling the opening and closing of the valve, etc. A control signal that can directly act on the electric water heater is generated according to the control information.
[0071] Step S204, adjusting the operating state of the electric water heater according to the control signal to control the water temperature at the water outlet to the target temperature.
[0072] Specifically, the electric water heater responds to the control signal and adjusts its own operating state according to the control signal to control the water temperature at the water outlet to the set target temperature to ensure the constancy and stability of the water temperature. In actual use, there is no need to blend cold water, and you can directly take a bath by turning on the water outlet switch of the electric water heater.
[0073] In this embodiment, the temperature control influencing information of the electric water heater is obtained, including water temperature information and environmental information. The water temperature information includes the water temperature at the water inlet of the electric water heater, the water temperature at the water outlet, the temperature deviation and the water temperature fluctuation trend, which is helpful to have a more comprehensive understanding of the temperature condition of the electric water heater; the environmental information includes the water pressure and ambient temperature of the electric water heater. Incorporating external factors into the control system can avoid temperature fluctuations caused by environmental changes; the temperature control influencing information is input into an adaptive fuzzy neural network, and the adaptive fuzzy neural network performs fuzzy reasoning based on various factors in the temperature control influencing information, adapts and responds to various complex environments, and generates accurate control information; a control signal that can act on the electric water heater is generated based on the control information, and the operating state of the electric water heater is adjusted based on the control signal to control the water temperature at the water outlet to the target temperature. In situations where environmental conditions change and precise temperature control is required, the water temperature can be controlled more comprehensively and accurately to avoid drastic fluctuations in the water temperature.
[0074] Furthermore, when obtaining the temperature deviation, the above-mentioned step of obtaining the temperature control influencing information of the electric water heater may include: collecting the temperature value of each measuring point in the electric water heater through a temperature sensor array, the temperature sensor array includes a plurality of temperature sensors arranged in the electric water heater, and the collected temperature values include the water temperature at the outlet of the electric water heater; obtaining the first weight corresponding to each temperature value according to the position of each measuring point, wherein the water temperature at the outlet has the largest first weight; performing weighted averaging on each temperature value to obtain the average water temperature of the electric water heater; and calculating the temperature deviation of the electric water heater based on the average water temperature and the preset target water temperature.
[0075] Specifically, a temperature sensor array is arranged in the electric water heater, and the temperature sensor array includes multiple temperature sensors, which are located at different measuring points in the electric water heater, and collect the temperature value of each measuring point in real time or at a preset frequency. In particular, a temperature sensor is set at the water outlet, which measures the water temperature at the outlet of the electric water heater. Temperature sensors can be set at key locations of the electric water heater, such as the inner tank, to collect temperature values.
[0076] Due to the different locations of the measurement points, the importance of the corresponding collected temperature values is also different. Therefore, the first weight is added to the temperature values of different measurement points to highlight the impact of temperature changes in key parts (such as the water outlet) in the overall temperature assessment. Since the water temperature at the water outlet has a direct impact on the user experience, it is given the largest first weight. At the same time, the electric water heater can also display the water temperature of the water outlet in real time through the display device to remind the user of the temperature.
[0077] The weighted temperature values are then averaged to obtain the comprehensive average water temperature of the electric water heater. The average water temperature is compared with the preset target water temperature to calculate the temperature deviation between the actual temperature and the target temperature. The temperature deviation is the basis for subsequent adjustment and control.
[0078] In this embodiment, the temperature values of multiple measuring points in the electric water heater are collected through a temperature sensor array, including the water temperature at the key water outlet; the first weight corresponding to each temperature value is obtained according to the position of each measuring point, highlighting the impact of temperature changes at key positions on the overall temperature evaluation, and the water temperature at the water outlet has the largest first weight; the temperature values are weighted averaged to obtain the average water temperature of the electric water heater, which can more accurately reflect the actual temperature condition of the electric water heater; based on the average water temperature and the preset target water temperature, the temperature deviation of the electric water heater can be accurately calculated, ensuring that the subsequent temperature control can be accurate and effective.
[0079] Furthermore, when obtaining the water temperature fluctuation trend, the step of obtaining the temperature control influencing information of the electric water heater may include: collecting the temperature values of each measuring point in the electric water heater at multiple time points through a temperature sensor array, the temperature sensor array comprising multiple temperature sensors arranged in the electric water heater; inputting the temperature values of each measuring point at multiple time points into a Kalman filter for data fusion filtering to obtain a fused temperature sequence; calculating the derivative indicators of the fused temperature sequence; and determining the fused temperature sequence and the derivative indicators as the water temperature fluctuation trend of the electric water heater.
[0080] Specifically, a temperature sensor array is arranged in the electric water heater. The temperature sensor array includes multiple temperature sensors. These temperature sensors collect the temperature values of each measurement point at multiple time points to obtain a temperature value sequence for each measurement point. The temperature value sequence captures the thermodynamic changes of the electric water heater at different times. In order to effectively process these data and extract valuable trend information from them, the collected temperature values are input into the Kalman filter.
[0081] The Kalman filter is a recursive estimation method that can provide more accurate state estimation in the presence of noise. The Kalman filter can process data from multiple sensors at the same time, perform weighted averaging and noise filtering based on the measurement errors and data correlation of each sensor, and obtain a more stable and accurate state estimation, namely the fused temperature sequence. The fused temperature sequence eliminates the noise influence of individual data points and reflects the changing trend of water temperature more smoothly and accurately.
[0082] After obtaining the fused temperature sequence, its derived indicators can be further calculated, including the temperature change rate, temperature fluctuation amplitude, and frequency of change. Among them, the temperature change rate includes the instantaneous change rate and the average change rate; the instantaneous change rate refers to the rate of change of the temperature value between adjacent time points, which can reflect the speed of water temperature change; the average change rate refers to the average change rate of the temperature value within a certain time window, which is used to analyze the overall trend. The temperature fluctuation amplitude refers to the difference between the maximum and minimum values of the temperature value in a specific time period, reflecting the range of water temperature fluctuation. The derived indicators can refine and quantify the characteristics of water temperature fluctuations and provide a reference for subsequent control strategies.
[0083] The fused temperature series and its derived indicators are determined as the water temperature fluctuation trend of the electric water heater. This trend information will be used to adjust the operating parameters of the electric water heater to maintain the stability of the outlet water temperature.
[0084] In this embodiment, the temperature values of each measuring point in the electric water heater at multiple time points are collected through a temperature sensor array to provide a global understanding of the temperature at different positions of the electric water heater; the temperature values of each measuring point at multiple time points are input into a Kalman filter for data fusion filtering to reduce the influence of noise, so that the extracted temperature trend is more accurate and smooth, and a fused temperature sequence is obtained; the derivative indicators of the fused temperature sequence are calculated to obtain detailed water temperature fluctuation characteristics, which can better reflect the dynamic changes of water temperature; the fused temperature sequence and the derivative indicators are determined as the water temperature fluctuation trend of the electric water heater, ensuring that the subsequent temperature control can be accurate and effective.
[0085] Furthermore, after the above-mentioned step of obtaining the temperature control influencing information of the electric water heater, it may also include: when the temperature deviation is greater than the preset temperature difference threshold, triggering a temperature difference alarm notification; or, when the existence time of the temperature deviation is greater than the preset time threshold, triggering a maintenance alarm notification.
[0086] Specifically, the electric water heater can also be set with a monitoring and alarm mechanism. Specifically, when it is detected that the temperature deviation of the electric water heater is greater than the preset temperature difference threshold, a temperature difference alarm notification can be triggered to ensure that the water temperature remains within a safe and comfortable range. Especially for electric water heaters used by infants and young children, water temperatures that are too high or too low may bring unsafe risks.
[0087] In addition, when the duration of the temperature deviation exceeds the preset duration threshold (or the temperature deviation exceeds the preset second temperature difference threshold and the duration of this state exceeds the preset duration threshold; the second temperature difference threshold is less than the previously mentioned temperature difference threshold, for example, assuming that the temperature range of the electric water heater is 25-43°C, the temperature control accuracy is 0.5°C, and the actual temperature control fluctuation is ±1.5°C, then 1.5°C can be determined as the second temperature difference threshold), the electric water heater will trigger a maintenance alarm notification. This function is designed to remind users that there may be system hardware failures or situations that require adjustment, such as sensor failure, heater performance degradation, and other problems. Through these alarm functions, potential risks and problems can be warned in a timely manner to avoid damage or accidents that may occur during long-term operation.
[0088] In one embodiment, for the electric water heater in the present application, heating is stopped when the heating reaches the target temperature, and heating is turned on when the water temperature drops by 0.5° C. (temperature control accuracy). The heating tube is powered in series with a thermal protection device.
[0089] In order to prevent overheating accidents, the first temperature threshold and the second temperature threshold are set. When the average water temperature of the electric water heater exceeds the first temperature threshold (for example, 46°C), an alarm reminder and automatic reset are issued. When it exceeds the second temperature threshold (for example, 50°C), an alarm reminder and manual reset are required to achieve double overheating protection.
[0090] In addition, a water level monitor can be provided in the electric water heater, such as a water level probe installed on the upper part of the inner tank. When the water level is too low, the electric water heater will stop heating and send out a water shortage alarm to avoid the accident of dry burning of the heating tube.
[0091] In this embodiment, when the temperature deviation is greater than the preset temperature difference threshold, a temperature difference alarm notification is triggered to ensure that the water temperature is maintained within a safe and comfortable range and to prevent users from using the water at an inappropriate temperature. This is especially important for infants and other children who are sensitive to water temperature. At the same time, it can quickly respond to abnormal temperature changes and issue timely alarms to reduce the risks of use due to abnormal temperatures. When the temperature deviation lasts longer than the preset duration threshold, a maintenance alarm notification is triggered, which enhances the self-diagnosis capability of the electric water heater and can identify potential hidden faults or performance degradations in the equipment, providing support for preventive maintenance and reducing the occurrence of sudden failures.
[0092] Furthermore, the adaptive fuzzy neural network includes a fuzzification layer, a rule layer, a normalization layer and an output layer. Then, the above-mentioned step of performing fuzzy reasoning according to various factors in the temperature control influence information through the adaptive fuzzy neural network to obtain the control information may include: fuzzifying various factors in the temperature control influence information through the fuzzification layer to obtain fuzzy representation parameters of various factors; determining the control rules corresponding to each fuzzy representation parameter through the rule layer, and obtaining the rule output corresponding to each control rule; obtaining the second weight of each control rule in the normalization layer, and calculating the weighted output according to the second weight of each control rule and its rule output; defuzzifying the weighted output in the output layer to obtain the control information.
[0093] Specifically, as mentioned above, the adaptive fuzzy neural network includes a fuzzification layer, a rule layer, a normalization layer and an output layer.
[0094] The fuzzification layer fuzzifies various factors in the input temperature control influencing information and converts them into fuzzy representation parameters, converting precise data into fuzzy sets to handle the uncertainty and ambiguity of the data. In practical applications, the obtained fuzzy representation parameters also have membership, which is determined by the membership function and indicates the degree to which a factor belongs to a set. For example, three fuzzy representation parameters of high, medium and low are set for the temperature deviation T-diff; three fuzzy representation parameters of rising, stable and falling are set for the water temperature fluctuation trend T_trend; and three fuzzy representation parameters of low, medium and high are set for the ambient temperature T_temp.
[0095] According to the temperature deviation, water temperature fluctuation trend and ambient temperature in the temperature control influence information, the output of the fuzzy layer is as follows (the corresponding membership degree is indicated in brackets):
[0096] Temperature deviation T_diff: high (0.7), medium (0.2), low (0.1);
[0097] Water temperature fluctuation trend T_trend: increasing (0.8), stable (0.2), decreasing (0.0);
[0098] Ambient temperature T_temp: low (0.9), medium (0.1), high (0.0).
[0099] The rule layer determines the corresponding control rules based on these fuzzy representation parameters and obtains the rule output of each control rule. The rule output of the control rule represents a suggestion or action for the temperature control of the electric water heater, such as adjusting the heater power or changing the water flow (in practice, it also includes how much the power is increased or decreased, and how much the water flow is increased or decreased). For example, now we have:
[0100] Control rule 1: If the temperature deviation T_diff is high and the water temperature fluctuation trend T_trend is increasing, then -20% power; wherein -20% power is the rule output of control rule 1, representing a 20% reduction in power.
[0101] Control rule 2: If the temperature deviation T_diff is low and the ambient temperature T_temp is low, then +15% power; wherein +15% power is the rule output of control rule 2, representing a 15% increase in power.
[0102] Control rule 3: If the temperature deviation T_diff is medium and the water temperature fluctuation trend T_trend is stable, then 0% power; wherein 0% power is the rule output of control rule 3, representing an increase / decrease of 0% power, that is, the power remains unchanged.
[0103] It can be understood that the above control rules and their corresponding rule outputs are just simple examples for ease of understanding. Practical applications may involve more complex control rules and their rule outputs, such as more specific PID control strategies.
[0104] The second weight of each control rule is obtained in the normalization layer. The second weight reflects the importance of the control rule. Based on the second weight of each control rule and its rule output, the weighted output is calculated to ensure that the results of all rules are reasonably integrated to obtain the optimal control strategy.
[0105] Finally, the output layer defuzzifies the weighted output and converts the fuzzy control strategy of the normalization layer into clear control information, which is convenient for adjusting the operating state of the electric water heater, such as adjusting the heating power or water flow rate, to achieve precise temperature control.
[0106] In this embodiment, the adaptive fuzzy neural network includes a fuzzification layer, a rule layer, a normalization layer and an output layer; the fuzzification layer performs fuzzification processing on various factors in the temperature control influencing information to obtain fuzzy representation parameters of various factors, effectively handles the fuzziness and uncertainty of the input data, and makes the influence of various factors on the control decision clearer and more accurate; the rule layer determines the control rules corresponding to each fuzzy representation parameter, and obtains the rule output corresponding to each control rule, ensuring that flexible and accurate control rules can be provided under complex and changeable conditions; the second weight of each control rule is obtained in the normalization layer, and the second weight represents the importance of the rule. According to the second weight of each control rule and its rule output, the weighted output is calculated to ensure that the results of all control rules are reasonably integrated to obtain the optimal control scheme. This calculation method takes into account the actual environment and improves the adaptability to various actual situations; the weighted output is defuzzified in the output layer to obtain clear control information, which is conducive to the subsequent adjustment of the operating state of the electric water heater.
[0107] Furthermore, the above-mentioned steps of obtaining the second weight of each control rule at the normalization layer and calculating the weighted output based on the second weight of each control rule and its rule output may include: calculating the activation degree of each control rule based on the membership of each fuzzy representation parameter to each control rule; obtaining the second weight of each control rule at the normalization layer; calculating the effective weight of each control rule based on the activation degree of each control rule and its second weight; calculating the weighted output based on the effective weight of each control rule and its rule output.
[0108] Specifically, as mentioned above, the obtained fuzzy representation parameters also have a membership degree, which characterizes the membership degree of each fuzzy representation parameter to each control rule. Each control rule has an activation degree, which is determined by the product of the membership degrees of the fuzzy representation parameters in the control rule. The activation degree reflects the applicability of the input data to the control rule.
[0109] Continuing with the example above, assuming that the second weight of control rule 1 is 0.5, the second weight of control rule 2 is 0.3, and the second weight of control rule 3 is 0.2, we can calculate:
[0110] Activation degree of control rule 1: T_diff(high)×T_trend(increasing)=0.7×0.8=0.56.
[0111] Activation degree of control rule 2: T_diff(low)×T_temp(low)=0.1×0.9=0.09.
[0112] Activation degree of control rule 3: T_diff(medium)×T_trend(stable)=0.2×0.2=0.04.
[0113] After determining the activation degree of each control rule, the second weight of each control rule is obtained in the normalization layer. The second weight is usually preset or dynamically adjusted through a learning algorithm, indicating the relative importance of the control rule in the overall system.
[0114] Next, the effective weight of each control rule is calculated according to the activation degree and the second weight of each control rule. The effective weight can be the product of the activation degree and the second weight, which is used to comprehensively evaluate the actual contribution of the control rule in the current situation.
[0115] Following the examples above, we can have:
[0116] Effective weight of control rule 1: 0.5×0.56=0.28;
[0117] Control rule 2 effective weight: 0.3×0.09=0.027;
[0118] Effective weight of control rule 3: 0.2×0.04=0.008.
[0119] Finally, according to the effective weight of each control rule and its rule output, the final weighted output is calculated. The weighted output represents the comprehensive result of all control rules and will be used to adjust the operating state of the electric water heater to achieve precise temperature control.
[0120] Continuing with the above example, the weighted output of control rules 1, 2, and 3 = (-20% × 0.28 + 15% × 0.027 + 0% × 0.008) / (0.28 + 0.027 + 0.008)
[0121] Right now:
[0122] Weighted output = (-5.6 + 0.405 + 0) / 0.315 = -16.46%. This result indicates that the system finally decides to reduce the heating power by 16.46%.
[0123] In this embodiment, the activation degree of each control rule is calculated according to the membership degree of each fuzzy representation parameter to each control rule, so as to obtain the applicability of each control rule; the second weight of each control rule is obtained in the normalization layer, and the effective weight of each control rule is calculated according to the activation degree of each control rule and its second weight, so as to more accurately reflect the actual contribution of each rule in the current scenario; the weighted output is calculated according to the effective weight of each control rule and its rule output, so as to make the control information more accurate and reliable, realize the refined temperature control of the electric water heater, ensure the stability of the outlet water temperature, and reduce the temperature fluctuation.
[0124] Furthermore, after the above-mentioned step of adjusting the operating state of the electric water heater according to the control signal, it can also include: performing reinforcement learning on the adaptive fuzzy neural network according to the reward function to adjust the second weight of the control rule and the rule output, and the reward function is constructed based on temperature deviation, energy consumption and water temperature fluctuation trend.
[0125] Specifically, the present application can also optimize the control performance of the terminal device in the electric water heater through reinforcement learning. In reinforcement learning, the control rules and parameters of the adaptive fuzzy neural network are dynamically adjusted using a reward function.
[0126] The reward function is a core element in reinforcement learning and is used to evaluate the effectiveness of system behavior. In this system, the reward function is constructed based on three main factors: temperature deviation, energy consumption, and water temperature fluctuation trend. Temperature deviation refers to the difference between the actual water temperature and the target temperature, reflecting the accuracy of the control system; energy consumption measures the energy efficiency of the system; and water temperature fluctuation trend indicates the system's performance in maintaining a stable temperature.
[0127] In practical applications, after adjusting the operating state of the electric water heater, the corresponding reward or penalty signal is generated by detecting the changes in these parameters. For example, when the system accurately controls the temperature within the target range, with low energy consumption and small water temperature fluctuations, the system will receive a positive reward; otherwise, it will receive a penalty signal. The adaptive fuzzy neural network receives these feedback signals, adjusts the second weight and rule output of its internal control rules, and gradually improves the control strategy, so that the electric water heater can always maintain the best performance under different operating conditions.
[0128] In one embodiment, the action space of reinforcement learning may further include the shape or parameters of the membership function, that is, the shape or parameters of the membership function are adjusted.
[0129] In this embodiment, reinforcement learning is performed on the adaptive fuzzy neural network according to the reward function to adjust the second weight of the control rule and the rule output. The reward function is constructed based on the temperature deviation, energy consumption and water temperature fluctuation trend. By real-time monitoring and adjusting the control rules, reinforcement learning enables the system to adapt to different usage environments and conditions. This adaptive ability helps to deal with complex and changeable situations. The reward function takes into account energy efficiency and the stability of the outlet water temperature while accurately controlling the water temperature. The comprehensive optimization of these factors can not only provide a stable and comfortable water temperature, but also effectively reduce energy waste and extend the life of the equipment.
[0130] In this application, reinforcement learning can continuously adapt to changes in the environment and user needs. For electric water heaters, different seasons, usage habits, and even fluctuations in power supply will affect the optimal control strategy. Continuous reinforcement learning can help the system dynamically adjust to optimize the control effect.
[0131] When continuing reinforcement learning, the stability of the system must also be maintained to avoid unstable or uncertain control effects caused by frequent adjustments. To this end, a certain learning rate can be set to control the magnitude of each adjustment, or some stabilization techniques can be used, such as Experience Replay or Target Network.
[0132] Reinforcement learning needs to find a balance between exploring new actions and exploiting the best known actions. Usually, a strategy such as ε-greedy is used, which selects the current best action (exploitation) most of the time, but also reserves a portion of the time to randomly select actions (exploration).
[0133] As time goes by, the system will gradually converge to a relatively stable strategy, that is, find a control strategy that is effective for most situations. At this time, the system's action selection will become more conservative, and the learning rate can be gradually reduced to reduce unnecessary policy fluctuations.
[0134] Although reinforcement learning can be a continuous process, termination conditions can also be set. For example, when the control performance of the system reaches or exceeds the set target (such as temperature control accuracy, energy efficiency, etc.), the learning process can be paused. Alternatively, when the Q value or control strategy changes little over a period of time, indicating that the system has basically converged, the learning can be slowed down or stopped. In actual applications, users or maintenance personnel can also manually enable or disable the learning function as needed.
[0135] The electric water heater in the present application can be designed for bathing infants and young children. A safe upper limit of the water temperature (for example, 43° C.) can be set to achieve high-precision temperature control, small water temperature fluctuations, and real-time monitoring and display of the water outlet water temperature.
[0136] At the same time, the electric water heater has a disinfection and sterilization function. The disinfection and sterilization device consists of an ultraviolet lamp, a glass cover tube, an electronic ballast dedicated to the ultraviolet lamp, and a control circuit. The ultraviolet lamp is sleeved into a glass sleeve and then installed in the inner tank of the water heater to directly irradiate the water body for disinfection and sterilization. Ultraviolet disinfection uses ultraviolet rays of appropriate wavelengths to destroy the molecular structure of DNA (deoxyribonucleic acid) or RNA (ribonucleic acid) in the cells of microorganisms, causing growth cell death and (or) regenerative cell death. Ultraviolet disinfection technology is based on modern epidemiology, medicine, and photodynamics. High-efficiency, high-intensity, and long-life UVC band ultraviolet light irradiates flowing water, directly killing various bacteria, viruses, parasites, algae, and other pathogens in the water. The above design achieves high safety of water for infant bathing and avoids infection of bacteria caused by bathing.
[0137] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).
[0138] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.
[0139] Further references Figure 3 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a temperature control device for an electric water heater, and the embodiment of the device is Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.
[0140] like Figure 3 As shown, the electric water heater temperature control device 300 described in this embodiment includes: an information acquisition module 301, an information input module 302, a signal generation module 303 and a state adjustment module 304, wherein:
[0141] The information acquisition module 301 is used to obtain the temperature control influencing information of the electric water heater. The temperature control influencing information includes water temperature information and environmental information. The water temperature information includes the water temperature at the water inlet of the electric water heater, the water temperature at the water outlet, the temperature deviation and the water temperature fluctuation trend. The environmental information includes the water pressure and ambient temperature of the electric water heater.
[0142] The information input module 302 is used to input the temperature control influence information into the adaptive fuzzy neural network, so as to perform fuzzy reasoning according to various factors in the temperature control influence information through the adaptive fuzzy neural network to obtain control information.
[0143] The signal generating module 303 is used to generate a control signal according to the control information.
[0144] The state adjustment module 304 is used to adjust the operating state of the electric water heater according to the control signal to control the water temperature at the water outlet to a target temperature.
[0145] In this embodiment, the temperature control influencing information of the electric water heater is obtained, including water temperature information and environmental information. The water temperature information includes the water temperature at the water inlet of the electric water heater, the water temperature at the water outlet, the temperature deviation and the water temperature fluctuation trend, which is helpful to have a more comprehensive understanding of the temperature condition of the electric water heater; the environmental information includes the water pressure and ambient temperature of the electric water heater. Incorporating external factors into the control system can avoid temperature fluctuations caused by environmental changes; the temperature control influencing information is input into an adaptive fuzzy neural network, and the adaptive fuzzy neural network performs fuzzy reasoning based on various factors in the temperature control influencing information, adapts and responds to various complex environments, and generates accurate control information; a control signal that can act on the electric water heater is generated based on the control information, and the operating state of the electric water heater is adjusted based on the control signal to control the water temperature at the water outlet to the target temperature. In situations where environmental conditions change and precise temperature control is required, the water temperature can be controlled more comprehensively and accurately to avoid drastic fluctuations in the water temperature.
[0146] In some optional implementations of this embodiment, when acquiring the temperature deviation, the information acquisition module 301 may include: a temperature acquisition submodule, a first acquisition submodule, a weighted average submodule, and a deviation calculation submodule, wherein:
[0147] The temperature acquisition submodule is used to collect the temperature values of each measuring point in the electric water heater through a temperature sensor array. The temperature sensor array includes multiple temperature sensors arranged in the electric water heater. The collected temperature values include the water temperature at the outlet of the electric water heater.
[0148] The first acquisition submodule is used to acquire the first weight corresponding to each temperature value according to the position of each measuring point, wherein the water temperature at the water outlet has the largest first weight.
[0149] The weighted average submodule is used to perform weighted average on each temperature value to obtain the average water temperature of the electric water heater.
[0150] The deviation calculation submodule is used to calculate the temperature deviation of the electric water heater based on the average water temperature and the preset target water temperature.
[0151] In this embodiment, the temperature values of multiple measuring points in the electric water heater are collected through a temperature sensor array, including the water temperature at the key water outlet; the first weight corresponding to each temperature value is obtained according to the position of each measuring point, highlighting the impact of temperature changes at key positions on the overall temperature evaluation, and the water temperature at the water outlet has the largest first weight; the temperature values are weighted averaged to obtain the average water temperature of the electric water heater, which can more accurately reflect the actual temperature condition of the electric water heater; based on the average water temperature and the preset target water temperature, the temperature deviation of the electric water heater can be accurately calculated, ensuring that the subsequent temperature control can be accurate and effective.
[0152] In some optional implementations of this embodiment, when obtaining the water temperature fluctuation trend, the information acquisition module 301 may include: a collection submodule, a fusion filter submodule, an index calculation submodule and a trend determination submodule, wherein:
[0153] The acquisition submodule is used to acquire the temperature values of each measuring point in the electric water heater at multiple time points through a temperature sensor array. The temperature sensor array includes multiple temperature sensors arranged in the electric water heater.
[0154] The fusion filter submodule is used to input the temperature values of each measurement point at multiple time points into the Kalman filter for data fusion filtering to obtain a fused temperature sequence.
[0155] The indicator calculation submodule is used to calculate the derived indicators of the fused temperature series.
[0156] The trend determination submodule is used to determine the fused temperature series and the derived indicators as the water temperature fluctuation trend of the electric water heater.
[0157] In this embodiment, the temperature values of each measuring point in the electric water heater at multiple time points are collected through a temperature sensor array to provide a global understanding of the temperature at different positions of the electric water heater; the temperature values of each measuring point at multiple time points are input into a Kalman filter for data fusion filtering to reduce the influence of noise, so that the extracted temperature trend is more accurate and smooth, and a fused temperature sequence is obtained; the derivative indicators of the fused temperature sequence are calculated to obtain detailed water temperature fluctuation characteristics, which can better reflect the dynamic changes of water temperature; the fused temperature sequence and the derivative indicators are determined as the water temperature fluctuation trend of the electric water heater, ensuring that the subsequent temperature control can be accurate and effective.
[0158] In some optional implementations of this embodiment, the electric water heater temperature control device 300 may further include: a temperature difference alarm module and a maintenance alarm module, wherein:
[0159] The temperature difference alarm module is used to trigger a temperature difference alarm notification when the temperature deviation is greater than a preset temperature difference threshold.
[0160] The maintenance alarm module is used to trigger a maintenance alarm notification when the existence time of the temperature deviation is greater than a preset time threshold.
[0161] In this embodiment, when the temperature deviation is greater than the preset temperature difference threshold, a temperature difference alarm notification is triggered to ensure that the water temperature is maintained within a safe and comfortable range and to prevent users from using the water at an inappropriate temperature. This is especially important for infants and other children who are sensitive to water temperature. At the same time, it can quickly respond to abnormal temperature changes and issue timely alarms to reduce the risks of use due to abnormal temperatures. When the temperature deviation lasts longer than the preset duration threshold, a maintenance alarm notification is triggered, which enhances the self-diagnosis capability of the electric water heater and can identify potential hidden faults or performance degradations in the equipment, providing support for preventive maintenance and reducing the occurrence of sudden failures.
[0162] In some optional implementations of this embodiment, the adaptive fuzzy neural network includes a fuzzification layer, a rule layer, a normalization layer and an output layer, and the information input module 302 may include: a fuzzy processing submodule, a rule acquisition submodule, an output calculation submodule and an information generation submodule, wherein:
[0163] The fuzzy processing submodule is used to perform fuzzy processing on various factors in the temperature control influencing information through the fuzzy layer to obtain fuzzy representation parameters of various factors.
[0164] The rule acquisition submodule is used to determine the control rules corresponding to each fuzzy representation parameter through the rule layer, and obtain the rule output corresponding to each control rule.
[0165] The output calculation submodule is used to obtain the second weight of each control rule in the normalization layer, and calculate the weighted output according to the second weight of each control rule and its rule output.
[0166] The information generation submodule is used to defuzzify the weighted output at the output layer to obtain control information.
[0167] In this embodiment, the adaptive fuzzy neural network includes a fuzzification layer, a rule layer, a normalization layer and an output layer; the fuzzification layer performs fuzzification processing on various factors in the temperature control influencing information to obtain fuzzy representation parameters of various factors, effectively handles the fuzziness and uncertainty of the input data, and makes the influence of various factors on the control decision clearer and more accurate; the rule layer determines the control rules corresponding to each fuzzy representation parameter, and obtains the rule output corresponding to each control rule, ensuring that flexible and accurate control rules can be provided under complex and changeable conditions; the second weight of each control rule is obtained in the normalization layer, and the second weight represents the importance of the rule. According to the second weight of each control rule and its rule output, the weighted output is calculated to ensure that the results of all control rules are reasonably integrated to obtain the optimal control scheme. This calculation method takes into account the actual environment and improves the adaptability to various actual situations; the weighted output is defuzzified in the output layer to obtain clear control information, which is conducive to the subsequent adjustment of the operating state of the electric water heater.
[0168] In some optional implementations of this embodiment, the output calculation submodule may include: an activation calculation unit, a weight acquisition unit, a valid calculation unit, and an output calculation unit, wherein:
[0169] The activation calculation unit is used to calculate the activation degree of each control rule according to the membership degree of each fuzzy representation parameter to each control rule.
[0170] The weight acquisition unit is used to acquire the second weight of each control rule in the normalization layer.
[0171] The effective calculation unit is used to calculate the effective weight of each control rule according to the activation degree of each control rule and its second weight.
[0172] The output calculation unit is used to calculate the weighted output according to the effective weight of each control rule and its rule output.
[0173] In this embodiment, the activation degree of each control rule is calculated according to the membership degree of each fuzzy representation parameter to each control rule, so as to obtain the applicability of each control rule; the second weight of each control rule is obtained in the normalization layer, and the effective weight of each control rule is calculated according to the activation degree of each control rule and its second weight, so as to more accurately reflect the actual contribution of each rule in the current scenario; the weighted output is calculated according to the effective weight of each control rule and its rule output, so as to make the control information more accurate and reliable, realize the refined temperature control of the electric water heater, ensure the stability of the outlet water temperature, and reduce the temperature fluctuation.
[0174] In some optional implementations of this embodiment, the electric water heater temperature control device 300 may also include: a reinforcement learning module, used to perform reinforcement learning on the adaptive fuzzy neural network according to a reward function to adjust the second weight of the control rule and the rule output, and the reward function is constructed based on temperature deviation, energy consumption and water temperature fluctuation trend.
[0175] In this embodiment, reinforcement learning is performed on the adaptive fuzzy neural network according to the reward function to adjust the second weight of the control rule and the rule output. The reward function is constructed based on the temperature deviation, energy consumption and water temperature fluctuation trend. By real-time monitoring and adjusting the control rules, reinforcement learning enables the system to adapt to different usage environments and conditions. This adaptive ability helps to deal with complex and changeable situations. The reward function takes into account energy efficiency and the stability of the outlet water temperature while accurately controlling the water temperature. The comprehensive optimization of these factors can not only provide a stable and comfortable water temperature, but also effectively reduce energy waste and extend the life of the equipment.
[0176] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4This is a basic structural block diagram of the computer device in this embodiment.
[0177] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.
[0178] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.
[0179] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the temperature control method of the electric water heater, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.
[0180] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run the computer-readable instructions stored in the memory 41 or process data, such as running the computer-readable instructions of the electric water heater temperature control method.
[0181] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.
[0182] The computer device provided in this embodiment can execute the above-mentioned electric water heater temperature control method. Here, the electric water heater temperature control method can be the electric water heater temperature control method of each of the above-mentioned embodiments.
[0183] In this embodiment, the temperature control influencing information of the electric water heater is obtained, including water temperature information and environmental information. The water temperature information includes the water temperature at the water inlet of the electric water heater, the water temperature at the water outlet, the temperature deviation and the water temperature fluctuation trend, which is helpful to have a more comprehensive understanding of the temperature condition of the electric water heater; the environmental information includes the water pressure and ambient temperature of the electric water heater. Incorporating external factors into the control system can avoid temperature fluctuations caused by environmental changes; the temperature control influencing information is input into an adaptive fuzzy neural network, and the adaptive fuzzy neural network performs fuzzy reasoning based on various factors in the temperature control influencing information, adapts and responds to various complex environments, and generates accurate control information; a control signal that can act on the electric water heater is generated based on the control information, and the operating state of the electric water heater is adjusted based on the control signal to control the water temperature at the water outlet to the target temperature. In situations where environmental conditions change and precise temperature control is required, the water temperature can be controlled more comprehensively and accurately to avoid drastic fluctuations in the water temperature.
[0184] The present application also provides another embodiment, namely, providing a computer-readable storage medium, which stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the electric water heater temperature control method as described above.
[0185] In this embodiment, the temperature control influencing information of the electric water heater is obtained, including water temperature information and environmental information. The water temperature information includes the water temperature at the water inlet of the electric water heater, the water temperature at the water outlet, the temperature deviation and the water temperature fluctuation trend, which is helpful to have a more comprehensive understanding of the temperature condition of the electric water heater; the environmental information includes the water pressure and ambient temperature of the electric water heater. Incorporating external factors into the control system can avoid temperature fluctuations caused by environmental changes; the temperature control influencing information is input into an adaptive fuzzy neural network, and the adaptive fuzzy neural network performs fuzzy reasoning based on various factors in the temperature control influencing information, adapts and responds to various complex environments, and generates accurate control information; a control signal that can act on the electric water heater is generated based on the control information, and the operating state of the electric water heater is adjusted based on the control signal to control the water temperature at the water outlet to the target temperature. In situations where environmental conditions change and precise temperature control is required, the water temperature can be controlled more comprehensively and accurately to avoid drastic fluctuations in the water temperature.
[0186] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.
[0187] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.
Claims
1. A method for controlling the temperature of an electric water heater, characterized in that: The steps include: Acquire temperature control influencing information of the electric water heater, wherein the temperature control influencing information includes water temperature information and environmental information, wherein the water temperature information includes water inlet water temperature, water outlet water temperature, temperature deviation and water temperature fluctuation trend of the electric water heater, and the environmental information includes water pressure and environmental temperature of the electric water heater; Inputting the temperature control influence information into an adaptive fuzzy neural network, so as to perform fuzzy reasoning according to various factors in the temperature control influence information through the adaptive fuzzy neural network to obtain control information; generating a control signal according to the control information; The operating state of the electric water heater is adjusted according to the control signal to control the water temperature at the water outlet to a target temperature.
2. The electric water heater temperature control method according to claim 1, characterized in that: When obtaining the temperature deviation, the step of obtaining the temperature control influence information of the electric water heater includes: The temperature value of each measuring point in the electric water heater is collected by a temperature sensor array, wherein the temperature sensor array comprises a plurality of temperature sensors arranged in the electric water heater, and the collected temperature value comprises the water temperature at the water outlet of the electric water heater; Obtaining the first weight corresponding to each temperature value according to the position of each measuring point, wherein the water temperature at the water outlet has the largest first weight; Taking a weighted average of the temperature values to obtain an average water temperature of the electric water heater; Based on the average water temperature and a preset target water temperature, a temperature deviation of the electric water heater is calculated.
3. The electric water heater temperature control method according to claim 1, characterized in that: When obtaining the water temperature fluctuation trend, the step of obtaining the temperature control influence information of the electric water heater includes: Collecting the temperature values of each measuring point in the electric water heater at multiple time points by means of a temperature sensor array, wherein the temperature sensor array comprises multiple temperature sensors arranged in the electric water heater; Inputting the temperature values of each measuring point at multiple time points into a Kalman filter for data fusion filtering to obtain a fused temperature sequence; calculating a derivative index of the fusion temperature series; The fused temperature sequence and the derived index are determined as the water temperature fluctuation trend of the electric water heater.
4. The temperature control method of an electric water heater according to claim 1, characterized in that: After the step of obtaining the temperature control influence information of the electric water heater, the method further includes: When the temperature deviation is greater than a preset temperature difference threshold, a temperature difference alarm notification is triggered; or, When the temperature deviation exists for a time greater than a preset time threshold, a maintenance alarm notification is triggered.
5. The electric water heater temperature control method according to claim 1, characterized in that: The adaptive fuzzy neural network includes a fuzzification layer, a rule layer, a normalization layer and an output layer. The step of performing fuzzy reasoning according to various factors in the temperature control influence information by the adaptive fuzzy neural network to obtain control information includes: Performing fuzzy processing on various factors in the temperature control influencing information through the fuzzification layer to obtain fuzzy representation parameters of the various factors; Determine the control rules corresponding to each fuzzy representation parameter through the rule layer, and obtain the rule output corresponding to each control rule; Acquiring the second weight of each control rule at the normalization layer, and calculating the weighted output according to the second weight of each control rule and the rule output thereof; The weighted output is defuzzified at the output layer to obtain control information.
6. The electric water heater temperature control method according to claim 5, characterized in that: The step of obtaining the second weight of each control rule at the normalization layer and calculating the weighted output according to the second weight of each control rule and its rule output comprises: Calculating the activation degree of each control rule according to the membership degree of each fuzzy representation parameter to each control rule; Acquiring, at the normalization layer, a second weight of each of the control rules; Calculating the effective weight of each control rule according to the activation degree of each control rule and its second weight; The weighted output is calculated based on the effective weights of the control rules and their rule outputs.
7. The electric water heater temperature control method according to claim 5, characterized in that: After the step of adjusting the operating state of the electric water heater according to the control signal, the method further includes: The adaptive fuzzy neural network is reinforced learned according to a reward function to adjust a second weight of a control rule and a rule output, wherein the reward function is constructed based on temperature deviation, energy consumption and water temperature fluctuation trend.
8. A temperature control device for an electric water heater, characterized in that: include: An information acquisition module, used to acquire temperature control influence information of the electric water heater, wherein the temperature control influence information includes water temperature information and environmental information, wherein the water temperature information includes water inlet water temperature, water outlet water temperature, temperature deviation and water temperature fluctuation trend of the electric water heater, and the environmental information includes water pressure and environmental temperature of the electric water heater; An information input module, used for inputting the temperature control influence information into an adaptive fuzzy neural network, so as to perform fuzzy reasoning according to various factors in the temperature control influence information through the adaptive fuzzy neural network to obtain control information; A signal generating module, used for generating a control signal according to the control information; The state adjustment module is used to adjust the operating state of the electric water heater according to the control signal to control the water temperature at the water outlet to a target temperature.
9. A computer device, comprising a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the electric water heater temperature control method according to any one of claims 1 to 7 when executing the computer-readable instructions.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the electric water heater temperature control method according to any one of claims 1 to 7 are implemented.
Citation Information
Patent Citations
PID thermostatic adjustment control system for directly-heated air energy water heater
CN103148594A
Water heater and control method thereof
CN105588336A
Directly-heated type heat pump system constant-temperature flow control method based on neural network
CN106369834A
Intelligent hot water control device and control method
CN115143646A
Multi-connected water heater control method and device and water heater parallel system
CN116086021A
Cited By
Intelligent heater control system with built-in flow meter
CN120021543A
Multifunctional intelligent steaming oven control system and intelligent steaming oven
CN121857883A
