Intelligent temperature control method and system of water heater

Abstract

The invention provides an intelligent temperature control method and system for a water heater, and the method comprises the steps: collecting the internal temperature, water inlet temperature and water flow of a water tank of the water heater as equipment operation state data, and uploading the equipment operation state data to a cloud server; the cloud server or the user terminal generates a control instruction according to the equipment operation state data and sends the control instruction to the water heater; the control instruction comprises execution of dynamic temperature control operation, and the dynamic temperature control operation comprises immediate adjustment operation; the real-time adjusting operation comprises the steps that when it is detected that the water flow exceeds a preset threshold value, the power output of the heating device is dynamically adjusted through a fuzzy-PID composite control algorithm based on the water tank internal target temperature set by a user, the real-time water inlet temperature and the current water flow. The fuzzy-PID composite control algorithm is adopted, the high-flow water demand can be quickly responded through instant adjustment, the water temperature fluctuation range is controlled more accurately, the problems that traditional temperature control lags behind and is low in precision are solved, and the comfort level of a user is improved.

Description

Technical Field

[0001] The present application relates to the technical field of water heater temperature control, and more specifically to an intelligent temperature control method and system for a water heater. Background Art

[0002] Water heaters are essential bathroom appliances for modern households. They heat water using electricity, gas, or solar energy, meeting daily needs for hot water for bathing, washing, and other tasks. They come in two types: storage and instantaneous. Some high-end models also offer features like constant temperature control, energy savings, and smart scheduling.

[0003] With the widespread adoption of smart homes, users are demanding higher levels of comfort, energy efficiency, and convenience from their water heaters. Existing smart water heaters, however, often employ a simple target temperature setting model for temperature control. Users set their desired water temperature, and the water heater then switches on and off using a mechanical or basic electronic thermostat to ensure the water temperature remains stable near the set value.

[0004] However, existing smart water heaters struggle to precisely match heating and stopping timing to changing user needs, resulting in fluctuating water temperatures and prolonged waiting times. Dynamically adjusting heating strategies during off-peak hours or when water usage fluctuates can be difficult, leading to energy waste. The inability to intelligently adjust based on factors such as water usage habits, ambient temperature, and inlet water temperature fluctuations results in a poor user experience. Summary of the Invention

[0005] To solve the problem that the timing of heating or stopping heating of the above-mentioned existing smart water heaters is difficult to accurately match changes in user needs, resulting in water temperature fluctuations or long waiting times, and it is difficult to dynamically adjust the heating strategy during non-water use periods or when water consumption changes, which easily leads to energy waste, and it is impossible to make intelligent adjustments based on water use habits, ambient temperature, water inlet temperature changes and other factors, resulting in poor user experience.

[0006] On one hand, the present application provides an intelligent temperature control method for a water heater, comprising the steps of:

[0007] Collecting the internal temperature of the water heater tank, the water inlet temperature, and the water flow rate as device operating status data, and uploading the device operating status data to the cloud server;

[0008] The cloud server or user terminal generates a control instruction based on the device operation status data and sends it to the water heater;

[0009] The control instructions include executing a dynamic temperature control operation, and the dynamic temperature control operation includes: an immediate adjustment operation;

[0010] The instant adjustment operation steps are:

[0011] When it is detected that the water flow rate exceeds a preset threshold, the fuzzy-PID composite control algorithm is used to dynamically adjust the power output of the heating device based on the user-set internal target temperature of the water tank, the real-time water inlet temperature and the current water flow rate.

[0012] In a feasible implementation, the dynamic temperature control operation further includes a preheating optimization operation, and the preheating optimization operation steps are:

[0013] Predicting water use periods and corresponding hot water demand based on historically recorded operating status data of the equipment;

[0014] Before the predicted water usage period begins, the optimal heating start time is calculated based on the current water tank internal temperature, water inlet temperature, ambient temperature and predicted hot water demand, and the preheating target temperature is set to 2-3°C higher than the predicted target temperature.

[0015] In a feasible implementation, the step of predicting the water usage period and the corresponding hot water demand based on the historical data of the equipment operation status includes:

[0016] Analyze historical water consumption data through the cloud server and establish user water consumption patterns using an LSTM time series model;

[0017] Inputting the user's water use pattern, current date type, and ambient temperature data into the LSTM time series model;

[0018] Determine a specific period in which the water flow output by the LSTM time series model is higher than the preset threshold as a predicted water use period;

[0019] The water flow corresponding to the predicted water use period output by the LSTM time series model is used as the predicted hot water demand.

[0020] In a feasible implementation, the dynamic temperature control operation further includes an energy-saving cruise operation, and the energy-saving cruise operation steps are:

[0021] When the water flow data is lower than the preset water peak flow data, the water tank temperature is automatically maintained at the preset energy-saving temperature, and the preset energy-saving temperature is dynamically adjusted according to the change of ambient temperature.

[0022] In a feasible implementation, the water temperature control accuracy range of the instant adjustment operation is within the range of ±1°C of the target temperature inside the water tank.

[0023] On the other hand, the present application provides an intelligent temperature control system for a water heater, which is used to implement any of the above-mentioned intelligent temperature control methods for a water heater, comprising: a local device layer, a cloud service layer, and a user interaction layer;

[0024] The local device layer includes: a temperature sensor group, a flow sensor, a heating device, a main control module and an IOT communication module;

[0025] The temperature sensor group is configured to collect the temperature of the core area of ​​the water heater tank and the water inlet in real time;

[0026] The flow sensor is installed on the water outlet pipe and is configured to detect the real-time water flow;

[0027] The heating device adopts a resistance heating tube structure and is configured to support power output adjustment through PWM duty cycle;

[0028] The main control module is configured to perform dynamic temperature control operations;

[0029] The IOT communication module is configured to support 4GCat.1, NB-IoT and WiFi communication protocols;

[0030] The cloud service layer is configured to store historical water consumption data, run the LSTM time series model to generate forecast instructions, and obtain external weather data through the ambient temperature API interface;

[0031] The user interaction layer includes a user terminal configured to receive device operation status data and issue control instructions;

[0032] The main control module establishes a two-way data connection with the cloud service layer through the IOT communication module. In a feasible implementation of the cloud service, the main control module is configured to perform dynamic temperature control operations, including: instant adjustment operation, preheating optimization operation and energy-saving cruise operation;

[0033] The instant adjustment operation is as follows: when the flow sensor detects that the water flow exceeds a preset threshold, the power output of the heating device is dynamically adjusted using a fuzzy-PID composite control algorithm based on the user-set internal target temperature of the water tank, the real-time water inlet temperature, and the current water flow;

[0034] The preheating optimization operation is: predicting the water use period and the corresponding hot water demand based on the historical record of the equipment operation status data;

[0035] Before the predicted water usage period begins, the optimal heating start time is calculated based on the current water tank internal temperature, water inlet temperature, ambient temperature, and predicted hot water demand, and the preheating target temperature is set to 2-3°C higher than the predicted target temperature;

[0036] The energy-saving cruise operation is: when the water flow data is lower than the preset water peak flow data, the water tank temperature is automatically maintained at a preset energy-saving temperature, and the preset energy-saving temperature is dynamically adjusted according to the change of ambient temperature.

[0037] In one feasible implementation, the LSTM time series model in the cloud service layer is configured as follows:

[0038] Analyze historical water use data and establish user water use patterns;

[0039] Based on the user's water use pattern, current date type and ambient temperature data, predict the water use period, predict the corresponding hot water demand and target temperature range, and obtain a prediction structure;

[0040] The prediction result is sent to the main control module to trigger the preheating optimization operation.

[0041] In a feasible implementation, the heating device realizes power linear control by adjusting the PWM duty cycle, and compensates for heat dissipation in the pipeline by increasing power during the preheating optimization operation.

[0042] In a feasible implementation, the IOT communication module supports updating the fuzzy-PID algorithm parameters and energy-saving cruise temperature logic of the main control module through OTA wireless communication.

[0043] As can be seen from the above, the present application provides a smart water heater temperature control method and system. This system utilizes a fuzzy-PID composite control algorithm, enabling real-time adjustments to quickly respond to high water demand, keeping water temperature fluctuations within ±1°C of the target temperature. This addresses the lag and low precision of traditional temperature control, improving user comfort. Preheat optimization uses historical water usage data and ambient temperature to preheat and appropriately set the target temperature, avoiding the high energy consumption and long wait times associated with traditional temporary heating. Energy-saving cruise control dynamically adjusts the water tank temperature, reducing inefficient heating energy consumption during off-peak hours and balancing energy conservation with water demand. A prediction mechanism based on an LSTM time series model, combined with date type and ambient temperature, accurately captures user water usage habits and provides personalized hot water supply strategies. Users can view device status in real time and remotely intervene through a terminal, enhancing intelligent device management. The system supports over-the-air (OTA) updates of the main control module's algorithm parameters and logic, ensuring continuous optimization of device performance. Furthermore, the LSTM model is regularly updated to dynamically adapt to changing user habits and maintain high prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings are incorporated into and constitute a part of this specification, illustrate embodiments consistent with the implementation of the present invention, and together with the description, serve to explain the principles of the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the implementation of the present invention. For those skilled in the art, other drawings can be derived from these drawings without inventive effort.

[0045] Figure 1 This is a flow chart of a method for intelligent temperature control of a water heater according to an embodiment of the present application;

[0046] Figure 2 This is a schematic diagram of the architecture of an intelligent temperature control system for water heaters shown in one embodiment of the present application. DETAILED DESCRIPTION

[0047] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the present invention will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to provide a thorough understanding of the implementation of the example embodiments of the present invention.

[0048] Existing smart water heaters, however, often use a simple target temperature setting model for temperature control. Users set their desired water temperature, and the water heater then switches on and off using a mechanical or basic electronic thermostat to ensure the water temperature remains stable near the set value. However, existing smart water heaters struggle to precisely match the timing of heating and stopping to changing user needs, resulting in fluctuating water temperatures and prolonged waiting times. Dynamically adjusting heating strategies during off-peak hours or when water consumption fluctuates can be difficult, leading to energy waste.

[0049] In order to solve the above problems, the present invention provides an intelligent temperature control method for a water heater. Figure 1 As shown, the steps include:

[0050] S100: Collect the internal temperature of the water heater tank, the water inlet temperature, and the water flow rate as the device operation status data, and upload the device operation status data to the cloud server;

[0051] S200: The cloud server or user terminal generates a control instruction based on the device operation status data and sends it to the water heater;

[0052] S300: The control instruction includes executing a dynamic temperature control operation, which includes an immediate adjustment operation S400. The immediate adjustment operation steps are:

[0053] S410: When it is detected that the water flow rate exceeds a preset threshold, the power output of the heating device is dynamically adjusted using a fuzzy-PID composite control algorithm based on the target temperature inside the water tank set by the user, the real-time water inlet temperature, and the current water flow rate.

[0054] Specifically, during water heater operation, the temperature sensors at the local device level continuously collect the temperature of the water tank core area and the water inlet, while the flow sensors monitor the water flow in the outlet pipe in real time. The main control module uploads these three types of device operating status data to the cloud server via the IoT communication module at preset intervals. The cloud server stores this basic data and generates control instructions based on the target temperature set by the user through the terminal.

[0055] When the user turns on the hot water valve, the flow sensor detects that the current flow exceeds the preset threshold, and the main control module immediately starts the real-time adjustment operation: based on the target temperature set by the user, the real-time water inlet temperature and the current flow, the fuzzy-PID composite control algorithm is used to calculate the required heating power, and the PWM duty cycle of the heating device is adjusted to achieve power output.

[0056] Data collection and upload provide a real-time basis for dynamic temperature control, while cloud-based command generation ensures intelligent control strategies. The instant adjustment provided by this embodiment directly responds to changes in water demand, enabling rapid and precise temperature control through algorithm fusion. This embodiment addresses the issues of delayed temperature control response and low precision encountered in traditional water heaters through real-time data collection and algorithm fusion. Fuzzy control addresses nonlinear dynamic changes, while PID control eliminates steady-state errors. The combination of these two ensures accurate control of water temperature fluctuations, enhancing user comfort.

[0057] In some embodiments of this application, continue to refer to Figure 1 As shown, the dynamic temperature control operation further includes a preheating optimization operation S500, and the preheating optimization operation steps include:

[0058] S510: Predicting water usage periods and corresponding hot water demand based on historically recorded equipment operating status data.

[0059] The cloud server regularly analyzes historical water usage data, such as the peak flow rate between 6:00 PM and 7:00 PM daily over the past 30 days. Combining the current date and ambient temperature, the LSTM model predicts the water usage period between 6:00 PM and 7:00 PM the following day, along with the corresponding hot water demand.

[0060] S520: Before the predicted water usage period begins, the optimal heating start time is calculated based on the current internal temperature of the water tank, the water inlet temperature, the ambient temperature, and the predicted hot water demand, and the preheating target temperature is set to be 2-3°C higher than the predicted target temperature.

[0061] The main control module initiates preheating optimization one hour before the predicted timeframe. For example, using the 6:00 PM to 7:00 PM water usage period and a user-set temperature of 45°C, the module starts at 5:00 PM. Based on the current water tank temperature, inlet water temperature, ambient temperature, and predicted demand, the optimal heating start time is calculated as 5:20 PM, and the preheating target temperature is set to 47°C, which is higher than the user-set temperature of 45°C. The heating device begins heating at 5:20 PM, ensuring the water tank temperature reaches 45°C by 6:00 PM after compensating for heat dissipation in the pipes.

[0062] This embodiment uses historical data analysis and prediction to inform preheating. The preheat target temperature setting compensates for heat loss in the pipes, ensuring accurate water temperature compliance during the water usage period. This addresses the high energy consumption and long wait times associated with temporary heating in traditional water heaters. By raising the preheat target temperature by 2-3°C, it effectively offsets heat loss in the pipes, stabilizes the starting water temperature, avoids overheating, and reduces energy consumption.

[0063] In some embodiments of the present application, the step S310 of predicting the water use period and the corresponding hot water demand based on the historically recorded device operating status data further includes the following specific operations and their corresponding effects:

[0064] S511: Analyze historical water consumption data through the cloud server and use the LSTM time series model to establish user water consumption patterns.

[0065] Using servers deployed in the cloud, we conduct in-depth mining and analysis of long-accumulated historical water consumption data. Through data preprocessing and feature extraction, we convert this historical water consumption data into a format suitable for processing by the LSTM time series model. Subsequently, we train the LSTM model on this historical water consumption data to capture the cyclical, seasonal, and trend characteristics of user water consumption, thereby establishing accurate user water consumption patterns.

[0066] This step helps understand users’ water use habits by establishing user water use patterns, providing a basis for subsequent predictions. The LST M model can capture long-term dependencies in time series data and is suitable for processing data with periodic and seasonal changes such as user water use.

[0067] S512: Input the user's water usage pattern, current date type, and ambient temperature data into the LSTM time series model.

[0068] Based on the user water usage patterns already established by the LSTM time series model, the current date type (such as weekday, weekend, or holiday) and real-time ambient temperature data are input into the model as additional input features. These features are converted into a format that the model can recognize through data preprocessing.

[0069] Incorporating data on the current date and ambient temperature improves prediction accuracy. These factors are crucial for influencing user water usage, and incorporating them into the model can make predictions more realistic.

[0070] S513: The specific time period in which the water flow output by the LSTM time series model is higher than the preset threshold is determined as the predicted water consumption period.

[0071] The LSTM time series model outputs a series of water flow forecasts corresponding to different time periods. By setting a preset threshold, we filter out specific time periods where the water flow forecast exceeds the threshold. These time periods are considered to be the predicted peak water use periods.

[0072] This step helps predict water usage periods, helping us understand user demand in advance and providing a basis for scheduling the hot water supply system. By setting thresholds, we can identify periods with high hot water demand, ensuring sufficient hot water supply during these periods.

[0073] S514: The water flow corresponding to the predicted water use period output by the LSTM time series model is used as the predicted hot water demand.

[0074] After determining the predicted water usage periods, the corresponding water flow forecast values ​​for these periods are extracted from the output of the LSTM time series model. These forecast values ​​are regarded as the predicted hot water demand.

[0075] Predicting hot water demand is key to scheduling and optimizing hot water supply systems. By using the predicted water flow rate corresponding to the predicted water usage period as the predicted hot water demand, the hot water supply system can be given a clear target and basis, ensuring efficient and stable system operation. This also helps reduce energy consumption and operating costs.

[0076] For example, consider historical water usage data with a timestamp of 2023-10-01 18:00:00, a flow rate of 5 L / min, a set temperature of 45°C, and a duration of 30 minutes. These four-dimensional features are input during LSTM model training on the cloud server. After model training is complete, the current date type (e.g., weekday), ambient temperature (e.g., 22°C), and the user's recent water usage pattern (e.g., water usage at 18:00 for five consecutive days) are input. The LSTM model outputs the predicted water usage period of the next day (18:00-18:30) and the corresponding peak flow rate of 4.8 L / min as the predicted hot water demand. Upon receiving the prediction, the main control module triggers preheating optimization.

[0077] This embodiment improves the LSTM model's prediction accuracy through multi-dimensional historical data training. The input of current environmental and date data makes the prediction results more tailored to actual needs. This embodiment uses the LSTM model to capture the temporal patterns and temperature correlations of users' water usage, addressing the problem of traditional timed preheating systems being unable to adapt to environmental changes. This higher prediction accuracy allows for more precise preheating operations, reduces ineffective heating, and lowers standby energy consumption.

[0078] In some embodiments of this application, continue to refer to Figure 1 As shown, the dynamic temperature control operation also includes energy-saving cruise operation S600, and the energy-saving cruise operation steps are:

[0079] S610: When the water flow data is lower than the preset water peak flow data, the water tank temperature is automatically maintained at the preset energy-saving temperature, and the preset energy-saving temperature is dynamically adjusted according to the change of the ambient temperature.

[0080] It's understood that when the system detects that the current water flow rate is lower than the preset peak flow rate, it indicates that it's currently off-peak, and the water tank temperature can be appropriately lowered to reduce energy consumption. If the current flow rate is lower than the preset peak flow rate, the main control module initiates energy-saving cruise control: maintaining the water tank temperature at a preset energy-saving temperature based on the ambient temperature. If the ambient temperature rises, the main control module consults a preset energy-saving temperature table and adjusts the energy-saving temperature accordingly; if the ambient temperature drops, the energy-saving temperature is adjusted lower accordingly.

[0081] For example, in the summer when the ambient temperature is high, the system may set the water tank temperature slightly higher to ensure that users can get sufficient comfort when using hot water; while in the winter when the ambient temperature is low, the system may set the water tank temperature slightly lower to reduce unnecessary energy consumption.

[0082] This step uses flow rate thresholds to distinguish between peak and off-peak water usage, and dynamically adjusts the energy-saving temperature to the ambient temperature, balancing energy conservation with immediate water demand. Maintaining low temperatures during off-peak hours eliminates the energy waste associated with traditional water heaters, which often maintain high temperatures. Dynamic energy-saving temperatures further reduce energy consumption, while ambient temperature compensation ensures that users don't have to wait for long periods of time for short, small water usage periods.

[0083] In some embodiments of the present application, the water temperature control accuracy range of the real-time adjustment operation is within the range of ±1°C of the target temperature inside the water tank to ensure that the temperature meets the requirements of use.

[0084] Another embodiment of the present application provides an intelligent temperature control system for a water heater, which is used to implement the intelligent temperature control method for a water heater in the above embodiment. Figure 2 As shown, the system includes: a local device layer, a cloud service layer and a user interaction layer.

[0085] The local device layer includes a temperature sensor group, flow sensors, a heating device, a main control module, and an IoT communication module. The temperature sensor group collects real-time temperatures in the core area of ​​the water heater tank and the water inlet. The flow sensor detects real-time water flow in the outlet pipe. The heating device uses a resistive heating tube structure and supports PWM duty cycle power regulation. The main control module performs dynamic temperature control operations. The IoT communication module establishes a bidirectional connection with the cloud service layer via 4G Cat.1, NB-IoT, and WiFi protocols. The cloud service layer stores historical water consumption data, runs an LSTM time series model to generate forecast instructions, and obtains external weather data through the ambient temperature API. The user terminal in the user interaction layer receives device operating status data and issues control instructions.

[0086] The temperature sensor group and flow sensor continuously provide temperature and flow data to the main control module, which transmits this data to the cloud service layer via the IoT communication module. The cloud service layer combines historical water usage data, LSTM model prediction results, and weather data from the ambient temperature API to generate a prediction instruction containing the heating duration and temperature setting. This instruction is transmitted back to the main control module via the IoT communication module, and the main control module dynamically adjusts the power output of the heating device using the PWM duty cycle. The user terminal simultaneously receives device status and prediction results pushed by the cloud, allowing users to remotely modify control instructions.

[0087] The system provided in this embodiment uses an LSTM model to predict water demand and ambient temperature changes, dynamically adjusting the PWM duty cycle to achieve precise power control. This solves the energy waste caused by fixed temperature settings in traditional water heaters. The introduction of an ambient temperature API compensates for the impact of external climate on heating efficiency, while the two-way interactive function of the user terminal enables users to intervene in device operation in real time. As a result, the system maintains water temperature stability while reducing ineffective heating energy consumption and improving users' ability to control device status.

[0088] In some embodiments of the present application, the main control module is configured to perform dynamic temperature control operations, which include three parts: immediate adjustment operation, preheating optimization operation and energy-saving cruise operation.

[0089] The instant adjustment operation is: when the flow sensor detects that the water flow exceeds the preset threshold, the fuzzy-PID composite control algorithm is used to dynamically adjust the power output of the heating device based on the user-set internal target temperature of the water tank, the real-time water inlet temperature and the current water flow.

[0090] The preheating optimization operation is to predict the water usage period and the corresponding hot water demand based on the historical equipment operation status data.

[0091] Before the predicted water usage period begins, the optimal heating start time is calculated based on the current internal temperature of the water tank, the water inlet temperature, the ambient temperature and the predicted hot water demand, and the preheating target temperature is set to 2-3°C higher than the predicted target temperature.

[0092] The energy-saving cruise operation is: when the water flow data is lower than the preset water peak flow data, the water tank temperature is automatically maintained at the preset energy-saving temperature, and the preset energy-saving temperature is dynamically adjusted according to the changes in ambient temperature.

[0093] Specifically, the main control module responds quickly to high flow demands through real-time adjustments to ensure stable water temperature. Preheat optimization predicts peak water usage based on historical data, enabling early heating to prevent temperature fluctuations. Energy-saving cruise control automatically adjusts the temperature during low-flow periods, reducing unnecessary energy consumption. These operations work together to optimize the heating system's responsiveness and efficiency.

[0094] This embodiment uses the main control module to improve the response speed of water temperature control and reduce temperature fluctuations during high flow rates. It also predicts water demand and preheats the water in advance, eliminating user wait times. It also dynamically maintains lower temperatures during low flow periods, reducing overall energy consumption. These benefits are achieved through the dynamic adjustment of the fuzzy-PID composite control algorithm, adaptive energy-saving settings based on ambient temperature, and a historical data-driven prediction mechanism, achieving a balance between energy conservation and user experience.

[0095] In some embodiments of the present application, the LSTM time series model in the cloud service layer is configured to: analyze historical water use data and establish a user water use pattern; based on the user water use pattern, the current date type and the ambient temperature data, predict the water use period, predict the corresponding hot water demand and the target temperature range, and obtain the prediction results; and send the prediction results to the main control module to trigger the preheating optimization operation.

[0096] This embodiment uses an LSTM time series model in the cloud service layer to conduct in-depth analysis of historical water usage data, accurately constructing user water usage patterns. Based on this pattern, combined with the current date type (e.g., weekday, weekend, holiday, etc.) and ambient temperature data, it can more accurately predict water usage time periods, corresponding hot water demand, and target temperature ranges. This provides accurate data support for subsequent preheating optimization operations, meeting users' actual hot water needs at different times and under different environmental conditions.

[0097] The LSTM time series model is also regularly updated, allowing it to dynamically adapt to changes in user habits. For example, changes in water usage times or amounts with the changing seasons, or new water habits formed over time, ensures an accurate understanding of user water usage patterns and ensures the reliability and practicality of predictions.

[0098] Furthermore, the model's prediction results are directly transmitted to the main control module, triggering local preheating optimization operations, forming a complete closed-loop control system. This closed-loop control can quickly respond to the prediction results and adjust preheating operations in a timely manner without excessive human intervention. This improves the system's automation and response efficiency, reduces energy waste, and improves energy efficiency. At the same time, it provides users with a more convenient and comfortable hot water experience, enhancing the overall system's intelligence level and user satisfaction.

[0099] In some embodiments of the present application, the heating device realizes power linear control by adjusting the PWM duty cycle, and compensates for the heat dissipation of the pipeline by increasing the power in the preheating optimization operation.

[0100] In the embodiments of this application, linear power control of the heating device is achieved by adjusting the PWM duty cycle, thereby ensuring the accuracy and stability of the heating process. Furthermore, during preheat optimization, by improving the heat dissipation of the power compensation pipe, heat loss during startup is effectively reduced, thereby improving heating efficiency and response speed, ensuring that the device can quickly reach the set operating temperature, thereby improving overall energy efficiency and operational performance.

[0101] In some embodiments of the present application, the IOT communication module supports updating the fuzzy-PID algorithm parameters and energy-saving cruise temperature logic of the main control module through OTA wireless communication.

[0102] In the embodiments of this application, the introduction of an IoT communication module enables the main control module's fuzzy-PID algorithm parameters and energy-saving cruise temperature logic to be updated via OTA wireless communication. This not only simplifies the device's maintenance and upgrade process, but also enables the device to adjust its control strategy in real time based on actual operating conditions and changes in the external environment, thereby achieving better energy savings and a longer service life. Through this intelligent remote update mechanism, users can enjoy a continuously optimized user experience, while manufacturers can more efficiently iterate products and enhance features.

[0103] The intelligent temperature control method and system of this application realizes dynamic temperature control operation of water heater through the collaborative work of multi-layer structure. The specific use process is as follows:

[0104] The temperature sensor group and flow sensor in the local device layer collect real-time data on the water heater's operating status, including the internal temperature of the water tank, the inlet water temperature, and the water flow rate. This data is regularly uploaded to the cloud server for storage and analysis via an IoT communication module (supporting 4G Cat.1, NB-IoT, and WiFi protocols).

[0105] The cloud service layer uses historical water consumption data and an LSTM time series model to model and predict user water usage patterns. It also uses the ambient temperature API to obtain external weather data. Using this data, the cloud generates control commands for real-time adjustments, preheating optimization, and energy-saving cruise control, and then sends these commands to the main control module.

[0106] Instant adjustment operation: When the flow sensor detects that the water flow exceeds the preset threshold, the main control module uses a fuzzy-PID composite control algorithm to dynamically adjust the power output of the heating device based on the user-set target temperature, real-time water inlet temperature and current water flow, ensuring that the water temperature is stable within the target temperature range of ±1°C.

[0107] Preheating optimization operation: Based on historical water use data, the water use period and hot water demand are predicted. Before the start of the predicted water use period, the optimal heating start time is calculated based on the current water tank internal temperature, water inlet temperature, ambient temperature and predicted demand, and the preheating target temperature is set to 2-3°C higher than the predicted target temperature to compensate for the heat dissipation loss in the pipeline.

[0108] Energy-saving cruise operation: When the water flow rate is lower than the preset peak flow threshold, the main control module maintains the water tank temperature at a preset energy-saving temperature that is dynamically adjusted according to the ambient temperature, thereby reducing energy consumption during off-peak hours.

[0109] The user terminal receives device operating status data and prediction results through the user interaction layer and can remotely modify control instructions. This two-way interaction mechanism improves the user experience and device management capabilities.

[0110] In summary, the intelligent water heater temperature control method and system described in this application utilizes a fuzzy-PID composite control algorithm. This real-time adjustment allows for rapid response to high water demand, keeping water temperature fluctuations within ±1°C of the target temperature. This addresses the lag and low precision of traditional temperature control, improving user comfort. Preheat optimization uses historical water usage data and ambient temperature to preheat and appropriately set the target temperature, avoiding the high energy consumption and long wait times associated with traditional temporary heating. Energy-saving cruise control dynamically adjusts the water tank temperature, reducing inefficient heating energy consumption during off-peak hours and balancing energy conservation with water demand. A prediction mechanism based on an LSTM time series model, combined with date type and ambient temperature, accurately captures user water usage habits and provides personalized hot water supply strategies. Users can view device status in real time and remotely intervene through a terminal, enhancing intelligent device management. The system supports over-the-air (OTA) updates of the main control module's algorithm parameters and logic, ensuring continuous optimization of device performance. Furthermore, the LSTM model is regularly updated to dynamically adapt to changing user habits and maintain high prediction accuracy.

[0111] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

Claims

1. An intelligent temperature control method for a water heater, characterized in that: Including steps: Collecting the internal temperature of the water heater tank, the water inlet temperature, and the water flow rate as device operating status data, and uploading the device operating status data to the cloud server; The cloud server or user terminal generates a control instruction based on the device operation status data and sends it to the water heater; The control instructions include executing a dynamic temperature control operation, and the dynamic temperature control operation includes: an immediate adjustment operation; The instant adjustment operation steps are: When it is detected that the water flow rate exceeds a preset threshold, the fuzzy-PID composite control algorithm is used to dynamically adjust the power output of the heating device based on the user-set internal target temperature of the water tank, the real-time water inlet temperature and the current water flow rate.

2. The intelligent temperature control method for a water heater according to claim 1, characterized in that: The dynamic temperature control operation also includes a preheating optimization operation, and the preheating optimization operation steps are: Predicting water use periods and corresponding hot water demand based on historically recorded operating status data of the equipment; Before the predicted water usage period begins, the optimal heating start time is calculated based on the current water tank internal temperature, water inlet temperature, ambient temperature and predicted hot water demand, and the preheating target temperature is set to 2-3°C higher than the predicted target temperature.

3. The intelligent temperature control method for a water heater according to claim 2, characterized in that: The step of predicting the water use period and the corresponding hot water demand based on the historically recorded equipment operating status data includes: Analyze historical water consumption data through the cloud server and establish user water consumption patterns using an LSTM time series model; Inputting the user's water use pattern, current date type, and ambient temperature data into the LSTM time series model; Determine a specific period in which the water flow output by the LSTM time series model is higher than the preset threshold as a predicted water use period; The water flow corresponding to the predicted water use period output by the LSTM time series model is used as the predicted hot water demand.

4. The intelligent temperature control method for a water heater according to claim 1, characterized in that: The dynamic temperature control operation also includes an energy-saving cruise operation, and the energy-saving cruise operation steps are: When the water flow data is lower than the preset water peak flow data, the water tank temperature is automatically maintained at the preset energy-saving temperature, and the preset energy-saving temperature is dynamically adjusted according to the change of ambient temperature.

5. The intelligent temperature control method for a water heater according to claim 1, characterized in that: The water temperature control accuracy range of the instant adjustment operation is within the range of ±1°C of the target temperature inside the water tank.

6. An intelligent temperature control system for a water heater, characterized in that: The intelligent temperature control method for a water heater according to any one of claims 1 to 5 above comprises: a local device layer, a cloud service layer, and a user interaction layer; The local device layer includes: a temperature sensor group, a flow sensor, a heating device, a main control module and an IOT communication module; The temperature sensor group is configured to collect the temperature of the core area of ​​the water heater tank and the water inlet in real time; The flow sensor is installed on the water outlet pipe and is configured to detect the real-time water flow; The heating device adopts a resistance heating tube structure and is configured to support power output adjustment through PWM duty cycle; The main control module is configured to perform dynamic temperature control operations; The IOT communication module is configured to support 4GCat.1, NB-IoT and WiFi communication protocols; The cloud service layer is configured to store historical water consumption data, run the LSTM time series model to generate forecast instructions, and obtain external weather data through the ambient temperature API interface; The user interaction layer includes a user terminal configured to receive device operation status data and issue control instructions; The main control module establishes a two-way data connection with the cloud service layer through the IOT communication module, and the cloud service layer pushes the prediction results and device operation status data to the user interaction layer.

7. The intelligent temperature control system for water heater according to claim 6, characterized in that: The main control module is configured to perform dynamic temperature control operations, including: instant adjustment operation, preheating optimization operation and energy-saving cruise operation; The instant adjustment operation is as follows: when the flow sensor detects that the water flow exceeds a preset threshold, the power output of the heating device is dynamically adjusted using a fuzzy-PID composite control algorithm based on the user-set internal target temperature of the water tank, the real-time water inlet temperature, and the current water flow; The preheating optimization operation is: predicting the water use period and the corresponding hot water demand based on the historical record of the equipment operation status data; Before the predicted water usage period begins, the optimal heating start time is calculated based on the current water tank internal temperature, water inlet temperature, ambient temperature, and predicted hot water demand, and the preheating target temperature is set to 2-3°C higher than the predicted target temperature; The energy-saving cruise operation is: when the water flow data is lower than the preset water peak flow data, the water tank temperature is automatically maintained at a preset energy-saving temperature, and the preset energy-saving temperature is dynamically adjusted according to the change of ambient temperature.

8. The intelligent temperature control system for water heater according to claim 7, characterized in that: The LSTM time series model configuration in the cloud service layer is: Analyze historical water use data and establish user water use patterns; Based on the user's water use pattern, current date type and ambient temperature data, predict the water use period, predict the corresponding hot water demand and target temperature range, and obtain a prediction structure; The prediction result is sent to the main control module to trigger the preheating optimization operation.

9. The intelligent temperature control system for water heater according to claim 7, characterized in that: The heating device realizes power linear control by adjusting the PWM duty cycle, and compensates for pipeline heat dissipation by increasing power during the preheating optimization operation.

10. The intelligent temperature control system for water heater according to claim 6, characterized in that: The IOT communication module supports updating the fuzzy-PID algorithm parameters and energy-saving cruise temperature logic of the main control module through OTA wireless communication.

Images