Heating control system and method of drinking water heater

Abstract

The invention provides a heating control system and method for a drinking water heater, and relates to the technical field of non-electrical variable control and regulation, and the system achieves the dynamic optimization control of the heating power and the internal pressure compensation power through the cooperative work of a data collection and analysis module, an evaluation model construction module, a weight selection module and other modules. The system not only can collect water quality and system operation data in real time and accurately predict the scaling rate, but also can intelligently adjust control parameters according to a prediction result, so that the balance of energy conservation and efficient scaling control is realized in different scaling states.

Description

Technical Field

[0001] The present invention relates to the technical field of control and regulation of non - electrical variables, and particularly to a heating control system and method for a drinking water heater. Background Art

[0002] In high - altitude and low - pressure areas, due to the relatively low environmental pressure, a drinking water heater needs to increase the pressure in the system through a pressure compensation unit to reach the boiling point of water. However, the scaling phenomenon may significantly affect the system performance. The boiling point of water decreases in a low - pressure environment, resulting in increased energy consumption and extended heating time during the heating process. Scaling reduces the heat conduction efficiency of the heating element, and at the same time, the deposition in the pipeline increases the flow resistance, further exacerbating the pressure instability of the system. This situation will cause the pressure compensation unit to frequently adjust to maintain the target pressure, increasing the operation burden and wear of the equipment, thus significantly increasing the operation cost and shortening the service life of the equipment; In the prior art, the publication number is CN108388288B, and the name is an intelligent heating system and heating method based on big data analysis of time periods, including a controller, a drinking water conduit, and a heating tank. A part of the pipe body of the drinking water conduit extends into the heating tank. The heating tank is filled with a heat - conducting agent. The heating tank is provided with a temperature detection device for detecting the temperature of the heat - conducting agent and a heating device for heating the heat - conducting agent. The controller includes: an acquisition module for acquiring the temperature detection value output by the temperature detection device; a monitoring module for judging whether the temperature detection value is less than a temperature preset value; and an execution module for controlling the heating device to start to heat the heat - conducting agent to a rated temperature value and then turn off when the temperature detection value is less than the temperature preset value.

[0003] When the prior art deals with the scaling problem during the heating process of drinking water in a low - pressure environment, it mainly relies on the pressure compensation unit to maintain the pressure in the system to ensure that the water can reach an appropriate boiling point. However, this method has significant deficiencies: The formation of scaling continuously reduces the heat conduction efficiency of the heating element, forcing the pressure compensation unit to frequently adjust the pressure to maintain the target pressure, resulting in an increased operation burden and wear of the equipment, and further shortening the service life of the equipment and increasing the maintenance cost; Traditional control systems often lack accurate monitoring and prediction of the real - time scaling rate, and cannot dynamically optimize control parameters according to changes in water quality and operating conditions, resulting in low energy utilization efficiency; There is an urgent need for an intelligent control system that can monitor in real time and dynamically adjust the heating power and internal pressure compensation power to effectively inhibit the occurrence of scaling, optimize energy utilization, and improve the operation stability and equipment life of the system.

[0004] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The object of the present invention is to provide a heating control system and method for a drinking water heater to solve the problems raised in the above background art.

[0006] To achieve the above object, the present invention provides the following technical solutions: A heating control system for a drinking water heater specifically includes: A data acquisition and analysis module: used to collect in real time the mineral ion concentration index of the water to be heated flowing into the drinking water heater, the temperature data of multiple hot zones on the surface of the heating element in the drinking water heater, and the pressure compensation index output by the internal pressure compensation unit; Based on the mineral ion concentration index, calculate the real-time scaling rate; Based on the temperature data of multiple hot zones, calculate the instantaneous heat transfer temperature deviation between each hot zone; An evaluation model construction module: used to input the instantaneous heat transfer temperature deviation, the mineral ion concentration index, and the pressure compensation index as independent variables and output the real-time scaling rate of the water to be heated as the dependent variable to construct a scaling state evaluation model based on regression analysis to evaluate the scaling state of the drinking water heater in real time; A predicted scaling rate set determination module: used to, on the basis that the mineral ion concentration index in the water to be heated is a constant value, make different combinations and adjustments to the instantaneous heat transfer temperature deviation and the pressure compensation index within their respective regulation ranges, and input these combinations into the scaling state evaluation model, and the scaling state evaluation model generates a predicted scaling rate set for these combinations; An optimal screening module: used to determine the mineral ion concentration index in the current water to be heated and generate a real-time predicted scaling rate set according to the predicted scaling rate set determination module; Screen out at least three lowest real-time predicted scaling rates from the real-time predicted scaling rate set and match the corresponding instantaneous heat transfer temperature deviation and pressure compensation index; A control parameter generation module: used to generate control adjustment parameters for the heating power of the heating element and the pressurization power of the internal pressure compensation unit corresponding to each combination according to the at least three combinations of the instantaneous heat transfer temperature deviation and the pressure compensation index selected; A weight selection module: used to set a judgment threshold for the real-time predicted scaling rate and assign corresponding selection weights to the heating power of the heating element and the pressurization power of the internal pressure compensation unit based on the comparison result of the judgment threshold; Determine the control adjustment parameter with the highest matching degree with the selection weight from the three groups of control adjustment parameters according to the selection weight.

[0007] A heating control method for a drinking water heater, the method being used to execute the heating control system of the drinking water heater, comprising: Step S1: Real-time collect the mineral ion concentration index of the water to be heated flowing into the drinking water heater, the temperature data of multiple hot zones on the surface of the heating element in the drinking water heater, and the pressure compensation index output by the internal pressure compensation unit; Calculate the real-time scaling rate based on the mineral ion concentration index; Calculate the instantaneous heat transfer temperature deviation between each hot zone based on the temperature data of multiple hot zones; Step S2: Use the instantaneous heat transfer temperature deviation, the mineral ion concentration index, and the pressure compensation index as independent variables, and the real-time scaling rate of the water to be heated as the dependent variable output, and construct a scaling state evaluation model based on regression analysis to evaluate the scaling state of the drinking water heater in real time; Step S3: On the basis that the mineral ion concentration index in the water to be heated is a constant value, make different combinations of adjustments to the instantaneous heat transfer temperature deviation and the pressure compensation index within their respective regulation ranges, and input these combinations into the scaling state evaluation model, and the scaling state evaluation model generates a set of predicted scaling rates for these combinations; Step S4: Determine the mineral ion concentration index of the current water to be heated, and generate a set of real-time predicted scaling rates according to the predicted scaling rate set determination module; Screen out at least three lowest real-time predicted scaling rates from the set of real-time predicted scaling rates, and match the corresponding instantaneous heat transfer temperature deviation and pressure compensation index; Step S5: Generate control adjustment parameters for the heating power of the heating element and the pressurization power of the internal pressure compensation unit corresponding to each combination according to the at least three combinations of the instantaneous heat transfer temperature deviation and the pressure compensation index screened out; Step S6: Set a judgment threshold for the real-time predicted scaling rate, and based on the comparison result of the judgment threshold, assign corresponding selection weights to the heating power of the heating element and the pressurization power of the internal pressure compensation unit; Determine the control adjustment parameter with the highest matching degree with the selection weight from the three groups of control adjustment parameters according to the selection weight.

[0008] Compared with the prior art, the beneficial effects of the present invention are as follows: Through the collaborative work of multiple modules such as the data acquisition and analysis module, the evaluation model construction module, and the weight selection module, dynamic optimization control of the heating power and the internal pressure compensation power is achieved; This system can not only collect water quality and system operation data in real time, accurately predict the scaling rate, but also intelligently adjust control parameters according to the prediction results, so as to achieve a balance between energy saving and efficient scaling control under different scaling states; It has significant advantages in the accuracy of scaling control and the energy utilization efficiency, can effectively extend the equipment life, reduce the operation cost, and improve the overall performance and reliability of the drinking water heater in a low-pressure environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 It is a schematic diagram of the overall system module of the present invention; Figure 2 It is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0010] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the following further details the present invention in combination with specific embodiments.

[0011] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those of ordinary skill in the field to which the present invention belongs. The "first", "second", and similar terms used in the present invention do not indicate any order, quantity, or importance, but are only used to distinguish different components. The terms such as "comprising" or "including" mean that the elements or objects appearing before this term cover the elements or objects listed after this term and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left", "right", etc. are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly. Embodiment 1

[0012] Please refer to Figure 1 , the present invention provides a technical solution: A heating control system for a drinking water heater, which is applied to a drinking water heater including an internal pressure compensation unit, specifically includes: A data acquisition and analysis module: used to collect in real time the mineral ion concentration index of the water to be heated flowing into the drinking water heater, the temperature data of multiple hot zones on the surface of the heating element in the drinking water heater, and the pressure compensation index output by the internal pressure compensation unit; Further explanation: The internal pressure compensation unit is used to increase the pressure inside the heating chamber corresponding to the heating element in the high-altitude low-pressure area to ensure that the water to be heated can reach the target boiling point; It should be noted that: A high-precision pressure sensor is installed at the pressure output end of the internal pressure compensation unit; the pressure sensor is directly connected to the heating chamber and is located in the section of the output pipeline of the pressure compensation unit closest to the heating chamber to ensure the accurate reflection of real-time pressure data; The following are the detailed operation steps and technical explanations of the internal pressure compensation unit: The internal pressure compensation unit adopts dynamic pressure regulation technology to make up for the decrease in boiling point in the high-altitude low-pressure environment by increasing the pressure inside the heating chamber; the pressure output from the internal pressure compensation unit directly affects the heat transfer efficiency inside the heating chamber and the setting of the water boiling point temperature; The pressure compensation unit calibrates the corresponding relationship between the output pressure and the target boiling point of the water to be heated, and the calibration relationship is based on the following formula: ; Where, is the target boiling point after pressure compensation, is the standard temperature of the boiling point at normal pressure, is the pressure increment output by the pressure compensation unit, and is characterized as the pressure compensation index; is the calibration coefficient related to the thermodynamic properties of water; is the real-time air pressure value of the current environment, is the standard pressure under atmospheric pressure; The beneficial effects of this embodiment are as follows: Traditional drinking water heating equipment usually ignores the influence of the high-altitude low-pressure environment on the heating efficiency, while this solution realizes the optimization of adaptation to special environments through the precise control of the internal pressure compensation unit, significantly improving the application range of the heating system.

[0013] By analyzing the conductivity data of the water to be heated to deduce the mineral ion concentration index, the specific deduction steps are as follows: The conductivity data is measured and obtained through a conductivity sensor; the conductivity sensor is installed at the water inlet of the drinking water heater to measure the conductivity of the water to be heated in real time, and the acquisition frequency is set to once per minute. The original conductivity data collected is converted into a digital signal through an analog-digital conversion module; subsequently, using a pre-calibrated calibration curve, the conductivity value is converted into a mineral ion concentration index. 1.1) Select typical water quality samples for experimental calibration: From the water sources actually used by the drinking water heater, select several representative samples to ensure that these samples cover the common mineral ion concentration ranges; the typical sample ranges include: Surface water: river water, lake water; Groundwater: Deep well water; Treated water: Tap water, purified water; Meanwhile, a series of concentration gradients (10 mg / L, 50 mg / L, 100 mg / L...) are set according to the samples. These samples are professionally measured for their mineral ion concentrations by a high-precision analysis laboratory. In this embodiment, ICP-MS or chemical titration method is used for measurement to obtain accurate mineral ion concentration indicators, and the standardized data is used as a reference; 1.2) Measure the conductivity of the water sample: Place the water sample whose mineral ion concentration has been measured in a calibration experimental device, and use a conductivity sensor consistent with that in the drinking water heater to measure the conductivity value of each experimental water sample, ensuring that the collected conductivity data is consistent with the original sensor signal collected in the actual device; Instrument calibration: Before the experiment, accurately calibrate the conductivity sensor to reduce noise interference and drift error; the reference standard is calibrated using a KCl experimental solution; the KCl experimental solution is used to characterize the standard conductivity values at different concentrations; Measure multiple water samples: Measure the conductivity of each experimental water sample one by one, record the mineral ion concentration indicators (mg / L) and the corresponding conductivity values (μS / cm) of different water samples; and record the mineral ion concentration indicator as ; Record the conductivity value as E; 1.3) Construct a calibration curve: The mineral ion concentration indicator and the conductivity value E are fitted into a calibration curve model according to the following relationship; ; Among them, the relationship function is a linear relationship or a non-linear distribution, and the fitting model is selected according to the actual data; common fitting models are: If the conductivity is proportional to the mineral ion concentration indicator, the following linear fitting is used: ; is the corresponding slope, representing the coefficient for converting unit conductivity to the mineral ion concentration indicator; is the intercept; If the conductivity and the mineral ion concentration indicator are non-proportional, quadratic or cubic polynomial fitting is used: ; Among them, are the coefficients fitted according to the experimental data; When there is a mutation between the low mineral ion concentration indicator and the high mineral ion concentration indicator within the coverage range of the conductivity, the calibration curve is segmented and linearly or non-linearly fitted respectively; Finally, save the calibration curve form and fitting coefficients in the internal database of the device as the conversion model during operation; 1.4) Real-time conversion of conductivity value to mineral ion concentration index: Retrieve the calibration curve model: In the data acquisition and analysis module, according to the pre-calibrated and stored calibration curve model , load the corresponding fitting model type, where the fitting model type includes linear, quadratic, or piecewise models, as well as fitting parameters.

[0014] Substitute the conductivity value E collected from the water to be heated into the calibration curve model for calculation to obtain the real-time mineral ion concentration index ; Re-calibrate the device through the user interface or external device, input new water sample ion concentration and conductivity data, and update the calibration model; When it is detected that the conductivity value E deviates from the applicable range of the existing calibration curve for a long time, the device will give a priority prompt to the user.

[0015] Automatically integrate the data of multiple offline manual calibrations into a cumulative curve and dynamically update the default calibration model of the device.

[0016] The pre-calibrated calibration curve is established based on experimental water samples, truly reflects the water quality environment faced by the drinking water heater, and the data is reliable; Through the adaptive calibration function, the device can continuously optimize the calibration curve to cope with water quality changes in different environments.

[0017] In summary, through the mineral ion concentration calibration curve established by pre-experimental calibration, the device can stably and effectively achieve the real-time calculation of the mineral ion concentration index of the water to be heated, laying a solid data foundation for the evaluation of the scaling rate; The beneficial effects of this embodiment of "deriving the mineral ion concentration index by analyzing the conductivity data of the water to be heated" are described as follows: There are the following problems in directly measuring the mineral ion concentration index of the water to be heated: Directly measuring the mineral ion concentration usually requires professional experimental equipment, such as high-precision instruments, reagents, etc., and requires trained personnel to operate; such measurement methods require more reagents and consumables.

[0018] Directly measuring the mineral ion concentration takes a certain amount of time, ranging from a few minutes to several hours, and does not have the ability of dynamic measurement and real-time response; The solution of deriving the mineral ion concentration index through conductivity data has significant advantages in the heating control system of the drinking water heater, including: The sensor has a simple structure, low cost, small volume, and is easy to integrate.

[0019] It has strong real-time performance and supports dynamic monitoring and instant feedback.

[0020] It has high adaptability and can flexibly adjust based on the calibration curve to support various water qualities.

[0021] It has high economy, good user experience, and is easy to maintain.

[0022] Further explanation: Calculate the real-time scaling rate based on the mineral ion concentration index; Determine the experimental calibration coefficient of the real-time scaling rate ; Experimental calibration coefficient The specific determination steps of the Determine that the heating element in the drinking water heater works in the heating cavity; Prepare water samples to be heated containing different types of mineral ions: Calcium carbonate type water quality (CaCO 3 ): Commonly found in groundwater or hard water; Calcium sulfate type water quality (CaSO 4 ): Commonly found in some tap water and industrial water; Magnesium-containing water quality (Mg²⁺): The scaling situation of the composite of magnesium ions and calcium ions needs to be considered.

[0023] Mixed composition water quality: Such as containing carbonate (CO 3 ²⁻), sulfate (SO 4 ²⁻), magnesium ions (Mg²⁺), etc. at the same time.

[0024] The mineral ion concentration of each water sample is selected according to the actual working conditions, such as 100mg / L, 200mg / L, 500mg / L, 1000mg / L, etc., increasing gradually.

[0025] Prepare the above various simulated water samples and simultaneously detect their mineral ion concentration indicators ; Load a pre-weighed heating element in the experimental simulation heating cavity.

[0026] The heating element needs to be completely clean and record the initial mass .

[0027] The material of the heating element is the same as that of the actual drinking water heater used; Select a typical heating temperature: The boiling point of ordinary drinking water is 100°C; Running time: The continuous heating time of each experiment is 2 hours, simulating the key stage of the actual cumulative scaling process; Pressure regulation: Simulate the conditions of low pressure 1atm and high pressure 2atm in different experimental groups to observe the influence of environmental pressure on the scaling rate.

[0028] When heating the heating chamber, continuously circulate the water sample to be measured, and simultaneously calculate the mineral ion concentration index of the water to be heated in real time. .

[0029] After heating is completed and the heating element has cooled to room temperature, gently rinse with deionized water to remove loose attachments.

[0030] Weigh the final mass of the heating element using a precision electronic balance. ; Calculate the scale formation amount through the following formula : ; Based on the scale formation amount obtained from the experiment , calculate the scale formation rate per hour , expressed as the scale formation mass per unit time: ; Where t is the experimental running time, and in this embodiment t = 2h; 2h represents 2 hours; Establish a functional relationship between the scale formation rate obtained from the experiment and the corresponding mineral ion concentration index : ; Fit the experimental data by linear regression method to obtain the value of the experimental calibration coefficient .

[0031] This embodiment gives the following example: If , the experiment measures ; then: ; Table 1 Determination of experimental calibration coefficient: Water quality type Main components Mineral ion concentration index range (mg / L) Flow rate (L / min) Temperature (°C) Experimental calibration coefficient <![CDATA[Hard water (CaCO 3 type)]]> <![CDATA[Ca²⁺,CO 3 ²⁻]]> 50–500 0.5 100 0.005 <![CDATA[Sulfate type (CaSO 4 type)]]> <![CDATA[Ca²⁺,SO 4 ²⁻]]> 100–500 0.5 100 0.007 Mixed hard water <![CDATA[Ca²⁺,Mg²⁺,CO 3 ²⁻]]> 200–600 0.4 100 0.006 High-magnesium water quality <![CDATA[Mg²⁺,CO 3 ²⁻]]> 50–400 0.3 100 0.0045 Magnesium sulfate water quality <![CDATA[Mg²⁺,SO 4 ²⁻]]> 100–400 0.5 100 0.0055 Composite mineral water quality <![CDATA[Ca²⁺,Mg²⁺,SO 4 ²⁻,CO 3 ²⁻]]> 100–500 0.6 100 0.0062 The heating control system stores a predefined scale formation rate calculation formula: ; Read the corresponding experimental calibration coefficient from the internal configuration file in real time according to the mineral ion type of the water to be heated currently ; Substitute the mineral ion concentration index calculated in real time into the scale formation rate calculation formula to calculate the real-time scale formation rate ; Achieve flexible adaptation to different water qualities through automatic calibration , with stronger adaptability compared to the traditional fixed parameter method.

[0032] High real-time performance and accuracy: By collecting and processing conductivity data in real time and combining with the calibration curve model and experimental calibration coefficients, the real-time scaling rate can be calculated quickly and accurately.

[0033] Based on the temperature data of multiple hot zones, calculate the instantaneous heat transfer temperature deviation between each hot zone; Further explanation: The temperature data of each hot zone on the surface of the heating element are collected in real time by a multi-point infrared temperature sensor. After denoising and calibration processing, the temperature value of each hot zone is obtained , where n represents the total number of hot zones on the surface of the heating element; Use the following formula to calculate the average temperature of multiple hot zones on the surface of the heating element : ; Among them, is the temperature value of hot zone i, and n is the total number of hot zones; Calculate the temperature deviation of hot zone i , and the specific formula is: ; Define the calculation formula of the instantaneous heat transfer temperature deviation as follows: ; Among them, is the instantaneous heat transfer temperature deviation between each hot zone; represents the absolute value of the temperature deviation of hot zone i; it is used to calculate the absolute average value of the deviation to avoid the cancellation of positive and negative temperatures inside; The larger the value, the greater the deviation degree of the heat transfer consistency on the surface of the heating element.

[0034] Evaluation model construction module: Used to input the instantaneous heat transfer temperature deviation, mineral ion concentration index, and pressure compensation index as independent variables, and output the real-time scaling rate of the water to be heated as the dependent variable, to construct a scaling state evaluation model based on regression analysis to evaluate the scaling state of the drinking water heater in real time; Further explanation: Obtain the following real-time data from the data acquisition and analysis module: Instantaneous heat transfer temperature deviation ; Mineral ion concentration index ; Pressure compensation index ; Real-time scaling rate ; Establish a structured database, store the above four types of data in real time according to the time series, and perform data preprocessing on these data to obtain the preprocessed data set; It should be noted that in this embodiment, the relational database management system (RDBMS) technology, specifically MySQL or PostgreSQL, is selected to construct the structured database; The preprocessed dataset includes independent variables which are standardized. The Z-score standardization is adopted to eliminate the influence of different dimensions on model training; Based on the preprocessed dataset, calculate the Pearson correlation coefficient between the independent variable and the dependent variable ; Based on the calculated Pearson correlation coefficient, determine the influence degree of each independent variable on the real-time fouling rate , and sort according to the absolute value of the Pearson correlation coefficient to identify the main driving factors; it should be noted that in this embodiment, the independent variable with the absolute value of the Pearson correlation coefficient greater than 0.6 is set as the main driving factor; Divide the preprocessed dataset into a training set (80%) and a test set (20%) according to the time series to ensure that the model is not affected by future data during training; Furthermore: Use the training set data to fit a multiple linear regression model and establish the linear relationship between the independent variable and the dependent variable : ; where is the intercept and is the regression coefficient.

[0035] Optimize the hyperparameters using cross-validation to ensure the stability and generalization ability of the model on different datasets; Furthermore: Apply the trained regression model on the test set to predict the real-time fouling rate ; Use the mean squared error (MSE), root mean squared error (RMSE), and coefficient of determination as model performance evaluation indicators to comprehensively measure the prediction accuracy and interpretability of the model; Calculate the MSE, RMSE, and between the predicted value and the actual value to evaluate the accuracy of the model.

[0036] Export the trained multiple linear regression model into a format suitable for embedded systems, including ONNX and PMML, to ensure efficient deployment in the heating control system.

[0037] The predicted fouling rate set determination module: Based on the mineral ion concentration index in the water to be heated being a constant value, different combinations of the instant heat transfer temperature deviation and the pressure compensation index are adjusted within their respective control ranges, and these combinations are input into the fouling state evaluation model, and the fouling state evaluation model generates a set of predicted fouling rates for these combinations; Further explanation: Determine the pressure compensation index Regulation range: Set the standard atmospheric pressure to 101.3 kPa as a reference benchmark; Through the atmospheric pressure sensor, real-time monitor the real-time air pressure value of the current environment ; Based on the calculation formula ; Based on the minimum and maximum pressure capacity output values of the internal pressure compensation unit, set the regulation range of the pressure compensation index to be ; is the lower limit value of the pressure compensation index; is the upper limit value of the pressure compensation index; According to the equipment specification manual, set the minimum output pressure value and the maximum output pressure value ; Set the regulation range of the instant heat transfer temperature deviation to be ; Obtain the maximum heating power and the minimum heating power ; is the lower limit value of the instant heat transfer temperature deviation; Set it to the instant heat transfer temperature deviation of the heating element at the minimum heating power; ensure that the heating efficiency is not lower than the basic requirement; is the upper limit value of the instant heat transfer temperature deviation; Set it to the instant heat transfer temperature deviation of the heating element at the maximum heating power; Establish a linear or non-linear relationship between the heating power and in order to precisely adjust at different power settings; Set and step sizes to be and ; Within the range from to , iterate to generate all values with step size ; Within the range from to , iterate to generate all values with step size Value; Generate all combinations using the Cartesian product, ensuring that each pair of combinations is within its respective regulation range; Remove obviously unreasonable or extreme combinations through pre-screening to ensure that the generated combination set is both comprehensive and safe; Input the combinations into the fouling state evaluation model and generate a set of predicted fouling rates; the specific implementation steps are as follows: Set the mineral ion concentration index to a constant value to ensure the consistency of the model input; For each combination, construct an input vector containing : ; Load the trained regression model parameters: For each input vector, apply the regression formula to calculate the predicted fouling rate: ; Store the value corresponding to each combination in the set of predicted fouling rates.

[0038] This technical solution systematically realizes the generation of an efficient and accurate set of predicted fouling rates based on the combination adjustment of under the condition of a fixed mineral ion concentration index by refining each operation step of the predicted fouling rate set determination module; ensuring that the system can maintain an intelligent and real-time fouling state evaluation ability under changing environments and working conditions.

[0039] Optimal screening module: used to determine the mineral ion concentration index in the current water to be heated, and generate a real-time predicted fouling rate set according to the predicted fouling rate set determination module; Screen out at least three of the lowest real-time predicted fouling rates from the real-time predicted fouling rate set, and match the corresponding instantaneous heat transfer temperature deviation and pressure compensation index; Further explanation: Transmit the mineral ion concentration index obtained in real time in the current water to be heated to the predicted fouling rate set determination module; The predicted fouling rate set determination module generates a corresponding real-time predicted fouling rate set according to the input , and combinations; The real-time predicted fouling rate set contains data records for each group ; Sort all the values in the real-time predicted fouling rate set in ascending order to ensure that the lowest real-time fouling rate is at the front; Select at least three of the lowest values from the sorted set of real-time predicted fouling rates to form an optimal candidate set ; Extract the corresponding combinations from the selected lowest real-time predicted fouling rates to form the following optimal control parameter set .

[0040] The beneficial effects of this embodiment are as follows: An efficient sorting and screening algorithm is adopted to ensure the rapid and accurate screening of the lowest fouling rate combinations in a large-scale dataset, improving the system's response speed and prediction accuracy.

[0041] The optimal screening module is closely integrated with the predicted fouling rate set determination module and the heating control system to form an intelligent closed-loop control system, significantly improving the overall intelligence level and operating efficiency of the system.

[0042] Control parameter generation module: used to generate control adjustment parameters for the heating power of the heating element and the pressurization power of the internal pressure compensation unit corresponding to each combination according to at least three combinations of instant heat transfer temperature deviation and pressure compensation indicators selected; Further explanation: establish a mapping relationship model between the heating power of the heating element and the instant heat transfer temperature deviation to generate the heating power of the corresponding heating element at different values ; Based on experimental data, use linear regression or non-linear fitting methods to establish the mathematical relationship model between and : ; where is the fitting parameter; Use independent test data to verify the accuracy of the mapping model to ensure that can accurately reflect the changes of ; Establish a mapping relationship model between the pressurization power in the internal pressure compensation unit and the pressure compensation indicator to generate the pressurization power of the internal pressure compensation unit at different values ; Specifically establish the mathematical relationship model between and : ; where is the fitting parameter; Use independent test data to verify the accuracy of the mapping model to ensure that Can accurately reflect of the change; Any combination in the optimal control parameter set is denoted as , and using the mapping relationship model established above, calculate the corresponding ; ; Among them , j is in the optimal control parameter set index of the combination; successively represent the corresponding combinations in the following optimal control parameter set: ; For each group of corresponding store as the following control adjustment parameter set: .

[0043] Weight selection module: used to set the judgment threshold for the real-time predicted scaling rate, and based on the comparison result of the judgment threshold, allocate corresponding selection weights to the heating power of the heating element and the pressurization power of the internal pressure compensation unit; According to the selection weights, determine the control adjustment parameter with the highest matching degree with the selection weights from the three groups of control adjustment parameters.

[0044] Further explanation: Analyze the historical data of system operation to determine the real-time predicted scaling rate normal range and abnormal range; Based on the statistical analysis result, set the judgment threshold for the real-time predicted scaling rate as ; In this embodiment, is set as the 95th percentile of the historical data to ensure that the normal and abnormal scaling rates can be effectively distinguished; Specifically determined by the entropy weight method; Under different working conditions, verify the effectiveness of through simulation operation to ensure that it can accurately reflect the scaling state of the actual system; The weight allocation ratio value between the heating power of the heating element and the pressurization power of the internal pressure compensation unit is ; When , preferentially reduce the heating power , and the weight allocation ratio value q1 is ; This embodiment sets ; The above settings have the following advantages: Energy conservation: The direct effect of reducing the heating power is that when the scaling rate is within a safe range, reducing the heating power can reduce energy consumption and achieve the energy-saving goal; this not only helps to reduce the operating cost but also meets the requirements of environmental protection.

[0045] Controlling temperature rise: Reducing the risk of overheating, reducing the heating power helps to control the temperature in the heating chamber and prevent the aggravation of mineral precipitation and scaling due to excessive temperature.

[0046] Extending equipment life: Reducing equipment wear, reducing the heating power not only saves energy but also reduces the working load of the heating element, extends the service life of the equipment, and reduces the maintenance cost.

[0047] When priority is given to increasing the pressurization power of the internal pressure compensation unit , and the weight distribution ratio value q2 is ; q1 and q2 are determined by the entropy weight method; The above settings have the following advantages: Increasing the boiling point: Delaying mineral precipitation, increasing the air pressure in the heating chamber will increase the boiling point of water, so that water remains liquid at a higher temperature. This helps to delay the precipitation of minerals and the formation of scaling, thus effectively inhibiting the scaling rate; Optimizing heat transfer efficiency: Enhancing the heat transfer process, a higher internal air pressure can improve the heat transfer efficiency in the heating chamber, making the heat more evenly distributed, reducing local overheating, and reducing the risk of scaling.

[0048] Controlling scaling characteristics: Changing the mineral precipitation dynamics, by adjusting the internal air pressure, the precipitation rate and precipitation mode of minerals in the heating chamber can be changed, reducing the formation of dense scaling, which is convenient for subsequent cleaning and maintenance.

[0049] This embodiment sets ; and the corresponding weights are determined by the entropy weight method; For each group of control adjustment parameters , calculate the matching degree with the current weight distribution : ; Select the control adjustment parameter with the largest value from ; Transmit the largest control adjustment parameter to the heating control system and the internal pressure compensation unit to guide the real-time adjustment of heating power and pressurization power. Embodiment 2

[0050] In this embodiment, through experiments, it is verified that in the weight selection module, when , the heating power is preferentially reduced; while when , the pressurization power of the internal pressure compensation unit is preferentially increased, thereby effectively controlling the scaling rate and improving the operation efficiency of the system. The experimental design covers the influence of the adjustment of the heating power and the pressurization power of the internal pressure compensation on the system performance under different scaling rates. The specific steps are as follows: The experimental equipment includes a standardized drinking water heating system, equipped with a high-precision mineral ion concentration sensor, a heating element, an internal pressure compensation unit, and a data acquisition and control system. The experimental water sample uses natural water, which is pretreated to ensure the consistency of water quality. Two main control parameters are set in the experiment: the heating power (unit: kilowatt, kW) and the pressurization power of the internal pressure compensation unit (unit: kilowatt, kW). The real-time predicted scaling rate (unit: mg / L⋅h) is used as the main monitoring index, and it is predicted and calculated through real-time sensor data.

[0051] Before the experiment starts, all sensors are calibrated to ensure the accuracy of data acquisition. When the heating system is in the non-powered state, the initial internal air pressure and the initial temperature are recorded.

[0052] By analyzing historical data and literature, the scaling rate judgment threshold is determined to be 100 mg / L⋅h.

[0053] The experiment is divided into two main stages: Stage 1: Real-time prediction of the scaling rate ; In this stage, by reducing the heating power , the influence on the scaling rate and system performance is observed. Three different reduction amplitudes (-10%, -20%, -30%) of the heating power are set, and the corresponding pressurization power of the internal pressure compensation unit and the real-time predicted scaling rate are recorded.

[0054] Stage 2: Real-time prediction of the scaling rate ; In this stage, by increasing the pressurization power of the internal pressure compensation unit , the scaling rate is controlled and reduced. Three different increase amplitudes (+10%, +20%, +30%) of the internal pressure compensation pressurization power are set, and the corresponding heating power and the real-time predicted scaling rate are recorded.

[0055] After each parameter adjustment, the system runs for 2 hours. After stabilization, the average scaling rate data is collected. At the same time, the actual values of the heating power and the pressurization power of the internal pressure compensation are recorded to ensure the accuracy and repeatability of the data.

[0056] The collected data is organized into a table to analyze the effects of different control parameter adjustments on the scaling rate and system performance. Through comparative analysis, the rationality and effectiveness of the control logic are verified.

[0057] According to the experimental results, the algorithms of the control parameter generation module and the weight selection module are optimized to ensure that the scaling rate can be flexibly and efficiently controlled in practical applications, improving the system operation efficiency and equipment life.

[0058] The following table records the heating power , the pressurization power of the internal pressure compensation unit , the real-time predicted scaling rate , and the experimental data of the total system energy consumption (unit: kilowatt-hour, kWh) under different control parameter adjustments.

[0059] Table 2 Research on the weight selection module: Parameter name Heating power (kW) Internal pressure compensation pressurization power (kW) Scaling rate (mg / L⋅h) Total system energy consumption (kWh) Experiment 1 - Reduce by 10% 9 5 85 14 Experiment 2 - Reduce by 20% 8 5 80 13 Experiment 3 - Reduce by 30% 7 5 78 12 Experiment 4 - Increase by 10% 10 5.5 95 15 Experiment 5 - Increase by 20% 10 6 90 16 Experiment 6 - Increase by 30% 10 6.5 85 17 From the above experimental data, the following rules can be seen: 1. When , reducing the heating power : In Experiments 1 to 3, as the heating power was gradually reduced from 10 kW to 7 kW, the scaling rate decreased from 85 mg / L·h to 78 mg / L·h, indicating that reducing the heating power effectively reduced the scaling rate. In addition, the total system energy consumption also decreased, from 14 kWh to 12 kWh, verifying the energy-saving effect. This shows that when the scaling rate is within the safe range, reducing the heating power can not only save energy but also further inhibit the occurrence of scaling and extend the equipment life.

[0060] 2. When , increasing the pressurization power of the internal pressure compensation unit ; In Experiments 4 to 6, the pressurization power of the internal pressure compensation increased from 5.5 kW to 6.5 kW, and the heating power remained at 10 kW. The scaling rate decreased from 95 mg / L·h to 85 mg / L·h, and the total system energy consumption increased from 15 kWh to 17 kWh. Although increasing the pressurization power of the internal pressure compensation slightly increases the system energy consumption, it significantly reduces the scaling rate, ensuring that the system operates in a stable and safe state and effectively preventing the negative impact of scaling on the system. Example 3

[0061] Please refer to Figure 2 , a heating control method for a drinking water heater, which is used to execute the heating control system of the drinking water heater, including: Step S1: Real-time collect the mineral ion concentration index of the water to be heated flowing into the drinking water heater, the temperature data of multiple hot zones on the surface of the heating element in the drinking water heater, and the pressure compensation index output by the internal pressure compensation unit; Calculate the real-time scaling rate based on the mineral ion concentration index; Calculate the instantaneous heat transfer temperature deviation between each hot zone based on the temperature data of multiple hot zones; Step S2: Use the instantaneous heat transfer temperature deviation, the mineral ion concentration index, and the pressure compensation index as independent variables, and the real-time scaling rate of the water to be heated as the dependent variable output, and construct a scaling state evaluation model based on regression analysis to evaluate the scaling state of the drinking water heater in real time; Step S3: On the basis that the mineral ion concentration index in the water to be heated is a constant value, make different combinations of adjustments to the instantaneous heat transfer temperature deviation and the pressure compensation index within their respective regulation ranges, and input these combinations into the scaling state evaluation model. The scaling state evaluation model generates a set of predicted scaling rates for these combinations; Step S4: Determine the mineral ion concentration index of the current water to be heated, and generate a real-time predicted scaling rate set according to the predicted scaling rate set determination module; Select at least three of the lowest real-time predicted scaling rates from the real-time predicted scaling rate set, and match the corresponding instantaneous heat transfer temperature deviation and pressure compensation index; Step S5: Generate control adjustment parameters for the heating power of the heating element and the pressurization power of the internal pressure compensation unit corresponding to each combination according to the at least three combinations of the instantaneous heat transfer temperature deviation and the pressure compensation index selected; Step S6: Set a judgment threshold for the real-time predicted scaling rate, and based on the comparison result of the judgment threshold, assign corresponding selection weights to the heating power of the heating element and the pressurization power of the internal pressure compensation unit; Determine the control adjustment parameter with the highest matching degree with the selection weight from the three groups of control adjustment parameters according to the selection weight.

[0062] It should be noted that: All calculation formulas in this application document adopt regression analysis including but not limited to machine learning algorithms to deeply analyze the relevant parameters collected, identify their natural trends and interrelationships. Using professional software, such as the Scikit-learn library of Python or the R language, a mathematical model matching the data is automatically generated. Then, the performance of the model is objectively evaluated through methods such as cross-validation, and combined with continuous feedback and optimization to ensure that the created formula truly reflects the internal laws of the data, thereby ensuring its effectiveness and accuracy, and ensuring that the calculation process conforms to the constraints of natural laws rather than being based on artificially set rules.

[0063] The technical solution of the present invention can be embodied in the form of a software product in essence or in the part that contributes to the prior art. This computer software product can be stored in a computer-readable storage medium, such as a floppy disk of a computer, a read-only memory (ROM), a random access memory (RAM), a flash memory (FLASH), a hard disk or an optical disc, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of various embodiments of the present invention.

[0064] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus or device and execute the instructions), or used in combination with these instruction execution systems, apparatus or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by or in combination with an instruction execution system, apparatus or device.

[0065] It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solution of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solution of the present invention, and all of them should be covered by the scope of the claims of the present invention.

Claims

1. A heating control system for a drinking water heater, characterized in that: Specifically include: Data acquisition and analysis module: used to collect in real time the mineral ion concentration index of the water to be heated flowing into the drinking water heater, the temperature data of multiple hot zones on the surface of the heating element in the drinking water heater, and the pressure compensation index output by the internal pressure compensation unit; Calculate the real-time scaling rate based on the mineral ion concentration index; Based on the temperature data of multiple hot zones, calculate the instantaneous heat transfer temperature deviation between the hot zones; Evaluation model building module: It is used to input the instant heat transfer temperature deviation, mineral ion concentration index and pressure compensation index as independent variables, output the real-time scaling rate of the water to be heated as the dependent variable, and build a scaling state evaluation model based on regression analysis to evaluate the scaling state of the drinking water heater in real time; Predicted scaling rate set determination module: used to adjust different combinations of instant heat transfer temperature deviation and pressure compensation index within their respective control ranges on the basis that the mineral ion concentration index in the water to be heated is a constant value, and input these combinations into the scaling state evaluation model, which generates the predicted scaling rate sets of these combinations; Optimal screening module: used to determine the mineral ion concentration index in the water to be heated, and generate a real-time predicted scaling rate set according to the predicted scaling rate set determination module; Select at least three lowest real-time predicted fouling rates from the real-time predicted fouling rate set, and match corresponding instantaneous heat transfer temperature deviations and pressure compensation indicators; A control parameter generation module: used to generate control adjustment parameters of heating power of the heating element and pressurization power of the internal pressure compensation unit corresponding to each combination according to at least three instant heat transfer temperature deviation and pressure compensation index combinations selected; Weight selection module: used to set the judgment threshold for real-time prediction of scaling rate, and to assign corresponding selection weights to the heating power of the heating element and the pressurization power of the internal pressure compensation unit based on the judgment threshold comparison result; According to the selection weight, the control adjustment parameter with the highest matching degree with the selection weight is determined from the three groups of control adjustment parameters.

2. A heating control system for a drinking water heater according to claim 1, characterized in that: The internal pressure compensation unit is used to ensure that the water to be heated can reach the target boiling point by increasing the internal pressure of the heating chamber corresponding to the heating element in the low-pressure area of ​​the plateau; The pressure compensation unit calibrates the output pressure to the target boiling point of the water to be heated. The calibration relationship is based on the following formula: ； in, is the target boiling point after pressure compensation, is the standard temperature of the boiling point at normal pressure, is the pressure increment output by the pressure compensation unit. Characterized as a pressure compensation indicator; is the calibration coefficient related to the thermodynamic properties of water; is the real-time air pressure value of the current environment. is the standard pressure under atmospheric pressure; The mineral ion concentration index is derived by analyzing the conductivity data of the water to be heated. The specific derivation steps are as follows: The mineral ion concentration index And the conductivity value E is fitted into a calibration curve model according to the following relationship; ； The relationship function Is it a linear relationship or nonlinear distribution, select the fitting model according to the actual data; The conductivity value E collected from the water to be heated is substituted into the calibration curve model for calculation to obtain the real-time mineral ion concentration index. .

3. A heating control system for a drinking water heater according to claim 2, characterized in that: Experimental calibration factors to determine real-time fouling rates ; The heating control system stores a predefined scaling rate calculation formula: ； Read the corresponding experimental calibration coefficient from the internal configuration file in real time according to the mineral ion type of the water to be heated ; The mineral ion concentration index calculated in real time Substitute into the scaling rate calculation formula to calculate the real-time scaling rate ; Calculate the average temperature of multiple hot spots on the surface of a heating element : ； in, is the temperature value of hot zone i, n is the total number of hot zones; Calculate the temperature deviation of hot zone i , the specific formula is: ； The instant heat transfer temperature deviation calculation formula is defined as follows: ； in, is the instantaneous heat transfer temperature deviation between the hot zones; represents the absolute value of the temperature deviation in hot zone i; The larger the value, the greater the deviation in the uniformity of heat transfer across the heating element surface.

4. A heating control system for a drinking water heater according to claim 3, characterized in that: The following real-time data is obtained from the data acquisition and analysis module: Instant heat transfer temperature deviation ; Mineral ion concentration index ; Pressure compensation index ; Real-time scaling rate ; Establish a structured database to store the above four types of data in real time according to time series, and preprocess these data to obtain preprocessed data sets; The preprocessed data set is divided into training set and test set according to the time series to ensure that the model is not affected by future data during the training process; Use the training set data to fit the multivariate linear regression model and establish independent variables With dependent variable The linear relationship between: ； in, is the intercept, is the regression coefficient.

5. A heating control system for a drinking water heater according to claim 4, characterized in that: Set the pressure compensation index based on the minimum and maximum pressure capacity output values ​​of the internal pressure compensation unit The control range is ; It is the lower limit of the pressure compensation index; is the upper limit of the pressure compensation index; Set instant heat transfer temperature deviation The control range is ; Get the maximum heating power of the heating element and minimum heating power ; It is set as the lower limit of the instantaneous heat transfer temperature deviation of the heating element at the minimum heating power; Set as the upper limit of the instantaneous heat transfer temperature deviation of the heating element at the maximum heating power; set up and The step lengths are and ; exist arrive In the range of Iterate to generate all value; exist arrive In the range of Iterate to generate all value; Use the Cartesian product to generate all combination, ensuring that each pair of combinations is within their respective control ranges; Combination corresponding to The values ​​are stored in the predicted fouling rate set.

6. A heating control system for a drinking water heater according to claim 5, characterized in that: The mineral ion concentration index obtained in real time in the water to be heated passing it to a predicted fouling rate set determination module; The predicted fouling rate set determination module is based on the input , and Combine and generate a corresponding real-time predicted fouling rate set; The real-time predicted fouling rate set contains each group Data records; For all real-time predictions of fouling rate The values ​​are sorted in ascending order to ensure that the lowest real-time fouling rate is at the top; Select at least three lowest real-time predicted fouling rates from the sorted set value, forming the optimal candidate set ; Select the lowest real-time predicted fouling rate Extract the corresponding Combination to form the following optimal control parameter set .

7. A heating control system for a drinking water heater according to claim 6, characterized in that: A mapping model between the heating power of the heating element and the instantaneous heat transfer temperature deviation is established to Under the value, the heating power of the corresponding heating element is generated ; A mapping relationship model between the pressurization power and the pressure compensation index in the internal pressure compensation unit is established to Under this condition, the pressurization power of the internal pressure compensation unit is generated. ; The optimal control parameter set is denoted as , using the mapping relationship model established above, calculate the corresponding ; ； in , j is the optimal control parameter set Combined index; Each group Corresponding Saves the following control adjustment parameter sets: 。 8. A heating control system for a drinking water heater according to claim 7, characterized in that: The judgment threshold for real-time prediction of scaling rate is set as ; The weight distribution ratio between the heating power of the heating element and the pressurizing power of the internal pressure compensation unit is recorded as ; when When the heating power is reduced , set the weight distribution ratio value q1 to ; when When the pressure is increased, the pressure compensation unit should be increased first. , set the weight distribution ratio value q2 to ;q1>q2; Adjust parameters for each group of controls , calculate and distribute the current weight The matching degree : ； from Select the control adjustment parameter with the largest value ; The maximum control adjustment parameter Transmitted to the heating control system and internal pressure compensation unit to guide real-time heating power and pressurization power adjustment.

9. A heating control method for a drinking water heater, characterized in that: The method is used to implement the heating control system of the drinking water heater according to any one of claims 1 to 8, comprising: Step S1: real-time collection of mineral ion concentration index of water to be heated flowing into the drinking water heater, temperature data of multiple hot zones on the surface of the heating element in the drinking water heater, and pressure compensation index output by the internal pressure compensation unit; Calculate the real-time scaling rate based on the mineral ion concentration index; Based on the temperature data of multiple hot zones, calculate the instantaneous heat transfer temperature deviation between the hot zones; Step S2: taking the instant heat transfer temperature deviation, the mineral ion concentration index and the pressure compensation index as independent variable inputs, taking the real-time scaling rate of the water to be heated as the dependent variable output, and constructing a scaling state evaluation model based on regression analysis to evaluate the scaling state of the drinking water heater in real time; Step S3: On the basis of the constant value of the mineral ion concentration index in the water to be heated, the instantaneous heat transfer temperature deviation and the pressure compensation index are adjusted in different combinations within their respective control ranges, and these combinations are input into the scaling state evaluation model, and the scaling state evaluation model generates a set of predicted scaling rates for these combinations. Step S4: determining the mineral ion concentration index in the water to be heated, and generating a real-time predicted scaling rate set according to the predicted scaling rate set determination module; Select at least three lowest real-time predicted fouling rates from the real-time predicted fouling rate set, and match corresponding instantaneous heat transfer temperature deviations and pressure compensation indicators; Step S5: generating control adjustment parameters of the heating power of the heating element and the pressurizing power of the internal pressure compensation unit corresponding to each combination according to the at least three selected combinations of instant heat transfer temperature deviation and pressure compensation index; Step S6: setting a judgment threshold for real-time prediction of scaling rate, and assigning corresponding selection weights to the heating power of the heating element and the pressurizing power of the internal pressure compensation unit based on the judgment threshold comparison result; According to the selection weight, the control adjustment parameter with the highest matching degree with the selection weight is determined from the three groups of control adjustment parameters.

Images