Intelligent kettle heating control method and system based on ultrasonic sensing

Abstract

The invention relates to the technical field of kettle heating control, and discloses an intelligent kettle heating control method and system based on ultrasonic sensing, and the method comprises the steps: constructing a sample training data set and a sample property data set based on a to-be-heated sample set and an intelligent kettle, training a neural network model through the sample training data set, and obtaining a neural network model; a boiling duration prediction model is obtained, heating duration estimation is carried out based on the sample property data set, the user selected power, the current water level depth and the current water quality feature set, the predicted heating duration is obtained, heating duration visual display is carried out according to the predicted heating duration, and a current display screen is obtained; and based on the boiling duration prediction model, obtaining a predicted boiling duration, and based on the predicted boiling duration, updating the current display screen to obtain a target display screen. The accuracy of boiling state prediction in the kettle heating process can be improved, and the intelligent degree of kettle heating control is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of kettle heating control, and in particular to an intelligent kettle heating control method and system based on ultrasonic sensing. BACKGROUND

[0002] In modern life, electric kettles have become indispensable heating tools, and the accuracy of their heating control is directly related to user experience, energy use efficiency and safety. Precise heating control not only avoids the wasteful consumption of energy, but also ensures use safety and prevents risks such as dry burning. At the same time, users' demand for knowing the heating duration is increasing. Therefore, it is of great practical value to realize intelligent and adaptive kettle heating control.

[0003] Traditional kettle heating control methods mainly rely on temperature sensors to monitor water temperature and cut off power when the temperature reaches a fixed boiling point. Although this method can achieve basic water boiling detection, it cannot adapt to different water qualities, resulting in inaccurate boiling prediction, and cannot sense internal physical changes in water, so it can only passively wait for temperature results, resulting in a lag in response. SUMMARY

[0004] The present application provides an intelligent kettle heating control method and system based on ultrasonic sensing, which aims to improve the accuracy of boiling state prediction during kettle heating and improve the intelligence of kettle heating control.

[0005] To achieve the above-mentioned purpose, the present application provides an intelligent kettle heating control method based on ultrasonic sensing, which comprises:

[0006] Confirming an intelligent kettle, wherein the intelligent kettle comprises an ultrasonic sensor and a standby display screen;

[0007] Collecting a set of samples to be heated, constructing a sample training data set and a sample property data set based on the set of samples to be heated and the intelligent kettle, training a pre-constructed neural network model using the sample training data set to obtain a boiling duration prediction model;

[0008] Receiving a user input instruction, identifying a user-selected power based on the user input instruction, and detecting a current water quality feature group and a current water level depth;

[0009] Estimating the heating duration based on the sample property data set, the user-selected power, the current water level depth and the current water quality feature group to obtain a predicted heating duration;

[0010] According to the predicted heating duration, performing visual display of the heating duration on the standby display screen to obtain a current display screen;

[0011] In the preset heating stage, the boiling duration prediction model is used for boiling duration prediction to obtain a predicted boiling duration, the current display screen is updated based on the predicted boiling duration to obtain a target display screen, and the intelligent kettle heating control based on ultrasonic wave sensing is completed based on the target display screen.

[0012] Optionally, the constructing a sample training data set and a sample property data set based on the sample set to be heated and the intelligent kettle comprises:

[0013] The sample to be heated is extracted from the sample set to be heated in sequence, wherein the sample to be heated is pure water, mineral water or hard water;

[0014] The speed-temperature empirical formula of the sample to be heated is constructed;

[0015] The sample to be heated is heated by the intelligent kettle to obtain a heating energy consumption and a sample heating data set;

[0016] The sample to be heated is collected for water quality by the pre-constructed water quality sensor set to obtain a sample water quality feature set, wherein the sample water quality feature set comprises a sample temperature;

[0017] The water level depth of the sample to be heated in the intelligent kettle is recorded, and the unit heating energy consumption is calculated according to the water level depth and the heating energy consumption;

[0018] The unit heating energy consumption, the speed-temperature empirical formula and the sample water quality feature set are matched to obtain sample property data;

[0019] Each sample heating data in the sample heating data set is supplemented by the sample water quality feature set to obtain a sample training data set;

[0020] The sample training data set corresponding to each sample to be heated is merged to obtain a sample training data set, and the sample property data corresponding to each sample to be heated is summarized to obtain a sample property data set.

[0021] Optionally, the heating of the sample to be heated by the intelligent kettle to obtain the heating energy consumption and the sample heating data set comprises:

[0022] An initial collection time of the preset sample heating instruction is determined;

[0023] The sample to be heated is heated based on the initial collection time and the intelligent kettle, and in the heating process, the sample to be heated is collected for parameters by the ultrasonic sensor and the pre-constructed temperature sensor to obtain an ultrasonic feature set and a current temperature;

[0024] The current temperature and the ultrasonic feature set are paired to obtain original heating data;

[0025] determining whether the sample to be heated is in a preset boiling state;

[0026] If the sample to be heated is not in the boiling state, an updated collection time is calculated according to a preset collection interval and an initial collection time, the updated collection time is taken as the initial collection time, and the step of heating the sample to be heated based on the initial collection time and the intelligent kettle is returned until the sample to be heated is in the boiling state.

[0027] If the sample to be heated is in the boiling state, the initial collection time is recorded as a sample boiling time, and the original heating data is summarized to obtain an original heating data set.

[0028] The original heating data set is updated using the sample boiling time to obtain a sample heating data set.

[0029] The total heating time is recorded, and the heating energy consumption is calculated based on the total heating time and a preset rated heating power.

[0030] Optionally, the updating of the original heating data set using the sample boiling time to obtain the sample heating data set comprises:

[0031] The original heating data is extracted in the original heating data set in sequence, and a data collection time of the original heating data is confirmed.

[0032] The sample boiling interval is calculated based on the data collection time and the sample boiling time.

[0033] The sample boiling interval is supplemented to the original heating data to obtain sample heating data, wherein the sample heating data comprises the sample boiling interval and the original heating data.

[0034] The sample heating data is summarized to obtain a sample heating data set.

[0035] Optionally, the training of the pre-constructed neural network model using the sample training data set to obtain a boiling time prediction model comprises:

[0036] The sample training data is extracted in the sample training data set in sequence, and the sample training data is recorded as target training data.

[0037] The target water quality feature group and the target heating data in the target training data are confirmed, and the real boiling interval, the target sample temperature and the target ultrasonic feature group are obtained based on the target heating data.

[0038] The target input vector is constructed according to the target water quality feature group, the target sample temperature and the target ultrasonic feature group.

[0039] The target input vector is input into the neural network model to obtain a predicted boiling interval, and a model loss value is calculated based on the predicted boiling interval and the real boiling interval.

[0040] If the model loss value is greater than the preset loss threshold, the neural network model is adjusted according to the model loss value to obtain an updated model;

[0041] The updated model is taken as the neural network model, and the step of sequentially extracting the sample training data in the sample training data set is returned until the model loss value is not greater than the loss threshold;

[0042] If the model loss value is not greater than the loss threshold, the neural network model is recorded as a boiling duration prediction model.

[0043] Optionally, the current water quality feature group and the current water level depth are detected, including:

[0044] The water quality is collected by using a water quality sensor group to obtain a current water quality feature group, wherein the water quality sensor group includes an acid-base degree sensor, a turbidity sensor, a residual chlorine sensor, and a conductivity sensor;

[0045] According to a preset reference pulse signal parameter and an ultrasonic sensor, a signal is emitted, and after the signal emission is completed, the ultrasonic sensor is switched to a receiving sensor, wherein the reference pulse signal parameter includes a reference frequency, a reference pulse width, and a reference pulse amplitude;

[0046] The emission time of the signal emission is confirmed;

[0047] According to the emission time and a preset collection frequency, a signal is received by using the receiving sensor in the collection interval to obtain an analog voltage signal;

[0048] Based on the analog voltage signal, the echo flight time is calculated;

[0049] Based on the current water quality feature group, similar property data in a sample property data set is identified, and a target empirical formula in the similar property data is continuously identified;

[0050] The unheated temperature is detected by using a temperature sensor, and the unheated sound speed is calculated according to the unheated temperature and the target empirical formula;

[0051] The current water level depth is calculated according to the unheated sound speed and the echo flight time.

[0052] Optionally, the echo flight time is calculated based on the analog voltage signal, including:

[0053] The analog voltage signal is converted into a discrete digital signal sequence, wherein the discrete digital signal sequence includes a plurality of discrete voltage values;

[0054] A discrete digital signal sequence is bandpass filtered to obtain a filtered digital signal sequence, and the envelope of the filtered digital signal sequence is extracted to obtain the envelope line.

[0055] Based on the preset amplitude threshold, query the water surface reflection voltage value on the envelope to confirm the index position of the water surface reflection voltage value;

[0056] The echo flight time is calculated based on the index location and the acquisition frequency delay.

[0057] Optionally, the step of estimating the heating duration based on the sample property dataset, user-selected power, current water level depth, and current water quality characteristic group to obtain the predicted heating duration includes:

[0058] Extract sample property data sequentially from the sample property dataset;

[0059] The water quality similarity is calculated based on the current water quality characteristic group and the sample water quality characteristic group in the sample property data, where the water quality similarity is the cosine value;

[0060] Summarize the water quality similarity to obtain a water quality similarity set, and normalize the water quality similarity set to obtain a normalized similarity set;

[0061] The predicted unit energy consumption is obtained by weighted summation based on the normalized similarity set and the sample property dataset.

[0062] The total energy consumption is calculated based on the predicted unit energy consumption and the current water level depth, and the predicted heating time is calculated based on the user-selected power and the predicted total energy consumption.

[0063] Optionally, the predicted unit energy consumption is expressed as:

[0064] ,

[0065] in, This indicates the predicted unit energy consumption. This indicates the number of normalized similarities in the normalized similarity set or the number of sample property data in the sample property dataset. Denotes the first in the normalized similarity set Normalized similarity, Indicates the properties of the sample in the dataset. Unit heating energy consumption in the sample property data.

[0066] To achieve the above objectives, the present invention also provides an intelligent kettle heating control system based on ultrasonic sensing, comprising:

[0067] The prediction model construction module is used for confirming the intelligent kettle, wherein the intelligent kettle comprises an ultrasonic sensor and a standby display screen, a sample set to be heated is collected, a sample training data set and a sample property data set are constructed based on the sample set to be heated and the intelligent kettle, a pre-constructed neural network model is trained by using the sample training data set, and a boiling time prediction model is obtained.

[0068] The water level depth detection module is used for receiving a user input instruction, identifying a user selected power based on the user input instruction, detecting a current water quality feature group and a current water level depth.

[0069] The heating time prediction module is used for performing heating time estimation based on the sample property data set, the user selected power, the current water level depth and the current water quality feature group, and obtaining a predicted heating time.

[0070] The heating information display module is used for performing visual display of the heating time on the standby display screen according to the predicted heating time, obtaining a current display screen, performing boiling time prediction by using the boiling time prediction model in a preset heating stage, obtaining a predicted boiling time, updating the current display screen based on the predicted boiling time, and obtaining a target display screen.

[0071] To solve the above problems, the present application further provides an electronic device, which comprises:

[0072] A memory for storing at least one instruction;

[0073] A processor for executing the instruction stored in the memory to implement the above-mentioned intelligent kettle heating control method based on ultrasonic sensing.

[0074] To solve the above problems, the present application further provides a computer readable storage medium, which stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned intelligent kettle heating control method based on ultrasonic sensing.

[0075] The present application is to solve the problems described in the background art. First, by configuring an ultrasonic sensor in the intelligent kettle, non-contact detection of the water level is achieved, avoiding the problem of easy scaling and corrosion of traditional contact sensors, and providing a key physical signal acquisition basis for subsequent processes. The integration of the display screen provides an intuitive interface for the user. The present scheme uses a sample training dataset to train a pre-built neural network model to obtain a boiling duration prediction model. This step builds a training set containing multi-dimensional features (water quality, acoustic characteristics, energy consumption) to enable the trained neural network model to deeply learn the physical change law of different water qualities at different heating stages, thereby significantly improving the accuracy of boiling time prediction and the generalization ability of the model. It solves the problem of insufficient accuracy of traditional temperature prediction models in variable water quality environments. Then, based on the sample property dataset, the user-selected power, the current water level depth and the current water quality feature group, the heating duration is estimated to obtain the predicted heating duration. This step estimates the energy consumption by calculating the similarity of the current water quality and the historical sample and performing weighted fusion, thereby combining dynamic judgments of historical data and current actual situations to enable the heating duration prediction to adapt to different users' water quality and water adding habits, improving the accuracy and reliability of personalized prediction. Furthermore, the present scheme also performs visual display of the heating duration on the standby display screen according to the predicted heating duration to obtain the current display screen. This step clearly shows the predicted heating duration under different selected powers to the user, providing a clear expectation, making it easy for the user to flexibly select the most suitable heating power according to the time requirement, and improving the intelligent level of the product. Finally, during the heating stage, the boiling duration prediction model is used to predict the boiling duration to obtain the predicted boiling duration, and the current display screen is updated based on the predicted boiling duration to obtain the target display screen. This step uses the trained model to perform real-time and dynamic boiling duration prediction during the heating process, which can more accurately determine the boiling point and stop heating in time, thereby effectively avoiding energy waste caused by excessive boiling. Therefore, the present application can improve the accuracy of boiling state prediction during the heating process of the kettle and improve the intelligent level of the kettle heating control. BRIEF DESCRIPTION OF DRAWINGS

[0076] Figure 1 A flowchart of the intelligent kettle heating control method based on ultrasonic sensing provided by an embodiment of the present application is shown in the figure.

[0077] Figure 2 A functional module diagram of the intelligent kettle heating control system based on ultrasonic sensing provided by an embodiment of the present application is shown in the figure.

[0078] Figure 3 A structural diagram of an electronic device implementing the intelligent kettle heating control method based on ultrasonic sensing provided by an embodiment of the present application is shown in the figure.

[0079] Figure 4A structure schematic diagram of an intelligent kettle provided by an embodiment of the present application and implementing the intelligent kettle heating control method based on ultrasonic wave sensing

[0080] Explanation of reference signs:

[0081] 1, electronic device; 10, processor; 11, memory; 12, bus; 21, ultrasonic wave sensor; 22, intelligent kettle; 23, standby display screen.

[0082] The implementation, functional features and advantages of the present application will be further explained with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0083] It should be understood that the specific embodiments described herein are merely intended to explain the present application and not to limit the present application.

[0084] An embodiment of the present application provides an intelligent kettle heating control method based on ultrasonic wave sensing. The execution subject of the intelligent kettle heating control method based on ultrasonic wave sensing includes but is not limited to at least one of electronic devices such as a server, a terminal and the like which can be configured to execute the method provided by the present application. In other words, the intelligent kettle heating control method based on ultrasonic wave sensing can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to a single server, a server cluster, a cloud server or a cloud server cluster and the like.

[0085] Reference Figure 1 Fig. 1 shows a flowchart of the intelligent kettle heating control method based on ultrasonic wave sensing provided by an embodiment of the present application. In the embodiment, the intelligent kettle heating control method based on ultrasonic wave sensing includes:

[0086] S1, confirming an intelligent kettle, wherein the intelligent kettle includes an ultrasonic wave sensor and a standby display screen.

[0087] It can be understood that the ultrasonic wave sensor refers to a piezoelectric transducer with both transmitting and receiving functions, which can detect the water level depth in the intelligent kettle and obtain an ultrasonic wave feature group in the heating process. The standby display screen refers to a liquid crystal touch screen integrated on the kettle body or the base, which can display the current heating time in real time, i.e., display the predicted boiling time in real time, and support user manual selection of the heating power of the intelligent kettle and the required heating time under different heating powers, i.e., display the predicted heating time.

[0088] S2, collect a set of samples to be heated, construct a sample training data set and a sample property data set based on the set of samples to be heated and the intelligent kettle, train a pre-constructed neural network model using the sample training data set, and obtain a boiling time prediction model.

[0089] It can be understood that the set of samples to be heated refers to a collection of multiple samples to be heated, wherein the samples to be heated refer to water samples of different water qualities collected by humans, including pure water, mineral water, hard water, etc. Since users will heat water of different water qualities when using the intelligent kettle, these samples to be heated are collected, and the sample training data set and the sample property data set are constructed based on the set of samples to be heated, so as to simulate the different water qualities of water that users need to heat in actual use. The sample training data set refers to data for training the subsequent neural network model, and the sample property data in the sample property data set refers to data representing the properties of the samples to be heated. The detailed composition of the sample training data and the sample property data will be explained later.

[0090] Further, the neural network model can be selected from: long short-term memory network (LSTM), gated recurrent unit (GRU), or deep feedforward neural network (DFF), etc. The boiling time model refers to the trained neural network model.

[0091] In detail, the sample training data set and the sample property data set are constructed based on the set of samples to be heated and the intelligent kettle, comprising:

[0092] extracting the samples to be heated in the set of samples to be heated in turn, wherein the samples to be heated are pure water, mineral water, or hard water;

[0093] constructing a sound speed temperature empirical formula of the samples to be heated;

[0094] heating the samples to be heated using the intelligent kettle to obtain a heating energy consumption and a sample heating data set;

[0095] collecting water quality of the samples to be heated based on a pre-constructed water quality sensor set to obtain a sample water quality feature set, wherein the sample water quality feature set includes sample temperature;

[0096] recording the heating water level depth of the samples to be heated in the intelligent kettle, and calculating unit heating energy consumption based on the heating water level depth and the heating energy consumption;

[0097] matching the unit heating energy consumption, the sound speed temperature empirical formula, and the sample water quality feature set to obtain sample property data;

[0098] supplementing each sample heating data in the sample heating data set using the sample water quality feature set to obtain a sample training data set;

[0099] merge each sample training data set corresponding to each to-be-heated sample to obtain a sample training data set, and aggregate each sample property data corresponding to each to-be-heated sample to obtain a sample property data set.

[0100] Need to explain, the sound speed temperature empirical formula refers to a mathematical expression describing the relationship between the propagation speed of sound waves in the to-be-heated sample and the water temperature. The sound speed temperature empirical formula is obtained in the following manner: a large number of temperature and sound speed are used for formula fitting, or an existing sound speed temperature empirical fitting formula is used. For example, under a standard atmospheric pressure, the sound speed temperature empirical formula is wherein, represents the sound speed, represents the water temperature.

[0101] Further, the heating energy consumption refers to the energy consumption required to heat the to-be-heated sample from the current state (i.e., the state at the sample temperature) to the boiling state. The sample heating data set will be given in detail later. The water quality sensor set refers to a combination of sensors for detecting the water quality of the to-be-heated sample. The water quality sensor set includes: a pH sensor, a turbidity sensor, a residual chlorine sensor, and a conductivity sensor. The pH sensor is used to measure the pH value of the water body. The turbidity sensor is an optical sensor used to measure the concentration of suspended particulate matter in water. The residual chlorine sensor is an electrochemical sensor used to detect the free chlorine content in water. The conductivity sensor is a sensor that indirectly reflects the total dissolved solids (TDS) content by measuring the conductivity of the water solution.

[0102] As can be understood, the sample water quality feature set refers to a combination of water quality parameters collected by each water quality sensor in the water quality sensor set. It should be noted that the sample water quality feature set also includes the sample temperature, which is detected by the temperature sensor. Since different to-be-heated samples at different temperatures require different energy consumption for heating, the temperature of the to-be-heated sample before heating (i.e., the sample temperature mentioned above) also needs to be included in the sample water quality feature set. The to-be-heated water level depth refers to the water level depth of the to-be-heated sample. The to-be-heated water level depth can be measured manually or by an ultrasonic sensor (the measurement method will be described in detail later). The supplement of the sample water quality feature set to each sample heating data in the sample heating data set means that the sample water quality feature set is supplemented to the sample heating data to obtain sample training data, i.e., the sample training data is a combination of the sample water quality feature set and the sample heating data. The same operation is performed on each sample heating data to obtain a sample training data set. The merging of each sample training data set corresponding to each to-be-heated sample means that all sample training data of each sample training data set corresponding to each to-be-heated sample is put into the same set. The set after being put in is the sample training data set.

[0103] In detail, the heating of the sample to be heated by the intelligent kettle obtains a heating energy consumption and a sample heating data set, which comprises:

[0104] Confirming an initial collection time of a preset sample heating instruction;

[0105] Based on the initial collection time and the heating of the sample to be heated by the intelligent kettle, and in the heating process, the parameters of the sample to be heated are collected by using the ultrasonic sensor and the pre-constructed temperature sensor to obtain an ultrasonic feature set and a current temperature;

[0106] The current temperature and the ultrasonic feature set are paired to obtain original heating data;

[0107] Judging whether the sample to be heated is in a preset boiling state;

[0108] If the sample to be heated is not in the boiling state, an updated collection time is calculated according to the preset collection interval and the initial collection time, the updated collection time is taken as the initial collection time, and the step of heating the sample to be heated by the intelligent kettle based on the initial collection time is returned until the sample to be heated is in the boiling state;

[0109] If the sample to be heated is in the boiling state, the initial collection time is recorded as a sample boiling time, and the original heating data is summarized to obtain an original heating data set;

[0110] The original heating data set is updated by using the sample boiling time to obtain a sample heating data set;

[0111] The total heating time is recorded, and the heating energy consumption is calculated based on the total heating time and a preset rated heating power.

[0112] It can be understood that the sample heating instruction refers to an instruction for starting the intelligent kettle initiated by a person, for example, Xiaozhang turns on the switch of the intelligent kettle, at this time, Xiaozhang is considered to have initiated the sample heating instruction. The initial collection time refers to the time when the above-mentioned sample heating instruction is generated.

[0113] Further, the temperature sensor refers to a sensor for collecting the temperature of the sample to be heated, such as a negative temperature coefficient (NTC) thermistor. The ultrasonic feature group refers to a combination of multiple ultrasonic features, wherein the ultrasonic feature refers to a feature of the ultrasonic wave collected by the ultrasonic sensor during the transmission of the ultrasonic wave in the sample to be heated. The ultrasonic feature can be the echo flight time, signal amplitude attenuation, frequency spectrum center shift, etc. Their acquisition methods are as follows: the echo flight time is obtained by calculating the time difference between the transmitted and received signals, the signal amplitude attenuation is obtained by comparing the peak amplitudes of the transmitted signal and the echo signal, and the frequency spectrum center shift is obtained by calculating the spectrum barycenter after Fourier transform of the echo signal (i.e. the signal received by the ultrasonic sensor). The acquisition methods of the above-mentioned ultrasonic features are all prior art and will not be described here. The current temperature refers to the temperature of the sample to be heated collected by the temperature sensor. The original heating data refers to the combination of the current temperature and the ultrasonic feature group. The boiling state refers to the physical state of water reaching the boiling point and continuously generating bubbles. The method for determining whether the sample to be heated is in the boiling state is to detect whether the water temperature reaches the boiling point under the current atmospheric pressure by the temperature sensor. This method is prior art and will not be described here.

[0114] Understandably, the collection interval refers to a time interval for collecting parameters of the sample to be heated set by humans. The update collection time refers to a time point one collection interval away from the initial collection time, for example, the initial collection time is time point A and the collection interval is G, then the update collection time is P = A + G. The total heating time refers to the total time from the start of heating the sample to be heated to the boiling state of the sample to be heated. The rated heating power refers to the working power of the intelligent kettle. The calculation method of the heating energy consumption is the total heating time multiplied by the rated heating power.

[0115] In detail, the original heating data set is updated by using the sample boiling time to obtain the sample heating data group, comprising:

[0116] The original heating data in the original heating data set is extracted in sequence, and the data collection time of the original heating data is confirmed;

[0117] The sample boiling interval is calculated based on the data collection time and the sample boiling time;

[0118] The sample boiling interval is supplemented to the original heating data to obtain the sample heating data, wherein the sample heating data includes the sample boiling interval and the original heating data;

[0119] The sample heating data is summarized to obtain the sample heating data group.

[0120] It can be understood that the data collection time refers to the time when the original heating data is collected, that is, the initial collection time corresponding to the original heating data. The sample boiling interval refers to the time interval between the data collection time and the sample boiling time. The supplement of the sample boiling interval to the original heating data refers to putting the sample boiling interval and the original heating data into a combination, and the combination is the sample heating data.

[0121] In detail, the training of the pre-constructed neural network model by using the sample training data set to obtain the boiling duration prediction model comprises:

[0122] The sample training data in the sample training data set is extracted in sequence, and the sample training data is denoted as target training data;

[0123] The target water quality feature group and the target heating data in the target training data are confirmed, and the real boiling interval, the target sample temperature, and the target ultrasonic feature group are obtained based on the target heating data;

[0124] The target input vector is constructed according to the target water quality feature group, the target sample temperature, and the target ultrasonic feature group;

[0125] The target input vector is input into the neural network model to obtain the predicted boiling interval, and the model loss value is calculated based on the predicted boiling interval and the real boiling interval;

[0126] If the model loss value is greater than the preset loss threshold, the neural network model is adjusted according to the model loss value to obtain an updated model;

[0127] The updated model is used as the neural network model, and the step of sequentially extracting the sample training data in the sample training data set is returned until the model loss value is not greater than the loss threshold;

[0128] If the model loss value is not greater than the loss threshold, the neural network model is denoted as the boiling duration prediction model.

[0129] It can be understood that the target training data refers to the sample training data used for subsequent input of the neural network model. The target water quality feature group and the target heating data respectively refer to the sample water quality feature group and the sample heating data in the target training data. The real boiling interval refers to the sample boiling interval in the target heating data, which represents real data and is used for subsequent comparison with the predicted data (i.e., the subsequent predicted boiling interval) output by the model. The target sample temperature and the target ultrasonic feature group respectively refer to the current temperature and the ultrasonic feature group (built-in the original heating data) contained in the target heating data.

[0130] Further, the target input vector refers to a vector composed of a target water quality feature group, a target sample temperature, and a target ultrasonic feature group. For example, the target water quality feature group is (pH value of 7.5, turbidity of 10.2 NTU, residual chlorine of 0.05 mg / L), the target sample temperature is 25.0℃, and the target ultrasonic feature group is (echo flight time of 0.15 ms, signal amplitude attenuation of -2.5 dB, and frequency spectrum center shift of 40.1 kHz). Thus, the target input vector is (7.5, 10.2, 0.05, 25.0, 0.15, -2.5, 40.1). After obtaining the target input vector, preprocessing operations such as normalization and standardization need to be performed on the target input vector, so that the input features are in the same scale, and the stability and convergence speed of model training are improved. The preprocessing operations are all prior art and will not be described here. The predicted boiling interval refers to the output value of the neural network model. The model loss value refers to a value quantifying the deviation between the predicted output value (i.e., the predicted boiling interval) and the true value (i.e., the true boiling interval). The larger the model loss value, the worse the prediction accuracy of the neural network model. The calculation method of the model loss value can be selected as mean square error (MSE) or mean absolute error (MAE). The loss threshold refers to a pre-set constant error value for judging whether the model converges. When the model loss value is greater than the loss threshold, it means that the neural network model has not met the training requirements, and the neural network model needs to be adjusted at this time. The adjustment method of the neural network model based on the model loss value can be selected as the back propagation algorithm combined with the gradient descent optimizer (such as Adam). The updated model refers to the neural network model after adjustment. When the model loss value is not greater than the loss threshold, it means that the neural network model has been trained and converged.

[0131] S3, receiving a user input instruction, identifying a user-selected power based on the user input instruction, detecting a current water quality feature group and a current water level depth.

[0132] It can be understood that the user input instruction refers to a power selection instruction issued by the user through the display screen or the related APP. For example, the working power of a certain intelligent kettle can be selected as 800W, 1000W, 1200W, and 1500W. If a user selects the working power of the intelligent kettle as 1000W through the display screen, it is considered that the user has issued the user input instruction. The user-selected power refers to the working power of the intelligent kettle contained in the user input instruction. For example, in the above example, the user-selected power is 1000W. The current water level depth refers to the water level depth of the contained water body detected by the intelligent kettle, wherein the contained water body is manually added by the user, and the current water level depth is automatically measured by the ultrasonic sensor. The current water quality feature group refers to the combination of the water quality features of the contained water body detected by the water quality sensor group, which corresponds to the sample water quality feature group described above.

[0133] In detail, the detection of the current water quality feature group and the current water level depth comprises:

[0134] The water quality is collected by using a water quality sensor group to obtain a current water quality feature group, wherein the water quality sensor group comprises an acid-base value sensor, a turbidity sensor, a residual chlorine sensor, and a conductivity sensor;

[0135] According to a preset reference pulse signal parameter and an ultrasonic sensor, a signal is emitted, and after the signal emission is completed, the mode of the ultrasonic sensor is switched to obtain a receiving sensor, wherein the reference pulse signal parameter comprises a reference frequency, a reference pulse width, and a reference pulse amplitude;

[0136] The emission time of the signal emission is confirmed;

[0137] According to the emission time and a preset collection frequency, a signal is received by using the receiving sensor in the collection interval to obtain an analog voltage signal;

[0138] Based on the analog voltage signal, the echo flight duration is calculated;

[0139] Based on the current water quality feature group, similar property data in the sample property data set is identified, and a target empirical formula in the similar property data is continuously identified;

[0140] The unheated temperature is detected by using a temperature sensor, and the unheated sound speed is calculated according to the unheated temperature and the target empirical formula;

[0141] The current water level depth is calculated according to the unheated sound speed and the echo flight duration.

[0142] It needs to be explained that the reference pulse signal parameter refers to an electrical parameter artificially set for driving the ultrasonic sensor to emit a signal, and the reference pulse signal parameter comprises a reference frequency, a reference pulse width, and a reference pulse amplitude, wherein the reference frequency refers to the center working frequency of the ultrasonic wave, such as 40 kHz, the reference pulse width refers to the duration of the pulse, such as 0.5 ms, and the reference pulse amplitude refers to the peak value of the driving voltage, such as 5 V. The mode switching refers to switching the working circuit of the ultrasonic sensor from the emission state to the receiving state, and the mode switching is the prior art, and the specific content is not described here. The above signal emission refers to that the ultrasonic sensor emits ultrasonic waves according to the reference pulse signal parameter. The receiving sensor refers to the ultrasonic sensor after the mode switching, and the receiving sensor is used for detecting and converting the returned acoustic echo signal. The emission time refers to the time of signal emission. The collection frequency refers to the sampling rate of the analog-digital conversion of the receiving sensor artificially set, such as 100 kHz. The analog voltage signal refers to the echo voltage signal output by the receiving sensor, which changes continuously with time.

[0143] Further, the similar property data refers to one sample property data in a sample property data set similar to the current water quality feature group, and the similar property data is obtained by: sequentially extracting sample property data in the sample property data set, calculating the water quality similarity between the current water quality feature group and the sample water quality feature group in the sample property data (the specific calculation method of the water quality similarity will be given later), the calculation method is to calculate the cosine value, and the water quality similarities corresponding to different sample property data are summarized to obtain a water quality similarity set, and the sample property data corresponding to the water quality similarity with the largest value in the water quality similarity set is recorded as the similar property data. The target empirical formula refers to the sound speed temperature empirical formula in the similar property data. The unheated temperature refers to the temperature of the water contained in the intelligent kettle detected by the temperature sensor. The unheated sound speed refers to the ultrasonic speed at the unheated temperature calculated by the target empirical formula. The calculation formula of the current water level depth is: wherein, represents the current water level depth, represents the echo flight time, represents the unheated sound speed. The acquisition method of the current water quality feature group is the same as that of the sample water quality feature group, which will not be repeated here.

[0144] In detail, the echo flight time is calculated based on the analog voltage signal, including:

[0145] The analog voltage signal is subjected to analog-digital conversion to obtain a discrete digital signal sequence, wherein the discrete digital signal sequence includes a plurality of discrete voltage values;

[0146] The discrete digital signal sequence is subjected to band-pass filtering to obtain a filtered digital signal sequence, and the filtered digital signal sequence is subjected to envelope extraction to obtain an envelope line;

[0147] According to a preset amplitude threshold, the water surface reflection voltage value is queried on the envelope line to confirm the index position of the water surface reflection voltage value;

[0148] The echo flight time is calculated based on the index position and the sampling frequency delay.

[0149] It can be understood that the analog-to-digital conversion refers to the process of discretizing an analog voltage signal into a digital sequence at a sampling frequency using an analog-to-digital converter (ADC). The discrete digital signal sequence refers to an ordered array of numbers obtained after analog-to-digital conversion, which includes a plurality of discrete voltage values, wherein the discrete voltage value refers to the numerical value obtained after quantizing the analog voltage at each sampling time. The band-pass filtering refers to a filtering algorithm that only allows signals of a specific frequency band to pass, and the purpose of the band-pass filtering is to suppress noise outside the passband frequency range (i.e. the specific frequency band, set by humans). The filtered digital signal sequence refers to the discrete digital signal sequence after band-pass filtering. The envelope extraction refers to the operation of extracting the amplitude trend over time from the filtered digital signal sequence, and the purpose of the envelope extraction is to highlight the amplitude information of the filtered digital signal sequence to facilitate subsequent peak detection. The envelope curve refers to a curve representing the amplitude variation of the filtered digital signal sequence. The amplitude threshold refers to a human-predefined voltage amplitude used to distinguish between valid echoes and background noise. The water surface reflection voltage value refers to the first amplitude greater than the amplitude threshold on the envelope curve, which represents the amplitude of the echo signal reflected back from the water surface by the ultrasonic wave. The index position refers to the arrangement number of the water surface reflection voltage value in the discrete digital signal sequence, i.e. the index position represents the specific time when the ultrasonic wave is reflected back from the water surface. The echo flight time length refers to the total time from the emission of the ultrasonic wave to the reception of the reflected wave from the water surface, and the calculation method of the echo flight time length is: wherein, represents the echo flight time length, represents the index position, represents the sampling frequency.

[0150] S4, based on the sample property data set, the user-selected power, the current water level depth, and the current water quality feature group, estimate the heating time length to obtain the predicted heating time length.

[0151] It needs to be explained that the predicted heating time length refers to the predicted time required for the water contained in the intelligent kettle to be heated to the boiling state according to the user-selected power.

[0152] In detail, the heating time length estimation based on the sample property data set, the user-selected power, the current water level depth, and the current water quality feature group to obtain the predicted heating time length includes:

[0153] Extracting sample property data from the sample property data set in sequence;

[0154] Calculating the water quality similarity according to the current water quality feature group and the sample water quality feature group in the sample property data, wherein the water quality similarity is a cosine value;

[0155] Summarize the water quality similarity to obtain a water quality similarity set, and normalize the water quality similarity set to obtain a normalized similarity set;

[0156] The predicted unit energy consumption is obtained by weighted summation based on the normalized similarity set and the sample property dataset.

[0157] The total energy consumption is calculated based on the predicted unit energy consumption and the current water level depth, and the predicted heating time is calculated based on the user-selected power and the predicted total energy consumption.

[0158] It is clear that the water quality similarity refers to a numerical value that quantifies the degree of similarity between the current water quality feature group and the sample water quality feature group. The higher the water quality similarity, the higher the degree of similarity between the current water quality feature group and the sample water quality feature group. The calculation method of the above water quality similarity is as follows: the current water quality feature group and the sample water quality feature group are vectorized respectively to obtain the current water quality feature vector and the sample water quality feature vector. The cosine value of the current water quality feature vector and the sample water quality feature vector is calculated, and the cosine value is recorded as the water quality similarity. Here, the current water quality feature vector and the sample water quality feature vector point to the quantized current water quality feature group and the sample water quality feature group, respectively. For example, if a current water quality feature group is (R1, R2, R3), then the current water quality feature group is vectorized to obtain the current water quality feature vector. The vectorization of the sample water quality feature group is the same as that of the current water quality feature group, and will not be repeated here. The normalized similarity set refers to the normalized water quality similarity set, wherein the normalization method can be selected as minimum-maximum normalization. The predicted unit energy consumption refers to the energy consumption required to heat the water contained in the smart kettle to one unit depth (i.e., the reciprocal of the current water level depth). The predicted total energy consumption refers to the product of the predicted unit energy consumption and the current water level depth, which represents the total energy consumption required to heat the contained water to a boiling state. The predicted heating time is calculated by dividing the predicted total energy consumption by the power selected by the user.

[0159] In detail, the predicted unit energy consumption is expressed as:

[0160] ,

[0161] in, This indicates the predicted unit energy consumption. This indicates the number of normalized similarities in the normalized similarity set or the number of sample property data in the sample property dataset. Denotes the first in the normalized similarity set Normalized similarity, Indicates the properties of the sample in the dataset. Unit heating energy consumption in the sample property data.

[0162] It needs to be explained that the purpose of introducing the normalized similarity in the above calculation formula of the predicted unit energy consumption is to give different weights to different sample property data, so that the more similar the sample property data to the current water quality, the greater the contribution to the prediction of the unit energy consumption, thereby improving the accuracy of the prediction.

[0163] S5, according to the predicted heating time, the visual display of the heating time is executed on the standby display screen, and the current display screen is obtained.

[0164] It can be understood that the current display screen refers to the display screen that displays the predicted heating time. The user can understand the heating time required under the user-selected power through the current display screen, and the user can reselect the user-selected power, and then repeat the above step of receiving the user input instruction.

[0165] S6, in the preset heating stage, the boiling time prediction model is used to predict the boiling time, and the predicted boiling time is obtained. The current display screen is updated based on the predicted boiling time, and the target display screen is obtained. Based on the target display screen, the intelligent kettle heating control based on ultrasonic wave sensing is completed.

[0166] It can be understood that the heating stage refers to the stage in which the user completes the selection of the power, starts the switch of the intelligent kettle, and then makes the intelligent kettle heat. The predicted boiling time refers to the time required for the intelligent kettle to complete heating. The target display screen refers to the current display screen updated by the predicted boiling time, wherein updating the current display screen based on the predicted boiling time refers to displaying the predicted boiling time in the current display screen, so that the user can know the progress of the intelligent kettle heating and the remaining time (i.e. the predicted boiling time) of the heating in real time.

[0167] Importantly, the boiling time prediction model is used to predict the boiling time, and the predicted boiling time is obtained, including:

[0168] Obtain the current ultrasonic feature group and the current water temperature;

[0169] According to the current ultrasonic feature group, the current water temperature and the current water quality feature group, a current input vector is constructed, and the current input vector is input into the boiling time prediction model to obtain the predicted boiling time.

[0170] It can be understood that the current input vector refers to a vector composed of the current ultrasonic feature group, the current water temperature and the current water quality feature group, and the construction of the current input vector has the same steps as the construction of the above target input vector, which will not be repeated here.

[0171] The present application is to solve the problems described in the background art. First, by configuring an ultrasonic sensor in the intelligent kettle, non-contact detection of the water level is achieved, avoiding the problem of easy fouling and corrosion of traditional contact sensors, while providing a key physical signal acquisition basis for subsequent processes. The integration of the display screen provides an intuitive interface for users. The present scheme uses a sample training data set to train a pre-built neural network model to obtain a boiling duration prediction model. This step builds a training set containing multi-dimensional features (water quality, acoustic characteristics, energy consumption) to enable the trained neural network model to deeply learn the physical change law of different water qualities at different heating stages, thereby significantly improving the accuracy of boiling time prediction and the generalization ability of the model. It solves the problem of insufficient accuracy of traditional temperature prediction models in variable water quality environments. Then, based on the sample property data set, the user-selected power, the current water level depth, and the current water quality feature group, the heating duration is estimated to obtain the predicted heating duration. This step estimates the energy consumption by calculating the similarity of the current water quality and the historical sample and performing weighted fusion, thereby combining dynamic judgments of historical data and current actual situations to enable the heating duration prediction to adapt to different users' water quality and water adding habits, improving the accuracy and reliability of personalized prediction. Further, the present scheme also performs visual display of the heating duration on the standby display screen according to the predicted heating duration to obtain the current display screen. This step clearly shows the predicted heating duration under different selected powers to the user, providing a clear expectation, making it easy for users to flexibly select the most suitable heating power according to time requirements, and improving the intelligent level of the product. Finally, during the heating stage, the boiling duration prediction model is used to predict the boiling duration to obtain the predicted boiling duration. Based on the predicted boiling duration, the current display screen is updated to obtain the target display screen. This step uses the trained model to perform real-time and dynamic boiling duration prediction during the heating process, which can more accurately determine the boiling point and stop heating in time, thereby effectively avoiding energy waste caused by excessive boiling. Therefore, the present application can improve the accuracy of boiling state prediction during the heating process of the kettle and improve the intelligent level of the kettle heating control.

[0172] As Figure 2 shown is a functional module diagram of an intelligent kettle heating control system based on ultrasonic sensing according to an embodiment of the present application.

[0173] The intelligent kettle heating control system 100 based on ultrasonic sensing can be installed in an electronic device. According to the functions implemented, the intelligent kettle heating control system 100 based on ultrasonic sensing can include a prediction model construction module 101, a water level depth detection module 102, a heating duration prediction module 103, and a heating information display module 104. The modules of the present application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete a fixed function, which are stored in the memory of the electronic device.

[0174] The prediction model construction module 101 is used to confirm an intelligent kettle, wherein the intelligent kettle includes an ultrasonic sensor and a standby display screen, collects a set of samples to be heated, constructs a set of sample training data and a set of sample properties based on the set of samples to be heated and the intelligent kettle, trains a pre-constructed neural network model using the set of sample training data, and obtains a boiling duration prediction model;

[0175] The water level depth detection module 102 is used to receive a user input instruction, identify a user-selected power based on the user input instruction, detect a current water quality feature group and a current water level depth;

[0176] The heating duration prediction module 103 is used to estimate the heating duration based on the set of sample properties, the user-selected power, the current water level depth, and the current water quality feature group, and obtain a predicted heating duration;

[0177] The heating information display module 104 is used to perform visual display of the heating duration on the standby display screen according to the predicted heating duration, obtain a current display screen, perform boiling duration prediction using the boiling duration prediction model in a preset heating stage, obtain a predicted boiling duration, update the current display screen based on the predicted boiling duration, and obtain a target display screen.

[0178] In detail, the modules in the intelligent kettle heating control system 100 based on ultrasonic sensing in the embodiments of the present application use the same technical means as the intelligent kettle heating control method based on ultrasonic sensing in the above Figure 1 , and can produce the same technical effects, which will not be described here.

[0179] As Figure 3 shown, it is a structural schematic diagram of an electronic device for implementing an intelligent kettle heating control method based on ultrasonic sensing according to an embodiment of the present application.

[0180] The electronic device 1 can include a processor 10, a memory 11, and a bus 12, and can also include a computer program stored in the memory 11 and executable on the processor 10, such as an intelligent kettle heating control method based on ultrasonic sensing program.

[0181] The memory 11 includes at least one type of readable storage medium, such as flash memory, mobile hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 1. Further, the memory 11 includes both an internal storage unit and an external storage device of the electronic device 1. The memory 11 can be used to store application software and various data installed on the electronic device 1, such as the code of the smart kettle heating control method program based on ultrasonic sensing, and can also be used to temporarily store data that has been output or will be output.

[0182] The processor 10 can be composed of an integrated circuit in some embodiments, such as a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more combinations of central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips, etc. The processor 10 is the control core of the electronic device, which connects various components of the entire electronic device through various interfaces and lines, executes programs or modules stored in the memory 11 (such as the smart kettle heating control method program based on ultrasonic sensing, etc.), and calls data stored in the memory 11 to perform various functions and process data of the electronic device 1.

[0183] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0184] Figure 3 Only the electronic device with components is shown, and those skilled in the art can understand that, Figure 3The illustrated structure does not constitute a limitation on the electronic device 1, and can include fewer or more components than illustrated, or combine certain components, or different component arrangements.

[0185] For example, although not shown, the electronic device 1 can also include a power source (such as a battery) to power the various components, and preferably the power source can be logically connected to the at least one processor 10 through a power management system, so that the power management system can implement functions such as charge management, discharge management, and power consumption management. The power source can also include one or more DC or AC power sources, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and any other components. The electronic device 1 can also include various sensors, Bluetooth modules, Wi-Fi modules, and the like, which are not described here.

[0186] Further, the electronic device 1 can also include a network interface, which can optionally include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), and is typically used to establish a communication connection between the electronic device 1 and other electronic devices.

[0187] Optionally, the electronic device 1 can also include a user interface, which can be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally a standard wired interface, a wireless interface. Optionally, in some embodiments, the display can be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch, etc. The display can also be appropriately referred to as a display screen or a display unit, and is used to display information processed in the electronic device 1 and to display a visualized user interface.

[0188] The ultrasonic sensor-based intelligent kettle heating control method program stored in the memory 11 in the electronic device 1 is a combination of multiple instructions, which, when executed in the processor 10, can achieve:

[0189] Confirming an intelligent kettle, wherein the intelligent kettle includes an ultrasonic sensor and a standby display screen;

[0190] Collecting a set of samples to be heated, constructing a sample training data set and a sample property data set based on the set of samples to be heated and the intelligent kettle, training a pre-constructed neural network model using the sample training data set to obtain a boiling duration prediction model;

[0191] Receiving a user input instruction, identifying a user-selected power based on the user input instruction, detecting a current water quality feature group and a current water level depth;

[0192] based on the sample property dataset, the user-selected power, the current water level depth, and the current water quality feature group, to obtain a predicted heating duration;

[0193] According to the predicted heating duration, a visual display of the heating duration is performed on the standby display screen to obtain a current display screen.

[0194] In a preset heating stage, a boiling duration prediction model is used to predict a boiling duration to obtain a predicted boiling duration, and the current display screen is updated based on the predicted boiling duration to obtain a target display screen, and the intelligent kettle heating control based on ultrasonic sensing is completed based on the target display screen.

[0195] Specifically, the specific implementation method of the processor 10 on the above instructions can refer to Figures 1 to 3 The description of related steps in the corresponding embodiments will not be repeated here.

[0196] Further, the modules / units integrated in the electronic device 1, if realized in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. The computer readable storage medium can be volatile or non-volatile. For example, the computer readable medium can include any entity or system capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory).

[0197] The application also provides a computer readable storage medium, which stores a computer program, and the computer program can realize the following when executed by a processor of an electronic device:

[0198] Confirm the intelligent kettle, wherein the intelligent kettle comprises an ultrasonic sensor and a standby display screen.

[0199] Collect a set of samples to be heated, construct a sample training dataset and a sample property dataset based on the set of samples to be heated and the intelligent kettle, train a pre-constructed neural network model using the sample training dataset to obtain a boiling duration prediction model.

[0200] Receive a user input instruction, identify a user-selected power based on the user input instruction, and detect a current water quality feature group and a current water level depth.

[0201] based on the sample property dataset, the user-selected power, the current water level depth, and the current water quality feature group, to obtain a predicted heating duration;

[0202] According to the predicted heating duration, a visual display of the heating duration is performed on the standby display screen to obtain a current display screen.

[0203] In the preset heating stage, the boiling duration prediction model is used for boiling duration prediction to obtain a predicted boiling duration, the current display screen is updated based on the predicted boiling duration to obtain a target display screen, and the intelligent kettle heating control based on ultrasonic wave sensing is completed based on the target display screen.

[0204] In several embodiments provided by the present application, it should be understood that the disclosed devices, systems and methods can be implemented in other manners. For example, the embodiments of the system described above are merely illustrative, and the actual implementation can have other division manners.

[0205] The modules described as separated components can or can not be physically separated, and the components displayed as modules can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments.

[0206] In addition, each functional module in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional modules.

[0207] It is obvious for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0208] Finally, it should be noted that the above embodiments are merely used to illustrate the technical solutions of the present application but not limit the present application, and although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application.

Claims

1. An intelligent kettle heating control method based on ultrasonic wave sensing, characterized in that, The method comprises: Confirming the intelligent kettle, wherein the intelligent kettle comprises an ultrasonic sensor and a standby display screen; Collecting a set of samples to be heated, constructing a sample training data set and a sample property data set based on the set of samples to be heated and the intelligent kettle, training a pre-constructed neural network model using the sample training data set to obtain a boiling duration prediction model; Receiving a user input instruction, identifying a user-selected power based on the user input instruction, detecting a current water quality feature group and a current water level depth; Based on the sample property data set, the user-selected power, the current water level depth, and the current water quality feature group, estimating the heating duration to obtain a predicted heating duration; According to the predicted heating duration, performing visual display of the heating duration on the standby display screen to obtain a current display screen; In a preset heating stage, the boiling duration prediction model is used to predict the boiling duration to obtain a predicted boiling duration, and the current display screen is updated based on the predicted boiling duration to obtain a target display screen, and the intelligent kettle heating control based on the ultrasonic sensor is completed based on the target display screen. 2.The ultrasonic sensor-based smart kettle heating control method of claim 1, wherein, The construction of the sample training data set and the sample property data set based on the set of samples to be heated and the intelligent kettle comprises: Extracting the samples to be heated in the set of samples to be heated in turn, wherein the samples to be heated are pure water, mineral water or hard water; Constructing a sound speed temperature empirical formula of the samples to be heated; Using the intelligent kettle to heat the samples to be heated to obtain heating energy consumption and a sample heating data group; Collecting water quality of the samples to be heated based on a pre-constructed water quality sensor group to obtain a sample water quality feature group, wherein the sample water quality feature group contains sample temperature; Recording the water level depth of the samples to be heated in the intelligent kettle, and calculating unit heating energy consumption according to the water level depth and the heating energy consumption; Matching the unit heating energy consumption, the sound speed temperature empirical formula, and the sample water quality feature group to obtain sample properties; Supplementing each sample heating data in the sample heating data group using the sample water quality feature group to obtain a sample training data group; Merging the sample training data group corresponding to each sample to be heated to obtain a sample training data set, and summarizing the sample property data corresponding to each sample to be heated to obtain a sample property data set. 3.The ultrasonic sensor-based smart kettle heating control method of claim 2, wherein, The heating of the samples to be heated using the intelligent kettle to obtain heating energy consumption and a sample heating data group comprises: Confirming the initial collection time of the preset sample heating instruction; Based on the initial collection time and the intelligent kettle, heating the samples to be heated, and in the heating process, using the ultrasonic sensor and the pre-constructed temperature sensor to collect parameters of the samples to be heated to obtain an ultrasonic feature group and a current temperature; Pairing the current temperature and the ultrasonic feature group to obtain original heating data; Judging whether the samples to be heated are in a preset boiling state; If the samples to be heated are not in the boiling state, calculating an updated collection time according to a preset collection interval and the initial collection time, taking the updated collection time as the initial collection time, and returning to the step of heating the samples to be heated based on the initial collection time and the intelligent kettle until the samples to be heated are in the boiling state; If the sample to be heated is in a boiling state, the initial collection time is recorded as the sample boiling time, and the original heating data is summarized to obtain the original heating dataset. The original heating dataset is updated using the boiling point of the sample to obtain the sample heating data set; Record the total heating time and calculate the heating energy consumption based on the total heating time and the preset rated heating power. 4.The ultrasonic sensor-based smart kettle heating control method of claim 3, wherein, The process of updating the original heating dataset using the sample boiling time to obtain a sample heating data set includes: Extract the original heating data sequentially from the original heating dataset to determine the data acquisition time of the original heating data. The sample boiling interval is calculated based on the data acquisition time and the sample boiling time. The sample boiling interval is added to the original heating data to obtain sample heating data, wherein the sample heating data includes: sample boiling interval and original heating data; Summarize the sample heating data to obtain the sample heating data set. 5.The ultrasonic sensor-based smart kettle heating control method of claim 4, wherein, The step of training a pre-built neural network model using a sample training dataset to obtain a boiling duration prediction model includes: Extract sample training data sequentially from the sample training dataset and denote the sample training data as the target training data. The target water quality feature set and target heating data in the target training data were identified, and the actual boiling interval, target sample temperature and target ultrasonic feature set were obtained based on the target heating data. Construct a target input vector based on the target water quality characteristic set, the target sample temperature, and the target ultrasonic characteristic set; The target input vector is input into the neural network model to obtain the predicted boiling interval, and the model loss value is calculated based on the predicted boiling interval and the actual boiling interval. If the model loss value is greater than the preset loss threshold, the neural network model is adjusted according to the model loss value to obtain an updated model; The updated model is used as a neural network model, and the steps of sequentially extracting sample training data from the sample training dataset are returned until the model loss value is not much greater than the loss threshold. If the model loss value is not greater than the loss threshold, the neural network model is recorded as the boiling time prediction model. 6.The ultrasonic sensor-based smart kettle heating control method of claim 5, wherein, The detection of the current water quality characteristic group and the current water level depth includes: Water quality data is collected using a water quality sensor array to obtain the current water quality characteristics. The water quality sensor array includes: a pH sensor, a turbidity sensor, a residual chlorine sensor, and a conductivity sensor. The ultrasonic sensor transmits a signal based on preset reference pulse signal parameters. After the signal transmission ends, the ultrasonic sensor is switched to a receiving sensor. The reference pulse signal parameters include: reference frequency, reference pulse width, and reference pulse amplitude. Confirm the transmission time of the signal; Based on the transmission time and the preset acquisition frequency, the receiving sensor is used to receive signals within the acquisition interval to obtain analog voltage signals; Echo flight duration is calculated based on analog voltage signals; Based on the current water quality characteristic group, identify similar property data in the sample property dataset, and continue to identify target empirical formulas in the similar property data; The unheated temperature is detected using a temperature sensor, and the unheated sound velocity is calculated based on the unheated temperature and the target empirical formula. The current water level depth is calculated based on the unheated sound speed and the echo flight time. 7.The ultrasonic sensor-based smart kettle heating control method of claim 6, wherein, The echo flight time is calculated based on the analog voltage signal, and the echo flight time is calculated based on the analog voltage signal. Analog-to-digital conversion is performed on the analog voltage signal to obtain a discrete digital signal sequence, wherein the discrete digital signal sequence includes a plurality of discrete voltage values. The discrete digital signal sequence is band-pass filtered to obtain a filtered digital signal sequence, and the filtered digital signal sequence is envelope extracted to obtain an envelope line. According to the preset amplitude threshold, the water surface reflection voltage value is queried on the envelope line, and the index position of the water surface reflection voltage value is confirmed. The echo flight time is calculated based on the index position and the sampling frequency delay. 8.The ultrasonic sensor-based smart kettle heating control method of claim 7, wherein, The heating time is estimated based on the sample property data set, the user-selected power, the current water level depth, and the current water quality feature group to obtain the predicted heating time, including: Sample property data is extracted from the sample property data set in sequence. The water quality similarity is calculated according to the current water quality feature group and the sample water quality feature group in the sample property data, wherein the water quality similarity is a cosine value. The water quality similarity set is obtained by normalizing the water quality similarity set. The predicted unit energy consumption is obtained by weighted summation according to the normalized similarity set and the sample property data set. The predicted total energy consumption is calculated according to the predicted unit energy consumption and the current water level depth, and the predicted heating time is calculated based on the user-selected power and the predicted total energy consumption. 9.The ultrasonic sensor-based smart kettle heating control method of claim 8, wherein, The predicted unit energy consumption is represented as: ， in, This indicates the predicted unit energy consumption. This indicates the number of normalized similarities in the normalized similarity set or the number of sample property data in the sample property dataset. Denotes the first in the normalized similarity set Normalized similarity, Indicates the properties of the sample in the dataset. Unit heating energy consumption in the sample property data.

10. An intelligent kettle heating control system based on ultrasonic wave sensing, characterized in that, The system includes: A prediction model construction module is used to confirm the intelligent kettle, wherein the intelligent kettle includes an ultrasonic sensor and a standby display screen, a sample set to be heated is collected, a sample training data set and a sample property data set are constructed based on the sample set to be heated and the intelligent kettle, and a neural network model is trained using the sample training data set to obtain a boiling time prediction model. A water level depth detection module is used to receive user input instructions, identify user-selected power based on user input instructions, detect current water quality feature groups and current water level depth. A heating time prediction module is used to estimate the heating time based on the sample property data set, the user-selected power, the current water level depth, and the current water quality feature group to obtain the predicted heating time. A heating information display module is used to perform visual display of the heating time on the standby display screen according to the predicted heating time to obtain a current display screen, and a boiling time prediction model is used to predict the boiling time in a preset heating stage to obtain a predicted boiling time.

Images