Intelligent monitoring method and system for pot temperature

Abstract

The present invention relates to the field of temperature monitoring technology, and in particular to an intelligent monitoring method and system for pot temperature. The method comprises the following steps: obtaining pot structure data; performing sensor array deployment on the pot structure data to generate pot sensor deployment data; performing multi-point calibration of temperature sensors on the pot sensor deployment data to generate pot sensor calibration data; using the pot sensor calibration data to perform pot temperature acquisition on the temperature sensor built into the pot to obtain standard pot temperature acquisition data; performing BM temperature curve conversion on the standard pot temperature acquisition data to generate a BM temperature conversion curve; performing extreme temperature extraction on the BM temperature conversion curve to obtain pot extreme temperature data. The present invention improves the accuracy and flexibility of intelligent monitoring of pot temperature through high-precision sensor arrays, intelligent mode division, fuzzy control feedback and cloud-based real-time learning.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature monitoring, and in particular to an intelligent monitoring method and system for the temperature of a cooker. Background Art

[0002] In the early days, the monitoring of pot temperature mainly relied on traditional physical measuring devices such as thermometers or thermocouples. Although these devices can provide real-time temperature data, they are not convenient to use and difficult to achieve remote monitoring. With the development of sensor technology, especially the advancement of temperature sensors and wireless transmission technology, more and more smart pots have begun to use integrated temperature sensors, which can collect temperature data of pots in real time and transmit data to smartphones or the cloud through wireless technologies such as Bluetooth and Wi-Fi. This technological breakthrough allows users to remotely monitor and control through mobile applications. In recent years, the combination of artificial intelligence and big data analysis has brought more accurate solutions for pot temperature monitoring. By integrating machine learning algorithms, the system can not only monitor the temperature of the pot in real time, but also automatically adjust the heating power according to the user's cooking habits and the heating status of the pot to avoid excessively high or low temperatures, thereby improving cooking efficiency and food quality. However, the current traditional pot temperature adjustment method is usually a simple temperature control, which cannot be intelligently adjusted according to the different working states of the pot (such as empty pot or load state). At the same time, the temperature or heating method is dynamically adjusted according to actual needs during the pot heating process, and it fails to be optimized in real time according to the user's usage, which leads to low accuracy and flexibility in intelligent monitoring of pot temperature. Summary of the invention

[0003] Based on this, it is necessary to provide an intelligent monitoring method and system for cookware temperature to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for intelligently monitoring the temperature of a cooker is provided, the method comprising the following steps:

[0005] Step S1: acquiring the structure data of the pot; performing sensor array deployment on the structure data of the pot to generate the pot sensor deployment data; performing multi-point calibration of the temperature sensor on the pot sensor deployment data to generate the pot sensor calibration data; using the pot sensor calibration data to perform pot temperature acquisition on the temperature sensor built into the pot to obtain the standard pot temperature acquisition data;

[0006] Step S2: converting the standard pot temperature collection data into a BM temperature curve to generate a BM temperature conversion curve; extracting the extreme temperature of the BM temperature conversion curve to obtain the pot extreme temperature data; dividing the pot into a first mode based on the pot extreme temperature data to generate a pot empty pot mode; performing a content temperature critical analysis on the standard pot temperature collection data based on the BM temperature conversion curve to generate a content temperature change critical temperature; dividing the second mode based on the content temperature change critical temperature to generate a pot load mode;

[0007] Step S3: predicting the pot heating stage for the pot empty mode and the pot loaded mode to generate pot heating stage prediction data; performing fuzzy control feedback on the pot according to the pot heating stage prediction data to generate control temperature feedback data; optimizing and adjusting the heating energy efficiency of the control temperature feedback data to generate an intelligent heating adjustment strategy;

[0008] Step S4: Upload the intelligent heating regulation strategy to the cloud platform to collect strategy execution data and obtain heating regulation strategy execution data; perform strategy cloud learning on the heating regulation strategy execution data to generate real-time heating strategy adjustment data; track the performance of the cookware through the real-time heating strategy adjustment data to generate cookware heating performance tracking data to perform normal cookware temperature intelligent monitoring operations.

[0009] The present invention can realize high-precision temperature monitoring of various parts of the pot by acquiring the pot structure data and deploying the sensor array. The data consistency and accuracy of each sensor are ensured by multi-point calibration, thereby eliminating the error in temperature acquisition, obtaining standard pot temperature data, and providing reliable basic data for subsequent intelligent adjustment. BM temperature curve conversion and extreme temperature extraction make the temperature data of the pot more intuitive and can capture the key temperature change trend. Through the division of empty pot mode and load mode, accurate identification of different use states of the pot is realized, thereby providing targeted strategies for subsequent heating stage prediction and temperature adjustment. By predicting the heating stage of the pot, the current heating stage of the pot can be accurately judged, so as to make dynamic adjustments. In this process, the fuzzy control feedback mechanism can perform intelligent temperature control according to real-time data, avoid the single temperature control method in the traditional system, improve the energy efficiency of the pot heating process, and realize more efficient heat distribution. The heating adjustment strategy is uploaded to the cloud platform, and combined with the cloud learning mechanism, the heating strategy can be continuously optimized according to the long-term accumulated data, so as to improve the adaptability and performance of the pot in different environments. Real-time heating strategy adjustment data and pot performance tracking can realize intelligent monitoring of the pot heating process, ensure that its temperature control performance is always in the best state, and make personalized adjustments according to usage habits or needs. Therefore, the present invention improves the accuracy and flexibility of intelligent monitoring of pot temperature through high-precision sensor array, intelligent mode division, fuzzy control feedback and real-time learning in the cloud.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: obtaining the pot structure data;

[0012] Step S12: Calculate the structure center point of the cookware structure data to obtain the cookware structure center point data; perform sensor array deployment based on the cookware structure center point data to generate cookware sensor deployment data, wherein the sensor array deployment includes pressure sensor array deployment and temperature sensor array deployment;

[0013] Step S13: performing multi-point calibration of the temperature sensor on the pot sensor deployment data to generate pot sensor calibration data; using the pot sensor calibration data to collect the pot temperature of the temperature sensor built into the pot to obtain the pot temperature collection data;

[0014] Step S14: performing data preprocessing on the pot temperature collection data to generate standard pot temperature collection data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization.

[0015] The present invention calculates the center point of the pot structure and deploys the sensor array based on the data to ensure that the sensor can cover the key area of ​​the pot, thereby improving the representativeness and reliability of temperature measurement. Multi-point calibration of the temperature sensor can eliminate errors caused by sensor inconsistency and improve the accuracy of the pot temperature acquisition data. By cleaning, denoising, filling missing values ​​and standardizing the pot temperature acquisition data, the data quality is ensured, providing a high-quality data foundation for subsequent analysis and optimization. Using the data that has been accurately calibrated and processed, the system can still maintain high accuracy under different environmental conditions, reducing the uncertainty caused by external interference or errors in the equipment itself.

[0016] Preferably, performing multi-point sensor calibration on the cookware sensor deployment data includes:

[0017] The temperature sensor is selected for calibration points in the working temperature range through the pot sensor deployment data to obtain calibration point data in the working temperature range; the temperature sensor is confirmed for multi-point heating data of the target point based on the calibration point data in the working temperature range to generate heating temperature data of the calibration point;

[0018] The actual temperature error analysis is performed on the calibration point data in the working temperature range and the heating temperature data at the calibration point to obtain the actual temperature relationship model. The actual temperature relationship model is used to perform thermal conduction delay compensation on the temperature sensor to generate the calibration data of the pot temperature sensor. The formula for the actual temperature error analysis is as follows:

[0019] ;

[0020] In the formula, Expressed as actual temperature, Expressed as the sensor output voltage, is the fitting coefficient;

[0021] The formula for thermal conduction delay compensation is as follows:

[0022] ;

[0023] In the formula, Expressed as the pot contents at time The temperature at Represented as the pot bottom at time The temperature at Indicated as the material and contents of the pot at the time The temperature difference.

[0024] The present invention ensures that the sensor can provide accurate temperature measurement under the actual working conditions of the pot by selecting appropriate calibration points in the working temperature range, thereby avoiding errors caused by the sensor working temperature range not being adapted to the actual environment. Through data confirmation of multi-point heating of the target point, the accuracy of the temperature sensor at different temperatures can be further improved, ensuring the accuracy at multiple different positions and different temperature conditions of the pot. Through the actual temperature error analysis, the actual temperature relationship model obtained helps to understand the relationship between the sensor output and the actual temperature, thereby achieving more accurate temperature measurement. The error model enables the sensor output to be optimized through the fitting coefficient, further improving the accuracy of the sensor. The heat conduction delay compensation formula can make up for the temperature difference between the material and the content in the pot, especially in the case of rapid heating or uneven heating, effectively reducing the measurement error caused by time delay, and ensuring the accuracy of the real-time temperature. Through this precise multi-point calibration and compensation method, the pot temperature sensor can work stably under a variety of use conditions, reduce the impact of temperature drift or inconsistency, and improve the stability and reliability of the entire pot temperature monitoring system. In summary, multi-point calibration and thermal conduction delay compensation not only improve the accuracy and response speed of the temperature sensor, but also enhance the performance of the system in complex usage environments, making pot temperature monitoring more accurate, real-time and reliable.

[0025] Preferably, step S2 comprises the following steps:

[0026] Step S21: converting the standard pot temperature collection data into a BM temperature curve to generate a BM temperature conversion curve; extracting the extreme temperature of the BM temperature conversion curve to obtain the pot extreme temperature data; comparing the pot extreme temperature data with a preset first temperature threshold, and when the pot extreme temperature data is greater than or equal to the preset first temperature threshold, a pot hot reminder is issued through an indicator light;

[0027] Step S22: when the extreme temperature data of the pot is greater than a preset first temperature threshold and greater than a preset second temperature threshold, a dry-burning warning is performed on the pot based on the extreme temperature data of the pot, thereby generating dry-burning warning data; the pot is divided into a first mode based on the dry-burning warning data, and a pot empty pot mode is generated;

[0028] Step S23: using the pressure sensor and the BM temperature conversion curve to perform a critical temperature analysis of the contents on the standard cookware temperature collection data, and generating a critical temperature of the contents temperature change;

[0029] Step S24: performing content state identification according to the critical temperature of the content temperature change to generate content state identification data; performing second mode division based on the content state identification data to generate a cookware load mode.

[0030] The present invention converts the standard pot temperature collection data into a temperature curve form that is easy to analyze through BM temperature curve conversion, and extracts extreme temperature data, which not only improves the accuracy of temperature measurement, but also lays the foundation for subsequent early warning and status analysis. The extreme temperature data of the pot is compared with the preset temperature threshold. When the temperature reaches or exceeds the set first temperature threshold, the indicator light can remind the user that the pot is overheated, effectively avoiding damage or danger to the pot caused by excessive temperature. By setting multiple temperature thresholds and performing accurate temperature comparisons, when the pot temperature exceeds the second temperature threshold, the system will issue a dry burning warning to prevent the pot from being damaged due to empty burning or dry burning in advance. This early warning mechanism can effectively extend the service life of the pot and improve safety. Based on the analysis of the extreme temperature data of the pot and the dry burning warning data, the system can automatically divide the working mode of the pot (such as the empty pot mode) and intelligently monitor the pot, which helps to automatically adjust the heating strategy under different working conditions, improve energy efficiency, and avoid waste and damage. Through the pressure sensor and the BM temperature conversion curve, the system can perform critical analysis of the temperature of the contents and obtain the critical point of the temperature change of the contents. Combined with this information, the status of the contents can be effectively identified, and the load mode of the pot can be further analyzed, thereby optimizing the cooking process and ensuring the cooking effect of the food and the safe use of the pot. Through layered temperature monitoring, dry-burning warning and load mode division, the system can monitor the status of the pot in real time while improving the safety and intelligence level of the pot, allowing users to automatically adjust the working status of the pot without frequent intervention, ensuring a smooth and safe cooking process.

[0031] Preferably, when the extreme temperature data of the cooker is greater than a preset first temperature threshold and greater than a preset second temperature threshold, the cooker is given a dry-burning warning based on the extreme temperature data of the cooker, including:

[0032] When the extreme temperature data of the pot is greater than a preset first temperature threshold and greater than a preset second temperature threshold, a pot array temperature change analysis is performed on the standard pot temperature collection data based on the extreme temperature data of the pot to generate pot temperature change data; the pot temperature change data is converted into a heat map to generate a pot temperature change heat map;

[0033] Performing heat map edge recognition on the heat map of pot temperature change to generate pot edge temperature change data; performing temperature gradient field calculation on the pot edge temperature change data to generate pot edge temperature gradient field; performing gradient amplitude calculation on the pot edge temperature gradient field to obtain edge temperature gradient field amplitude data;

[0034] The edge temperature gradient field amplitude data is used to perform a thermal map texture analysis on the temperature change heat map of the cookware to generate thermal map texture temperature change amplitude data. Based on the thermal map texture temperature change amplitude data, the heat uniformity of the cookware is analyzed to generate heat uniformity data for the cookware. Based on the heat uniformity data for the cookware, a dry-burning warning is given to the cookware to generate dry-burning warning data.

[0035] The present invention combines the extreme temperature data of the pot with the temperature collection data of the standard pot to analyze the temperature change of the pot array, and can monitor the temperature change of each area of ​​the pot in detail. This detailed analysis helps to find the problem of uneven heating or overheating of the pot early. Converting the temperature change data of the pot into a thermal map and performing edge recognition on it helps to accurately locate the high-temperature area of ​​the pot, especially the temperature distribution in the edge area of ​​the pot. This provides a key basis for judging whether the pot is dry-burned. Calculating the temperature gradient field at the edge of the pot can deeply understand the spatial distribution of temperature changes, thereby revealing the heating situation of the pot. This method can clearly display the area with uneven heating, especially the area with large temperature gradient, indicating the risk of dry burning. By analyzing the temperature change amplitude of the thermal map texture, the system can further evaluate the uniformity of the heating of the pot. Accurately identifying the area where the pot is heated unevenly can provide a basis for optimizing the heating plan or early warning, and help avoid the danger of dry burning or overheating of the pot during operation. Based on the analysis of the heat uniformity data of the pot, when it is found that the temperature distribution of the pot is uneven and there is a risk of dry burning, the system can issue a dry burning warning in time to prevent the pot from being damaged due to local overheating or empty burning. This function greatly improves the safety of the system through multi-level temperature change data and intelligent algorithms. By real-time monitoring of the temperature changes of the pot and issuing early warnings, it can effectively prevent damage to the pot caused by dry burning or uneven heating. This system can extend the service life of the pot and improve the safety and user experience during the cooking process. In summary, through detailed temperature change analysis, thermal map conversion and heat uniformity evaluation, the steps effectively improve the intelligent monitoring capabilities of the pot, timely detect potential dry burning risks, and significantly improve the safety and durability of the pot.

[0036] Preferably, identifying the state of the contents according to the critical temperature of the contents temperature change comprises the following steps:

[0037] Based on the critical temperature of the temperature change of the contents, a multi-point temperature field distribution matrix is ​​constructed to obtain the multi-point temperature field distribution data in the pot; the temperature change rate and acceleration characteristics of the multi-point temperature field distribution data in the pot are extracted to obtain the pot temperature change rate and the pot temperature change acceleration data;

[0038] The temperature mutation point of the multi-point temperature field distribution data in the pot is confirmed by using the temperature change rate of the pot, and the temperature mutation point data is obtained; the heating steady-state interval of the temperature mutation point data is analyzed by the acceleration data of the temperature change of the pot, and the heating steady-state interval of the pot load is generated; the key temperature threshold value of the pot load heating steady-state interval and the temperature mutation point data is identified based on the phase change theory, and the key temperature threshold value data is generated;

[0039] The pressure sensor is used to analyze the pot pressure changes in the steady-state interval of the pot load heating to generate pot pressure change data; the pressure fluctuation cycle of the pot pressure change data is analyzed to generate cooking state pressure characteristic data; the content state is identified based on the key temperature threshold data and the cooking state pressure characteristic data to generate content state identification data.

[0040] The present invention constructs a multi-point temperature field distribution matrix based on the critical temperature of the temperature change of the contents, and can accurately capture the temperature changes in various areas of the pot. The confirmation of the temperature mutation point and the extraction of the change rate and acceleration characteristics provide a detailed temperature change trajectory to help identify the heating state of the contents. The heating steady-state interval is analyzed by phase change theory, and the key temperature threshold is identified in combination with the temperature mutation point data, which can accurately capture the phase change process of the contents (such as water boiling, frying, etc.). This method can effectively determine the heating state of the contents in the pot, thereby realizing intelligent cooking process control. The pressure sensor is used to analyze the pressure change in the steady-state heating interval of the pot load. Through the pressure fluctuation cycle analysis, the system can identify different cooking states (such as boiling, evaporation, etc.). These pressure characteristic data provide an important basis for the accurate identification of the cooking state. By combining the key temperature threshold data with the cooking state pressure characteristic data, the system can accurately identify the state of the contents in the pot (such as liquid, gaseous, solidified, etc.). This intelligent identification function can help automatically adjust the heating strategy and optimize the cooking process. By accurately identifying the state of the contents, the system can adjust the heating mode and temperature control of the pot in real time to avoid overheating or underheating, improve cooking accuracy and efficiency, and ensure the best cooking effect of food. Content status recognition not only improves the intelligence of the cooking process, but also provides users with real-time feedback to avoid common cooking problems (such as burning, overflow, etc.). Through accurate status recognition, the system can automatically adjust to improve user convenience and cooking safety.

[0041] Preferably, step S3 comprises the following steps:

[0042] Step S31: predicting the pot heating stage for the pot empty mode and the pot loaded mode, and generating pot heating stage prediction data;

[0043] Step S32: performing fuzzy control on the heating power of the cooker according to the prediction data of the cooking pot heating stage, and generating heating power adjustment data; performing temperature adjustment feedback on the standard cooker temperature collection data according to the heating power adjustment data, and generating control temperature feedback data;

[0044] Step S33: performing power consumption and energy saving analysis on the temperature control feedback data to generate temperature control power energy saving data;

[0045] Step S34: Utilize the temperature control power energy saving data to optimize the heating energy efficiency of the control temperature feedback data, thereby generating an intelligent heating adjustment strategy.

[0046] The present invention predicts the heating stage of the empty pot mode and the load mode of the pot, so that the system can accurately identify the heating process of the pot under different cooking conditions, thereby reasonably predicting the heating time and temperature change. This accurate prediction helps to better control the heating process, avoid overheating or overcooling, and improve the cooking effect. Based on the prediction data of the heating stage of the pot, the system adjusts the heating power through a fuzzy control algorithm, and can accurately adjust the heating power of the pot. By real-time feedback control of the temperature, the system can adjust the heating strategy according to the actual temperature change, thereby achieving a more stable and accurate temperature control process. On the basis of the control temperature feedback data, the system performs power consumption energy saving analysis and generates temperature control power energy saving data. This step ensures that the energy efficiency of the heating process is maximized, reduces unnecessary energy waste, and achieves energy saving effects. Through accurate energy consumption control, energy can be saved and the power consumption caused by long-term use can be reduced. With the support of temperature control power energy saving data, the system can optimize the heating energy efficiency. By comprehensively analyzing the heating state and power consumption of the pot, the intelligent heating adjustment strategy can minimize energy consumption and optimize the heating process while ensuring the cooking effect. Through intelligent heating adjustment strategies, the system can automatically adjust the heating power according to the heating status of the pot, eliminating the complexity of manual adjustment and improving the user experience. Users do not need to worry about the temperature being too high or too low, the system can automatically adjust to the optimal state. Intelligent heating control ensures that the temperature of the pot changes more smoothly, reduces uneven cooking caused by human factors or equipment fluctuations, and improves the stability and consistency of cooking.

[0047] Preferably, step S31 includes the following steps:

[0048] Step S311: extracting heating stage characteristics of the cooker in the empty pot mode and the cooker in the loaded pot mode to obtain cooking stage characteristic data;

[0049] Step S312: dividing the characteristic data of the pot heating stage into a data set to generate a model training set and a model test set; using a decision tree algorithm to perform model training on the model training set to generate a pot stage prediction pre-model; performing model optimization iteration on the pot stage prediction pre-model through the model test set to generate a pot heating stage prediction model;

[0050] Step S313: importing the pot heating stage characteristic data into the pot heating stage prediction model to perform pot heating stage prediction and generate pot heating stage prediction data.

[0051] The present invention extracts the heating stage features of the pot in the empty pot mode and the load mode, so that the system can identify and analyze the changes in different states during the heating process and form accurate heating stage feature data. This feature extraction method helps the system to deeply understand the key factors such as temperature changes and power fluctuations during the heating process, and improves the accuracy of the prediction model. Reasonable data set division of the pot heating stage feature data is helpful for the separation of model training and testing, prevents overfitting, and improves the generalization ability of the model. The decision tree algorithm is used for model training, which can not only automatically learn the rules in the heating process according to historical data, but also continuously improve the prediction accuracy through optimization iteration. This process ensures the stability and reliability of the heating stage prediction model in practical applications. The decision tree algorithm can effectively handle nonlinear relationships and complex multi-feature data, and can quickly identify the decision rules between features when predicting the heating stage of the pot, and has strong explanatory and visualization capabilities. The use of decision trees ensures the efficiency and transparency of the prediction of the heating stage of the pot, and is easy to debug and optimize. By optimizing and iterating the pot stage prediction pre-model using the model test set, the system can timely discover and correct the prediction error. Each iteration can fine-tune the model, making the prediction model closer and closer to the actual heating stage, significantly improving the ability to accurately predict the heating process. Inputting the characteristic data of the pot heating stage into the optimized heating stage prediction model can generate accurate prediction data for the pot heating stage. This step can predict the different stages of the heating process in real time, thereby providing reliable decision support for subsequent heating power adjustment and temperature control feedback, and further optimizing the cooking effect and time control. Through accurate heating stage prediction, the system can intelligently adjust the heating process of the pot to reduce overheating or insufficient heating. This process will greatly improve the degree of automation in the use of pots, and users only need to focus on cooking itself without excessively intervening in the heating operation of the pot. Accurate heating stage prediction can make the pot heat more efficiently and avoid unnecessary energy consumption caused by overheating or repeated heating. Through precise heating stage control, the system can maximize energy saving while ensuring cooking quality, with energy-saving and environmental protection effects.

[0052] Preferably, step S4 comprises the following steps:

[0053] Step S41: using the Internet of Things technology to upload the intelligent heating regulation strategy to the cloud platform to collect strategy execution data, and obtain heating regulation strategy execution data;

[0054] Step S42: performing strategy effectiveness evaluation on the heating regulation strategy execution data to generate heating strategy effectiveness evaluation data; performing strategy cloud learning on the intelligent heating regulation strategy according to the heating strategy effectiveness evaluation data to generate real-time heating strategy adjustment data;

[0055] Step S43: Tracking the performance of the cookware by adjusting the data of the real-time heating strategy, thereby generating cookware heating performance tracking data to perform normal cookware temperature intelligent monitoring operations.

[0056] The present invention uses the Internet of Things technology to upload the intelligent heating adjustment strategy to the cloud platform, and can obtain the execution data of the pot heating process in real time. This combination of real-time uploading and strategy execution ensures that each adjustment step in the pot heating process can be monitored and optimized in real time. The user can remotely control and supervise the execution of the heating strategy, which helps to improve the intelligence and accuracy of the cooking process. The effectiveness evaluation of the heating adjustment strategy execution data can timely determine whether the current strategy is effective and how it performs under different usage conditions. Based on the strategy evaluation data, the cloud learning mechanism can optimize the existing heating strategy to achieve continuous improvement of the strategy. This process ensures the efficiency and adaptability of the heating strategy, and can adapt to different types of pots and cooking needs. Through real-time heating strategy adjustment data, the system can track the performance of the pot and ensure that the heating process of the pot is always kept in the optimal state. This feedback mechanism enables any deviation in the heating process to be quickly corrected, avoiding problems such as too high or too low temperature, thereby ensuring the stability of the pot performance. The cloud learning system can not only analyze historical data, but also learn and optimize the heating strategy in real time during actual use. The execution data of each heating adjustment strategy will become the input of system learning, further improving the accuracy and flexibility of intelligent heating control. This allows the cooker to automatically adjust the heating mode according to different environmental changes (such as cooker material, ambient temperature, etc.) to ensure the best heating effect. Real-time tracking of cooker performance and strategy adjustment can ensure that the cooker is always in the best working condition during use, avoiding performance degradation or energy waste. Continuous monitoring of heating performance can also help detect potential anomalies or failures, thereby improving the longevity and stability of the cooker. Through real-time data collection and strategy adjustment, the system can provide users with a personalized cooking experience. For example, based on the cooking habits of different users or the characteristics of ingredients, the system can adjust the heating strategy to adapt to various needs and optimize each cooking task.

[0057] In this specification, a smart monitoring system for pot temperature is provided, which is used to execute the smart monitoring method for pot temperature. The smart monitoring system for pot temperature includes:

[0058] The sensor deployment module is used to obtain the pot structure data; perform sensor array deployment on the pot structure data to generate pot sensor deployment data; perform multi-point temperature sensor calibration on the pot sensor deployment data to generate pot sensor calibration data; use the pot sensor calibration data to perform pot temperature acquisition on the temperature sensor built into the pot to obtain standard pot temperature acquisition data;

[0059] The pot mode analysis module is used to perform BM temperature curve conversion on the standard pot temperature collection data to generate a BM temperature conversion curve; perform extreme temperature extraction on the BM temperature conversion curve to obtain pot extreme temperature data; perform first mode division on the pot according to the pot extreme temperature data to generate a pot empty pot mode; perform content temperature critical analysis on the standard pot temperature collection data based on the BM temperature conversion curve to generate a content temperature change critical temperature; perform second mode division according to the content temperature change critical temperature to generate a pot load mode;

[0060] The pot temperature control module is used to predict the pot heating stage for the empty pot mode and the pot load mode, and generate the pot heating stage prediction data; perform fuzzy control feedback on the pot according to the pot heating stage prediction data, and generate control temperature feedback data; optimize and adjust the heating energy efficiency of the control temperature feedback data, so as to generate an intelligent heating adjustment strategy;

[0061] The pot temperature feedback module is used to upload the intelligent heating regulation strategy to the cloud platform for strategy execution data collection to obtain heating regulation strategy execution data; perform strategy cloud learning on the heating regulation strategy execution data to generate real-time heating strategy adjustment data; track the performance of the pot through the real-time heating strategy adjustment data to generate pot heating performance tracking data to perform normal pot temperature intelligent monitoring operations.

[0062] The beneficial effect of the present invention is that by acquiring the structural data of the pot and deploying a sensor array on the pot, each temperature point of the pot can be accurately monitored. Multi-point sensor calibration ensures the accuracy of the collected data, thereby providing a reliable basis for subsequent temperature adjustment and optimization. Through BM temperature curve conversion and extreme temperature extraction, the key temperature threshold can be analyzed and identified in real time during the heating process of the pot, so that the pot state can be adjusted according to the temperature change to reduce the risk of excessive or low temperature. The pot state is divided into the first and second modes (empty pot mode and load mode), so that the pot can automatically switch to the corresponding mode according to different cooking conditions, thereby ensuring the stability and energy efficiency of the heating process. Through the prediction of the heating stage, the system can identify the state changes that occur during the heating process in advance and prevent the influence of temperature fluctuations on the cooking effect. Through the fuzzy control feedback mechanism, the system can make intelligent adjustments according to the predicted data of the heating stage. Through precise optimization and adjustment of heating energy efficiency, the heating process of the pot is more energy-saving and efficient, ensuring accurate temperature control during the cooking process. This intelligent heating adjustment strategy can not only improve the heating efficiency, but also reduce energy consumption, reduce unnecessary heat waste, and improve overall energy efficiency. After uploading the intelligent heating adjustment strategy to the cloud platform, the system can continuously optimize and adjust the heating strategy through cloud learning. This process enables the system to dynamically learn according to the cooking needs and pot performance of different users in actual applications, and continuously improve the heating process. Through real-time heating strategy adjustment data, the system can continuously track the heating process of the pot to ensure that the heating performance of the pot is maintained in the optimal state at each stage, thereby avoiding uneven heating or overheating. Through cloud platform learning and real-time strategy adjustment, the system can provide personalized cooking solutions according to user needs and improve user experience. The pot automatically adapts to different cooking tasks according to different temperature changes and heating stages, so that users do not need to manually adjust the temperature or heating mode. The temperature monitoring and adjustment process of the pot is fully automated. The user only needs to set the preliminary conditions, and the system can intelligently complete the temperature control operation. Through performance tracking, the user can monitor the heating status of the pot in real time to ensure that the cooking process proceeds smoothly. Therefore, the present invention improves the accuracy and flexibility of intelligent monitoring of pot temperature through high-precision sensor arrays, intelligent mode division, fuzzy control feedback and real-time learning in the cloud. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A schematic diagram of the steps of an intelligent method for monitoring the temperature of a cooker;

[0064] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0065] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0066] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0067] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0068] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0069] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0070] To achieve this, please refer to Figures 1 to 3 , an intelligent method for monitoring the temperature of a cooker, the method comprising the following steps:

[0071] Step S1: acquiring the structure data of the pot; performing sensor array deployment on the structure data of the pot to generate the pot sensor deployment data; performing multi-point calibration of the temperature sensor on the pot sensor deployment data to generate the pot sensor calibration data; using the pot sensor calibration data to perform pot temperature acquisition on the temperature sensor built into the pot to obtain the standard pot temperature acquisition data;

[0072] Step S2: converting the standard pot temperature collection data into a BM temperature curve to generate a BM temperature conversion curve; extracting the extreme temperature of the BM temperature conversion curve to obtain the pot extreme temperature data; dividing the pot into a first mode based on the pot extreme temperature data to generate a pot empty pot mode; performing a content temperature critical analysis on the standard pot temperature collection data based on the BM temperature conversion curve to generate a content temperature change critical temperature; dividing the second mode based on the content temperature change critical temperature to generate a pot load mode;

[0073] Step S3: predicting the pot heating stage for the pot empty mode and the pot loaded mode to generate pot heating stage prediction data; performing fuzzy control feedback on the pot according to the pot heating stage prediction data to generate control temperature feedback data; optimizing and adjusting the heating energy efficiency of the control temperature feedback data to generate an intelligent heating adjustment strategy;

[0074] Step S4: Upload the intelligent heating regulation strategy to the cloud platform to collect strategy execution data and obtain heating regulation strategy execution data; perform strategy cloud learning on the heating regulation strategy execution data to generate real-time heating strategy adjustment data; track the performance of the cookware through the real-time heating strategy adjustment data to generate cookware heating performance tracking data to perform normal cookware temperature intelligent monitoring operations.

[0075] The present invention can realize high-precision temperature monitoring of various parts of the pot by acquiring the pot structure data and deploying the sensor array. The data consistency and accuracy of each sensor are ensured by multi-point calibration, thereby eliminating the error in temperature acquisition, obtaining standard pot temperature data, and providing reliable basic data for subsequent intelligent adjustment. BM temperature curve conversion and extreme temperature extraction make the temperature data of the pot more intuitive and can capture the key temperature change trend. Through the division of empty pot mode and load mode, accurate identification of different use states of the pot is realized, thereby providing targeted strategies for subsequent heating stage prediction and temperature adjustment. By predicting the heating stage of the pot, the current heating stage of the pot can be accurately judged, so as to make dynamic adjustments. In this process, the fuzzy control feedback mechanism can perform intelligent temperature control according to real-time data, avoid the single temperature control method in the traditional system, improve the energy efficiency of the pot heating process, and realize more efficient heat distribution. The heating adjustment strategy is uploaded to the cloud platform, and combined with the cloud learning mechanism, the heating strategy can be continuously optimized according to the long-term accumulated data, so as to improve the adaptability and performance of the pot in different environments. Real-time heating strategy adjustment data and pot performance tracking can realize intelligent monitoring of the pot heating process, ensure that its temperature control performance is always in the best state, and make personalized adjustments according to usage habits or needs. Therefore, the present invention improves the accuracy and flexibility of intelligent monitoring of pot temperature through high-precision sensor array, intelligent mode division, fuzzy control feedback and real-time learning in the cloud.

[0076] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a schematic diagram of a process flow of an intelligent method for monitoring the temperature of a cooker according to the present invention. In this example, the intelligent method for monitoring the temperature of a cooker includes the following steps:

[0077] Step S1: acquiring the structure data of the pot; performing sensor array deployment on the structure data of the pot to generate the pot sensor deployment data; performing multi-point calibration of the temperature sensor on the pot sensor deployment data to generate the pot sensor calibration data; using the pot sensor calibration data to perform pot temperature acquisition on the temperature sensor built into the pot to obtain the standard pot temperature acquisition data;

[0078] In an embodiment of the present invention, detailed structural data of the cookware is obtained by three-dimensional scanning technology or CAD modeling. These data include the size, shape, material, inner and outer surface morphology, etc. of the cookware. The structural data of the cookware can be stored in a three-dimensional point cloud, vector data or other structured form, and the high precision and accuracy of the data can be ensured. By analyzing the structural data of the cookware, the key heating area, temperature sensitive area and the location where the sensor needs to be deployed are determined. According to the working environment and expected temperature range of the cookware, a suitable temperature sensor (such as a thermocouple, RTD sensor or thermistor) is selected. According to the shape and usage scenario of the cookware, a reasonable sensor array layout is designed. The sensors should be evenly distributed in the key areas of the cookware (such as the bottom, side wall, upper edge, etc.) to comprehensively monitor the temperature distribution inside the cookware. The temperature sensor is installed in the structure of the cookware through a reasonable wiring method or wireless transmission equipment. The sensor needs to be firmly fixed to ensure stability during long-term operation. The sensor can be connected to the data acquisition unit through wired or wireless communication technology (such as I2C, SPI, Bluetooth, Wi-Fi, etc.) to realize real-time acquisition and transmission of temperature data. Design a set of standard calibration experiments. In a controlled environment, use precise temperature control equipment (such as a thermostat, standard heat source) to heat the pot and measure the temperature point by point. Analyze the measurement error of each sensor by comparing the standard heat source temperature with the reading of each sensor. Correct the measurement deviation of each sensor through mathematical models or experimental adjustments. Ensure that multiple sensors can obtain accurate readings at different temperature points. For different sensors, different calibration methods (such as linear regression, segmented calibration, etc.) can be used for precise adjustment. Record the calibration data of each sensor, including deviation value, error range, calibration coefficient, etc., for subsequent use and verification. Start collecting temperature data at different locations inside the pot through the calibrated temperature sensor. The sensor will read the temperature at various locations inside the pot in real time and transmit the data to the data processing unit. Set an appropriate acquisition frequency according to the requirements of the pot heating process. For example, the acquisition frequency can be once per second to monitor temperature changes in real time. The collected temperature data needs to be standardized by the data processing unit, outliers are eliminated, and data smoothing and denoising are performed to ensure the accuracy of the temperature data. The collected temperature data is stored in the cloud platform or local server for further analysis (such as temperature trend prediction, heating uniformity analysis, etc.).

[0079] Step S2: converting the standard pot temperature collection data into a BM temperature curve to generate a BM temperature conversion curve; extracting the extreme temperature of the BM temperature conversion curve to obtain the pot extreme temperature data; dividing the pot into a first mode based on the pot extreme temperature data to generate a pot empty pot mode; performing a content temperature critical analysis on the standard pot temperature collection data based on the BM temperature conversion curve to generate a content temperature change critical temperature; dividing the second mode based on the content temperature change critical temperature to generate a pot load mode;

[0080] In the embodiment of the present invention, data is collected by inputting the standard pot temperature, which comes from a calibrated temperature sensor and includes real-time temperature data of each point inside the pot. The BM temperature curve is a curve based on the temperature change during batch heating. By weighted averaging or interpolating the temperature of each point in the pot, the overall temperature change curve inside the pot at each moment is obtained. The standard temperature collection data is converted into a curve by mathematical modeling (such as polynomial fitting or weighted average method) to generate a BM temperature conversion curve. The curve reflects the temperature change characteristics of the pot at different time points. The extreme points are extracted from the BM temperature curve using mathematical methods (such as the second-order derivative method or the local maximum / minimum search algorithm). The extreme points include the maximum and minimum values ​​of the temperature, indicating the extreme temperature changes during the heating process. The extracted extreme temperature will be used for subsequent pot mode division. For example, the maximum temperature represents the critical point at which the pot enters the heating steady state, and the minimum value represents the starting point at which the pot starts to heat. The extreme temperature data of the pot is obtained, including the maximum temperature and the minimum temperature during the heating process, for subsequent analysis. The working state of the pot is judged according to the extracted extreme temperature data. If the temperature of the pot rises rapidly in a short period of time and remains stable after reaching a certain extreme value, it means that the pot is in an empty pot state. By analyzing the temperature change rate and change amplitude (such as rapid temperature rise and stable maintenance), it is determined whether the pot is in the empty pot mode. At this time, the pot has no load and the temperature changes relatively quickly. According to the judgment result, it is determined that the pot is in the empty pot mode and the corresponding mode data is generated. In this mode, the temperature change of the pot is more drastic and the stability is poor. Based on the BM temperature conversion curve, the stage characteristics of the temperature change during the heating process of the pot are observed. The critical temperature refers to the temperature point at which the contents in the pot begin to undergo important phase changes or other physical changes. By subdividing the heating section of the BM curve, key temperature change points are extracted, such as the inflection point of temperature rise, the beginning and end of the stable period, etc. These temperature points represent the critical points of the temperature change of the contents in the pot. Finally, the critical temperature data of the temperature change of the contents is generated as the basis for subsequent mode division and heating adjustment. According to the critical temperature data of the temperature change of the contents extracted in step S24, the load state during the heating process of the pot is judged. If the temperature of the pot fluctuates violently, and the temperature changes slowly after reaching the critical temperature at a certain point, it means that there is a certain load in the pot. The critical temperature of the temperature change of the contents is used to determine whether the pot is in load mode. In this mode, the load in the pot affects the heating process, causing the temperature change to slow down. Based on the judgment results, the pot load mode data is generated. In this mode, the temperature of the pot rises slowly and the temperature fluctuation is relatively gentle, indicating that the contents have begun to affect the heating process of the pot.

[0081] Step S3: predicting the pot heating stage for the pot empty mode and the pot loaded mode to generate pot heating stage prediction data; performing fuzzy control feedback on the pot according to the pot heating stage prediction data to generate control temperature feedback data; optimizing and adjusting the heating energy efficiency of the control temperature feedback data to generate an intelligent heating adjustment strategy;

[0082] In an embodiment of the present invention, the heating process of the pot is divided into multiple stages, such as the initial heating stage, the steady-state heating stage, and the end heating stage, by dividing the temperature change process and mode of the pot. The temperature data of the pot in the empty pot mode and the load mode are input into the heating stage prediction model, and the model predicts the heating stage according to the historical data and the temperature change law. According to the temperature characteristics of the empty pot mode and the load mode of the pot, the characteristic data related to the heating stage (such as the temperature change rate, the stabilization time, the heating rate, etc.) are extracted. The extracted characteristic data is trained using a machine learning algorithm (such as a decision tree, a neural network, a support vector machine, etc.) to generate the prediction data of the heating stage of the pot. The prediction data can clarify the various stages of the heating process and its turning points. A fuzzy control system based on the prediction data of the heating stage is designed. The system generates a suitable heating power or temperature adjustment value according to the current heating stage of the pot and the target temperature setting value. The current heating stage prediction data of the pot is used as input, combined with real-time data such as temperature sensor feedback and pot load information. Fuzzy control rules are defined according to the heating stage of the pot, such as the initial heating stage, the steady-state heating stage, etc. For example, in the initial heating stage, when the temperature is lower than the set value, the heating power is increased; in the steady-state stage, when the temperature is close to the set value, the heating power is reduced. According to the fuzzy control rules, the control temperature feedback data is output to adjust the heating power of the pot to ensure that the temperature gradually stabilizes to the predetermined range. According to the control temperature feedback data, the energy efficiency of the pot is analyzed. The energy utilization efficiency of the pot heating process is judged by the relationship between the temperature change rate and the heating power. For example, after the pot reaches the target temperature, if the heating power is too high, energy will be wasted. Use energy efficiency optimization algorithms (such as genetic algorithms, particle swarm algorithms, etc.) to optimize and adjust the heating power. The algorithm dynamically adjusts the heating power or adjusts the heating cycle according to the heating stage, real-time temperature, load conditions and other data of the pot to optimize the overall heating energy efficiency. Based on the optimized energy efficiency data, an intelligent heating adjustment strategy is generated. This strategy can dynamically adjust the heating power of the pot at different heating stages to achieve the best energy efficiency and heating stability. A pot performance tracking system is established to monitor the heating process of the pot in real time. Sensors are used to collect information such as the temperature data, heating power, and load conditions of the pot. Based on real-time data, define heating performance evaluation indicators, such as heating stability, temperature uniformity, heating time, etc. Analyze the collected pot heating performance data in real time to determine any deviations or problems in the pot heating process (such as uneven heating, poor energy efficiency, etc.). Adjust the intelligent heating regulation strategy based on performance tracking data. If energy efficiency loss or large temperature fluctuations are found at certain stages of the heating process, the system will automatically adjust the heating power or heating cycle to ensure that the pot heating process is more efficient and stable.

[0083] Step S4: Upload the intelligent heating regulation strategy to the cloud platform to collect strategy execution data and obtain heating regulation strategy execution data; perform strategy cloud learning on the heating regulation strategy execution data to generate real-time heating strategy adjustment data; track the performance of the cookware through the real-time heating strategy adjustment data to generate cookware heating performance tracking data to perform normal cookware temperature intelligent monitoring operations.

[0084] In an embodiment of the present invention, the intelligent heating regulation strategy is uploaded to the cloud platform through the Internet of Things (IoT) technology. The cloud platform needs to be able to receive and parse these strategies to ensure that the strategies can be executed remotely. When the pot executes the heating regulation strategy, various data in the execution process are collected in real time, such as the temperature change of the pot, the heating power, the heating time, the load status, etc. These data are transmitted to the cloud platform through sensors and IoT devices. All collected data will be stored in the database of the cloud platform for subsequent analysis and management. Ensure the real-time and accuracy of the data so that it can be used in subsequent strategy optimization. Use the computing resources of the cloud platform to conduct in-depth analysis of the heating regulation strategy execution data. Through machine learning and data mining technology, identify key patterns and deviations in the heating process. For example, problems such as inaccurate temperature control and insufficient energy efficiency. Based on historical execution data, machine learning algorithms (such as reinforcement learning, regression analysis, decision trees, etc.) are used to learn the strategy execution in the cloud. The algorithm adjusts the heating strategy according to the collected data to make it more in line with the heating requirements of the pot. For example, in certain heating stages, the system automatically adjusts the heating power to improve energy efficiency or speed up the heating speed. According to the cloud learning results, real-time heating strategy adjustment data is generated. This data can dynamically adjust the heating mode of the pot, further optimize the heating process, ensure accurate temperature control and maximize energy efficiency. Through the cloud platform, the heating performance of the pot is continuously tracked. Real-time data of the pot is collected by temperature sensors, pressure sensors, power sensors, etc., and key performance indicators such as the heating process, power consumption, and temperature fluctuation of the pot are monitored. Real-time tracking data is analyzed to evaluate the heating effect and performance of the pot. For example, check whether the pot has reached the predetermined temperature, whether the temperature is too high or too low, or whether the heating efficiency has reached the optimization target. Based on the performance tracking data, the pot heating performance tracking data is generated, and corresponding optimization suggestions are given. If obvious energy efficiency loss or uneven temperature is detected during the heating process, the system will automatically adjust the strategy to optimize the heating process. Real-time monitoring of pot temperature is carried out using the cloud platform. Through the Internet of Things technology, all temperature data, heating power data, etc. are ensured to be uploaded to the cloud in real time for analysis by the cloud platform. Based on the real-time monitoring data, the temperature adjustment task is automatically performed to ensure that the heating process of the pot can be kept within the set range. For example, if the pot temperature is low, the system will automatically increase the heating power; if the pot temperature is too high, the system will reduce the power or suspend heating. During the cooking process, data is continuously fed back and the heating strategy is adjusted based on the feedback results. If problems such as uneven temperature and poor energy efficiency are found in some heating stages, the system will automatically optimize the adjustment strategy.

[0085] Preferably, step S1 comprises the following steps:

[0086] Step S11: obtaining the pot structure data;

[0087] Step S12: Calculate the structure center point of the cookware structure data to obtain the cookware structure center point data; perform sensor array deployment based on the cookware structure center point data to generate cookware sensor deployment data, wherein the sensor array deployment includes pressure sensor array deployment and temperature sensor array deployment;

[0088] Step S13: performing multi-point calibration of the temperature sensor on the pot sensor deployment data to generate pot sensor calibration data; using the pot sensor calibration data to collect the pot temperature of the temperature sensor built into the pot to obtain the pot temperature collection data;

[0089] Step S14: performing data preprocessing on the pot temperature collection data to generate standard pot temperature collection data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization.

[0090] In an embodiment of the present invention, detailed structural data of the pot is obtained by 3D scanning technology or CAD model. These data include the shape, size, material and other design features of the pot. The data can come from the manufacturer's design drawings, actual scanning data of the pot or simulation model. According to the three-dimensional structural data of the pot, the geometric center point of the pot is calculated. The center point can be obtained by calculating the centroid of the geometric shape, or a numerical optimization method can be used. Based on the data of the center point of the pot structure, the arrangement of the sensor array is designed. The sensor array mainly includes: according to the functional requirements of the pot, a pressure sensor is installed at an appropriate position of the pot (such as the bottom and side wall) to monitor the pressure change in the pot. Temperature sensors are arranged in different areas of the pot (such as the bottom of the pot, the wall of the pot, etc.) to ensure that the key temperature area of ​​the pot is covered. The sensor array can adopt a distributed deployment method to ensure that accurate temperature data is obtained. The installed temperature sensor is calibrated at multiple points. The sensor is calibrated using a known temperature source or standard equipment to ensure the consistency of the readings of each sensor. After the sensor is calibrated, the calibration data is used to collect the real-time temperature of the built-in temperature sensor of the pot. These data will be used for subsequent pot temperature analysis. To remove noise, duplicate data, and invalid data from the collected data, it is necessary to use algorithms to filter out extreme values ​​or outliers. Use filtering algorithms (such as mean filtering, Kalman filtering, etc.) to denoise the temperature collection data to reduce environmental interference or sensor errors. To fill missing or blank values ​​in the data, interpolation methods (such as linear interpolation, interpolation, etc.) can be used to fill missing values. Standardize the temperature data and convert the data to a unified range or standard format (for example, scale the data to the [0, 1] interval, or convert it to a standard normal distribution) to facilitate subsequent analysis and application.

[0091] Preferably, performing multi-point sensor calibration on the cookware sensor deployment data includes:

[0092] The temperature sensor is selected for calibration points in the working temperature range through the pot sensor deployment data to obtain calibration point data in the working temperature range; the temperature sensor is confirmed for multi-point heating data of the target point based on the calibration point data in the working temperature range to generate calibration point heating temperature data;

[0093] The actual temperature error analysis is performed on the calibration point data in the working temperature range and the heating temperature data at the calibration point to obtain the actual temperature relationship model. The actual temperature relationship model is used to perform thermal conduction delay compensation on the temperature sensor to generate the calibration data of the pot temperature sensor. The formula for the actual temperature error analysis is as follows:

[0094] ;

[0095] In the formula, Expressed as actual temperature, Expressed as the sensor output voltage, is the fitting coefficient;

[0096] The formula for thermal conduction delay compensation is as follows:

[0097] ;

[0098] In the formula, Expressed as the pot contents at time The temperature at Represented as the pot bottom at time The temperature at Indicated as the material and contents of the pot at the time The temperature difference.

[0099] In an embodiment of the present invention, the operating temperature range of the pot is analyzed based on the pot sensor deployment data, such as the range from the temperature at the beginning of the pot heating to the maximum operating temperature. Select multiple specific temperature points within these ranges as calibration points, which will be used to verify the accuracy of the sensor, usually including low temperature, medium temperature and high temperature ranges. The calibration point data of the operating temperature range of the pot sensor is obtained by performing temperature measurement through experiments or reference standard equipment. Based on the selected calibration point data of the operating temperature range, the temperature sensor is heated based on the multi-point heating method of the target point. Accurate heating is performed at each target temperature point, and the output voltage of the temperature sensor at this time is measured. The output voltage of each temperature point represents the response of the sensor at that temperature. Record the heating data of each calibration point to obtain the calibration point heating temperature data. Compare the actual temperature of each calibration point with the voltage data output by the sensor, and calculate the error. Use the polynomial fitting method to model the relationship between the actual temperature (T_actual) and the sensor output voltage (V). The fitting formula is as follows: ; In the formula, Expressed as actual temperature, Expressed as the sensor output voltage, is the fitting coefficient; according to the fitting model, the error is analyzed and the actual response error of the sensor at different temperatures is obtained. In the measurement data of the pot temperature sensor, the heat conduction delay between the material and the content of the pot is taken into account. The heat conduction delay compensation formula is used to correct the measurement data: ; In the formula, Expressed as the pot contents at time The temperature at Represented as the pot bottom at time The temperature at Indicated as the material and contents of the pot at the time Temperature difference According to the actual situation, the correction value can be calculated through the heat conduction model or obtained through experimental data. This compensation formula helps to eliminate the thermal hysteresis effect in the pot temperature measurement, making the temperature of the pot contents closer to the true value. Using the actual temperature relationship model obtained by fitting and the heat conduction delay compensation formula, the output data of the pot temperature sensor is corrected to generate calibrated pot temperature data to ensure that these data can accurately reflect the true temperature of the pot contents. The calibration data will serve as the basis for subsequent data processing and pot temperature control to ensure that the working temperature of the pot can be accurately controlled.

[0100] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0101] Step S21: converting the standard pot temperature collection data into a BM temperature curve to generate a BM temperature conversion curve; extracting the extreme temperature of the BM temperature conversion curve to obtain the pot extreme temperature data; comparing the pot extreme temperature data with a preset first temperature threshold, and when the pot extreme temperature data is greater than or equal to the preset first temperature threshold, a pot hot reminder is issued through an indicator light;

[0102] Step S22: when the extreme temperature data of the pot is greater than a preset first temperature threshold and greater than a preset second temperature threshold, a dry-burning warning is performed on the pot based on the extreme temperature data of the pot, thereby generating dry-burning warning data; the pot is divided into a first mode based on the dry-burning warning data, and a pot empty pot mode is generated;

[0103] Step S23: using the pressure sensor and the BM temperature conversion curve to perform a critical temperature analysis of the contents on the standard cookware temperature collection data, and generating a critical temperature of the contents temperature change;

[0104] Step S24: performing content state identification according to the critical temperature of the content temperature change to generate content state identification data; performing second mode division based on the content state identification data to generate a cookware load mode.

[0105] In an embodiment of the present invention, the standard pot temperature acquisition data is converted into a BM temperature curve (i.e., a curve form based on the pot temperature, BM represents a specific temperature conversion model or algorithm) for further analysis and processing. Obtain the standard pot temperature acquisition data, which comes from the built-in temperature sensor of the pot. Use the BM temperature curve conversion model (for example, based on certain algorithms such as polynomial fitting, exponential function fitting, etc.) to convert the standard pot temperature acquisition data to obtain a BM temperature conversion curve. Extract the maximum and minimum temperature values ​​from the BM temperature conversion curve as the extreme temperature data of the pot. Analyze the temperature fluctuation of the pot to ensure that it is within the working range. The extreme temperature data will be used for subsequent safety reminders and warnings. Compare the extreme temperature data of the pot with the preset first temperature threshold. When the extreme temperature data of the pot is greater than or equal to the first temperature threshold, a pot heat reminder is issued through the indicator light to remind the user that the pot temperature is too high. When the extreme temperature data of the pot is greater than the preset first temperature threshold and greater than the preset second temperature threshold, a dry-burning warning is triggered, and dry-burning warning data is generated, prompting the user that the temperature of the pot is close to the dry-burning state and needs to be operated immediately (such as turning off the fire or adding water). According to the dry-burning warning data, the pot is divided into modes to determine whether it is in the empty pot mode. If the temperature of the pot rises abnormally and there is not enough content, it is divided into the empty pot mode, and the empty pot mode data of the pot is generated to remind the user to add water or stop heating. The pressure data of the contents in the pot is obtained through the pressure sensor. The pressure data can reflect the state of the contents inside the pot (such as whether it is boiling). The BM temperature conversion curve is combined with the pressure data for analysis to determine the critical temperature of the content temperature change. This temperature reflects the critical state of the content, such as starting to boil or reaching a certain thermal transition point. According to the critical temperature of the content temperature change, combined with the pressure sensor data and the temperature data, the state of the contents in the pot (such as boiling, cooked, burnt dry, etc.) is identified, and the content state identification data is generated, such as marked as "boiling state" or "burnt dry state". Based on the content status recognition data, the load mode of the pot is divided. For example, if the content in the pot has boiled and started to decrease, it can be divided into "overload" mode, reminding the user to reduce the heating time or check the content, generate the pot load mode data, and help the user adjust the use of the pot to avoid overload or uneven heating.

[0106] Preferably, when the extreme temperature data of the cooker is greater than a preset first temperature threshold and greater than a preset second temperature threshold, the cooker is given a dry-burning warning based on the extreme temperature data of the cooker, including:

[0107] When the extreme temperature data of the pot is greater than a preset first temperature threshold and greater than a preset second temperature threshold, a pot array temperature change analysis is performed on the standard pot temperature collection data based on the extreme temperature data of the pot to generate pot temperature change data; the pot temperature change data is converted into a heat map to generate a pot temperature change heat map;

[0108] Performing heat map edge recognition on the heat map of pot temperature change to generate pot edge temperature change data; performing temperature gradient field calculation on the pot edge temperature change data to generate pot edge temperature gradient field; performing gradient amplitude calculation on the pot edge temperature gradient field to obtain edge temperature gradient field amplitude data;

[0109] The edge temperature gradient field amplitude data is used to perform a thermal map texture analysis on the temperature change heat map of the cookware to generate thermal map texture temperature change amplitude data. Based on the thermal map texture temperature change amplitude data, the heat uniformity of the cookware is analyzed to generate heat uniformity data for the cookware. Based on the heat uniformity data for the cookware, a dry-burning warning is given to the cookware to generate dry-burning warning data.

[0110] In an embodiment of the present invention, when the extreme temperature data of the pot is greater than the preset first temperature threshold and second temperature threshold, the temperature change of the pot is analyzed to identify the potential risk of dry burning. The extreme temperature data of the pot and the temperature acquisition data of the standard pot are obtained. The temperature change analysis of the pot array is performed on the standard pot temperature acquisition data, and the temperature distribution and change trend of each part of the pot are analyzed to generate the temperature change data of the pot, indicating the temperature change of different areas inside the pot. The temperature change heat map of the pot is generated by the temperature change data of the pot to visualize the temperature distribution inside the pot. The temperature change data of the pot is converted into a heat map format, and the temperature distribution of different areas in the pot is represented by color changes to generate a heat map of the temperature change of the pot. The high temperature area in the figure is displayed by different colors to facilitate the identification of hot spots or overheating areas. The temperature distribution edge in the heat map of the temperature change of the pot is identified, and the trend of temperature change is further analyzed. The edge recognition is performed on the heat map of the temperature change of the pot, and the boundary of the temperature change in the heat map is detected by using an edge detection algorithm (such as Canny edge detection, Sobel operator, etc.), and the edge temperature change data of the pot edge is generated, marking the edge area with more drastic temperature change in the heat map. The temperature gradient at the edge of the pot is calculated through the edge temperature change data to evaluate the uniformity of the pot's heating. The temperature gradient field is calculated based on the temperature change data at the edge of the pot. The gradient field reflects the speed and direction of temperature change, and can indicate the severity of the temperature change. The temperature gradient field at the edge of the pot is generated to indicate the temperature change rate of each area at the edge of the pot. The temperature fluctuations in each area of ​​the pot are further analyzed by calculating the amplitude of the temperature gradient field. The gradient amplitude of the temperature gradient field at the edge of the pot is calculated to obtain gradient amplitude data, which indicates the temperature change amplitude of the edge area of ​​the pot, and the edge temperature gradient field amplitude data is generated. These data help to determine which areas have large temperature changes and thermal unevenness. Texture analysis is performed on the pot temperature change heat map to analyze the uniformity of the pot's heating and the distribution of hot spots. Based on the edge temperature gradient field amplitude data, a heat map texture analysis is performed on the pot temperature change heat map to identify temperature fluctuations and hot spots in the heat map, and heat map texture temperature change amplitude data is generated. These data show the amplitude and location of the pot temperature fluctuations, helping to identify the cause of the pot's uneven temperature. The heat map texture temperature change amplitude data is used to analyze the uniformity of the pot's heating and determine whether there is a risk of dry burning. Based on the temperature change amplitude data of the heat map texture, analyze whether the pot is heated unevenly, especially whether the temperature in some areas rises too quickly or too high. Assess the uniformity of the pot's heating. If the temperature in some areas of the pot is too high and the heating is uneven, it indicates that the pot is at risk of dry burning. When the temperature of the pot is uneven or overheating occurs, a dry burning warning is triggered to protect the pot from damage. Based on the pot's heating uniformity analysis data, determine whether the pot is at risk of dry burning.If the pot is partially overheated or the temperature changes drastically, it indicates that the pot is dry-burning, and dry-burning warning data is generated. The user is informed through an alarm or prompt that there is a risk of dry-burning in the pot, and the user is reminded to take measures (such as reducing heating, adding water or stopping heating).

[0111] Preferably, the process of identifying the state of the contents according to the critical temperature of the contents temperature change comprises the following steps:

[0112] Based on the critical temperature of the temperature change of the contents, a multi-point temperature field distribution matrix is ​​constructed to obtain the multi-point temperature field distribution data in the pot; the temperature change rate and acceleration characteristics of the multi-point temperature field distribution data in the pot are extracted to obtain the pot temperature change rate and the pot temperature change acceleration data;

[0113] The temperature mutation point of the multi-point temperature field distribution data in the pot is confirmed by using the temperature change rate of the pot, and the temperature mutation point data is obtained; the heating steady-state interval of the temperature mutation point data is analyzed by the acceleration data of the temperature change of the pot, and the heating steady-state interval of the pot load is generated; the key temperature threshold value of the pot load heating steady-state interval and the temperature mutation point data is identified based on the phase change theory, and the key temperature threshold value data is generated;

[0114] The pressure sensor is used to analyze the pot pressure changes in the steady-state interval of the pot load heating to generate pot pressure change data; the pressure fluctuation cycle of the pot pressure change data is analyzed to generate cooking state pressure characteristic data; the content state is identified based on the key temperature threshold data and the cooking state pressure characteristic data to generate content state identification data.

[0115] The present invention arranges multiple temperature sensors in the pot, which are evenly distributed at different positions in the pot (such as the bottom of the pot, the wall of the pot, and the liquid surface). Each sensor monitors the temperature change at the position in real time and transmits the temperature data to a central processing unit (such as an embedded system or an intelligent control unit). A temperature field distribution matrix is ​​constructed using these temperature data, and each element of the matrix represents the temperature value of a certain position in the pot. The size of the matrix is ​​determined by the number and position of the sensors. The temperature field distribution data includes the real-time temperature of each position in the pot, which can be recorded as a time series data set for subsequent analysis. The rate and acceleration of temperature change are extracted from the multi-point temperature field data to reflect the temperature change trend during the heating process. The rate of change of the temperature of each temperature sensor point, that is, the rate of change of the temperature of each sensor relative to time, is calculated, usually using the differential formula: temperature change rate = (temperature value at the current time - temperature value at the previous moment) ÷ time interval. Based on the temperature change rate, the acceleration of temperature change is further calculated to represent the change of the temperature change rate, which is usually calculated as the second-order derivative of the rate: temperature change acceleration = (temperature change rate at the current time - temperature change rate at the previous moment) ÷ time interval. The temperature change rate and acceleration data provide preliminary characteristics of the temperature change in the pot, which are used to further identify the temperature mutation point. Based on the temperature change rate data of each temperature sensor in the pot, the temperature mutation point of each sensor point is calculated. The temperature mutation point refers to the time point when the temperature change rate suddenly increases or decreases sharply, which represents the phase change of the material inside the pot or the instantaneous fluctuation of heating. By setting a threshold (for example, the standard deviation of the rate exceeds a certain limit), when the temperature change rate of a certain sensor exceeds the threshold, it is considered that a temperature mutation has occurred at this point. The temperature mutation point data records the time and location of all mutations, which are subsequently used for the identification of the heating steady-state interval and the phase change theory analysis. Once the temperature mutation point is confirmed, it is necessary to analyze the steady-state interval during the heating process. The steady-state interval is usually characterized by the acceleration of temperature change close to zero, indicating that the temperature change tends to be stable and the load of the pot enters a stable state of heating. Using the temperature change acceleration data, the time intervals with acceleration values ​​close to zero are found, and it is considered that the temperature changes in these intervals are stable and no longer change drastically. These stable areas correspond to the steady-state intervals of the pot load heating, indicating that the heating process is in a balanced state. By analyzing the steady-state interval and temperature mutation point data of the pot load heating, combined with the phase change theory, the key temperature threshold is identified to help determine the state of the contents (such as whether it is in the boiling, melting, etc. process). Based on the phase change theory, the temperature mutation during the heating process is usually related to the phase change point of the substance (such as the boiling point of water or the melting point of ice). Therefore, by analyzing the temperature data of the pot temperature mutation point and the steady-state interval, the key temperature threshold of the contents can be extracted. In the temperature range within the steady-state interval, find the upper and lower fluctuation range of the temperature mutation point, set the temperature interval boundary, and identify whether phase change behavior occurs.For example, if the temperature of the liquid in the pot reaches or exceeds 100°C at a certain moment, this temperature is the critical temperature threshold for boiling. The pressure sensor is used to analyze the pressure change in the steady-state interval of the pot load heating, generate cooking state pressure characteristic data, and further assist in the identification of the content state. A pressure sensor is installed inside the pot to monitor the pressure change of the pot load in real time. The pressure change data reflects the pressure fluctuations during the gasification, evaporation, and dissolution of the liquid in the pot. The pressure data is analyzed periodically to analyze the periodicity of the pressure fluctuations and obtain the pressure characteristic data of the cooking state. For example, during the liquid heating process, as the temperature rises, the pressure fluctuation cycle will change, forming a recognizable periodic feature. Based on the critical temperature threshold data and the cooking state pressure characteristic data, the state of the contents in the pot is finally identified. Combined with the temperature and pressure characteristic data, the cooking state of the contents is classified through machine learning algorithms (such as decision trees, neural networks, SVMs, etc.). The critical temperature threshold data is used to determine whether the substance is in a phase change state, while the pressure fluctuation cycle data helps to identify whether the cooking process is in boiling, evaporation, or other stages of heating. Based on these analysis results, the cooking state of the contents, such as boiling, heating, dissolving, etc., is generated, and the content state identification data is generated to indicate the current state of the contents (such as boiling, cooked, melted, etc.). This data can be used to adjust the heating process to ensure precise control of cooking.

[0116] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0117] Step S31: predicting the pot heating stage for the pot empty mode and the pot loaded mode, and generating pot heating stage prediction data;

[0118] Step S32: performing fuzzy control on the heating power of the cooker according to the prediction data of the cooking pot heating stage, and generating heating power adjustment data; performing temperature adjustment feedback on the standard cooker temperature collection data according to the heating power adjustment data, and generating control temperature feedback data;

[0119] Step S33: performing power consumption and energy saving analysis on the temperature control feedback data to generate temperature control power energy saving data;

[0120] Step S34: Utilize the temperature control power energy saving data to optimize the heating energy efficiency of the control temperature feedback data, thereby generating an intelligent heating adjustment strategy.

[0121] In the embodiment of the present invention, the heating stage of the pot is predicted by the empty pot mode and the load mode of the pot, so as to accurately determine the current heating state of the pot for subsequent adjustment. The load state of the pot is monitored by a sensor to determine whether the pot is in the empty pot mode. The empty pot mode generally refers to the absence of food or water or other substances in the pot, and only the heating part of the pot body exists. At this time, the heating rate is fast and the temperature rises rapidly. The load state of the pot is monitored by a sensor to determine whether the pot is in the load mode. The load mode generally refers to the presence of food or liquid in the pot, the heat transfer rate is slow, and the temperature rise of the pot is relatively gentle. Based on the temperature data in the pot, the load information and the real-time feedback during the heating process, the current heating stage of the pot is predicted by a machine learning algorithm (such as a decision tree, a support vector machine, etc.), and the heating stage prediction data is generated. The heating stage includes different stages such as initial heating, stable heating, and near boiling. According to the prediction data of the heating stage of the pot, the heating power is dynamically adjusted to ensure the accuracy of temperature control, and temperature adjustment feedback is performed. According to the prediction data of the heating stage, the heating power of the pot is adjusted using a fuzzy control algorithm. For example, in empty pot mode, the heating power of the pot can be set to a high level for fast heating, while in load mode, the power can be adjusted to a moderate level to avoid burning or overheating of the food. The fuzzy control algorithm outputs a power adjustment value based on factors such as pot load, temperature rise rate, and heating stage. Feedback control is performed on the standard temperature collection data of the pot based on the heating power adjustment data. The pot temperature is monitored in real time by sensors and temperature control is performed according to the predetermined target temperature. If the pot temperature is lower than the target value, the system automatically adjusts the heating power; if the temperature exceeds the set value, the heating power is reduced to avoid overheating. The temperature adjustment feedback data includes information such as real-time temperature data, adjustment power, and error value, which provide a basis for subsequent steps. Power consumption and energy saving analysis is performed on the temperature control during the pot heating process to identify energy saving space and optimize the heating process. The power consumption data of the pot is monitored in real time by power sensors, and the power consumption at each moment during the heating process is recorded. Combined with the temperature feedback data of the pot, the relationship between the heating power consumption and the actual temperature change is analyzed. By comparing the power consumption data at different heating stages and pot load conditions, the links with excessive power consumption are found and the potential space for energy saving is identified. Based on the power consumption analysis, the temperature control power energy saving data is generated. The data includes the energy saving effect of the pot in different heating stages and the room for energy efficiency improvement, forming an energy saving model. Based on the temperature control power energy saving data, the power regulation strategy in the pot heating process is optimized using optimization algorithms (such as genetic algorithms, particle swarm optimization, etc.). The optimization goals include improving heating efficiency, reducing energy waste, and maintaining precise temperature control. The heating strategy of the pot is adjusted according to the optimization results. For example, in the stage of low energy efficiency, the system will reduce power to save energy; while in the stage of high energy efficiency, the heating power will be appropriately increased to increase the heating speed.The optimized heating strategy will serve as an intelligent heating regulation strategy to ensure maximum power utilization efficiency during the pot heating process and maintain precise temperature control.

[0122] Preferably, step S31 includes the following steps:

[0123] Step S311: extracting heating stage characteristics of the cooker in the empty pot mode and the cooker in the loaded pot mode to obtain cooking stage characteristic data;

[0124] Step S312: dividing the characteristic data of the pot heating stage into a data set to generate a model training set and a model test set; using a decision tree algorithm to perform model training on the model training set to generate a pot stage prediction pre-model; performing model optimization iteration on the pot stage prediction pre-model through the model test set to generate a pot heating stage prediction model;

[0125] Step S313: importing the pot heating stage characteristic data into the pot heating stage prediction model to perform pot heating stage prediction and generate pot heating stage prediction data.

[0126] In the embodiment of the present invention, in the empty pot mode, the temperature rises quickly during the heating process of the pot, so it is necessary to collect data such as the initial rate of temperature change of the pot, heating power, and temperature rise amplitude. The temperature change of the pot can be monitored in real time by a temperature sensor, and the heating power and temperature data at each time point can be recorded. In the load mode, there are ingredients or liquids in the pot, so the heating rate is slow. It is necessary to extract characteristic data such as the rising curve of the temperature in the pot, heating power, load, and temperature stable stage. The sensor data needs to feedback the temperature change and load information inside the pot in real time. The characteristic data includes temperature change rate, heating power change, temperature mutation point, load information (such as ingredient type, liquid amount), heating time period, and other data. Through these characteristic data, the heating stage characteristics of the pot in different modes can be described. The heating stage characteristic data is divided, usually into a training set and a test set at a ratio of 70% / 30%. The training set is used for model training, and usually includes characteristic data of the heating stage and corresponding labels (i.e., which heating stage the pot is in). The purpose of the training set is to allow the model to learn the relationship between different features and heating stages. The test set is used to evaluate the performance and generalization ability of the trained model to ensure that the model can not only perform well on the training data, but also make accurate predictions on unknown data. The decision tree algorithm is selected for training. The decision tree is a simple and effective classification and regression method, which is suitable for situations where there are obvious decision rules between features and targets. In this scenario, the decision tree can classify the pot heating stage through feature data. Using the feature data of the training set, the decision tree algorithm gradually establishes decision rules and selects the best feature split point to minimize the prediction error. Finally, the pot heating stage prediction model (pot stage prediction pre-model) is generated. The trained decision tree model is verified using the test set data to evaluate the model's performance indicators such as accuracy, recall rate, and F1 value. Based on the feedback from the test set, the decision tree is optimized and adjusted, such as adjusting hyperparameters such as the depth of the tree and the minimum number of samples of leaf nodes to improve the prediction accuracy of the model. According to the optimization results, training and testing are repeated until the performance of the model reaches the expected level, and finally a pot heating stage prediction model is generated. Input the real-time characteristic data of the pot heating stage (such as temperature change rate, heating power, load mode, etc.) into the trained heating stage prediction model. Based on the model prediction, determine the current heating stage of the pot. The prediction results include heating stages such as "initial heating", "stable heating stage", and "near boiling stage". The prediction results will be used as output data to reflect the current heating status of the pot. These data will provide a basis for subsequent heating adjustment and intelligent control.

[0127] Preferably, step S4 comprises the following steps:

[0128] Step S41: using the Internet of Things technology to upload the intelligent heating regulation strategy to the cloud platform to collect strategy execution data, and obtain heating regulation strategy execution data;

[0129] Step S42: performing strategy effectiveness evaluation on the heating regulation strategy execution data to generate heating strategy effectiveness evaluation data; performing strategy cloud learning on the intelligent heating regulation strategy according to the heating strategy effectiveness evaluation data to generate real-time heating strategy adjustment data;

[0130] Step S43: Tracking the performance of the cookware by adjusting the data of the real-time heating strategy, thereby generating cookware heating performance tracking data to perform normal cookware temperature intelligent monitoring operations.

[0131] In an embodiment of the present invention, the optimized intelligent heating regulation strategy is uploaded to the cloud platform through an IoT device. The IoT device can be a temperature control system integrated in the smart kitchen, which can convert the regulation strategy into parameters such as heating power, heating time, heating mode, etc., and transmit them remotely to the cloud platform. The cloud platform monitors relevant data during the heating process of the pot through the IoT device, such as pot temperature, heating power, power consumption and other information. These data can reflect the execution effect of the heating regulation strategy in real time and provide basic data for subsequent analysis. The execution data is returned to the local device or control system through the cloud platform to form a closed-loop monitoring, thereby supporting real-time decision-making and adjustment. According to the heating regulation strategy execution data, several performance indicators are set, such as heating speed, energy efficiency ratio, pot temperature stability, etc., to evaluate whether the strategy has achieved the expected goal. By comparing the heating effects before and after the implementation of the heating strategy through data analysis, the effectiveness of the heating strategy is evaluated in combination with dimensions such as temperature control accuracy, power consumption, and cooking time, and the heating strategy effectiveness evaluation data is generated to indicate whether there are problems in the execution of the strategy, such as overheating, large temperature fluctuations, and low energy efficiency. According to the heating strategy effectiveness evaluation data, the intelligent heating regulation strategy is optimized using a cloud learning algorithm (such as reinforcement learning or other machine learning algorithms). The evaluation data will be fed back to the cloud system, and the cloud platform will automatically adjust the parameters of the heating adjustment strategy (such as temperature setting, heating power, heating time, etc.) according to the evaluation results, and upload it to the device again for application. Based on the cloud learning model, the adjusted intelligent heating strategy will be dynamically updated according to the real-time heating data, so that the strategy can adapt to different cooking needs and pot loads. The IoT device monitors the key performance indicators of the pot such as heating temperature, power consumption, cooking time, etc. in real time to generate pot heating performance tracking data. The data of the pot heating process is collected in real time, and the data processing algorithm is used to analyze whether the pot is within the normal temperature control range. If abnormal conditions such as temperature fluctuations, overheating, and overcooling are found, the system will automatically adjust the heating strategy to ensure stable pot temperature control. The intelligent temperature monitoring system of the pot continuously monitors the status of the pot. The temperature information of the pot is obtained through the temperature sensor, and the system determines whether the heating power or time needs to be adjusted based on the temperature change data. If the system detects that the heating status of the pot does not meet expectations (such as the temperature exceeds the set range, the heating efficiency decreases, etc.), it will trigger an alarm to notify the user to make adjustments or automatically adjust the heating parameters.

[0132] In this specification, a smart monitoring system for pot temperature is provided, which is used to execute the smart monitoring method for pot temperature. The smart monitoring system for pot temperature includes:

[0133] The sensor deployment module is used to obtain the pot structure data; perform sensor array deployment on the pot structure data to generate pot sensor deployment data; perform multi-point temperature sensor calibration on the pot sensor deployment data to generate pot sensor calibration data; use the pot sensor calibration data to perform pot temperature acquisition on the temperature sensor built into the pot to obtain standard pot temperature acquisition data;

[0134] The pot mode analysis module is used to perform BM temperature curve conversion on the standard pot temperature collection data to generate a BM temperature conversion curve; perform extreme temperature extraction on the BM temperature conversion curve to obtain pot extreme temperature data; perform first mode division on the pot according to the pot extreme temperature data to generate a pot empty pot mode; perform content temperature critical analysis on the standard pot temperature collection data based on the BM temperature conversion curve to generate a content temperature change critical temperature; perform second mode division according to the content temperature change critical temperature to generate a pot load mode;

[0135] The pot temperature control module is used to predict the pot heating stage for the empty pot mode and the pot load mode, and generate the pot heating stage prediction data; perform fuzzy control feedback on the pot according to the pot heating stage prediction data, and generate control temperature feedback data; optimize and adjust the heating energy efficiency of the control temperature feedback data, so as to generate an intelligent heating adjustment strategy;

[0136] The pot temperature feedback module is used to upload the intelligent heating regulation strategy to the cloud platform for strategy execution data collection to obtain heating regulation strategy execution data; perform strategy cloud learning on the heating regulation strategy execution data to generate real-time heating strategy adjustment data; track the performance of the pot through the real-time heating strategy adjustment data to generate pot heating performance tracking data to perform normal pot temperature intelligent monitoring operations.

[0137] The beneficial effect of the present invention is that by acquiring the structural data of the pot and deploying a sensor array on the pot, each temperature point of the pot can be accurately monitored. Multi-point sensor calibration ensures the accuracy of the collected data, thereby providing a reliable basis for subsequent temperature adjustment and optimization. Through BM temperature curve conversion and extreme temperature extraction, the key temperature threshold can be analyzed and identified in real time during the heating process of the pot, so that the pot state can be adjusted according to the temperature change to reduce the risk of excessive or low temperature. The pot state is divided into the first and second modes (empty pot mode and load mode), so that the pot can automatically switch to the corresponding mode according to different cooking conditions, thereby ensuring the stability and energy efficiency of the heating process. Through the prediction of the heating stage, the system can identify the state changes that occur during the heating process in advance and prevent the influence of temperature fluctuations on the cooking effect. Through the fuzzy control feedback mechanism, the system can make intelligent adjustments according to the predicted data of the heating stage. Through precise optimization and adjustment of heating energy efficiency, the heating process of the pot is more energy-saving and efficient, ensuring accurate temperature control during the cooking process. This intelligent heating adjustment strategy can not only improve the heating efficiency, but also reduce energy consumption, reduce unnecessary heat waste, and improve overall energy efficiency. After uploading the intelligent heating adjustment strategy to the cloud platform, the system can continuously optimize and adjust the heating strategy through cloud learning. This process enables the system to dynamically learn according to the cooking needs and pot performance of different users in actual applications, and continuously improve the heating process. Through real-time heating strategy adjustment data, the system can continuously track the heating process of the pot to ensure that the heating performance of the pot is maintained in the optimal state at each stage, thereby avoiding uneven heating or overheating. Through cloud platform learning and real-time strategy adjustment, the system can provide personalized cooking solutions according to user needs and improve user experience. The pot automatically adapts to different cooking tasks according to different temperature changes and heating stages, so that users do not need to manually adjust the temperature or heating mode. The temperature monitoring and adjustment process of the pot is fully automated. The user only needs to set the preliminary conditions, and the system can intelligently complete the temperature control operation. Through performance tracking, the user can monitor the heating status of the pot in real time to ensure that the cooking process proceeds smoothly. Therefore, the present invention improves the accuracy and flexibility of intelligent monitoring of pot temperature through high-precision sensor arrays, intelligent mode division, fuzzy control feedback and real-time learning in the cloud.

[0138] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0139] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An intelligent method for monitoring the temperature of a cooker, characterized in that: The following steps are involved: Step S1: acquiring the structure data of the pot; performing sensor array deployment on the structure data of the pot to generate the pot sensor deployment data; performing multi-point calibration of the temperature sensor on the pot sensor deployment data to generate the pot sensor calibration data; using the pot sensor calibration data to perform pot temperature acquisition on the temperature sensor built into the pot to obtain the standard pot temperature acquisition data; Step S2: converting the standard pot temperature collection data into a BM temperature curve to generate a BM temperature conversion curve; extracting the extreme temperature of the BM temperature conversion curve to obtain the pot extreme temperature data; dividing the pot into a first mode based on the pot extreme temperature data to generate a pot empty pot mode; performing a critical analysis of the content temperature of the standard pot temperature collection data based on the BM temperature conversion curve to generate a critical temperature of the content temperature change; dividing the second mode according to the critical temperature of the content temperature change to generate a pot load mode; Step S2 includes the following steps: Step S21: converting the standard pot temperature collection data into a BM temperature curve to generate a BM temperature conversion curve; extracting the extreme temperature of the BM temperature conversion curve to obtain the pot extreme temperature data; comparing the pot extreme temperature data with a preset first temperature threshold, and when the pot extreme temperature data is greater than or equal to the preset first temperature threshold, a pot hot reminder is issued through an indicator light; Step S22: when the extreme temperature data of the pot is greater than a preset first temperature threshold and greater than a preset second temperature threshold, a dry-burning warning is issued to the pot based on the extreme temperature data of the pot, thereby generating dry-burning warning data; the pot is divided into a first mode based on the dry-burning warning data, and a pot empty pot mode is generated; wherein, when the extreme temperature data of the pot is greater than the preset first temperature threshold and greater than the preset second temperature threshold, a dry-burning warning is issued to the pot based on the extreme temperature data of the pot, including: When the extreme temperature data of the pot is greater than a preset first temperature threshold and greater than a preset second temperature threshold, a pot array temperature change analysis is performed on the standard pot temperature collection data based on the extreme temperature data of the pot to generate pot temperature change data; the pot temperature change data is converted into a heat map to generate a pot temperature change heat map; Performing heat map edge recognition on the heat map of pot temperature change to generate pot edge temperature change data; performing temperature gradient field calculation on the pot edge temperature change data to generate pot edge temperature gradient field; performing gradient amplitude calculation on the pot edge temperature gradient field to obtain edge temperature gradient field amplitude data; Perform a heat map texture analysis on the temperature change heat map of the pot through the edge temperature gradient field amplitude data to generate the heat map texture temperature change amplitude data; perform a heat uniformity analysis on the pot based on the heat map texture temperature change amplitude data to generate the heat uniformity data of the pot; perform a dry burning warning on the pot based on the heat uniformity data of the pot to generate the dry burning warning data; Step S23: using the pressure sensor and the BM temperature conversion curve to perform a critical temperature analysis of the contents on the standard cookware temperature collection data, and generating a critical temperature of the contents temperature change; Step S24: identifying the state of the contents according to the critical temperature of the contents temperature change, and generating contents state identification data; performing a second mode division based on the contents state identification data, and generating a cookware load mode; wherein identifying the state of the contents according to the critical temperature of the contents temperature change includes: Based on the critical temperature of the temperature change of the contents, a multi-point temperature field distribution matrix is ​​constructed to obtain the multi-point temperature field distribution data in the pot; the temperature change rate and acceleration characteristics of the multi-point temperature field distribution data in the pot are extracted to obtain the pot temperature change rate and the pot temperature change acceleration data; The temperature mutation point of the multi-point temperature field distribution data in the pot is confirmed by using the temperature change rate of the pot, and the temperature mutation point data is obtained; the heating steady-state interval of the temperature mutation point data is analyzed by the acceleration data of the temperature change of the pot, and the heating steady-state interval of the pot load is generated; the key temperature threshold value of the pot load heating steady-state interval and the temperature mutation point data is identified based on the phase change theory, and the key temperature threshold value data is generated; The pressure sensor is used to analyze the change in pressure of the pot during the steady-state heating period of the pot load, and the pressure change data of the pot is generated; the pressure fluctuation cycle of the pot pressure change data is analyzed to generate the pressure characteristic data of the cooking state; the content state is identified based on the key temperature threshold data and the pressure characteristic data of the cooking state, and the content state identification data is generated; Step S3: predicting the heating stage of the pot for the empty pot mode and the loaded pot mode, and generating the prediction data of the heating stage of the pot; performing fuzzy control on the heating power of the pot according to the prediction data of the heating stage of the pot, and generating the heating power adjustment data; performing control temperature adjustment feedback on the standard pot temperature collection data according to the heating power adjustment data, and generating the control temperature feedback data; optimizing and adjusting the heating energy efficiency of the control temperature feedback data, and thus generating the intelligent heating adjustment strategy; Step S4: Upload the intelligent heating regulation strategy to the cloud platform to collect strategy execution data and obtain heating regulation strategy execution data; perform strategy cloud learning on the heating regulation strategy execution data to generate real-time heating strategy adjustment data; track the performance of the cookware through the real-time heating strategy adjustment data to generate cookware heating performance tracking data to perform normal cookware temperature intelligent monitoring operations.

2. The intelligent monitoring method of cookware temperature according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: obtaining the pot structure data; Step S12: Calculate the structure center point of the cookware structure data to obtain the cookware structure center point data; perform sensor array deployment based on the cookware structure center point data to generate cookware sensor deployment data, wherein the sensor array deployment includes pressure sensor array deployment and temperature sensor array deployment; Step S13: performing multi-point calibration of the temperature sensor on the pot sensor deployment data to generate pot sensor calibration data; using the pot sensor calibration data to collect the pot temperature of the temperature sensor built into the pot to obtain the pot temperature collection data; Step S14: performing data preprocessing on the pot temperature collection data to generate standard pot temperature collection data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization.

3. The intelligent monitoring method of the cookware temperature according to claim 2, characterized in that: Performing multi-point sensor calibration on the pan sensor deployment data includes: The temperature sensor is selected for calibration points in the working temperature range through the pot sensor deployment data to obtain calibration point data in the working temperature range; the temperature sensor is confirmed for multi-point heating data of the target point based on the calibration point data in the working temperature range to generate heating temperature data of the calibration point; The actual temperature error analysis is performed on the calibration point data in the working temperature range and the heating temperature data at the calibration point to obtain the actual temperature relationship model. The actual temperature relationship model is used to perform thermal conduction delay compensation on the temperature sensor to generate the calibration data of the pot temperature sensor. The formula for the actual temperature error analysis is as follows: ； In the formula, Expressed as actual temperature, Expressed as the sensor output voltage, are the fitting coefficients; The formula for thermal conduction delay compensation is as follows: ； In the formula, Expressed as the pot contents at time The temperature at Represented as the pot bottom at time The temperature at Indicated as the material and contents of the pot at the time The temperature difference.

4. The intelligent monitoring method of cookware temperature according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: predicting the pot heating stage for the pot empty mode and the pot loaded mode, and generating pot heating stage prediction data; Step S32: performing fuzzy control on the heating power of the cooker according to the prediction data of the cooking pot heating stage, and generating heating power adjustment data; performing temperature adjustment feedback on the standard cooker temperature collection data according to the heating power adjustment data, and generating control temperature feedback data; Step S33: performing power consumption and energy saving analysis on the temperature control feedback data to generate temperature control power energy saving data; Step S34: Utilize the temperature control power energy saving data to optimize the heating energy efficiency of the control temperature feedback data, thereby generating an intelligent heating regulation strategy.

5. The intelligent monitoring method of the cookware temperature according to claim 4, characterized in that: Step S31 includes the following steps: Step S311: extracting heating stage characteristics of the cooker in the empty pot mode and the cooker in the loaded pot mode to obtain cooking stage characteristic data; Step S312: dividing the characteristic data of the pot heating stage into a data set to generate a model training set and a model test set; using a decision tree algorithm to perform model training on the model training set to generate a pot stage prediction pre-model; performing model optimization iteration on the pot stage prediction pre-model through the model test set to generate a pot heating stage prediction model; Step S313: importing the pot heating stage characteristic data into the pot heating stage prediction model to perform pot heating stage prediction and generate pot heating stage prediction data.

6. The intelligent monitoring method of cookware temperature according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: using the Internet of Things technology to upload the intelligent heating regulation strategy to the cloud platform to collect strategy execution data, and obtain heating regulation strategy execution data; Step S42: performing strategy effectiveness evaluation on the heating regulation strategy execution data to generate heating strategy effectiveness evaluation data; performing strategy cloud learning on the intelligent heating regulation strategy according to the heating strategy effectiveness evaluation data to generate real-time heating strategy adjustment data; Step S43: Tracking the performance of the cookware by adjusting the data of the real-time heating strategy, thereby generating cookware heating performance tracking data to perform normal cookware temperature intelligent monitoring operations.

7. An intelligent monitoring system for pot temperature, characterized in that: The intelligent monitoring system for the temperature of a cooker according to claim 1 comprises: The sensor deployment module is used to obtain the pot structure data; perform sensor array deployment on the pot structure data to generate pot sensor deployment data; perform multi-point temperature sensor calibration on the pot sensor deployment data to generate pot sensor calibration data; use the pot sensor calibration data to perform pot temperature acquisition on the temperature sensor built into the pot to obtain standard pot temperature acquisition data; The pot mode analysis module is used to perform BM temperature curve conversion on the standard pot temperature collection data to generate a BM temperature conversion curve; perform extreme temperature extraction on the BM temperature conversion curve to obtain pot extreme temperature data; perform first mode division on the pot according to the pot extreme temperature data to generate a pot empty pot mode; perform content temperature critical analysis on the standard pot temperature collection data based on the BM temperature conversion curve to generate a content temperature change critical temperature; perform second mode division according to the content temperature change critical temperature to generate a pot load mode; The pot temperature control module is used to predict the pot heating stage for the empty pot mode and the pot load mode, and generate the pot heating stage prediction data; perform fuzzy control feedback on the pot according to the pot heating stage prediction data, and generate control temperature feedback data; optimize and adjust the heating energy efficiency of the control temperature feedback data, so as to generate an intelligent heating adjustment strategy; The pot temperature feedback module is used to upload the intelligent heating regulation strategy to the cloud platform for strategy execution data collection to obtain heating regulation strategy execution data; perform strategy cloud learning on the heating regulation strategy execution data to generate real-time heating strategy adjustment data; track the performance of the pot through the real-time heating strategy adjustment data to generate pot heating performance tracking data to perform normal pot temperature intelligent monitoring operations.

Images