Charging type induction cooker control method and system based on data analysis and induction cooker

Abstract

The invention discloses a charging type induction cooker control method and system based on data analysis and an induction cooker, and particularly relates to the technical field of induction cooker control. According to the method, time-frequency domain conjoint analysis is carried out on original energy distribution data of an induction cooker heating area, time-space change characteristics of energy distribution are extracted, and abnormal fluctuation indexes of dynamic changes of a thermal field are identified. Extracting a significant feature mode of position offset of the heating region through principal component analysis, and establishing a recognition model of an energy anomaly concentration region; and positioning the spatial position and boundary information of the heat concentration abnormal region in the real-time heating process by adopting clustering analysis, judging the stability state of the current heating mode, and outputting a comprehensive evaluation result of heating distribution. The excitation frequency and the output power of each coil in the induction coil array of the induction cooker are adjusted according to the comprehensive evaluation result, real-time balance control over heat distribution is achieved, the problem that an existing induction cooker is difficult to cope with dynamic deviation of a heating area under fixed frequency control is effectively solved, and heating uniformity is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of induction cooker control, and more particularly to a data analysis-based control method and system for a rechargeable induction cooker, and the induction cooker. Background Art

[0002] Induction cookers use an induction coil to apply an alternating magnetic field to generate high-frequency electrical energy for heating, and the energy distribution in the actual heating area is prone to dynamic changes.

[0003] Existing induction cooker control systems generally rely on fixed frequency and power control strategies, which make it difficult to identify the position offset and morphological changes of the heating area under high-frequency electromagnetic action, resulting in abnormal heat concentration and making it difficult to effectively solve the degradation of heating performance caused by uneven heat distribution.

[0004] With the development and maturity of data analysis and processing technology and intelligent control technology, an intelligent control technology solution based on data analysis is now provided to solve the above technical problems. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a data analysis-based control method and system for a rechargeable induction cooker and an induction cooker to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: A data analysis-based control method for a rechargeable induction cooker comprises the following steps: S1: Collect high-frequency current waveform data at different positions of the induction coil of the induction cooker and obtain the original energy distribution data of the heating area based on the time series synchronization method; S2: Based on the original energy distribution data, the wavelet transform method is used to perform time-frequency domain feature analysis, extract the spatiotemporal variation characteristics of energy distribution, and determine the abnormal fluctuation index of thermal field dynamic changes; S3: Based on the abnormal fluctuation index, the characteristic pattern of the heating area position offset is identified through the principal component analysis algorithm, and an identification model for the energy abnormal concentration area is constructed; S4: Using cluster analysis algorithm, based on the recognition model, the spatial location and boundary information of the abnormal heat concentration area during the real-time heating process are determined; S5: Based on the spatial location and boundary information of the abnormal heat concentration area, the stability state of the current heating mode is judged, and a comprehensive evaluation result of whether the heating distribution is abnormal is output; S6: Dynamically adjust the excitation frequency and output power of each coil in the induction coil array of the induction cooker according to the comprehensive evaluation results.

[0007] In a preferred embodiment, S1 is specifically: Collect high-frequency current waveform data at each induction coil position in the induction coil array of the induction cooker; Based on the timing synchronization method, the high-frequency current waveform data at each induction coil position is time-stamped and aligned to generate high-frequency current waveform data; According to the high-frequency current waveform data, the energy distribution value of each induction coil position is calculated to obtain the original energy distribution data of the heating area.

[0008] In a preferred embodiment, S2 is specifically: Based on the original energy distribution data of the heating area, the wavelet transform method is used to perform a joint analysis of the original energy distribution data in the time domain and frequency domain; By performing multi-scale decomposition operations on the original energy distribution data, the time-frequency domain feature components corresponding to different time moments and different frequencies are extracted; According to the energy value changes and spatial position changes of the characteristic components in the time-frequency domain, the abnormal fluctuation indicators that appear during the dynamic changes of the thermal field are determined.

[0009] In a preferred embodiment, S3 is specifically: Based on the abnormal fluctuation indexes appearing in the dynamic change of thermal field, the principal component analysis algorithm is used to perform feature dimensionality reduction processing to determine several principal components that play a major role in the dynamic change of thermal field. Extracting significant characteristic patterns when the position of the corresponding heating area shifts according to the determined principal components. The significant characteristic patterns include the shift direction and the shift amplitude characteristics of the energy concentration area. Based on the significant feature patterns, an identification model for energy abnormal concentration areas is established.

[0010] In a preferred embodiment, S4 is specifically: Based on the recognition model of abnormal energy concentration areas, a cluster analysis algorithm is used to cluster the characteristic patterns of high-frequency current waveform data appearing in the real-time heating process; The spatial location of the abnormal energy concentration area that appears in real time is determined by cluster analysis algorithm, and the spatial boundary location of the abnormal energy concentration area is calculated; According to the spatial boundary position, the spatial position information and spatial boundary information of the real-time heat concentration abnormal area are generated.

[0011] In a preferred embodiment, S5 is specifically: Based on the spatial location information and spatial boundary information of the real-time heat concentration abnormal area, a stability judgment model is used to judge the stability state of the real-time heating mode; The stability determination model determines whether the real-time heating mode is in a stable state by comparing the spatial distribution characteristics of the real-time heat concentration abnormal area with the heat spatial distribution characteristics under the preset stable state; Based on the determination result of the stability determination model, a comprehensive evaluation result indicating whether the heating distribution in the real-time heating mode is abnormal is generated.

[0012] In a preferred embodiment, S6 is specifically: determining, based on a comprehensive evaluation result indicating whether heating distribution in the real-time heating mode is abnormal, an induction coil requiring adjustment of excitation frequency and output power; For the induction coils that need to be adjusted, the excitation frequency adjustment amount and output power adjustment amount of the induction coils are calculated based on the spatial distribution characteristics and spatial boundary information of the real-time abnormal heat concentration area; The calculated excitation frequency adjustment amount and output power adjustment amount of the induction coil are applied to the induction coil array of the induction cooker respectively, and the excitation frequency and output power of each induction coil in the induction coil array of the induction cooker are adjusted in real time.

[0013] In another aspect, the present invention provides a data analysis-based control system for a rechargeable induction cooker, comprising: Data acquisition module: collects high-frequency current waveform data at different positions of the induction coil of the induction cooker, and obtains the original energy distribution data of the heating area based on the time series synchronization method; Feature extraction module: Based on the original energy distribution data, the wavelet transform method is used to perform time-frequency domain feature analysis, extract the spatiotemporal variation characteristics of energy distribution, and determine the abnormal fluctuation index of thermal field dynamic changes; Pattern recognition module: Based on the abnormal fluctuation index, the principal component analysis algorithm is used to identify the characteristic pattern of the heating area position offset and build an identification model for the energy abnormal concentration area; Regional positioning module: uses cluster analysis algorithm to determine the spatial location and boundary information of abnormal heat concentration areas during real-time heating based on the recognition model; Stability Assessment Module: This module determines the stability of the current heating mode based on the spatial location and boundary information of the abnormal heat concentration area, and outputs a comprehensive evaluation result on whether the heating distribution is abnormal. Parameter control module: dynamically adjusts the excitation frequency and output power of each coil in the induction coil array of the induction cooker based on the comprehensive evaluation results.

[0014] On the other hand, the present invention provides a rechargeable induction cooker, comprising a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, the above-mentioned rechargeable induction cooker control method based on data analysis is implemented.

[0015] Beneficial effects: Compared with the existing technology, the present invention collects high-frequency current waveform data at different positions of the induction coil of the induction cooker, and obtains the original energy distribution data of the heating area based on the time synchronization method, thereby improving the spatial resolution of the heating state; through wavelet transform to perform time-frequency domain feature extraction, it can capture the dynamic changes of energy distribution at multiple scales and identify the unstable characteristics of the thermal field; combined with the principal component analysis algorithm to identify the abnormal heat concentration trend, and construct an identification model, which has the ability to identify the position offset of the heating area; the cluster analysis algorithm is used to delineate the spatial position and boundary information of the abnormal heat concentration area, thereby enhancing the accuracy of abnormal positioning; the comprehensive evaluation results of the heating distribution anomaly are output through the stability state judgment mechanism, thereby realizing the judgment of the heat distribution state; by dynamically adjusting the excitation frequency and output power, the output response of each induction coil is finely controlled, so that the magnetic field effect and the heat distribution in the heating area are coupled and matched in real time, thereby improving the heating uniformity, adaptability and intelligent control level of the induction cooker as a whole. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of a control method for a rechargeable induction cooker based on data analysis according to the present invention; Figure 2 The figure is a structural diagram of a rechargeable induction cooker control system based on data analysis according to the present invention. DETAILED DESCRIPTION

[0017] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0018] Example 1 Figure 1 The present invention provides a control method for a rechargeable induction cooker based on data analysis, which includes the following steps: S1: Collect high-frequency current waveform data at different positions of the induction coil of the induction cooker and obtain the original energy distribution data of the heating area based on the time series synchronization method; S2: Based on the original energy distribution data, the wavelet transform method is used to perform time-frequency domain feature analysis, extract the spatiotemporal variation characteristics of energy distribution, and determine the abnormal fluctuation index of thermal field dynamic changes; S3: Based on the abnormal fluctuation index, the characteristic pattern of the heating area position offset is identified through the principal component analysis algorithm, and an identification model for the energy abnormal concentration area is constructed; S4: Using cluster analysis algorithm, based on the recognition model, the spatial location and boundary information of the abnormal heat concentration area during the real-time heating process are determined; S5: Based on the spatial location and boundary information of the abnormal heat concentration area, the stability state of the current heating mode is judged, and a comprehensive evaluation result of whether the heating distribution is abnormal is output; S6: Dynamically adjust the excitation frequency and output power of each coil in the induction coil array of the induction cooker according to the comprehensive evaluation results.

[0019] S1: Collect high-frequency current waveform data at different positions of the induction coil of the induction cooker, and obtain the original energy distribution data of the heating area based on the time series synchronization method, including: Collect high-frequency current waveform data at each induction coil position in the induction coil array of the induction cooker; Specifically, the induction coil array of an induction cooker includes multiple independently controlled induction coils, and each induction coil position is equipped with a sensor device for measuring the high-frequency current waveform. The high-frequency current waveform data includes the amplitude of the high-frequency current, the phase of the high-frequency current, and the frequency of the high-frequency current. Among them, the high-frequency current amplitude is used to reflect the size of the coil energy output, the high-frequency current phase is used to reflect the timing relationship between the induction coils, and the high-frequency current frequency is used to reflect the characteristics of energy transmission. The method for measuring the amplitude, phase, and frequency of the high-frequency current is as follows: a high-speed current sensor and a synchronous clock module are respectively set at the position of each induction coil, and the amplitude of the high-frequency current of each coil is measured in real time by the high-speed current sensor. At the same time, the current phase of each coil is recorded in real time in conjunction with the phase detection module, and the frequency of the current waveform of each coil is measured in real time using a frequency meter to obtain high-frequency current waveform information.

[0020] Based on the timing synchronization method, the high-frequency current waveform data at each induction coil position is time-stamped and aligned to generate high-frequency current waveform data; Specifically, the timing synchronization method is implemented as follows: first, a unified reference clock source is set up in the induction cooker induction coil array. The reference clock source is connected to the synchronization clock module at each induction coil position to achieve synchronous distribution of a unified clock signal. The high-frequency current waveform data collected at each induction coil position is marked with the timestamp information provided by the reference clock source. This allows all collected high-frequency current waveform data to be aligned and synchronized using a unified time scale, ensuring that data at different locations have a precise time correspondence. The collected high-frequency current waveform data with timestamp information is uploaded to a cloud server via a wireless network. The cloud server performs timing synchronization on the high-frequency current waveform data based on the timestamp information.

[0021] After achieving data timing synchronization, the high-frequency current waveform data at each induction coil position is combined to form high-frequency current waveform data. Specifically, the high-frequency current waveform data records the current amplitude, current phase, and current frequency at each induction coil position at each moment, forming a continuous information set that can reflect the real-time energy status of the entire heating area.

[0022] According to the high-frequency current waveform data, the energy distribution value of each induction coil position is calculated to obtain the original energy distribution data of the heating area; Specifically, the method for calculating the energy distribution value at each induction coil position is as follows: First, the instantaneous power value at the corresponding position of each induction coil is calculated using the synchronized high-frequency current waveform data. The instantaneous power value is calculated by multiplying the high-frequency current amplitude measured at each induction coil by the instantaneous voltage amplitude of the coil at the corresponding position, and correcting it by the power factor. The power factor is determined by the phase difference of the high-frequency current and is expressed as the cosine value of the phase difference between the high-frequency current and the coil voltage. The correction factor is included in the product when calculating the instantaneous power value. That is, the instantaneous power value is equal to the current amplitude multiplied by the voltage amplitude, and then multiplied by the cosine value of the phase difference between the current amplitude and the voltage amplitude.

[0023] The instantaneous power values ​​at the corresponding positions of each induction coil are integrated over a unified time base to obtain the cumulative energy value at each induction coil position over a specific time period. By summarizing and organizing the cumulative energy values ​​at each induction coil position, the raw energy distribution data for the induction cooker's heating area can be obtained. This raw energy distribution data reflects the real-time distribution characteristics of energy transmission at each induction coil position and can demonstrate the energy concentration at various locations within the entire induction cooker's heating area. The raw energy distribution data is a collection of cumulative energy values ​​obtained by integrating multiple power variation sequences generated at each induction coil position over a specific time period.

[0024] S2: Based on the original energy distribution data, the wavelet transform method is used to perform time-frequency domain feature analysis, extract the spatiotemporal variation characteristics of the energy distribution, and determine the abnormal fluctuation indicators of the dynamic changes of the thermal field, including: Based on the original energy distribution data of the heating area, the wavelet transform method is used to perform a joint analysis of the original energy distribution data in the time domain and frequency domain; Specifically, after obtaining the raw energy distribution data for the induction cooker's heating area, we used a wavelet transform to perform a joint time-domain and frequency-domain analysis of the raw energy distribution data to analyze the dynamic characteristics of the energy distribution during the real-time heating process. Wavelet transforms can simultaneously reflect the signal's changing characteristics in both the time and frequency dimensions, detecting abnormal energy changes in the heating area of ​​the induction cooker's induction coil array and effectively identifying local anomalies at different time points and frequency components.

[0025] By performing multi-scale decomposition operations on the original energy distribution data, the time-frequency domain feature components corresponding to different time moments and different frequencies are extracted; Specifically, the raw energy distribution data is preprocessed to ensure the validity of the wavelet analysis. The preprocessing method includes removing abnormal data points caused by measurement noise or data acquisition errors, and correcting missing data through interpolation to ensure the continuity and smoothness of the data.

[0026] After data preprocessing is completed, the original energy distribution data is decomposed into low-frequency and high-frequency components of different scales by continuously performing multiple wavelet transform decomposition operations on the original energy distribution data: the original energy distribution data is subjected to a wavelet decomposition to obtain an approximate low-frequency component and several detailed high-frequency components; the obtained approximate low-frequency component is further subjected to secondary, tertiary or even higher-order multi-scale wavelet decomposition to gradually obtain characteristic components at different scales.

[0027] From the low-frequency and high-frequency components of different scales obtained through multi-scale decomposition, the energy values ​​and spatial position features corresponding to each specific moment are extracted to form a complete set of time-frequency domain feature components. For example, at a specific moment, by calculating the signal strength at components of different scales, analyzing the energy levels at different locations, and recording the corresponding positions and scales, a set of time-frequency domain feature components is formed. The specific calculation method is: for each scale feature component, the energy distribution value at that scale is squared and then summed to obtain the characteristic energy value at that moment.

[0028] According to the energy value change and spatial position change of the characteristic components in the time-frequency domain, the abnormal fluctuation index appearing in the dynamic change process of the thermal field is determined; Specifically, the abnormal fluctuation index is determined by analyzing the energy value change trend of the time-frequency domain characteristic components at different time points and different scales, identifying abnormal fluctuation signals that significantly deviate from the normal preset range, and recording the location, intensity and frequency scale of the abnormal fluctuation signal. The abnormal fluctuation index is defined as follows: at each specific moment, the energy values ​​of the characteristic components extracted at each frequency scale are analyzed separately, and the absolute value of the difference in energy values ​​between adjacent moments on a specific frequency scale is taken to obtain the energy fluctuation intensity on the frequency scale; the absolute value of the difference in energy values ​​between adjacent spatial positions at the same moment is also taken to determine the energy difference amplitude at the spatial position; the fluctuation intensity on the frequency scale is multiplied by the energy difference amplitude at the spatial position to obtain the abnormal fluctuation value under the joint action of the frequency scale and the spatial position; the abnormal fluctuation values ​​obtained under the joint action of all frequency scales and spatial positions are accumulated to obtain the abnormal fluctuation index of the entire thermal field dynamic change.

[0029] S3: Based on the abnormal fluctuation index, the principal component analysis algorithm is used to identify the characteristic pattern of the heating area position offset and build an identification model for the energy abnormal concentration area, including: Based on the abnormal fluctuation indexes appearing in the dynamic change of thermal field, the principal component analysis algorithm is used to perform feature dimensionality reduction processing to determine several principal components that play a major role in the dynamic change of thermal field. Specifically, the basic principle of the principal component analysis algorithm is to project high-dimensional feature data into a new, lower-dimensional space to remove redundant information from the data, retaining only the key features that fully describe the changes in the original data. The abnormal fluctuation indicators are normalized by subtracting the overall mean of the abnormal fluctuation indicators from each individual abnormal fluctuation indicator, and then dividing by the overall standard deviation of the abnormal fluctuation indicators.

[0030] The standardized abnormal fluctuation index is input into the principal component analysis algorithm. The eigenvalues ​​corresponding to the eigenvectors are determined by calculating the covariance matrix and eigenvalues ​​and eigenvectors of the abnormal fluctuation index. The eigenvalue indicates the degree to which the principal component represented by the corresponding eigenvector contributes to the overall change in the abnormal fluctuation index. The principal component analysis algorithm sorts the eigenvalues ​​by size and selects eigenvectors with large eigenvalues ​​and cumulative contribution rates exceeding a predetermined threshold to form a small number of principal components. The eigenvalue selection criteria are: sort the eigenvalues ​​from large to small, accumulate the contribution rates of each eigenvalue, that is, the proportion of each eigenvalue to the sum of all eigenvalues, and stop selecting when the cumulative contribution rate reaches a predetermined threshold (for example, above 90%), thereby ensuring that the principal components fully represent the main characteristic information of the original data.

[0031] Extracting significant characteristic patterns when the position of the corresponding heating area shifts according to the determined principal components. The significant characteristic patterns include the shift direction and the shift amplitude characteristics of the energy concentration area. Significant characteristic patterns include the direction and magnitude of the energy concentration area's positional offset. The method for extracting these significant characteristic patterns is as follows: first, based on the principal components obtained, the energy concentration area distribution characteristics at each location in the heating area under normal conditions are used as a reference. The real-time principal components are then compared to calculate the difference in magnitude and spatial characteristics between the real-time and normal states, identifying whether the energy concentration area exhibits significant spatial offset. The positional change of the offset area is then calculated, including the offset direction (e.g., along the long or short axis of the induction coil array) and the offset magnitude (specifically, the distance difference between the center of the offset area and the normal position).

[0032] The method for calculating the difference size and spatial difference characteristics between the real-time state and the normal state is: Determine the principal component characteristic data in the normal state, that is, the principal component data set pre-recorded or trained under the normal working state of the induction cooker, as the standard reference benchmark data.

[0033] The real-time abnormal fluctuation index data is projected into the principal component space through the same principal component analysis method to obtain the principal component feature data set of the real-time state.

[0034] Compare the difference between the real-time state principal component feature data and the normal state principal component feature data in the principal component space position by position: Corresponding to each induction coil position, respectively calculating the difference between the principal component feature data of the real-time state and the principal component feature data of the normal state; Add the absolute values ​​of the above differences to quantify the size of the difference.

[0035] The method for calculating spatial difference features is: Analyze several locations where the real-time state differs most from the normal state in the principal component space; The amplitude of the position principal component data deviation and the range of spatial distribution are calculated to determine the location and regional range where obvious spatial abnormal fluctuations occur.

[0036] Determine the offset direction: determine the spatial coordinates of each induction coil array in the heating area (e.g., clearly divide the induction coil array space into two spatial directions: long axis and short axis); Taking the position center of the energy concentration area in the normal state as the original reference, determine the coordinates of the position center of the energy concentration area in the real-time state; Through the difference in coordinate positions, the direction of change of the center of the energy concentration area in the real-time state relative to the center in the normal state is clarified, and the offset direction is determined to be along the long axis, the short axis, or a specific direction between the two axes; For example, if the center coordinates of the energy concentration region in the real-time state move more toward the long axis direction than the center coordinates in the normal state, the offset direction is defined as along the long axis direction.

[0037] The offset amplitude is calculated as follows: First, determine the center position of the energy concentration area in the induction cooker's heating zone under normal operating conditions. This center position is calculated by taking the weighted average of the energy distribution values ​​at each induction coil position under normal operating conditions. Then, determine the center position of the energy concentration area in real time. In the event of abnormal energy concentration or offset, the actual center position is calculated using the same weighted average method using the energy distribution values ​​corresponding to each induction coil position obtained in real time. The actual center position calculated in real time is compared with the center position under normal conditions in the spatial coordinates of the induction cooker's induction coil array. The specific calculation method is to determine the distance of the position offset by calculating the Euclidean distance between the two center positions in spatial coordinates. The distance of the position offset is defined as the offset amplitude, which reflects the actual spatial offset of the real-time energy concentration area relative to the center position under normal conditions.

[0038] Based on the significant characteristic patterns, an identification model for energy abnormal concentration areas is established; Specifically, based on the acquired significant feature patterns, including the position offset direction and offset amplitude, an identification model for abnormal energy concentration areas is established. The identification model is established by using the acquired significant feature pattern data as training data, selecting a supervised machine learning method (such as a support vector machine or decision tree algorithm), using the significant feature pattern data as input and the spatial location labels corresponding to the abnormal energy concentration areas as output, to train a model capable of automatically identifying abnormal energy concentration areas. Model training and cross-validation are performed using multiple sets of actual significant feature pattern data collected from abnormal energy concentration areas. Through multiple verification and optimization of parameter configurations, such as kernel function selection in the support vector machine algorithm or node partitioning thresholds in the decision tree algorithm, the optimal model parameter configuration is determined to ensure the model has high recognition accuracy and stability.

[0039] S4: Using a cluster analysis algorithm, based on the recognition model, the spatial location and boundary information of the abnormal heat concentration area during the real-time heating process are determined, including: Based on the recognition model of abnormal energy concentration areas, a cluster analysis algorithm is used to cluster the characteristic patterns of high-frequency current waveform data appearing in the real-time heating process; The spatial location of the abnormal energy concentration area that appears in real time is determined by cluster analysis algorithm, and the spatial boundary location of the abnormal energy concentration area is calculated; Generate the spatial location information and spatial boundary information of the real-time heat concentration abnormal area according to the spatial boundary position; Specifically, in order to accurately locate the abnormal energy concentration area during the actual operation of the induction cooker, it is necessary to perform cluster analysis on the high-frequency current waveform data collected in real time to clearly locate the position and boundary information of the abnormal energy concentration area in real time.

[0040] During real-time operation, the system uses a model to identify abnormally concentrated energy areas, performing cluster analysis on the characteristic patterns of real-time high-frequency current waveform data collected from various locations in the induction coil array of the induction cooker. The cluster analysis algorithm uses density cluster analysis. Abnormally concentrated energy areas within the induction coil array of the induction cooker exhibit distinct spatial clustering characteristics, and the density cluster analysis algorithm is effective in identifying spatially dense regions in the data distribution.

[0041] First, feature extraction and preprocessing of the real-time high-frequency current waveform data are performed. Feature extraction involves extracting characteristic patterns significantly associated with energy concentration areas from the real-time high-frequency current waveform data at each induction coil location. These patterns include the amplitude characteristics, phase differences, and frequency variations of the high-frequency current at each coil location. After feature extraction, all feature data are normalized to ensure uniform data scale across different features, facilitating cluster analysis.

[0042] The standardized feature data is used as input and clustered using a density clustering analysis algorithm. The implementation of the density clustering analysis algorithm involves first determining the parameters for determining the density of data points in the data space, including the data density threshold parameter and the minimum data sample number parameter. This determination is achieved by repeatedly clustering historical data and adjusting the parameters until the clustering results can stably and effectively identify historically confirmed areas of anomaly concentration. After determining the data density threshold parameter and the minimum data sample number parameter, the density clustering analysis algorithm is executed as follows: Each data point in the data space is individually determined to determine whether the number of points within a specified spatial radius around it meets the set minimum sample number. If so, the area is defined as a density core region. All density core regions are then connected to form larger spatial cluster regions until all energy anomaly concentration areas are identified.

[0043] Through this clustering process, the specific spatial location of the abnormal energy concentration area that appears in real time is determined. The spatial location is expressed as the center position of each cluster. That is, the specific spatial center position of the abnormal concentration area is obtained by averaging the spatial coordinates corresponding to all data points within each cluster. It is then located at the specific coil position area in the induction coil array of the induction cooker.

[0044] To determine the specific spatial boundary locations of energy-abnormally concentrated regions, the boundary locations of each cluster are calculated. The boundary location calculation method is as follows: for each determined energy-abnormally concentrated region, starting from the spatial center of the cluster, the spatial distances of the data points in each direction from the center are calculated one by one. When the density of energy data points at the spatial distance from the center is significantly lower than the density threshold parameter set by the density clustering algorithm, the distance position is defined as the spatial boundary location of the region. By calculating the spatial distances in different directions, the complete spatial boundary location data of the cluster is obtained.

[0045] Based on the calculated spatial boundary position, the spatial position information and spatial boundary information set of the real-time abnormal heat concentration area are generated: taking the central spatial position of each cluster as the benchmark, combined with the calculated spatial boundary positions in each direction, the spatial range and contour boundaries of the energy abnormal concentration area in the induction cooker heating area under real-time conditions are marked, forming a specific data set of real-time abnormal heat concentration area spatial position information and spatial boundary information.

[0046] S5: Based on the spatial location and boundary information of the abnormal heat concentration area, the stability state of the current heating mode is judged, and a comprehensive evaluation result of whether the heating distribution is abnormal is output, including: Based on the spatial location information and spatial boundary information of the real-time heat concentration abnormal area, a stability judgment model is used to judge the stability state of the real-time heating mode; The stability determination model determines whether the real-time heating mode is in a stable state by comparing the spatial distribution characteristics of the real-time heat concentration abnormal area with the heat spatial distribution characteristics under the preset stable state; generating a comprehensive evaluation result indicating whether the heating distribution in the real-time heating mode is abnormal based on the determination result of the stability determination model; Specifically, the stability determination model requires defining the spatial distribution characteristics of heat when the induction cooker's heating mode is in a stable state, referred to as the stable baseline characteristic data. This stable baseline characteristic data is determined by collecting energy distribution data at each induction coil position over a long period of time under the optimally designed stable operating conditions of the induction cooker's induction coil array. This data is then integrated and averaged over time to determine the spatial position information and boundary characteristics of the energy distribution in the stable state, ensuring the representativeness and accuracy of the stable baseline characteristic data.

[0047] During real-time operation, the stability judgment model performs a comparative analysis of the spatial distribution of the real-time abnormal heat concentration area based on its spatial location information and spatial boundary information, compared with the predetermined stable baseline feature data. The spatial distribution comparative analysis specifically involves using the spatial location determined by the stable baseline feature data as a reference standard to calculate in real time the degree of spatial overlap and spatial difference between the real-time abnormal heat concentration area and the stable state, including calculations of spatial overlap rate and spatial offset. The spatial overlap rate calculation method involves spatially superimposing the real-time abnormal heat concentration area and the stable baseline area, and calculating the ratio of the spatial intersection area to the area of ​​the stable baseline area to determine the degree of spatial overlap between the real-time state and the stable state. The spatial offset calculation method involves calculating the spatial distance between the center position of the real-time abnormal heat concentration area and the center position of the stable baseline area, characterizing the degree of spatial positional deviation of the real-time abnormal heat concentration area relative to the stable state.

[0048] After obtaining the spatial overlap rate and spatial offset, the stability judgment model performs stability state judgment according to pre-defined threshold rules: through statistical analysis of a large amount of historical stable and unstable state data under the actual operation of the induction cooker, a minimum threshold value of the spatial overlap rate and a maximum threshold value of the spatial offset are set. When the spatial overlap rate calculated in real time is lower than the set minimum threshold value of the spatial overlap rate or the spatial offset exceeds the set maximum threshold value, it can be determined that the current real-time heating mode is in an unstable state; otherwise, the real-time heating mode is considered to be in a stable state.

[0049] To ensure the accuracy and reliability of the stability determination model, the model was built through multiple training and validation exercises using historical data to optimize the specific values ​​of the spatial overlap rate and spatial offset threshold parameters. This optimization method involves repeatedly calculating actual abnormal state samples and normal stable state samples from historical data. With the goal of accurately distinguishing historical states, the spatial overlap rate and spatial offset thresholds are continuously adjusted until the stability determination model achieves the highest accuracy, thereby determining the optimal threshold parameters.

[0050] The stability assessment model comprehensively analyzes the spatial differences between the real-time and stable states. Based on the calculated spatial overlap and spatial offset, it outputs a comprehensive evaluation result indicating whether the real-time heating mode is stable. This comprehensive evaluation is generated as follows: if the calculated spatial overlap falls below the minimum threshold or the spatial offset exceeds the maximum threshold, the comprehensive evaluation indicates abnormal heating distribution, indicating that the real-time heating mode is unstable and requires heating adjustment and control measures. Otherwise, the comprehensive evaluation indicates normal heating distribution, indicating that the real-time heating mode is stable.

[0051] The above stability judgment model can accurately capture the slight deviation changes in the spatial position of the real-time energy concentration area, promptly discover potential heating imbalances or abnormal conditions, and ensure that the induction cooker is always in a safe and stable working state, thereby effectively improving the heating accuracy, efficiency and service life of the induction cooker.

[0052] S6: Dynamically adjust the excitation frequency and output power of each coil in the induction coil array of the induction cooker according to the comprehensive evaluation results, including: determining, based on a comprehensive evaluation result indicating whether heating distribution in the real-time heating mode is abnormal, an induction coil requiring adjustment of excitation frequency and output power; Specifically, the induction coils requiring dynamic adjustment are determined based on the comprehensive evaluation results. When the comprehensive evaluation indicates abnormal heating distribution, the induction coils located in or near the abnormal area are identified based on the real-time spatial location and boundary information of the abnormal heat concentration region. These coils are then compared and matched with the layout of the induction cooker's induction coil array, and the induction coils within the abnormal area are identified as the target for adjustment.

[0053] For the induction coils that need to be adjusted, the excitation frequency adjustment amount and output power adjustment amount of the induction coils are calculated based on the spatial distribution characteristics and spatial boundary information of the real-time abnormal heat concentration area; Specifically, based on the spatial distribution characteristics and spatial boundary information of the real-time abnormal heat concentration area, the target energy output state required for each induction coil is calculated. This means setting the target output energy distribution value for each coil position. This target output energy distribution value is determined by comparing the energy concentration state of the current abnormal area with the ideal energy distribution under stable conditions, calculating the energy difference between the two, and then determining the energy output target required for each induction coil based on the size of this difference and its spatial position.

[0054] Calculate the excitation frequency adjustment and output power adjustment for each specific induction coil separately: The method for calculating the excitation frequency adjustment amount is as follows: analyze the influence of the current real-time frequency of the induction coil on the energy transmission efficiency and spatial distribution characteristics, and clarify the quantitative relationship between the change in high-frequency current frequency and the change in induction heating depth and regional distribution; based on the quantitative relationship, calculate the frequency difference between the current energy output state and the target output state of each induction coil, and determine the frequency value that needs to be adjusted for each specific coil through a linear or nonlinear proportional relationship: the frequency adjustment amount is equal to the difference between the current frequency and the target frequency obtained according to the target energy output state.

[0055] The output power adjustment amount is calculated by first determining the difference between the current real-time output power of each induction coil and the target power. The real-time coil current and voltage amplitudes are then calculated, and power correction is performed based on the target power requirement. The power correction method is: after subtracting the current output power from the target output power, correction is performed based on the corresponding power factor to obtain the output power value that needs to be adjusted for each induction coil.

[0056] The various calculation parameters of the above frequency and power dynamic adjustment algorithm (such as the coefficient of the relationship between frequency and energy distribution, and the correction coefficient of power adjustment) have been verified and optimized through a large amount of historical operation data.

[0057] Applying the calculated excitation frequency adjustment amount and output power adjustment amount of the induction coil to the induction coil array of the induction cooker, respectively, to adjust the excitation frequency and output power of each induction coil in the induction coil array of the induction cooker in real time; Specifically, the cloud server automatically issues instructions based on the analysis results. The induction cooker then sends the calculated adjustments for the induction coil's excitation frequency and output power to the cooker's frequency and power control modules, respectively. High-precision frequency and power regulators enable real-time frequency and power adjustments for each induction coil. After these real-time adjustments, the actual output state of each coil in the cooker's induction coil array is aligned with the target state, enabling timely correction of areas of abnormal energy concentration and ensuring a rapid return to a stable overall thermal field distribution.

[0058] Example 2 The difference between Example 2 of the present invention and Example 1 is that this example introduces a rechargeable induction cooker control system based on data analysis.

[0059] Figure 2 A structural diagram of a rechargeable induction cooker control system based on data analysis is provided in the present invention. The rechargeable induction cooker control system based on data analysis includes: Data acquisition module: collects high-frequency current waveform data at different positions of the induction coil of the induction cooker, and obtains the original energy distribution data of the heating area based on the time series synchronization method; Feature extraction module: Based on the original energy distribution data, the wavelet transform method is used to perform time-frequency domain feature analysis, extract the spatiotemporal variation characteristics of energy distribution, and determine the abnormal fluctuation index of thermal field dynamic changes; Pattern recognition module: Based on the abnormal fluctuation index, the principal component analysis algorithm is used to identify the characteristic pattern of the heating area position offset and build an identification model for the energy abnormal concentration area; Regional positioning module: uses cluster analysis algorithm to determine the spatial location and boundary information of abnormal heat concentration areas during real-time heating based on the recognition model; Stability Assessment Module: This module determines the stability of the current heating mode based on the spatial location and boundary information of the abnormal heat concentration area, and outputs a comprehensive evaluation result on whether the heating distribution is abnormal. Parameter control module: dynamically adjusts the excitation frequency and output power of each coil in the induction coil array of the induction cooker based on the comprehensive evaluation results.

[0060] Example 3 The present invention provides a rechargeable induction cooker, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the aforementioned data analysis-based control method for the rechargeable induction cooker is implemented.

[0061] The rechargeable induction cooker provided by the present invention not only has charging and discharging functions, overcomes the limitations of the power wiring harness of traditional electric induction cookers, and can meet different usage scenarios, but also has a rechargeable induction cooker control system based on data analysis. The system enables the rechargeable induction cooker to have the function of data analysis, can make the induction cooker heat more uniformly, and has higher adaptability and intelligent control level. Compared with traditional induction cookers on the market, it has better application prospects and commercial value.

[0062] The above embodiments can be implemented in whole or in part via software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in the embodiments of this application are fully or partially performed. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0063] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0064] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0065] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0066] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected to achieve the purpose of this embodiment according to actual needs.

[0067] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0068] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0069] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0070] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A control method for a rechargeable induction cooker based on data analysis, characterized in that: The steps include: S1: Collect high-frequency current waveform data at different positions of the induction coil of the induction cooker and obtain the original energy distribution data of the heating area based on the time series synchronization method; S2: Based on the original energy distribution data, the wavelet transform method is used to perform time-frequency domain feature analysis, extract the spatiotemporal variation characteristics of energy distribution, and determine the abnormal fluctuation index of thermal field dynamic changes; S3: Based on the abnormal fluctuation index, the characteristic pattern of the heating area position offset is identified through the principal component analysis algorithm, and an identification model for the energy abnormal concentration area is constructed; S4: Using cluster analysis algorithm, based on the recognition model, the spatial location and boundary information of the abnormal heat concentration area during the real-time heating process are determined; S5: Based on the spatial location and boundary information of the abnormal heat concentration area, the stability state of the current heating mode is judged, and a comprehensive evaluation result of whether the heating distribution is abnormal is output; S6: Dynamically adjust the excitation frequency and output power of each coil in the induction coil array of the induction cooker according to the comprehensive evaluation results.

2. The data analysis-based control method for a rechargeable induction cooker according to claim 1, characterized in that: S1 is specifically: Collect high-frequency current waveform data at each induction coil position in the induction coil array of the induction cooker; Based on the timing synchronization method, the high-frequency current waveform data at each induction coil position is time-stamped and aligned to generate high-frequency current waveform data; According to the high-frequency current waveform data, the energy distribution value of each induction coil position is calculated to obtain the original energy distribution data of the heating area.

3. The data analysis-based control method for a rechargeable induction cooker according to claim 2, characterized in that: S2 is specifically: Based on the original energy distribution data of the heating area, the wavelet transform method is used to perform a joint analysis of the original energy distribution data in the time domain and frequency domain; By performing multi-scale decomposition operations on the original energy distribution data, the time-frequency domain feature components corresponding to different time moments and different frequencies are extracted; According to the energy value changes and spatial position changes of the characteristic components in the time-frequency domain, the abnormal fluctuation indicators that appear during the dynamic changes of the thermal field are determined.

4. The data analysis-based control method for a rechargeable induction cooker according to claim 3, characterized in that: S3 specifically: Based on the abnormal fluctuation indexes appearing in the dynamic change of thermal field, the principal component analysis algorithm is used to perform feature dimensionality reduction processing to determine several principal components that play a major role in the dynamic change of thermal field. Extracting significant characteristic patterns when the position of the corresponding heating area shifts according to the determined principal components. The significant characteristic patterns include the shift direction and the shift amplitude characteristics of the energy concentration area. Based on the significant feature patterns, an identification model for energy abnormal concentration areas is established.

5. The data analysis-based control method for a rechargeable induction cooker according to claim 4, characterized in that: S4 is specifically: Based on the recognition model of abnormal energy concentration areas, a cluster analysis algorithm is used to cluster the characteristic patterns of high-frequency current waveform data appearing in the real-time heating process; The spatial location of the abnormal energy concentration area that appears in real time is determined by cluster analysis algorithm, and the spatial boundary location of the abnormal energy concentration area is calculated; According to the spatial boundary position, the spatial position information and spatial boundary information of the real-time heat concentration abnormal area are generated.

6. The data analysis-based control method for a rechargeable induction cooker according to claim 5, characterized in that: S5 is specifically: Based on the spatial location information and spatial boundary information of the real-time heat concentration abnormal area, a stability judgment model is used to judge the stability state of the real-time heating mode; The stability determination model determines whether the real-time heating mode is in a stable state by comparing the spatial distribution characteristics of the real-time heat concentration abnormal area with the heat spatial distribution characteristics under the preset stable state; Based on the determination result of the stability determination model, a comprehensive evaluation result indicating whether the heating distribution in the real-time heating mode is abnormal is generated.

7. The data analysis-based control method for a rechargeable induction cooker according to claim 6, characterized in that: S6 specifically: determining, based on a comprehensive evaluation result indicating whether heating distribution in the real-time heating mode is abnormal, an induction coil requiring adjustment of excitation frequency and output power; For the induction coils that need to be adjusted, the excitation frequency adjustment amount and output power adjustment amount of the induction coils are calculated based on the spatial distribution characteristics and spatial boundary information of the real-time abnormal heat concentration area; The calculated excitation frequency adjustment amount and output power adjustment amount of the induction coil are applied to the induction coil array of the induction cooker respectively, and the excitation frequency and output power of each induction coil in the induction coil array of the induction cooker are adjusted in real time.

8. A rechargeable induction cooker control system based on data analysis, used to implement the rechargeable induction cooker control method based on data analysis according to any one of claims 1 to 7, characterized in that: include: Data acquisition module: collects high-frequency current waveform data at different positions of the induction coil of the induction cooker, and obtains the original energy distribution data of the heating area based on the time series synchronization method; Feature extraction module: Based on the original energy distribution data, the wavelet transform method is used to perform time-frequency domain feature analysis, extract the spatiotemporal variation characteristics of energy distribution, and determine the abnormal fluctuation index of thermal field dynamic changes; Pattern recognition module: Based on the abnormal fluctuation index, the principal component analysis algorithm is used to identify the characteristic pattern of the heating area position offset and build an identification model for the energy abnormal concentration area; Regional positioning module: uses cluster analysis algorithm to determine the spatial location and boundary information of abnormal heat concentration areas during real-time heating based on the recognition model; Stability Assessment Module: This module determines the stability of the current heating mode based on the spatial location and boundary information of the abnormal heat concentration area, and outputs a comprehensive evaluation result on whether the heating distribution is abnormal. Parameter control module: dynamically adjusts the excitation frequency and output power of each coil in the induction coil array of the induction cooker based on the comprehensive evaluation results.

9. A rechargeable induction cooker comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the data analysis-based rechargeable induction cooker control method described in any one of claims 1 to 7 is implemented.

Images