Automatic cleaning method of intelligent soup cooking machine

Abstract

The invention relates to the technical field of computer program control systems, particularly provides an automatic cleaning method of an intelligent soup cooking machine, and solves the problem of lack of special automatic cleaning equipment for the soup cooking machine. The method comprises the following steps: embedding sensors for monitoring grease and protein residues into the inner wall of a pot body of the soup cooking machine and the surface of a rotary blade; grease and protein residues are divided into mild, moderate and severe stains through a sensor; according to a grease and protein residue division result, matching with a cleaning mechanism stored in a soup cooking machine mechanical arm controller to obtain cleaning mechanisms of stains at different positions; meanwhile, the soup cooking machine mechanical arm plans a cleaning path according to the stain position; and the current stain removal rate is obtained through grease and protein residues monitored by a sensor and a cleaning mechanism of the mechanical arm, and the water outlet pressure value of the mechanical arm is dynamically adjusted according to the stain removal rate until grease and protein are cleaned completely. The problems of incomplete cleaning or resource waste and the like possibly occurring in a traditional cleaning method are solved.

Description

Technical Field

[0001] The invention relates to the technical field of computer program control systems, and in particular to an automatic cleaning method for an intelligent soup maker. Background Art

[0002] With the rapid development of smart home appliances, smart soup makers have gradually become important equipment in home kitchens. A large number of computer programs are embedded in them, which simplifies the cumbersome process of traditional soup making through automated cooking technology. However, after cooking, existing smart soup makers often require users to manually disassemble parts for cleaning, especially the residual grease and food residues inside the pot body are difficult to completely remove, resulting in the following problems: low cleaning efficiency, manual cleaning is time-consuming and labor-intensive, and requires frequent operations, which reduces user experience; health hazards, residues are prone to breed bacteria, and long-term accumulation may affect equipment performance and food safety; equipment wear and tear, repeated disassembly and cleaning may accelerate component aging and increase maintenance costs. In addition, although there are some automatic cleaning solutions in the prior art, most of them focus on a single cleaning mechanism (such as high-pressure spraying or mechanical scraping), lack intelligent control logic, and cannot dynamically adjust cleaning parameters according to the type of stains and the shape of the pot body, resulting in poor cleaning effects or waste of resources.

[0003] Prior art 1, Chinese patent, application number: 202110247684.5 discloses a smart home kitchen system and its control method, the smart home kitchen system includes a central control center, a server group, food procurement equipment, food preparation equipment, automatic cooking equipment, automatic meal delivery equipment, automatic tableware cleaning and replacement equipment. The food procurement equipment is used to purchase food, and the purchased food is prepared by the food preparation equipment. The prepared food is cooked by the automatic cooking equipment and the cooked dishes are delivered to the user's table by the automatic meal delivery equipment. After the user confirms that the meal is over, the tableware is collected and sorted, cleaned and stored by the automatic tableware cleaning and replacement equipment. The analysis and calculation process in each device is completed by the server group, and unified coordination is carried out through the central control center. Although it can achieve a high degree of automation of the home kitchen, reduce the manual participation process, reduce the operating cost, and improve the user experience; however, its structure and function are relatively complex, and it is not suitable for the automatic cleaning of the soup maker, and there is no cleaning solution specifically for the soup maker.

[0004] Prior art 2, Chinese patent, application number 201811530464.8 discloses an intelligent kitchen control system and control method thereof, including a main controller, and food cleaning control module, cutting control module, cooking control module, feeding control module, dish delivery control module, cleaning control module, operation panel module and power module connected to the main controller. Although the functions are comprehensive, the overall functions of the kitchen are integrated, modularized, automated, intelligent, efficient, and highly adaptable, and the functions of an intelligent kitchen can be realized; however, it is only for the cleaning of the cooking process in the kitchen, and there is no design for the internal cleaning of some special kitchen equipment, especially the internal cleaning of the soup maker.

[0005] Prior art three, Chinese patent, application number 202210733695.9 discloses a kitchenware automation equipment and system, including a kitchenware support frame, a stove platform equipment and system, a cooking pot, main material and auxiliary material bin equipment, a metering device, a special tool for holding food, a water supply equipment, a cleaning equipment and a sewage discharge equipment, and also includes a fume collection and purification device, an alarm processing device, and also includes a circuit integration and system, a system for controlling the operation of each operation area, and also includes a circuit integrated PCB board welding corresponding electronic components, a chip communication module, a main control module, a smart terminal device mobile phone APP applet and a third-party system integration and voice interaction to operate the equipment control. Although the automated structure is adopted, the power mechanism and the coordination of various processes are added to the design to achieve unmanned and automated operation of kitchenware equipment, making the existing restaurants, restaurants, canteens, and household kitchens more hygienic and tidy kitchens; but it covers most of the kitchen equipment, and does not make specific cleaning plans for some kitchen appliances, and there are certain limitations in specific applications.

[0006] At present, the existing technologies 1, 2 and 3 lack automatic cleaning equipment specifically for soup cookers; at the same time, manual disassembly of parts for cleaning leads to low cleaning efficiency, sanitation hazards and equipment loss. Therefore, the present invention provides an automatic cleaning method for an intelligent soup cooker. Summary of the invention

[0007] In order to achieve the above object, the present invention adopts the following technical scheme: In one aspect of the present invention, there is provided an automatic cleaning method for an intelligent soup maker, comprising the following steps: Sensors for monitoring grease and protein residues are embedded in the inner wall of the soup maker pot and the surface of the rotating blade; the sensors classify grease and protein residues into light, medium and heavy stains; According to the classification results of grease and protein residues, the cleaning mechanism stored in the controller of the soup maker robot arm is matched to obtain the cleaning mechanism of stains at different positions; at the same time, the soup maker robot arm plans the cleaning path according to the position of the stain; The current stain removal rate is obtained through the grease and protein residues monitored by the sensor and the cleaning mechanism of the robotic arm. The water outlet pressure value of the robotic arm is dynamically adjusted according to the stain removal rate. When the preset cleaning threshold is reached, the soup maker robotic arm moves to the next grease and protein residue until the grease and protein on the inner wall of the pot and the rotating blade are cleaned.

[0008] In an optional embodiment, the process of classifying grease and protein residues into light, medium and heavy stains by a sensor comprises the following steps: Optical reflectivity sensors and dielectric constant sensors are arranged on the inner wall of the pot and the surface of the rotating blade. The optical reflectivity sensors and dielectric constant sensors detect the distribution of grease through the change of light reflection intensity in the near-infrared band, and identify the amount of protein residue through the difference in dielectric loss tangent value under high-frequency electric field; The original signals of the optical reflectance sensor and the dielectric constant sensor are collected to extract the light absorption peak value related to the carbon chain length in the grease residue area, and the dielectric loss gradient related to the degree of protein denaturation in the protein residue area; a quantitative model related to the stain thickness and adhesion strength is established based on the carbon-hydrogen bond vibration spectrum characteristics of grease and the polar group distribution characteristics of protein; The time-space distribution data of optical signals and dielectric signals are input into a multidimensional correlation matrix, and the spatial aggregation degree and adhesion energy density of the stains are extracted using matrix singular value decomposition. A composite stain index is generated based on the product of the aggregation degree and the density, and the stain grade is classified by index interval division, which is then associated with the cleaning mechanism of stains at different locations.

[0009] In an optional embodiment, wherein, for light stains: the spectral absorbance is lower than a preset baseline value and the dielectric loss gradient changes without cross-linking denaturation; Moderate stains: The spectral absorbance shows multiple peaks and the dielectric loss gradient changes locally; Heavy stains: Spectral absorbance continues to saturate and dielectric loss gradient protein-lipid complex cross-links and solidifies.

[0010] In an optional implementation, the process of implementing stain level classification by index interval division includes the following steps: The spatiotemporal distributions of the optical and dielectric signals are represented as fourth-order tensors and the high-frequency electric field frequency, respectively, and the fourth-order tensors are expanded into multi-dimensional correlation matrices, whose elements are calculated through cross-domain coupling coefficients; The multi-dimensional correlation matrix is ​​subjected to truncated singular value decomposition to extract two key features: spatial aggregation degree and adhesion energy density; The composite stain index is calculated through nonlinear coupling, and the stain level is determined according to the composite stain index.

[0011] In an optional implementation, the optical signal tensor includes two-dimensional spatial coordinates, time sampling points, and near-infrared spectral channels; the dielectric signal tensor includes the same spatial coordinates and time sampling points.

[0012] In an optional embodiment, the process of obtaining the cleaning mechanism of stains at different positions comprises the following steps: Based on the output composite stain index and its spatial aggregation degree and adhesion energy density, a three-dimensional feature space is constructed: the required water pressure impact energy is calculated according to the adhesion energy density; The cleaning mechanism stored in the controller of the soup maker robot arm is matched based on the carbon chain length of the grease and the degree of protein cross-linking of the stain; The parameters of the cleaning mechanism are associated with the thermal conductivity and surface roughness of the pot material to generate a dynamic cleaning parameter mapping table, and the parameter deviation of the cleaning mechanism is corrected through real-time feedback.

[0013] In an optional implementation, the process of generating a dynamic cleaning parameter mapping table includes the following steps: Obtain the temperature field distribution, stain adhesion strength and surface roughness in the pot; quantify the local aggregation of stains based on the spatial autocorrelation coefficient of stain distribution; construct a three-dimensional adhesion energy density map through the adhesion force at different positions; Real-time monitoring of key parameters of pressure changes and temperature distribution during cleaning; The three-dimensional adhesion energy density map is fused with the key parameters monitored in real time to construct a global view of the cleaning process. Based on the global view, the cleaning parameters are dynamically adjusted and a dynamic cleaning parameter mapping table is generated to guide the cleaning operation.

[0014] In an optional implementation, the process of the soup maker robot arm planning a cleaning path according to the location of the stain includes the following steps: The inner wall of the pot and the surface of the blade are discretized into micro-element grids, and each grid point is assigned a weighted sum of adhesion energy density and spatial aggregation degree to form an energy density topological map; Identify the local extreme points in the energy density topology map, i.e., the stain core area, and mark them as the key nodes of the soup maker robot arm cleaning path; use the key nodes as anchor points and use the minimum energy consumption principle to generate the initial path of the soup maker robot arm; The geometric mutation area of ​​the pot body is detected in real time, and the curvature adaptive interpolation method is used to adjust the nozzle posture; the Pareto optimality between cleaning coverage, time efficiency and energy consumption is achieved, and the path weight of the soup maker robot arm is fine-tuned in real time through dynamic pressure field matching.

[0015] In an optional implementation manner, the process of obtaining the current stain removal rate comprises the following steps: Through the data collected by the optical reflectivity sensor and the dielectric constant sensor, the sensor monitors the changes in grease and protein residues, records the difference in residues before and after cleaning; calculates the ratio of stain coverage area to total surface area, and updates the stain coverage rate in real time; The chemical composition concentration of the residue is detected by sensors, and the residue concentration is calculated in real time; The stain removal rate is dynamically calculated based on the stain coverage rate and residue concentration; the water outlet pressure and cleaning time of the robotic arm are adjusted accordingly; if the stain removal rate reaches the preset cleaning threshold, the current area is judged to be cleaned, and the robotic arm automatically moves to the next stain area to continue cleaning until the stains on the inner wall of the pot and the rotating blade are cleaned.

[0016] In an optional embodiment, the process of calculating the ratio of the stain coverage area to the total surface area includes the following steps: identifying the distribution of grease and protein residues by detecting the reflectivity of the light of the optical reflectivity sensor on the inner wall of the pot body and the surface of the rotating blade; the dielectric constant sensor distinguishes the concentration differences of grease and protein residues by measuring the changes in dielectric constants in different areas; before cleaning, the sensor collects initial data and records the stain coverage area and residue concentration; during the cleaning process, the sensor continuously collects data, compares the difference in residue amount before and after cleaning, and records the reduction ratio of the stain coverage area and the decrease in residue concentration.

[0017] The stain monitoring and classification of the present invention accurately identifies the distribution and degree of stains, providing data support for the formulation of cleaning strategies; cleaning mechanism matching and path planning, different stain levels correspond to different cleaning parameters (such as water outlet pressure, cleaning time, etc.); at the same time, the robotic arm plans the most optimized cleaning path according to the specific location of the stain; realizes the reasonable allocation of cleaning resources to ensure the efficient completion of the cleaning task while reducing ineffective actions and energy consumption; dynamic feedback and cleaning completion judgment, during the cleaning process, the sensor continuously monitors the stain removal rate, and the robotic arm dynamically adjusts the water outlet pressure according to real-time data to achieve the best cleaning effect; the cleaning process is intelligentized through a dynamic feedback mechanism to ensure the thoroughness and efficiency of cleaning. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 This is a flow chart of the automatic cleaning method of the intelligent soup maker provided in Embodiment 1 of the present invention; Figure 2 This is a process diagram for classifying grease and protein residues into light, medium and heavy stains provided in Example 2 of the present invention; Figure 3A process diagram of implementing stain level classification by index interval division provided in Embodiment 3 of the present invention; Figure 4 A process diagram of a cleaning mechanism for obtaining stains at different positions provided in Example 4 of the present invention; Figure 5 A process diagram for generating a dynamic cleaning parameter mapping table provided in Embodiment 5 of the present invention; Figure 6 A process diagram of a soup maker robot arm planning a cleaning path according to the location of stains provided in Example 6 of the present invention; Figure 7 A process diagram for obtaining the current stain removal rate provided in an embodiment of the present invention; Figure 8 A system block diagram provided in an embodiment of the present invention; Fig. 9 A block diagram of a computer-readable storage medium according to the present invention. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present invention will be described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0020] In the following, the terms "first", "second", etc. are used only for convenience of description and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0021] In the present invention, unless otherwise clearly specified and limited, the term "connection" should be understood in a broad sense, for example, "connection" can be a fixed mechanical connection, or a detachable mechanical connection, or integrated; or, "connection" can be a direct connection, or an indirect connection through an intermediate medium. In addition, unless otherwise clearly specified and limited, the term "coupling" should be understood in a broad sense, for example, "coupling" can be a direct electrical connection, such as physical contact and electrical conduction between two components, and can also be understood as electrical connection between different components in a circuit structure through physical lines such as copper foil or wires on a printed circuit board (PCB) that can transmit electrical signals to transmit electrical signals; or, "coupling" can be an indirect electrical connection between two components through an intermediate medium; or, "coupling" can be an electrical connection between two components in an air-spaced / non-contact manner, for example, two components are electrically connected by capacitive coupling to transmit electrical signals.

[0022] In the embodiments of the present invention, directional terms such as "up", "down", "left" and "right" may be defined including but not limited to the orientation relative to the schematic placement of the components in the drawings. It should be understood that these directional terms may be relative concepts, which are used for relative description and clarification, and may change accordingly according to the change of the orientation of the components in the drawings.

[0023] The embodiments of the present invention can significantly reduce the user's cleaning burden in home use scenarios; by automatically identifying the degree of stains and combining a dynamic cleaning mechanism, the inner wall of the pot and the rotating blade can be thoroughly cleaned, the service life of the equipment can be extended, and the user's experience can be improved. In commercial kitchens such as restaurants and canteens, soup machines usually need to process a large amount of food, the cleaning frequency is high, and the stains are more stubborn; they can complete the cleaning task quickly and efficiently, reduce manual intervention, improve kitchen operation efficiency, and ensure that the equipment meets the hygiene standards. In the field of food processing, soup machines may be used for batch production of soup products. Through automated cleaning processes, production interruption time can be reduced, equipment hygiene standards can be guaranteed, food safety regulations can be met, and the overall efficiency of the production line can be improved. It provides a technical reference for the research and development of smart home appliances. Its core logic of stain monitoring, dynamic cleaning, and path planning can be applied to other smart devices that require automatic cleaning functions (such as dishwashers, soymilk machines, etc.), promoting technological innovation and optimization in the home appliance industry.

[0024] Example 1

[0025] like Figure 1 As shown, an embodiment of the present invention provides an automatic cleaning method for an intelligent soup maker, comprising the following steps: Step S100: embedding sensors for monitoring grease and protein residues in the inner wall of the soup pot and the surface of the rotating blade of the soup pot; and classifying the grease and protein residues into light, medium and heavy stains through the sensors; Step S200: According to the classification result of grease and protein residues, the cleaning mechanism stored in the controller of the soup maker robot arm is matched to obtain the cleaning mechanism of stains at different positions; at the same time, the soup maker robot arm plans the cleaning path according to the position of the stain; Step S300: The current stain removal rate is obtained by monitoring the grease and protein residues through the sensor and the cleaning mechanism of the robotic arm. The water outlet pressure value of the robotic arm is dynamically adjusted according to the stain removal rate. When the preset cleaning threshold is reached, the soup maker robotic arm moves to the next grease and protein residue until the grease and protein on the inner wall of the pot and the rotating blade are cleaned.

[0026] In the above embodiment, step S100 stain monitoring and classification accurately identifies the distribution and degree of stains, providing data support for the formulation of cleaning strategies; step S200 cleaning mechanism matching and path planning, different stain levels correspond to different cleaning parameters (such as water outlet pressure, cleaning time, etc.); at the same time, the robot arm plans the most optimized cleaning path according to the specific location of the stain; realizes the reasonable allocation of cleaning resources, ensures the efficient completion of the cleaning task, and reduces ineffective actions and energy consumption. Step S300 dynamic feedback and cleaning completion judgment, during the cleaning process, the sensor continuously monitors the stain removal rate, and the robot arm dynamically adjusts the water outlet pressure according to real-time data to achieve the best cleaning effect; the cleaning process is intelligentized through the dynamic feedback mechanism to ensure the thoroughness and efficiency of cleaning.

[0027] In summary, this embodiment realizes the efficiency and precision of the cleaning process of the smart soup maker by combining the three steps of stain monitoring, cleaning mechanism matching and dynamic feedback, and solves the problems of incompleteness or waste of resources that may occur in traditional cleaning methods.

[0028] Example 2 like Figure 2 As shown, based on Example 1, the process of classifying grease and protein residues into light, medium and heavy stains by using a sensor in step S100 provided in the embodiment of the present invention includes the following steps: Step S101: Optical reflectivity sensors and dielectric constant sensors are arranged on the inner wall of the pot body and the surface of the rotating blade. The optical reflectivity sensors and dielectric constant sensors detect the distribution of grease through the change of light reflection intensity in the near-infrared band, and identify the amount of protein residue through the difference of dielectric loss tangent value under high-frequency electric field; Step S102: collecting the original signals of the optical reflectance sensor and the dielectric constant sensor, extracting the light absorption peak value related to the carbon chain length for the grease residue area, and extracting the dielectric loss gradient related to the degree of protein denaturation for the protein residue area; establishing a quantitative model related to the stain thickness and adhesion strength based on the carbon-hydrogen bond vibration spectrum characteristics of the grease and the polar group distribution characteristics of the protein; Among them, for light stains: the spectral absorbance is lower than the preset baseline value (characterizing monolayer adsorption) and the dielectric loss gradient changes gently (no cross-linking denaturation); Moderate stains: spectral absorbance shows multi-peak superposition (multi-layer grease accumulation) and dielectric loss gradient locally changes (partial protein thermal denaturation); Severe stains: spectral absorption rate continues to be saturated (grease carbonization and coking) and the dielectric loss gradient oscillates violently (protein-grease complex cross-linking and curing); Step S103: Input the time-space distribution data of the optical signal and the dielectric signal into a multi-dimensional correlation matrix, and use the matrix singular value decomposition to extract the spatial aggregation degree and adhesion energy density of the stain; generate a composite stain index based on the product of the aggregation degree and the density, and classify the stain level by dividing the index interval, and associate it with the cleaning mechanism of stains in different positions.

[0029] In the above embodiment, step S101 is sensor layout and signal acquisition. The optical reflectivity sensor detects the distribution of grease through the change of light reflection intensity in the near-infrared band, and the dielectric constant sensor identifies the amount of protein residue through the change of the dielectric loss tangent value under the high-frequency electric field; the complementarity of optical and dielectric technologies is used to comprehensively obtain the residual information of grease and protein, and provide multi-dimensional data support for stain classification. Step S102 is signal feature extraction and quantitative modeling. According to the carbon-hydrogen bond vibration spectrum characteristics of grease and the polar group distribution characteristics of protein, a quantitative model related to the thickness and adhesion strength of the stain is established; through feature extraction and modeling, the original signal is converted into quantifiable physical parameters (such as absorbance, dielectric gradient, etc.), providing a scientific basis for stain classification. Step S103 is multi-dimensional signal analysis and stain classification. According to the product of polymerization degree and density, a composite stain index is generated, and the stain grade classification is realized through index interval division, and it is associated with the cleaning mechanism of stains in different positions. Through multi-dimensional data analysis and mathematical modeling, accurate classification of stains is realized, and clear input conditions are provided for cleaning mechanism matching.

[0030] In summary, this embodiment achieves accurate identification and classification of oil and protein residues through sensor deployment, signal feature extraction and multi-dimensional analysis, providing reliable technical support for the automatic cleaning of the smart soup maker.

[0031] Example 3 like Figure 3 As shown, based on Example 2, the process of implementing stain level classification by index interval division in step S103 provided in the embodiment of the present invention includes the following steps: Step S1031: The spatiotemporal distribution of the optical signal and the dielectric signal are respectively expressed as fourth-order tensors, wherein the optical signal tensor contains two-dimensional spatial coordinates, time sampling points, and near-infrared spectral channels; the dielectric signal tensor contains the same spatial coordinates and time sampling points, as well as the high-frequency electric field frequency, and the fourth-order tensor is expanded into a multi-dimensional correlation matrix, whose elements are calculated by cross-domain coupling coefficients; Step S1032: performing truncated singular value decomposition on the multi-dimensional correlation matrix to extract two key features: spatial aggregation degree and adhesion energy density; Step S1033: Calculate the composite stain index through nonlinear coupling, and determine the stain level according to the composite stain index.

[0032] Among them, the multi-dimensional correlation matrix is ​​constructed, assuming that the spatial and temporal distribution of the optical signal is a fourth-order tensor , the spatiotemporal distribution of the dielectric signal is a fourth-order tensor , Represents the two-dimensional coordinates of the pot surface; Indicates the time sampling point; represents the near-infrared spectral channel; Represents the frequency of the high-frequency electric field; Expand a tensor into a multi-dimensional incidence matrix , whose elements are defined by: ; In the formula, Represents the cross-domain coupling coefficient, characterizing the near-infrared spectral channel With high frequency electric field frequency The physical correlation of (calibrated by lipid-protein molecular polarizability experiments); Indicates the total number of spatial positions (N = pot surface area / 0.1mm 2 ); represents the joint time-frequency dimension, , Indicates the interval of time sampling points; Indicates the maximum value of the high-frequency electric field frequency; Indicates the minimum value of the high-frequency electric field frequency; Indicates the change value of the high-frequency electric field frequency; Represents the row and column labels in a multidimensional incidence matrix; Indicates the number of time sampling points; Singular value decomposition and feature extraction for multi-dimensional correlation matrices Perform a truncated singular value decomposition: ; In the formula, is the number of principal components retained, and the following features are extracted; represents the result of matrix decomposition; U represents the left singular matrix, represents a diagonal matrix, the diagonal elements are singular values, and V represents a right singular matrix; represents the noise component remaining after singular value decomposition; Spatial aggregation express: ; In the formula, represents the kth singular value; represents the spatial weight matrix (negatively correlated with the pot curvature radius); represents the Hadamard product (element-wise multiplication); represents the kth column of the left singular matrix, which represents the projection of the kth principal component in the data; F represents the Frobenius norm, which is the 2-norm of the matrix and is used to measure the overall size of the matrix; Adhesion energy density express: ; In the formula, represents the time-frequency energy weight function , is the attenuation coefficient, , represents the high-frequency electric field frequency at the jth time point; represents the influence of the kth principal component of the right singular matrix at the jth time point, Indicates the total number of time points; Represents the time value of the jth time point; represents the natural logarithm of the energy weight in the frequency domain; represents the frequency value corresponding to the jth time point; Composite soiling index generation, calculation of composite soiling index by nonlinear coupling express: ; In the formula, , , represents the coupling coefficient of experimental calibration; , Represents the mean and standard deviation of spatial aggregation; , represents the mean and standard deviation of adhesion energy density; represents the error function, represents the complementary error function; s, e represent the integral variables, which represent the integral variables of spatial aggregation degree and adhesion energy density respectively; represents the hyperbolic tangent function; It represents the nonlinear coupling relationship between the spatial polymerization degree s and the adhesion energy density e; Represents the double integral symbol, indicating Integrate the second-order partial derivatives of the function with respect to e and s respectively; Determination of stain level, based on Classification: ; In the formula, , represents the dynamic threshold, , is the maximum theoretical index; , , Represents the gradient sensitivity parameter (calibrated by material fatigue test); The Laplacian operator representing the adhesion energy density (characterizing the sudden change in energy distribution).

[0033] In the above embodiment, step S1031 constructs a multi-dimensional correlation matrix, and realizes the unified representation of cross-modal data by expressing the spatiotemporal distribution of optical signals and dielectric signals as a fourth-order tensor and expanding it into a joint matrix; the introduction of the cross-domain coupling coefficient quantifies the physical correlation between the wavelength of the near-infrared spectral channel and the frequency of the high-frequency electric field. Step S1032 truncated singular value decomposition and feature extraction, truncated singular value decomposition of the joint matrix, extracting the principal component (retained energy ratio ≥ 95%), significantly reducing the data dimension, while retaining the key features; by calculating the spatial aggregation degree and adhesion energy density, the aggregation degree and adhesion energy distribution of the stain in space are quantified respectively, providing a physical quantification basis for the accurate description of the stain state. Step S1033 composite stain index generation and grade determination, the composite stain index is calculated by a nonlinear coupling formula, the two characteristics of spatial aggregation degree and adhesion energy density are integrated, and the comprehensive state of the stain is fully characterized; based on the dynamic threshold and gradient criterion, the stain grade is determined, and the mapping from quantitative indicators to classification results is realized, providing a scientific basis for the formulation of cleaning strategies.

[0034] The joint analysis of optical signals and dielectric signals in this embodiment fuses optical signals (near-infrared spectra) with dielectric signals (high-frequency electric fields). Based on the theory of multi-physical field coupling, it can more comprehensively capture the material composition, distribution state and adhesion characteristics of stains; through the cross-domain coupling coefficient calibrated by the experiment, the physical correlation between the spectral wavelength and the electric field frequency is quantified, providing a theoretical basis for cross-modal signal fusion. Tensor analysis and dimensionality reduction technology expands the fourth-order tensor into a multi-dimensional correlation matrix, realizes the unified representation of high-dimensional data, and provides a framework for dimensionality reduction; truncated singular value decomposition extracts the principal components through singular value decomposition, realizes data dimensionality reduction and noise suppression, and retains the main characteristics of the signal. Nonlinear dynamics and energy distribution analysis, spatial aggregation degree and adhesion energy density are extracted based on the physical model to quantify the spatial distribution and adhesion energy of stains; the composite stain index is calculated through the nonlinear coupling formula, which integrates multi-dimensional features and realizes the comprehensive quantification of the stain state; dynamic threshold and gradient sensitivity, through the experimental calibration of dynamic threshold and gradient sensitivity, combined with the Laplace operator, the accurate determination of the stain level is realized.

[0035] This embodiment, through the fusion of optical signals and dielectric signals, can characterize the material composition, distribution state and adhesion characteristics of the stains in a multi-dimensional and multi-level manner, thus solving the limitation problem of the single signal analysis method; through tensor expansion and truncated singular value decomposition, efficient dimensionality reduction and noise suppression of data are achieved, thus improving the accuracy and computational efficiency of signal processing; spatial aggregation degree and adhesion energy density are extracted, and a composite stain index is generated using a nonlinear coupling formula, thus comprehensively reflecting the comprehensive state of the stains; through dynamic thresholds and gradient sensitivity parameters, the stain level is refined and graded; the introduction of the Laplace operator can capture the mutation of the adhesion energy density, thus improving the accuracy and robustness of classification judgment.

[0036] Example 4 like Figure 4 As shown, based on Example 1, the process of obtaining the cleaning mechanism of stains at different positions in step S200 provided in the embodiment of the present invention includes the following steps: Step S201: constructing a three-dimensional feature space based on the output composite stain index and its spatial aggregation degree and adhesion energy density: calculating the required water pressure impact energy according to the adhesion energy density; Step S202: matching the cleaning mechanism stored in the soup maker robot arm controller based on the oil carbon chain length and protein cross-linking degree of the stain; The cleaning mechanism includes: Low-frequency eddy current stripping (for light stains) uses piezoelectric ceramics to stimulate 10-50Hz mechanical vibration to destroy monomolecular layer adsorption; High-frequency cavitation jet (for medium stains), using ultrasonic transducers to generate 20-100kHz cavitation bubble groups to penetrate multiple layers of grease accumulation; Thermal-mechanical synergistic decoupling (for heavy stains), simultaneous injection of 80-95°C steam to soften the cross-linked structure, and superposition of high-pressure water wedges (>5MPa) to achieve carbonized layer peeling; Step S203: Associating the parameters of the cleaning mechanism with the thermal conductivity and surface roughness of the pot body material, generating a dynamic cleaning parameter mapping table, and correcting the parameter deviation of the cleaning mechanism through real-time feedback.

[0037] In the above embodiment, step S201 constructs a three-dimensional feature space through the composite stain index, spatial polymerization degree and adhesion energy density of the stain to provide a quantitative basis for cleaning; step S202 matches the cleaning mechanism based on the stain characteristics, and selects the optimal cleaning mechanism according to the oil carbon chain length and protein cross-linking degree of the stain to achieve efficient stain removal; step S203 dynamically adjusts the cleaning parameters according to the thermal conductivity and surface roughness of the pot material to ensure the cleaning effect and avoid damaging the surface.

[0038] Example 5 like Figure 5As shown, based on Example 4, the process of generating a dynamic cleaning parameter mapping table in step S203 provided in the embodiment of the present invention includes the following steps: Step S2031: obtaining the temperature field distribution, stain adhesion strength and surface roughness in the pot; quantifying the local aggregation of stains based on the spatial autocorrelation coefficient of stain distribution; constructing a three-dimensional adhesion energy density map through the adhesion forces at different positions; Step S2032: Real-time monitoring of key parameters of pressure change and temperature distribution during the cleaning process; Step S2033: fusing the three-dimensional adhesion energy density map with the key parameters monitored in real time to construct a global view of the cleaning process; based on the global view, dynamically adjusting the cleaning parameters to generate a dynamic cleaning parameter mapping table to guide the cleaning operation.

[0039] In the above embodiment, step S2031 data collection and modeling provide basic data for the cleaning parameter mapping table and establish an accurate model of stain distribution and environmental parameters; the temperature field distribution reflects the dynamic changes of the temperature in the pot and provides a basis for the selection of the thermal cleaning mechanism; the stain adhesion strength quantifies the difficulty of stain removal and guides the setting of cleaning pressure and time; the surface roughness evaluates the contact efficiency between the cleaning medium (such as water, steam) and the surface; the spatial autocorrelation coefficient analyzes the local aggregation characteristics of the stains and optimizes the selection of the cleaning path; the three-dimensional adhesion energy density map integrates the stain distribution and adhesion energy density into a unified three-dimensional model. Step S2032 real-time monitoring and dynamic feedback capture the dynamic changes of key parameters in the cleaning process to ensure real-time optimization of the cleaning effect; real-time adjustment of the water pressure impact energy to ensure the matching of the cleaning intensity and the stain adhesion strength; dynamic control of the temperature of the cleaning medium to avoid reduced cleaning efficiency or material damage due to overheating or overcooling. Step S2033 integrates data and generates mapping tables. Through multi-source data fusion and global view construction, cleaning parameters are dynamically adjusted to achieve accurate and efficient cleaning. The three-dimensional adhesion energy density map is integrated with the key parameters monitored in real time to build a global view of the cleaning process to ensure the comprehensiveness and accuracy of parameter adjustment. The theoretical model support is provided for the dynamic optimization of the cleaning strategy. Based on the global view, the cleaning parameters (such as pressure, temperature, time, and nozzle posture) are adjusted in real time to generate a dynamic mapping table to provide accurate guidance for cleaning operations.

[0040] Example 6 like Figure 6 As shown, based on Example 1, the process of planning a cleaning path according to the location of the stain by the mechanical arm of the soup maker in step S200 provided in the embodiment of the present invention includes the following steps: Step S204: discretizing the inner wall of the pot and the surface of the blade into micro-element grids, assigning a value to each grid point as a weighted sum of adhesion energy density and spatial aggregation degree, and forming an energy density topological map; Step S205: identifying local extreme value points (i.e., stain core areas) in the energy density topology map and marking them as key nodes of the cleaning path of the soup maker robot arm; using the key nodes as anchor points and adopting the minimum energy consumption principle to generate the initial path of the soup maker robot arm; Step S206: Real-time detection of geometric mutation areas of the pot body, and use of curvature adaptive interpolation method to adjust the nozzle posture; achieve Pareto optimality among cleaning coverage, time efficiency and energy consumption, and fine-tune the path weight of the soup maker robot arm in real time through dynamic pressure field matching.

[0041] In the above embodiment, step S204 discretization modeling and energy density topology map generation quantifies the stain distribution on the inner wall of the pot and the blade surface into a computable model, providing accurate data support for path planning. Step S205 key node identification and initial path generation locates the stain core area and generates the initial path of the robot arm to ensure cleaning efficiency and energy consumption optimization. Step S206 dynamic path adjustment and Pareto optimization respond to geometric mutations in real time to optimize the balance between cleaning coverage, time efficiency and energy consumption.

[0042] Example 7 like Figure 7 As shown, based on Example 1, the process of obtaining the current stain removal rate in step S300 provided in the embodiment of the present invention includes the following steps: Step S301: The sensor monitors the changes in grease and protein residues through the data collected by the optical reflectivity sensor and the dielectric constant sensor, and records the difference in the residues before and after cleaning; calculates the ratio of the stain coverage area to the total surface area, and updates the stain coverage rate in real time; The distribution of grease and protein residues can be identified by detecting the reflectivity of the light of the optical reflectivity sensor on the inner wall of the pot and the surface of the rotating blade. The optical reflectivity of the stained area is usually lower than that of the clean area. The dielectric constant sensor distinguishes the concentration difference of grease and protein residues by measuring the change of dielectric constant in different areas. The dielectric constant of the stained area is usually higher than that of the clean area. Before cleaning, the sensor collects initial data and records the stain coverage area and residue concentration. During the cleaning process, the sensor continuously collects data, compares the difference in residue before and after cleaning, and records the reduction ratio of the stain coverage area and the decrease in residue concentration. Step S302: detecting the chemical component concentration of the residue by a sensor and calculating the residue concentration in real time; Step S303: dynamically calculating the stain removal rate based on the stain coverage rate and the residue concentration; adjusting the water outlet pressure and cleaning time of the robot arm accordingly; if the stain removal rate reaches a preset cleaning threshold, it is determined that the current area is cleaned, and the robot arm automatically moves to the next stain area to continue cleaning until the stains on the inner wall of the pot body and the rotating blade are cleaned; ; in, Indicates the stain removal rate, represents the initial value of the stain coverage, Indicates the current value of the stain coverage, represents the initial value of the residue concentration, Indicates the current value of the residue concentration.

[0043] In the above embodiment, step S301 calculates and updates the stain coverage rate, collects the change data of the stain distribution in real time through the optical reflectivity sensor and the dielectric constant sensor, monitors the dynamic change of the stain coverage area during the cleaning process; calculates the ratio of the stain coverage area to the total surface area, updates the stain coverage rate, and provides basic data for the calculation of the stain removal rate; realizes the spatial quantitative evaluation of the stain distribution, and ensures real-time monitoring and dynamic feedback during the cleaning process. Step S302 detects and calculates the residue concentration, detects the chemical composition concentration of the residue in real time through the sensor, and records the difference in concentration before and after cleaning; is used to evaluate the cleaning intensity and the stain removal effect, and provides key support for the calculation of the stain removal rate; realizes the real-time monitoring and quantitative analysis of the chemical characteristics of the residue, and ensures the accurate evaluation of the cleaning effect. Step S303: Calculation and dynamic adjustment of stain removal rate. Calculate the stain removal rate based on the dynamic changes of stain coverage and residue concentration; obtain the cleaning effect of the current area, and adjust the water outlet pressure and cleaning time of the robot arm in real time according to the stain removal rate to ensure the optimization of cleaning efficiency and effect. When the stain removal rate reaches the preset cleaning threshold, it is determined that the cleaning of the current area is completed, and the robot arm automatically moves to the next area to continue cleaning until all stains are cleaned; realize adaptive adjustment and precise control of the cleaning process to ensure dynamic optimization of cleaning efficiency and effect. The formula for dynamically calculating the stain removal rate comprehensively considers the dynamic changes of stain coverage and residue concentration, and weights and averages the cleaning effects of the two to ensure the comprehensiveness and accuracy of the removal rate calculation; evaluate the cleaning effect in real time through the stain removal rate to ensure precise control during the cleaning process; dynamically adjust the water outlet pressure and cleaning time of the robot arm based on the removal rate to optimize the cleaning efficiency and effect.

[0044] Figure 8 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present invention is shown.

[0045] The electronic device may include a central processing unit / microprocessor / main control chip, etc.; a storage medium, coupled to the central processing unit / microprocessor / main control chip, etc., and storing computer executable instructions therein, for performing the steps of each method of an embodiment of the present invention when executed by the processor.

[0046] The central processing unit / microprocessor / main control chip etc. may include but are not limited to, for example, one or more processors or microprocessors etc.

[0047] The storage medium may include, but is not limited to, for example, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (e.g., hard disk, floppy disk, solid-state drive, removable disk, CD-ROM, DVD-ROM, Blu-ray disc, etc.).

[0048] In addition, the electronic device may also include (but not limited to) a data bus, an input / output bus / external bus / device bus, a display, and input / output devices (eg, keyboard, mouse, speaker, etc.), etc.

[0049] The central processing unit / microprocessor / main control chip etc. can communicate with external devices via an I / O bus via a wired or wireless network (not shown).

[0050] The storage medium may also store at least one computer executable instruction for executing the various functions and / or method steps in the embodiments described in the present technology when executed by a central processing unit / microprocessor / main control chip, etc.

[0051] In one embodiment, the at least one computer executable instruction may also be compiled into or constitute a software product, wherein one or more computer executable instructions are executed by a processor to perform the various functions and / or method steps in the embodiments described in the present technology.

[0052] Fig. 9 A schematic diagram of a computer-readable storage medium according to an embodiment of the present invention is shown.

[0053] like Fig. 9 As shown, instructions are stored on a non-transitory computer-readable storage medium, and the instructions are, for example, computer-readable instructions. When the computer-readable instructions are executed by the processor, the various methods described above can be executed. The non-transitory computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may, for example, include random access memory (RAM) and / or cache memory (cache), etc. The non-transitory non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc. For example, the non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device runs the computer-readable instructions stored on the computer-readable storage medium, the various methods described above may be performed.

[0054] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units 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 units, which can be electrical, mechanical or other forms.

[0055] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0056] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0057] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or 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, including several instructions for executing all or part of the steps of the various embodiments of the present invention through a computer device (which can be a personal computer, server, or network device, etc.). The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (full name in English: Read-Only Memory, English abbreviation: ROM), random access memory (full name in English: Random Access Memory, English abbreviation: RAM), disk or optical disk, etc. Various media that can store program codes.

[0058] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An automatic cleaning method for an intelligent soup maker, characterized in that: The following steps are involved: Sensors for monitoring grease and protein residues are embedded in the inner wall of the soup maker pot and the surface of the rotating blade; the sensors classify grease and protein residues into light, medium and heavy stains; According to the classification results of grease and protein residues, the cleaning mechanisms stored in the robotic arm controller of the soup maker are matched to obtain the cleaning mechanisms for different stain locations; at the same time, the robotic arm of the soup maker plans the cleaning path according to the stain location; The current stain removal rate is obtained by monitoring the grease and protein residues through sensors and the cleaning mechanism of the robotic arm. The water outlet pressure value of the robotic arm is dynamically adjusted according to the stain removal rate. When the preset cleaning threshold is reached, the robotic arm of the soup maker moves to the next grease and protein residue until the grease and protein residues on the inner wall of the pot and the rotating blade are cleaned.

2. The automatic cleaning method of the intelligent soup maker according to claim 1, characterized in that: The process of classifying grease and protein residues into light, medium and heavy stains by sensors includes the following steps: Optical reflectivity sensors and dielectric constant sensors are arranged on the inner wall of the pot and the surface of the rotating blade. The optical reflectivity sensors and dielectric constant sensors detect the distribution of grease through the change of light reflection intensity in the near-infrared band, and identify the amount of protein residue through the difference in dielectric loss tangent value under high-frequency electric field; The original signals of the optical reflectance sensor and the dielectric constant sensor are collected to extract the light absorption peak value related to the carbon chain length in the grease residue area, and the dielectric loss gradient related to the degree of protein denaturation in the protein residue area; a quantitative model related to the stain thickness and adhesion strength is established based on the carbon-hydrogen bond vibration spectrum characteristics of grease and the polar group distribution characteristics of protein; The time-space distribution data of optical signals and dielectric signals are input into a multidimensional correlation matrix, and the spatial aggregation degree and adhesion energy density of the stains are extracted using matrix singular value decomposition. A composite stain index is generated based on the product of the spatial aggregation degree and the adhesion energy density, and the stain grade classification is achieved through index interval division, which is then associated with the cleaning mechanism of different stain locations.

3. The automatic cleaning method of the intelligent soup maker according to claim 2, characterized in that: in, Mild stains: spectral absorbance is lower than the preset baseline value and the dielectric loss gradient changes without cross-linking denaturation; Moderate stains: The spectral absorbance shows multiple peaks and the dielectric loss gradient changes locally; Heavy stains: Spectral absorbance continues to saturate and dielectric loss gradient protein-lipid complex cross-links and solidifies.

4. The automatic cleaning method of the intelligent soup maker according to claim 2, characterized in that: The process of achieving soil level classification by index interval division includes the following steps: The spatiotemporal distributions of the optical and dielectric signals are represented as fourth-order tensors and the high-frequency electric field frequency, respectively, and the fourth-order tensors are expanded into multi-dimensional correlation matrices, whose elements are calculated through cross-domain coupling coefficients; The multi-dimensional correlation matrix is ​​subjected to truncated singular value decomposition to extract two key features: spatial aggregation degree and adhesion energy density; The composite stain index is calculated through nonlinear coupling, and the stain level is determined according to the composite stain index.

5. The automatic cleaning method of the intelligent soup maker according to claim 4, characterized in that: The optical signal tensor contains two-dimensional spatial coordinates, time sampling points and near-infrared spectral channels; the dielectric signal tensor contains the same two-dimensional spatial coordinates and time sampling points.

6. The automatic cleaning method of the intelligent soup maker according to claim 2, characterized in that: The process of obtaining the cleaning mechanism for different stain locations includes the following steps: Based on the composite stain index, spatial aggregation degree and adhesion energy density, a three-dimensional feature space is constructed: the required water pressure impact energy is calculated according to the adhesion energy density; The cleaning mechanism stored in the robot controller of the soup maker is matched based on the carbon chain length of the oil and the degree of protein cross-linking of the stain; The parameters of the cleaning mechanism are associated with the thermal conductivity and surface roughness of the soup maker pot material to generate a dynamic cleaning parameter mapping table, and the parameter deviation of the cleaning mechanism is corrected through real-time feedback.

7. The automatic cleaning method of the intelligent soup maker according to claim 6, characterized in that: The process of generating a dynamic cleaning parameter mapping table includes the following steps: Obtain the temperature field distribution, stain adhesion strength and surface roughness in the pot of the soup maker; quantify the local aggregation of stains based on the spatial autocorrelation coefficient of stain distribution; construct a three-dimensional adhesion energy density map through the adhesion force at different positions; Real-time monitoring of key parameters of pressure changes and temperature distribution during cleaning; Data fusion of 3D adhesion energy density maps with key parameters monitored in real time to build a global view of the cleaning process; Based on the global view, the cleaning parameters are dynamically adjusted and a dynamic cleaning parameter mapping table is generated to guide the cleaning operation.

8. The automatic cleaning method of the intelligent soup maker according to claim 2, characterized in that: The process of the soup maker's robotic arm planning the cleaning path based on the location of the stain includes the following steps: The inner wall of the pot and the surface of the blade are discretized into micro-element grids, and each grid point in the micro-element grid is assigned a value which is a weighted sum of adhesion energy density and spatial aggregation degree, thereby forming an energy density topological map; Identify the local extreme points in the energy density topology map, i.e., the stain core area, and mark them as the key nodes of the soup maker's robotic arm cleaning path; use the key nodes as anchor points and use the minimum energy consumption principle to generate the soup maker's robotic arm initial path; Real-time detection of the geometric mutation area of ​​the pot body, and the curvature adaptive interpolation method is used to adjust the nozzle posture; Achieve Pareto optimality among cleaning coverage, time efficiency and energy consumption, and fine-tune the path weight of the robotic arm of the real-time soup maker through dynamic pressure field matching.

9. The automatic cleaning method of the intelligent soup maker according to claim 2, characterized in that: The process of obtaining the current stain removal rate includes the following steps: Through the data collected by the optical reflectivity sensor and the dielectric constant sensor, the sensor monitors the changes in grease and protein residues, records the difference in residues before and after cleaning; calculates the ratio of stain coverage area to total surface area, and updates the stain coverage rate in real time; The chemical composition concentration of the residue is detected by sensors, and the residue concentration is calculated in real time; The stain removal rate is dynamically calculated based on the stain coverage rate and residue concentration; the water outlet pressure and cleaning time of the robotic arm are adjusted accordingly; if the stain removal rate reaches the preset cleaning threshold, the current area is judged to be cleaned, and the robotic arm automatically moves to the next stain area to continue cleaning until the stains on the inner wall of the pot and the rotating blade are cleaned.

10. The automatic cleaning method of the intelligent soup maker according to claim 9, characterized in that: The process of calculating the ratio of the stain coverage area to the total surface area includes the following steps: identifying the distribution of grease and protein residues by detecting the reflectivity of the light of the optical reflectivity sensor on the inner wall of the pot body and the surface of the rotating blade; the dielectric constant sensor distinguishes the concentration differences of grease and protein residues by measuring the changes in dielectric constants in different areas; before cleaning, the sensor collects initial data and records the stain coverage area and residue concentration; during the cleaning process, the sensor continuously collects data, compares the difference in residue amount before and after cleaning, and records the reduction ratio of the stain coverage area and the decrease in residue concentration.

Images