Control method, device and equipment of smoke range integrated machine and storage medium

Abstract

This invention relates to the field of kitchen appliance control technology, and particularly to a control method, device, equipment, and storage medium for an integrated range hood and cooktop. The method first establishes a closed-loop control mechanism covering the entire process from device startup and data acquisition to operational status adjustment and anomaly protection, overcoming the technical shortcomings of traditional integrated range hood and cooktop control systems with independent control or simple linkage. Second, by integrating fuzzy control and model predictive control as core control technologies, it utilizes system state vectors to achieve a comprehensive representation of the device's operational status. Combined with oil fume concentration prediction, it upgrades the range hood control from passive response to active adjustment, effectively solving the multi-variable strong coupling problem of heat flow and oil fume flow in multi-burner layouts. Furthermore, while achieving adaptive linkage control of the range hood to the burner's operating status, the method also achieves synergistic optimization of improved oil fume capture efficiency and energy consumption, and configures a full-process anomaly monitoring and protection strategy to ensure the safety of the cooking process.

Description

Technical Field

[0001] This invention relates to the field of kitchen appliance control technology, and in particular to a control method, device, equipment and storage medium for an integrated range hood and stove. Background Technology

[0002] In current kitchen cooking scenarios, range hoods and induction cooktops are mostly controlled independently or in simple linkage. The industry has not yet developed a standardized, intelligent linkage system for related control technologies, resulting in many common technical problems in practical applications: Firstly, the core parameters of the range hood, such as the fan speed and damper opening, mostly rely on manual adjustment by the user. They cannot achieve adaptive linkage according to the actual working status of the burner. This not only increases the user's operating costs, but also easily leads to the escape of oil fumes and pollution of the kitchen environment due to untimely adjustment. Secondly, for the layout of multiple burners on both sides of the range hood, the existing technology does not fully consider the strong coupling effect of multivariable heat flow and oil fume flow between the burners, and lacks effective spatial differentiation control methods. The oil fumes on both sides interfere with each other, resulting in low oil fume capture efficiency of the range hood. Third, kitchen thermodynamic systems have significant nonlinear characteristics, and the dynamic changes in food type, cooking method, and stove heating power during cooking will bring a lot of system uncertainty. Existing single control algorithms are difficult to adapt to nonlinear and uncertain scenarios at the same time, and the control accuracy and robustness are insufficient. Fourth, the integration of model predictive control and fuzzy control is not yet mature in the field of kitchen appliances. A multi-objective optimization system that takes into account oil fume capture efficiency, energy consumption, and actuator control stability has not been constructed. Furthermore, the hardware physical constraints and system performance constraints in the control process are not adequately considered, which can easily lead to abnormal equipment operation.

[0003] It is evident that existing technologies still need improvement and enhancement. Summary of the Invention

[0004] In order to overcome the shortcomings of the existing technology, the purpose of this invention is to provide a control method for an integrated range hood and cooktop, which constructs a closed-loop control mechanism for the entire process from device startup, data acquisition to operation status adjustment and abnormal protection, thus overcoming the technical defects of traditional integrated range hood and cooktop independent control or simple linkage.

[0005] The first aspect of this invention provides a control method for an integrated range hood and cooktop, comprising: when the integrated range hood and cooktop are started, acquiring real-time operating data, the real-time operating data including real-time burner temperature, real-time oil fume concentration, and real-time duct wind speed and pressure; performing preprocessing and data fusion processing on the real-time operating data sequentially to construct a current system state vector including multi-dimensional feature parameters; generating predicted oil fume concentration values ​​for the next N control cycles based on the current system state vector, where N is a preset prediction time-domain parameter and N≥1; performing fuzzification processing on the predicted oil fume concentration values ​​and the current system state vector, and calculating the activation intensity of each fuzzy rule according to a pre-constructed fuzzy rule library; inputting the current system state vector into a pre-trained Takagi-Sugeno fuzzy inference model, and calculating the control parameter set including the range hood fan speed adjustment amount and the range hood damper opening adjustment amount based on the activation intensity of each fuzzy rule; adjusting the operating state of the integrated range hood and cooktop according to the control parameter set, and acquiring the adjusted real-time operating parameters; if an abnormal scenario is determined based on the real-time operating parameters, triggering an abnormal protection strategy.

[0006] Optionally, in a first implementation of the first aspect of the present invention, when the integrated range hood and cooktop are started, acquiring real-time operating data, including real-time burner temperature, real-time oil fume concentration, and real-time duct wind speed and pressure, includes: acquiring real-time oil fume concentration collected by an oil fume concentration sensor, wherein three oil fume concentration sensors are respectively located on the left, middle, and right sides of the air inlet of the range hood; acquiring real-time burner temperature collected by a temperature sensor, wherein multiple temperature sensors are respectively located at the center of the burner heating panel, the inner side of each induction cooker burner, and the oil fume gathering areas on the left and right sides of the range hood; acquiring real-time duct wind speed and pressure collected by a wind speed and pressure sensor, wherein two wind speed and pressure sensors are respectively located at the air inlet and outlet of the duct of the range hood; acquiring the current rotation speed of the range hood fan and the current opening degree of the damper, and combining the real-time burner temperature, real-time oil fume concentration, and real-time duct wind speed and pressure to form real-time operating data.

[0007] Optionally, in a second implementation of the first aspect of the present invention, the step of sequentially preprocessing and data fusion processing the real-time operating data to construct a current system state vector including multi-dimensional feature parameters includes: sequentially performing noise reduction processing, outlier correction processing, and missing value completion processing on the real-time operating data to obtain preprocessed operating data; calculating feature quantities based on the preprocessed operating data to obtain burner temperature feature parameters, oil fume concentration feature parameters, and duct velocity and pressure feature parameters; and performing fusion processing on the burner temperature feature parameters, oil fume concentration feature parameters, and duct velocity and pressure feature parameters to construct a current system state vector including multi-dimensional feature parameters.

[0008] Optionally, in a third implementation of the first aspect of the present invention, generating predicted values ​​of oil fume concentration for the next N control cycles based on the current system state vector includes: identifying the current cooking type, the working combination of the induction cooker burners, and the burner power change trend through feature matching based on the current system state vector; acquiring a pre-constructed basic generation curve database covering multiple cooking types and different burner powers, the basic generation curve database including multiple trend curves of oil fume concentration changing over time; matching the current cooking mode and burner power change trend with the basic generation curve database to extract an initial oil fume generation trend curve; correcting the initial oil fume generation trend curve based on the current system state vector, and obtaining predicted values ​​of oil fume concentration for the next N control cycles based on the corrected initial oil fume generation trend curve.

[0009] Optionally, in the fourth implementation of the first aspect of the present invention, the step of fuzzifying the predicted oil fume concentration and the current system state vector, and calculating the activation intensity of each fuzzy rule based on a pre-constructed fuzzy rule library, includes: obtaining a pre-constructed fuzzy rule library, and initializing the parameters of the universe of discourse, fuzzy subset, and membership function of the fuzzy rule library, wherein the fuzzy subset includes five fuzzy levels; performing fuzzification on the predicted oil fume concentration and the current system state vector using the initialized membership function to obtain the membership value corresponding to the predicted oil fume concentration and the current system state vector; and calculating the activation intensity of each fuzzy rule using a product method based on the antecedent conditions of each rule in the fuzzy rule library and the membership value.

[0010] Optionally, in the fifth implementation of the first aspect of the present invention, the step of inputting the current system state vector into a pre-trained Takagi-Sugeno fuzzy inference model and calculating the control parameter set including the adjustment amount of the range hood fan speed and the adjustment amount of the range hood damper opening, includes: inputting the current system state vector into a pre-trained Takagi-Sugeno fuzzy inference model, and calculating the system state trajectory for the next N control cycles by combining the activation intensity of each fuzzy rule and the predicted value of the oil fume concentration; obtaining a pre-constructed multi-objective quadratic objective function. The multi-objective quadratic objective function, with the objectives of maximizing fume capture efficiency, minimizing energy consumption, and optimizing control stability, is defined by a set of constraints, including actuator physical constraints, control increment constraints, and system performance constraints. Based on the multi-objective quadratic objective function, constraints, and system state trajectory, an optimal control sequence for the next M control cycles is generated, where M is a preset control time-domain parameter and M≥1. Based on the optimal control sequence, membership values, and activation strengths of each fuzzy rule, a set of control parameters, including the adjustment of the smoke fan speed and the adjustment of the smoke fan damper opening, is calculated.

[0011] Optionally, in the sixth implementation of the first aspect of the present invention, the step of adjusting the operating state of the integrated range hood and cooktop according to the control parameter set and obtaining the adjusted real-time operating parameters, and triggering an abnormal protection strategy if an abnormal scenario is determined based on the real-time operating parameters, includes: sending a speed adjustment command and a damper opening adjustment command to the integrated range hood and cooktop according to the control parameter set to adjust the operating state of the integrated range hood and cooktop; obtaining the adjusted real-time operating parameters and comparing the real-time operating parameters with a preset normal parameter threshold to obtain a comparison result; if the comparison result shows that the real-time operating parameters exceed the normal parameter threshold, an abnormal scenario is determined to exist, and an abnormal protection strategy is triggered, wherein the abnormal scenario includes burner overheating, excessive oil fume concentration, induction cooker dry burning, and cooking overflow.

[0012] A second aspect of the present invention provides a control device for an integrated range hood and cooktop, comprising: an acquisition module, configured to acquire real-time operating data when the integrated range hood and cooktop are started, the real-time operating data including real-time burner temperature, real-time oil fume concentration, and real-time duct wind speed and pressure; a construction module, configured to perform preprocessing and data fusion processing on the real-time operating data sequentially to construct a current system state vector including multi-dimensional feature parameters; a prediction module, configured to generate predicted oil fume concentration values ​​for the next N control cycles based on the current system state vector, wherein N is a preset prediction time-domain parameter and N≥1; and a processing module, configured to process the oil fume concentration... The predicted value and the current system state vector are fuzzified, and the activation intensity of each fuzzy rule is calculated based on a pre-built fuzzy rule base. The calculation module is used to input the current system state vector into a pre-trained Takagi-Sugeno fuzzy inference model and calculate the activation intensity of each fuzzy rule to obtain a set of control parameters, including the adjustment amount of the range hood fan speed and the adjustment amount of the range hood damper opening. The adjustment module is used to adjust the operating state of the integrated range hood and stove according to the control parameter set and obtain the adjusted real-time operating parameters. If an abnormal scenario is determined based on the real-time operating parameters, an abnormal protection strategy is triggered.

[0013] A third aspect of the present invention provides a control device for an integrated range hood and cooktop, the control device comprising: a memory and at least one processor, the memory storing instructions; the at least one processor calling the instructions in the memory to cause the control device to execute the various steps of the control method for the integrated range hood and cooktop described above.

[0014] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions that, when executed by a processor, implement the steps of the control method for the integrated range hood and cooktop described above.

[0015] The technical solution of this invention first constructs a closed-loop control mechanism covering the entire process from equipment startup and data acquisition to operational status adjustment and anomaly protection, overcoming the technical defects of traditional integrated range hood and stove control systems with independent control or simple linkage. Second, by integrating fuzzy control and model predictive control as core control technologies, it utilizes system state vector construction to achieve a comprehensive representation of the equipment's operational status. Combined with oil fume concentration prediction, it upgrades the range hood control from passive response to active adjustment, effectively solving the multivariate strong coupling problem of heat flow and oil fume flow in multi-burner layouts. Furthermore, while achieving adaptive linkage control of the range hood to the burner's working status, the method also achieves synergistic optimization of oil fume capture efficiency and energy consumption optimization, and configures a full-process anomaly monitoring and protection strategy to ensure the safety of the cooking process. Attached Figure Description

[0016] Figure 1 A logic flowchart of the control method for the integrated range hood and cooktop provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the control device for the integrated range hood and stove provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the control device for the integrated range hood and stove provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the integrated range hood and cooktop provided by the present invention. Detailed Implementation

[0017] This invention provides a control method, apparatus, device, and storage medium for an integrated range hood and cooktop. In this invention, the terms "first," "second," "third," "fourth," etc. (if applicable) in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0018] Please see Figure 4The integrated range hood and cooktop used in this invention adopts a symmetrical layout with a central range hood and two burners on both sides. The main body of the range hood is centrally located, with at least one induction cooktop on each of the left and right sides. The heating panels of the burners are positioned opposite the air intake area of ​​the range hood. A three-point oil fume concentration sensor is arranged at the air intake end of the range hood, corresponding to the oil fume gathering area of ​​the left burner, the central air intake core area of ​​the range hood, and the oil fume gathering area of ​​the right burner. Multiple temperature sensors are arranged at the center of the burner heating panel, the inner side of the burner, and the left and right oil fume gathering areas of the range hood. Wind speed and pressure sensors are arranged at the air inlet and outlet of the range hood duct to collect airflow state parameters. The actuators of the range hood include an adjustable speed fan and independently controlled dampers on the left and right sides. The fan is used to adjust the overall exhaust volume, and the dampers are used to allocate the exhaust ratio on the left and right sides. The actuators can receive control commands to achieve precise adjustment of speed and opening.

[0019] This application discloses a control method for an integrated range hood and cooktop. For ease of understanding, the specific process of the embodiments of this invention is described below. Please refer to [link / reference]. Figure 1 One embodiment of the control method for the integrated range hood and cooktop in this invention includes: 101. When the integrated range hood and stove is started, real-time operating data is acquired, including real-time burner temperature, real-time oil fume concentration, and real-time air duct speed and pressure. In this embodiment, after the integrated range hood and cooktop completes the start-up operation, the control system will automatically trigger the data acquisition process without requiring any additional manual operation from the user. The data acquisition process involves the targeted collection of three types of key physical quantity data from the burner working area and the core area of ​​the range hood duct. The acquisition process starts synchronously with the equipment operation to ensure the timeliness of data acquisition. The three types of data collected provide the basic sensing data source for all subsequent control decision-making processes.

[0020] 102. The real-time running data is preprocessed and fused sequentially to construct a current system state vector including multi-dimensional feature parameters; In this embodiment, the collected real-time operating data is optimized to eliminate invalid interference information. Then, through data fusion and integration of multi-dimensional data analysis features, the originally independent physical quantity data is systematically integrated and transformed into a system state vector that can comprehensively and accurately characterize the overall working status of the integrated range hood and stove. The system state vector includes the core operating characteristic parameters of the burner and range hood, providing a unified state representation basis for subsequent prediction, inference and other control links.

[0021] 103. Based on the current system state vector, generate predicted values ​​of oil fume concentration for the next N control cycles, where N is a preset prediction time-domain parameter and N≥1; In this embodiment, the current system state vector, which characterizes the overall working state of the device, is used as the core basis. Data prediction methods are used to deduce and calculate the changing trend of oil fume concentration, obtaining the specific value of oil fume concentration within a preset control period in the future. This enables advance prediction of oil fume concentration during cooking, transforming the range hood's operation control from traditional passive response adjustment to active predictive adjustment. This effectively avoids the problem of oil fume escape caused by adjusting after oil fume generation, significantly improving the timeliness of the range hood's oil fume capture. The prediction time domain parameter N is a positive integer greater than or equal to 1, and its specific value can be flexibly set according to the actual application scenario and control requirements of the integrated range hood and stove.

[0022] 104. The predicted value of oil fume concentration and the current system state vector are fuzzified, and the activation intensity of each fuzzy rule is calculated according to the pre-constructed fuzzy rule library; In this embodiment, precise numerical data such as the predicted value of oil fume concentration and the current system state vector are converted into fuzzy data suitable for fuzzy inference. Then, a pre-built fuzzy rule library is called, and the rules in the library are matched according to the features of the fuzzy data, and the activation intensity of each fuzzy rule is calculated. This achieves an effective conversion of precise data into fuzzy data, enabling control decisions to better fit the nonlinear and uncertain characteristics of kitchen cooking scenarios. The scene matching degree is quantified by the activation intensity of fuzzy rules, providing standardized data support for subsequent fuzzy inference calculations and improving the algorithm's adaptability to complex cooking scenarios.

[0023] 105. Input the current system state vector into the pre-trained Takagi-Sugeno fuzzy inference model, and calculate the control parameter set including the adjustment amount of the smoke fan speed and the adjustment amount of the smoke fan damper opening by combining the activation intensity of each fuzzy rule; In this embodiment, the current system state vector is input into a trained and validated Takagi-Sugeno fuzzy inference model. Weighted inference calculations are performed based on the activation intensity of each fuzzy rule, and the output includes a set of control parameters, including the adjustment amount of the range hood fan speed and the adjustment amount of the damper opening. The fuzzy inference model enables accurate inference from multi-source data, and the output quantified control parameters can directly guide the actions of the range hood's execution components. This effectively solves the problems of poor adaptability and low control accuracy of traditional single control algorithms in complex kitchen scenarios, and improves the accuracy and scientific nature of range hood control.

[0024] 106. Adjust the operating status of the integrated range hood and stove according to the control parameter set, and obtain the adjusted real-time operating parameters. If an abnormal scenario is determined based on the real-time operating parameters, trigger the abnormal protection strategy. In this embodiment, the control parameter set is converted into control commands that the range hood's execution components can recognize, thereby adjusting the fan speed and damper opening. This effectively transforms the control parameters into actual equipment actions, ensuring a high degree of match between the range hood's operating state and the stove's fume generation state. Simultaneously, the adjusted real-time operating parameters are collected and compared with preset normal thresholds. If an abnormal scenario is detected, the corresponding safety protection strategy is immediately triggered, achieving full-process safety protection for the equipment and promptly avoiding various safety hazards during cooking, thus ensuring the safety of equipment use and the cooking process.

[0025] The control method for the integrated range hood and cooktop disclosed in this application firstly constructs a closed-loop control mechanism covering the entire process from device startup and data acquisition to operational status adjustment and anomaly protection, overcoming the technical shortcomings of traditional integrated range hood and cooktop control systems with independent control or simple linkage. Secondly, by integrating core control technologies of fuzzy control and model predictive control, it utilizes system state vector construction to achieve a comprehensive representation of the device's operational status. Combined with oil fume concentration prediction, it upgrades the range hood control from passive response to active adjustment, effectively solving the multi-variable strong coupling problem of heat flow and oil fume flow in multi-burner layouts. Furthermore, while achieving adaptive linkage control of the range hood to the burner's working status, the method also achieves synergistic optimization of oil fume capture efficiency and energy consumption optimization, and configures a full-process anomaly monitoring and protection strategy to ensure the safety of the cooking process.

[0026] Furthermore, in this embodiment of the invention, when the integrated range hood and cooktop is started, real-time operating data is acquired. This real-time operating data includes real-time burner temperature, real-time oil fume concentration, and real-time duct wind speed and pressure, including: 201. When the integrated range hood and stove is started, the real-time oil fume concentration collected by the oil fume concentration sensor is obtained. The oil fume concentration sensor includes three sensors, which are respectively set on the left, middle and right sides of the air inlet of the range hood. In this embodiment, after the integrated range hood and cooktop is started, three oil fume concentration sensors arranged on the left, middle, and right sides of the range hood's air intake end simultaneously collect real-time oil fume concentration data. The three oil fume concentration sensors correspond to the oil fume gathering area of ​​the left burner, the core air intake area of ​​the range hood, and the oil fume gathering area of ​​the right burner, respectively. This can accurately reflect the differences in oil fume distribution in different areas, thus achieving precise differentiation of the oil fume generation intensity of the left and right burners, providing core data support for subsequent spatial differentiation control.

[0027] 202. Obtain the real-time burner head temperature collected by temperature sensors, wherein multiple temperature sensors are respectively set in the center of the burner head heating panel, the inner side of each induction cooker burner head, and the oil fume gathering areas on the left and right sides of the range hood. In this embodiment, temperature sensors are respectively arranged at the center of the burner heating panel, the inside of each induction cooker burner, and the oil fume gathering areas on the left and right sides of the range hood. The temperature sensor at the center of the heating panel directly reflects the heating intensity of the burner, the temperature sensor on the inside of the burner monitors the internal working temperature of the burner, and the temperature sensor in the oil fume gathering area reflects the oil fume thermal state. The multi-position temperature sensor layout enables comprehensive temperature monitoring of the core working area of ​​the burner and the oil fume gathering area of ​​the range hood, which can accurately characterize the heating state of the burner and the oil fume thermal characteristics, providing reliable temperature data for subsequent cooking type identification and abnormal scene judgment, and improving the completeness of the state characterization.

[0028] 203. Obtain the real-time wind speed and pressure of the air duct collected by the wind speed and pressure sensor. The wind speed and pressure sensor includes two sensors, which are respectively set at the air inlet and air outlet of the air duct of the smoke machine. In this embodiment, wind speed and pressure sensors are respectively arranged at the air inlet and air outlet of the range hood duct. The wind speed and pressure sensor at the air inlet monitors the airflow state of the range hood intake, and the wind speed and pressure sensor at the air outlet monitors the airflow state of the range hood exhaust. The combination of the two types of data can fully reflect the airflow resistance and fan efficiency in the duct, so as to accurately reflect the actual operation effect of the duct after the fan speed and damper opening are adjusted. This provides direct airflow field data support for subsequent control parameter optimization and improves the accuracy of range hood airflow regulation.

[0029] 204. Obtain the current speed of the smoke hood fan and the current opening of the damper, and combine them with the real-time burner temperature, real-time oil fume concentration and real-time air duct speed and pressure to form real-time operating data; In this embodiment, the current speed of the smoke hood fan and the current opening of the damper are collected simultaneously. These data are then integrated with data from three types of sensors: burner temperature, oil fume concentration, and duct wind speed and pressure. This forms a complete real-time operating data set that includes the burner, smoke hood sensors, and smoke hood actuators. This avoids the problem of incomplete state representation caused by the lack of the smoke hood's own operating parameters, and provides more comprehensive and accurate basic data for subsequent data analysis and control decisions.

[0030] Furthermore, in this embodiment of the invention, the step of sequentially preprocessing and data fusion processing the real-time running data to construct a current system state vector including multi-dimensional feature parameters includes: 301. The real-time running data is sequentially subjected to noise reduction processing, outlier correction processing, and missing value completion processing to obtain preprocessed running data; In this embodiment, Butterworth low-pass filtering algorithm is used for noise reduction to eliminate noise interference from the kitchen environment; the 3σ principle is used for outlier correction, and data exceeding the mean ± 3 times the standard deviation are identified as outliers and replaced with the mean of adjacent period data; linear interpolation is used for missing value completion, using the linear relationship between two valid data points before and after the missing point to fill in the missing data; the three-level preprocessing process effectively eliminates noise, outliers and missing data in the original data, significantly improving the validity and accuracy of the data.

[0031] 302. Based on the preprocessed operating data, characteristic parameters are calculated to obtain characteristic parameters of furnace head temperature, characteristic parameters of oil fume concentration, and characteristic parameters of air duct velocity and pressure. In this embodiment, the characteristic parameters of the burner head temperature include the average temperature, maximum temperature, and temperature change rate of each burner head; the characteristic parameters of the oil fume concentration include the average concentration of the left, middle, and right points, the deviation of the concentration between the left and right sides and the middle, and the concentration change rate; the characteristic parameters of the air duct wind speed and pressure include the average wind speed at the air inlet and air outlet, the pressure difference between the air inlet and air outlet, and the wind speed change rate.

[0032] 303. The characteristic parameters of the burner head temperature, the characteristic parameters of the oil fume concentration, and the characteristic parameters of the air duct velocity and pressure are fused to construct a current system state vector including multi-dimensional characteristic parameters; In this embodiment, the characteristic parameters of burner temperature, oil fume concentration, and air duct velocity and pressure are arranged in a fixed order to form a multi-dimensional column vector. That is, the constructed current system state vector is [average burner temperature, maximum burner temperature, burner temperature change rate, left oil fume concentration, right oil fume concentration, oil fume concentration deviation, inlet air velocity, outlet air velocity, air duct pressure difference, current fan speed, current damper opening]. The multi-dimensional state vector constructed through standardized fusion rules can comprehensively and accurately characterize the real-time operating status of the integrated range hood and stove from multiple dimensions, realize the systematic integration of discrete characteristic parameters, and provide a unified state representation form for subsequent prediction, reasoning and other control links.

[0033] Furthermore, in this embodiment of the invention, generating predicted values ​​of oil fume concentration for the next N control cycles based on the current system state vector includes: 401. Based on the current system state vector, identify the current cooking type, the working combination of the induction cooker burners, and the trend of burner power change through feature matching; In this embodiment, the preset feature matching library is a feature template library built based on massive cooking experiment data. It stores feature vector templates corresponding to different cooking types (stir-frying, stewing, steaming, frying), stove working combinations (single-sided left, single-sided right, double-sided), and stove power change trends (rising, stable, falling). For example, stir-frying corresponds to a feature combination of high stove temperature change rate, high oil fume concentration change rate, and rapid power increase. Through feature matching, the core information of cooking can be accurately identified, and key information that fits the actual operation scenario can be quickly obtained, providing a core scenario basis for subsequent oil fume concentration prediction.

[0034] 402. Obtain a pre-constructed database of basic generation curves covering multiple cooking types and different stove power, wherein the database of basic generation curves includes multiple trend curves of oil fume concentration changing over time; In this embodiment, a large amount of cooking experiment data is constructed from the basic generation curve database, covering a variety of cooking types and different combinations of stove power. The basic generation curve database stores multiple trend curves of oil fume concentration changing over time. Each trend curve corresponds to a specific cooking type and combination of stove power, such as the curve of oil fume concentration rising rapidly and then stabilizing in the stir-fry scenario.

[0035] 403. Match the current cooking mode and the trend of stove power change with the basic generation curve database to extract the initial oil fume generation trend curve; In this embodiment, the identified cooking type, stove working combination, and power change trend are used as matching conditions. The curve that best matches the current scenario is selected from the basic generation curve database as the initial oil fume generation trend curve. This provides a realistic trend basis for subsequent oil fume concentration prediction, effectively improving the initial accuracy of the prediction and reducing the workload of subsequent corrections.

[0036] 404. Based on the current system state vector, the initial oil fume generation trend curve is corrected, and based on the corrected initial oil fume generation trend curve, the predicted oil fume concentration for the next N control cycles is obtained. In this embodiment, based on the real-time oil fume concentration change rate and the burner temperature change rate in the current system state vector, the correction coefficient k is calculated as follows: k = (real-time oil fume concentration change rate / oil fume concentration change rate of the initial oil fume generation trend curve) × (real-time temperature change rate / temperature change rate of the initial oil fume generation trend curve). By multiplying k by the oil fume concentration value of the initial oil fume generation trend curve, the corrected oil fume concentration prediction value is obtained. Through dynamic correction based on the real-time operating status, the oil fume generation trend curve accurately matches the actual state of the equipment, avoiding prediction deviations caused by fixed curves.

[0037] Furthermore, in this embodiment of the invention, the step of fuzzifying the predicted oil fume concentration and the current system state vector, and calculating the activation intensity of each fuzzy rule based on a pre-built fuzzy rule base, includes: 501. Obtain a pre-built fuzzy rule base and initialize the parameters of the universe of discourse, fuzzy subsets and membership function of the fuzzy rule base, wherein the fuzzy subsets include five fuzzy levels; In this embodiment, the fuzzy rule base is constructed based on the experience of cooking experts and experimental data. It includes a set of fuzzy rules in the form of IF-THEN. The input variables include oil fume concentration deviation, temperature change rate, burner power, and predicted oil fume concentration. The fuzzy subsets are divided into five fuzzy levels: {extremely low, low, medium, high, and extremely high}. The antecedent condition of each fuzzy rule is a combination of fuzzy subsets of the input variables. For example, IF Left oil fume concentration deviation is high AND Burner temperature change rate is high THEN Fan speed adjustment is high AND Left damper opening adjustment is high.

[0038] 502. The initial membership function is used to perform fuzzification processing on the predicted value of oil fume concentration and the current system state vector to obtain the membership value corresponding to the predicted value of oil fume concentration and the current system state vector; In this embodiment, the initialized triangular membership function is used to convert the predicted value of oil fume concentration and the precise value in the current system state vector into membership values ​​of five corresponding fuzzy subsets. The membership value of each value ranges from 0 to 1, reflecting the degree to which the value belongs to the corresponding fuzzy level. The membership function realizes the standardized conversion of precise data to fuzzy data, making the original precise values ​​suitable for the matching calculation requirements of the fuzzy rule base, and providing standardized fuzzy data support for subsequent rule activation intensity calculation.

[0039] 503. Based on the antecedent conditions of each rule in the fuzzy rule base and combined with the membership value, calculate the activation strength of each fuzzy rule using the product method; In this embodiment, based on the antecedent conditions of each fuzzy rule, the activation strength is calculated by multiplying the membership values ​​of the corresponding input variables. That is, the activation strength is the product of the membership values ​​of all input variables in the antecedent conditions. The larger the value, the higher the matching degree of the fuzzy rule with the current scene, which can provide accurate quantitative basis for subsequent fuzzy inference model calculation.

[0040] Further, in this embodiment of the invention, the current system state vector is input into a pre-trained Takagi-Sugeno fuzzy inference model, and the activation intensity of each fuzzy rule is used for calculation to obtain a set of control parameters including the adjustment amount of the smoke fan speed and the adjustment amount of the smoke fan damper opening, including: 601. Input the current system state vector into the pre-trained Takagi-Sugeno fuzzy inference model, and combine the activation intensity of each fuzzy rule with the predicted value of the oil fume concentration to predict the system state trajectory for the next N control cycles. In this embodiment, a large amount of cooking experiment data is collected, including system state vectors and corresponding control parameters under different working conditions, which are divided into training set and validation set in a 7:3 ratio; fuzzy C-means clustering algorithm is used to determine the number of fuzzy rules and the parameters of the antecedent membership function; weighted least squares method is used to fit the parameters of the consequent linear equation; the model prediction accuracy is verified using the validation set. If the mean square error exceeds the preset threshold, gradient descent method is used to iteratively optimize the consequent parameters until the accuracy requirements are met, thus obtaining the trained and verified Takagi-Sugeno fuzzy inference model. The current system state vector, the activation intensity of each fuzzy rule, and the predicted value of the oil fume concentration are input into the trained Takagi-Sugeno fuzzy inference model to predict the system state trajectory for the next N control cycles. The system state trajectory is in the form of a multi-dimensional column vector sequence. Each vector includes core state parameters such as furnace head temperature, oil fume concentration, wind speed, and pressure, which can accurately reflect the future operating trend of the equipment. This allows control decisions to take into account both the current state and future changes, improving the foresight and adaptability of the control.

[0041] 602. Obtain a pre-constructed multi-objective quadratic objective function and preset constraints. The multi-objective quadratic objective function aims to maximize oil fume capture efficiency, minimize energy consumption, and optimize control stability. The constraints include actuator physical constraints, control increment constraints, and system performance constraints. In this embodiment, the multi-objective quadratic objective function is exemplified as J = ∑(w1 × (e_L² + e_R²) + w2n² + w3 (Δn² + Δd_L² + Δd_R²)), where w1 = 0.6 (oil fume capture efficiency weight), w2 = 0.2 (energy consumption weight), w3 = 0.2 (control stability weight), e_L and e_R are the oil fume concentration deviations on the left and right sides, respectively, n is the fan speed, and Δn, Δd_L, and Δd_R are control increments. The constraints include actuator physical constraints: 0 ≤ n ≤ 1500 rpm, 0 ≤ d_L ≤ 100%, 0 ≤ d_R ≤ 100%; control increment constraints: |Δn| ≤ 50 rpm / cycle, |Δd_L| ≤ 5% / cycle, |Δd_R| ≤ 5%; system performance constraints: |e_L| ≤ 0.5 mg / m³, |e_R| ≤ 0.5 mg / m³, and burner head temperature ≤ 250℃.

[0042] 603. Based on the multi-objective quadratic objective function, constraints, and system state trajectory, generate the optimal control sequence for the next M control cycles, where M is a preset control time-domain parameter and M≥1; In this embodiment, based on the multi-objective quadratic objective function, constraints, and system state trajectory, the optimal control sequence for the next M control cycles is obtained by solving the quadratic programming algorithm. The optimal control sequence includes multiple control elements, each of which includes the fan speed adjustment Δn and the damper opening adjustment Δd_L / Δd_R.

[0043] 604. Based on the optimal control sequence, membership values, and activation strength of each fuzzy rule, calculate the control parameter set including the adjustment amount of the flue fan speed and the adjustment amount of the flue damper opening; In this embodiment, the preset parameter calculation rule is to use the centroid method for defuzzification, multiply the consequent parameter of each fuzzy rule by the corresponding activation intensity, sum them and divide by the total activation intensity to obtain the precise control parameter value. For example, the fan speed adjustment Δn = ∑(ω_i×n_i) / ∑ω_i, where ω_i is the activation intensity of the i-th fuzzy rule and n_i is the fan speed adjustment of the consequent of the i-th rule.

[0044] Furthermore, in this embodiment of the invention, the step of adjusting the operating state of the integrated range hood and cooktop according to the control parameter set and obtaining the adjusted real-time operating parameters, and triggering an anomaly protection strategy if an abnormal scenario is determined based on the real-time operating parameters, includes: 701. Send speed adjustment commands and damper opening adjustment commands to the integrated range hood and cooktop according to the control parameter set to adjust the operating status of the integrated range hood and cooktop; In this embodiment, the control parameter set is converted into standardized instructions that the smoke hood can recognize. The speed adjustment instruction is sent to the fan, and the opening adjustment instruction is sent to the left and right dampers respectively. The execution component completes the action adjustment according to the instruction, so that the smoke hood air volume and exhaust direction match the oil fume generation state of the burner, thereby improving the oil fume capture effect and operating efficiency.

[0045] 702. Obtain the adjusted real-time operating parameters and compare them with the preset normal parameter thresholds to obtain the comparison results; In this embodiment, the real-time operating parameters obtained specifically include burner temperature, oil fume concentration, duct wind speed and pressure, fan speed, damper opening, and burner power. Each real-time operating parameter is compared with a preset normal threshold to obtain a comparison result indicating whether it exceeds the normal range. This enables dynamic monitoring of the equipment's operating status, provides accurate quantitative basis for judging abnormal scenarios, and avoids abnormal operation caused by improper equipment adjustments.

[0046] 703. If the comparison results show that the real-time operating parameters exceed the normal parameter threshold, it is determined that there is an abnormal scenario and the abnormal protection strategy is triggered. The abnormal scenario includes burner overheating, excessive oil fume concentration, induction cooker dry burning and cooking overflow. In this embodiment, the abnormal scenario determination conditions and protection strategies include: When any burner head temperature is >250℃ and lasts for ≥2s, it is determined that the burner head is overheating. At this time, the maximum speed of the fan is triggered, an overheating alarm is issued, and an abnormality log is recorded. When the oil fume concentration on any side is greater than 1.0 mg / m³ and lasts for ≥3 seconds, it is determined that the oil fume concentration is too high. At this time, the maximum speed of the fan is triggered and a high concentration oil fume alarm is issued. When the rate of change of the burner head temperature is greater than 50℃ / min and the temperature is greater than 300℃, it is determined that the induction cooker is dry burning. At this time, the heating power of the corresponding burner head is cut off, the maximum speed of the fan is triggered, and a dry burning alarm is issued. When the burner temperature drops by more than 20°C / s and the oil fume concentration rises by more than 0.3mg / m³ / s, it is determined to be cooking overflow. At this time, the heating power of the corresponding burner is cut off and an overflow alarm is issued. By accurately identifying and promptly avoiding various safety hazards during the cooking process, the safety of the integrated range hood and cooktop is ensured.

[0047] The control method of the integrated range hood and cooktop in the embodiments of the present invention has been described above. The control device of the integrated range hood and cooktop in the embodiments of the present invention will be described below. Please refer to [link / reference]. Figure 2 One embodiment of the control device for the integrated range hood and cooktop of the present invention includes: The acquisition module 801 is used to acquire real-time operating data when the integrated range hood and stove is started. The real-time operating data includes real-time burner temperature, real-time oil fume concentration, and real-time air duct speed and pressure. The construction module 802 is used to perform preprocessing and data fusion processing on the real-time running data in sequence to construct a current system state vector including multi-dimensional feature parameters. The prediction module 803 is used to generate predicted values ​​of oil fume concentration for the next N control cycles based on the current system state vector, where N is a preset prediction time domain parameter and N≥1; The processing module 804 is used to perform fuzzification processing on the predicted value of oil fume concentration and the current system state vector, and calculate the activation intensity of each fuzzy rule according to the pre-built fuzzy rule library; The calculation module 805 is used to input the current system state vector into the pre-trained Takagi-Sugeno fuzzy inference model, and calculate the control parameter set including the adjustment amount of the smoke fan speed and the adjustment amount of the smoke fan damper opening by combining the activation intensity of each fuzzy rule. The adjustment module 806 is used to adjust the operating status of the integrated range hood and stove according to the control parameter set, and to obtain the adjusted real-time operating parameters. If an abnormal scenario is determined based on the real-time operating parameters, an abnormal protection strategy is triggered.

[0048] Based on the same ideas as the methods in the above embodiments, the apparatus provided in this application can implement the methods in the above embodiments.

[0049] above Figure 2 The control device of the integrated range hood and stove in this embodiment of the invention will be described in detail from the perspective of modular functional entities. The control equipment of the integrated range hood and stove in this embodiment of the invention will be described in detail from the perspective of hardware processing.

[0050] Figure 3 This is a schematic diagram of the structure of a control device 900 for a range hood and cooktop integrated appliance provided in an embodiment of the present invention. The control device 900 can vary significantly due to different configurations or performance characteristics. It may include one or more central processing units (CPUs) 910 and a memory 920, and one or more storage media 930 (e.g., one or more mass storage devices) storing application programs 933 or data 932. The memory 920 and storage media 930 can be temporary or persistent storage. The program stored in the storage media 930 may include one or more modules (not shown in the diagram), each module including a series of instruction operations on the control device 900 of the range hood and cooktop integrated appliance. Furthermore, the processor 910 may be configured to communicate with the storage media 930 and execute the series of instruction operations in the storage media 930 on the control device 900 of the range hood and cooktop integrated appliance to implement the steps of the control method for the range hood and cooktop integrated appliance provided in the above-described method embodiments.

[0051] The control device 900 of the integrated range hood and cooktop may also include one or more power supplies 940, one or more wired or wireless network interfaces 950, one or more input / output interfaces 960, and / or one or more operating systems 931, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will understand that... Figure 3 The control device structure of the integrated range hood and cooktop shown does not constitute a limitation on the control device of the integrated range hood and cooktop. It may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0052] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the steps of the control method for the integrated range hood and stove.

[0053] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system, device, or unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0054] If the integrated unit is implemented as 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0055] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A control method of a smoke range all-in-one machine, characterized by, include: When the integrated range hood and cooktop is started, real-time operating data is acquired, including real-time burner temperature, real-time oil fume concentration, and real-time air duct speed and pressure. The real-time running data is preprocessed and fused sequentially to construct a current system state vector including multi-dimensional feature parameters; Based on the current system state vector, generate predicted values ​​of oil fume concentration for the next N control cycles, where N is a preset prediction time-domain parameter and N≥1; The predicted value of oil fume concentration and the current system state vector are fuzzified, and the activation intensity of each fuzzy rule is calculated based on the pre-constructed fuzzy rule library. The current system state vector is input into the pre-trained Takagi-Sugeno fuzzy inference model, and the activation intensity of each fuzzy rule is combined to calculate the control parameter set including the adjustment amount of the smoke fan speed and the adjustment amount of the smoke fan damper opening. The operating status of the integrated range hood and cooktop is adjusted according to the control parameter set, and the adjusted real-time operating parameters are obtained. If an abnormal scenario is determined based on the real-time operating parameters, an abnormal protection strategy is triggered.

2. The control method of claim 1, wherein When the integrated range hood and cooktop is started, real-time operating data is acquired, including real-time burner temperature, real-time oil fume concentration, and real-time airflow speed and pressure in the duct. When the integrated range hood and cooktop is started, the real-time oil fume concentration is obtained from the oil fume concentration sensor. The oil fume concentration sensor includes three sensors, which are respectively set on the left, middle and right sides of the air inlet of the range hood. The real-time burner head temperature is acquired by temperature sensors, which include multiple sensors and are respectively set in the center of the burner head heating panel, the inner side of each induction cooker burner head, and the oil fume gathering areas on the left and right sides of the range hood. The real-time air velocity and pressure in the duct are acquired by the wind speed and pressure sensors, which include two sensors respectively installed at the air inlet and air outlet of the duct of the smoke hood. The system acquires the current speed of the range hood fan and the current opening of the damper, and combines this with real-time burner temperature, real-time oil fume concentration, and real-time duct velocity and pressure to form real-time operating data.

3. The control method of claim 1, wherein The process of preprocessing and fusing the real-time operating data sequentially to construct a current system state vector including multi-dimensional feature parameters includes: The real-time running data is sequentially subjected to noise reduction, outlier correction, and missing value completion to obtain preprocessed running data; Based on the preprocessed operating data, characteristic parameters such as furnace head temperature, oil fume concentration, and air duct velocity and pressure are calculated to obtain characteristic parameters of furnace head temperature, oil fume concentration, and air duct velocity and pressure. The characteristic parameters of the burner head temperature, the characteristic parameters of the oil fume concentration, and the characteristic parameters of the air duct velocity and pressure are fused to construct a current system state vector that includes multi-dimensional characteristic parameters.

4. The control method of claim 1, wherein The step of generating predicted oil fume concentration values ​​for the next N control cycles based on the current system state vector includes: Based on the current system state vector, the current cooking type, the working combination of the induction cooker burners, and the trend of burner power change are identified through feature matching. Obtain a pre-built database of basic generation curves covering various cooking types and different stove power, the database of basic generation curves including multiple trend curves of oil fume concentration changing over time; The current cooking mode and the trend of stove power change are matched with the basic generation curve database to extract the initial oil fume generation trend curve; The initial oil fume generation trend curve is corrected based on the current system state vector, and the predicted oil fume concentration for the next N control cycles is obtained based on the corrected initial oil fume generation trend curve.

5. The control method of claim 1, wherein The process of fuzzifying the predicted oil fume concentration and the current system state vector, and calculating the activation strength of each fuzzy rule based on a pre-built fuzzy rule base, includes: Obtain a pre-built fuzzy rule base and initialize the parameters of the universe of discourse, fuzzy subsets, and membership function of the fuzzy rule base, wherein the fuzzy subsets include five fuzzy levels; The initial membership function is used to perform fuzzification processing on the predicted value of oil fume concentration and the current system state vector to obtain the membership value corresponding to the predicted value of oil fume concentration and the current system state vector. Based on the antecedent conditions of each rule in the fuzzy rule base and combined with the membership value, the activation strength of each fuzzy rule is calculated using the product method.

6. The control method for the integrated range hood and cooktop according to claim 5, characterized in that, The current system state vector is input into a pre-trained Takagi-Sugeno fuzzy inference model, and the activation intensity of each fuzzy rule is used for calculation to obtain a set of control parameters including the adjustment amount of the smoke fan speed and the adjustment amount of the smoke fan damper opening, including: The current system state vector is input into the pre-trained Takagi-Sugeno fuzzy inference model. The activation intensity of each fuzzy rule and the predicted value of the oil fume concentration are combined to predict the system state trajectory for the next N control cycles. Obtain a pre-constructed multi-objective quadratic objective function and preset constraints. The multi-objective quadratic objective function aims to maximize oil fume capture efficiency, minimize energy consumption, and optimize control stability. The constraints include actuator physical constraints, control increment constraints, and system performance constraints. Based on the multi-objective quadratic objective function, constraints, and system state trajectory, an optimal control sequence for the next M control cycles is generated, where M is a preset control time-domain parameter and M≥1; Based on the optimal control sequence, membership values, and activation strength of each fuzzy rule, a set of control parameters including the adjustment amount of the smoke fan speed and the adjustment amount of the smoke fan damper opening is calculated.

7. The control method for the integrated range hood and cooktop according to claim 1, characterized in that, The process involves adjusting the operating status of the integrated range hood and cooktop based on the control parameter set, obtaining the adjusted real-time operating parameters, and triggering an anomaly protection strategy if an abnormal scenario is determined based on the real-time operating parameters. This strategy includes: Based on the control parameter set, the speed adjustment command and damper opening adjustment command are sent to the integrated range hood and cooktop to adjust the operating status of the integrated range hood and cooktop; Obtain the adjusted real-time operating parameters and compare them with the preset normal parameter thresholds to obtain the comparison results; If the comparison results show that the real-time operating parameters exceed the normal parameter threshold, it is determined that there is an abnormal scenario and an abnormal protection strategy is triggered. The abnormal scenarios include burner overheating, excessive oil fume concentration, dry burning of the induction cooker, and cooking overflow.

8. A control device for an integrated range hood and cooktop, characterized in that, include: The acquisition module is used to acquire real-time operating data when the integrated range hood and stove is started. The real-time operating data includes real-time burner temperature, real-time oil fume concentration, and real-time air duct speed and pressure. The construction module is used to preprocess and fuse the real-time running data sequentially to construct a current system state vector including multi-dimensional feature parameters. The prediction module is used to generate predicted values ​​of oil fume concentration for the next N control cycles based on the current system state vector, where N is a preset prediction time domain parameter and N≥1; The processing module is used to perform fuzzification processing on the predicted value of oil fume concentration and the current system state vector, and calculate the activation intensity of each fuzzy rule according to the pre-built fuzzy rule library; The calculation module is used to input the current system state vector into the pre-trained Takagi-Sugeno fuzzy inference model, and calculate the control parameter set including the adjustment amount of the smoke fan speed and the adjustment amount of the smoke fan damper opening by combining the activation intensity of each fuzzy rule. The adjustment module is used to adjust the operating status of the integrated range hood and stove according to the control parameter set, and to obtain the adjusted real-time operating parameters. If an abnormal scenario is determined based on the real-time operating parameters, an abnormal protection strategy is triggered.

9. A control device for an integrated range hood and cooktop, characterized in that, The control device of the integrated range hood and cooktop includes: a memory and at least one processor, wherein the memory stores instructions; At least one of the processors invokes the instructions in the memory to cause the control device of the integrated range hood and cooktop to perform the various steps of the control method of the integrated range hood and cooktop as claimed in any one of claims 1-7.

10. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the various steps of the control method for the integrated range hood and cooktop as described in any one of claims 1-7.

Images