Multi-dimensional sensing and adjusting optimization method and system for kitchen electrical environment parameters

Abstract

The invention provides a multi-dimensional sensing and adjusting optimization method and system for kitchen electrical environment parameters, and relates to the field of kitchen oil fume control, and the method comprises the steps: collecting cooking heat source temperature and behavior data, and recognizing cooking state features; generating cooking fume motion space-time prediction information by combining a ratio relationship between the cooking fume particle rising speed and the airflow speed; dividing a cooking area into a plurality of control blocks, and forming a block airflow control scheme by adopting a gradient air pressure control strategy; when the lampblack diffusion trend is detected, airflow parameters are adjusted to establish a protective gas field; and recording the control effect to generate optimal configuration information. According to the invention, the oil smoke diffusion path can be accurately predicted, multi-area cooperative control is realized, and the oil smoke trapping efficiency is improved.

Description

Technical Field

[0001] This invention relates to kitchen fume control technology, and more particularly to a method and system for multi-dimensional sensing and adjustment optimization of kitchen appliance environmental parameters. Background Technology

[0002] As people's living standards improve, the health and comfort of the kitchen environment are receiving increasing attention. Cooking fumes not only affect indoor air quality but can also harm human health. Traditional kitchen exhaust systems primarily rely on fans to extract these fumes, but this method often suffers from low energy efficiency and high noise levels. In recent years, smart kitchen appliance technology has developed rapidly, integrating sensor technology, airflow dynamics, and artificial intelligence into kitchen environment management, becoming a significant trend in the industry. Current smart range hoods on the market are beginning to employ technologies such as temperature sensing and fan speed adjustment, attempting to achieve precise capture and treatment of cooking fumes.

[0003] However, current technologies lack the ability to accurately perceive the dynamic characteristics of the cooking process. Most devices judge the cooking status based on only a single or limited parameter, failing to accurately predict the timing and spatial distribution of oil fumes, leading to untimely fume collection or energy waste. Traditional kitchen appliances treat oil fumes by uniformly exhausting them throughout the entire area, ignoring the non-uniformity of fume diffusion within the kitchen space. This makes it impossible to precisely control the differences in fume concentration in different areas, resulting in insufficient fume treatment in some areas and over-treatment in others. Existing kitchen appliance control systems lack adaptive learning optimization mechanisms, failing to continuously adjust and optimize control strategies based on actual control effects. They lack specificity for oil fume control under different cooking habits and environments, making it difficult to achieve the optimal balance between energy efficiency and control performance. Summary of the Invention

[0004] This invention provides a method and system for multi-dimensional sensing and adjustment optimization of kitchen appliance environmental parameters, which can solve the problems in the prior art.

[0005] A first aspect of this invention provides a method for multi-dimensional sensing and adjustment optimization of kitchen appliance environmental parameters, comprising: Collect data on cooking heat source temperature and cooking behavior; Based on the fluctuation pattern of cooking heat source temperature and the displacement trajectory of cooking behavior, the characteristics of cooking state are identified, and combined with the ratio of the rising velocity of oil fume particles to the velocity of surrounding airflow, spatiotemporal prediction information of oil fume movement is generated. Based on spatiotemporal prediction information, the cooking area is divided into multiple control blocks. A gradient air pressure control strategy is adopted to calculate the airflow guidance parameters of each control block and form a block airflow control scheme. Collect oil fume movement data from each control block. When an oil fume diffusion trend is detected, adjust the airflow parameters of adjacent control blocks according to the block airflow control scheme to establish a protective air field. Record the control effect of the protective air field on the oil fume, extract the correspondence between airflow parameters and control effect, generate optimal block airflow configuration information, and control the operation of environmental conditioning equipment based on the optimal block airflow configuration information.

[0006] Based on the fluctuation patterns of cooking heat source temperature and the displacement trajectory of cooking behavior, cooking state characteristics are identified. Combined with the ratio of the rising velocity of oil fume particles to the surrounding airflow velocity, spatiotemporal prediction information for oil fume movement is generated, including: Collect cooking heat source temperature data, calculate the temperature change rate of adjacent sampling points, obtain temperature fluctuation curves, and determine the fluctuation pattern of cooking heat source temperature based on the frequency and peak amplitude of temperature change rate. Obtain the spatial coordinates of the cooking utensils, calculate the instantaneous velocity and instantaneous acceleration of the position coordinates, and determine the displacement trajectory of the cooking behavior based on the combined changes in the velocity and acceleration directions; By performing time-domain fusion of the abrupt change point of the fluctuation pattern with the motion component of the displacement trajectory, and identifying the cooking state characteristics based on the changing trends of the temperature gradient and motion component before and after the abrupt change point; Collect the surrounding airflow velocity at the time corresponding to the cooking state characteristics, and calculate the rising velocity of oil fume particles by combining the convection effect of the temperature field, and obtain the ratio relationship between the rising velocity of oil fume particles and the surrounding airflow velocity. Based on the fluctuation patterns of cooking state characteristics, displacement trajectories, and the gradient distribution of the ratio relationship in space, spatiotemporal prediction information for the movement of cooking fumes is generated.

[0007] Based on spatiotemporal prediction information, the cooking area is divided into multiple control blocks. A gradient pressure control strategy is adopted, and the airflow guidance parameters of each control block are calculated to form a block airflow control scheme, including: Based on spatiotemporal prediction information, the cooking area is divided into multiple control blocks using dynamic clustering. The temperature gradient and pressure gradient are calculated based on the residence time and diffusion rate of oil fume particles in each block. Collect oil fume concentration data for each control block, calculate the oil fume diffusion direction and diffusion rate by combining the temperature gradient change trend, and determine the oil fume movement trajectory based on the spatial distribution of the air pressure gradient. Based on the movement trajectory of the oil fume, an alternating high and low pressure gradient is established between adjacent control blocks. The inlet and outlet air flow rates of each control block are calculated, and the pressure gradient coefficient is determined based on the ratio of the inlet and outlet air flow rates. Calculate the airflow guidance parameters for each control block based on the pressure gradient coefficient, adjust the operating status of the air supply equipment to construct a directional airflow channel, and when the oil fume diffusion exceeds the preset diffusion range, adjust the air pressure step, record the adjustment effect of the air pressure step, and form a block airflow control scheme.

[0008] Based on the trajectory of the cooking fumes, alternating high and low pressure gradients are established between adjacent control blocks. The inflow and outflow rates of each control block are calculated, and the pressure gradient coefficient is determined based on the ratio of the inflow and outflow rates, including: The system acquires the trajectory of cooking fumes and the location information of adjacent control blocks, calculates the spatial distance between control blocks, establishes a pressure transfer function based on the spatial distance, and generates the reference air pressure value and initial pressure increment for each control block. Based on the reference pressure value and the initial pressure increment, a pressure ladder with alternating high and low pressure is constructed between adjacent control blocks. The pressure attenuation coefficient of the pressure ladder is calculated, and the initial pressure ladder structure is formed according to the pressure attenuation coefficient. The inlet and outlet air flow rates of each control block under the initial pressure gradient structure are collected, the ratio of inlet to outlet air flow rates is calculated, the airflow accumulation state of each block is determined based on the ratio of inlet to outlet air flow rates, and the airflow regulation coefficient is calculated based on the airflow accumulation state. The oil fume concentration data of each control block is obtained, and the pressure correction amount is calculated in combination with the airflow regulation coefficient. The pressure increment in the pressure step is dynamically adjusted according to the pressure correction amount to generate the adjusted pressure step. Based on the adjusted pressure gradient, a multi-objective optimization function is constructed with airflow balance, system energy consumption, and airflow velocity as optimization objectives. The pressure gradient coefficient is obtained by solving the multi-objective optimization function.

[0009] Collect oil fume movement data from each control block. When an oil fume diffusion trend is detected, adjust the airflow parameters of adjacent control blocks according to the block's airflow control scheme to establish a protective air field, including: The oil fume motion data of each control block is collected by an array of oil fume concentration sensors. The concentration gradient and rate of change of adjacent sampling points are calculated based on the airflow guidance parameters in the block airflow control scheme. The oil fume motion feature vector is established by combining the oil fume motion data. The oil fume diffusion trend is analyzed and detected based on the feature vector. According to the block airflow control scheme, the pressure transfer coefficient is calculated based on the detected oil fume diffusion trend, and the pressure value of each control block and the pressure gradient value between adjacent control blocks are set according to the pressure transfer coefficient. Collect airflow parameters for each control block, calculate the airflow field characteristics within the control block by combining airflow guidance parameters, and generate airflow parameter adjustment amounts for adjacent control blocks based on the airflow field characteristics. Adjust the supply and exhaust air parameters of adjacent control blocks according to the airflow parameter adjustment amount, update the pressure gradient value between blocks in real time, and when the airflow field characteristics of a block exceed the preset protection value, reset the pressure value and pressure gradient value of each control block according to the adjusted supply and exhaust air parameters to establish a protective air field.

[0010] The airflow parameters of each control block are collected, and the airflow field characteristics within the control block are calculated in combination with the airflow guidance parameters. Based on the airflow field characteristics, the airflow parameter adjustment amounts for adjacent control blocks are generated, including: Collect airflow parameters for each control block, including wind speed data and pressure data; The direction of airflow is determined based on wind speed data, and the pressure change value is determined based on pressure data. The direction of airflow is compared with the airflow guidance parameters to obtain the airflow deviation. The characteristics of the airflow field in the control block are calculated based on the airflow deviation and the pressure change value. The correlation degree of airflow movement between adjacent control blocks is calculated based on the airflow field characteristics. The supply and exhaust air conditioning requirements of adjacent control blocks are determined based on the airflow movement correlation degree, and the airflow parameter adjustment amount of adjacent control blocks is generated.

[0011] Record the control effect of the protective air field on cooking fumes, extract the correspondence between airflow parameters and control effects, generate optimal block airflow configuration information, and control the operation of environmental conditioning equipment based on the optimal block airflow configuration information, including: Collect oil fume concentration data at the boundary of the protective gas field, calculate the spatial distribution and temporal variation of the oil fume concentration data, determine the boundary breach point based on the spatial distribution, calculate the oil fume diffusion intensity based on the temporal variation, and combine the boundary breach point and oil fume diffusion intensity to generate control effect data of the protective gas field. Establish a correspondence between the airflow parameters of each control block and the control effect data, extract the airflow parameter combination when the control effect data is optimal, and generate the optimal block airflow configuration information; Adjust the operating status of the environmental control equipment according to the optimal block airflow configuration information, and collect the control effect data after adjustment. When the control effect data decreases, update the airflow configuration information.

[0012] A second aspect of this invention provides a multi-dimensional sensing and adjustment optimization system for kitchen appliance environmental parameters, comprising: The first unit is used to collect data on cooking heat source temperature and cooking behavior. The second unit is used to identify cooking state characteristics based on the fluctuation pattern of cooking heat source temperature and the displacement trajectory of cooking behavior, and generate spatiotemporal prediction information of oil fume movement by combining the ratio of the rising velocity of oil fume particles to the velocity of the surrounding airflow. The third unit is used to divide the cooking area into multiple control blocks based on spatiotemporal prediction information, adopt a gradient air pressure control strategy, calculate the airflow guidance parameters of each control block, and form a block airflow control scheme. The fourth unit is used to collect the oil fume movement data of each control block. When the oil fume diffusion trend is detected, the airflow parameters of the adjacent control blocks are adjusted according to the block airflow control scheme to establish a protective air field. The fifth unit is used to record the control effect of the protective air field on the oil fume, extract the correspondence between airflow parameters and control effect, generate optimal block airflow configuration information, and control the operation of environmental conditioning equipment based on the optimal block airflow configuration information.

[0013] A third aspect of the present invention provides an electronic device, comprising: processor; Memory used to store processor-executable instructions; The processor is configured to invoke instructions stored in the memory to execute the aforementioned method.

[0014] A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the aforementioned method.

[0015] In this embodiment, by intelligently collecting and analyzing cooking heat source temperature and behavioral data, the trajectory of cooking fumes can be accurately predicted, enabling advance anticipation of fume diffusion during cooking. This effectively avoids the problem of fume diffusion caused by the delayed response of traditional range hoods, thus improving fume capture efficiency. A multi-block gradient air pressure control strategy is adopted, dynamically adjusting the airflow parameters of each control block based on the spatiotemporal prediction information of fume movement. This forms a precise protective air field, effectively controlling fumes from their initial generation and preventing their diffusion throughout the kitchen space. This significantly improves the quality of the kitchen environment and reduces the risk of user exposure to fumes. By continuously recording and analyzing the control effect of the protective air field and constantly optimizing the block airflow configuration information, intelligent adaptive control of the environmental control equipment is achieved. This ensures effective fume control while reducing energy consumption, improving system operating efficiency, and providing users with a more comfortable and healthy cooking environment. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the multi-dimensional sensing and adjustment optimization method for kitchen appliance environmental parameters according to an embodiment of the present invention. Figure 2 This is a flowchart illustrating the process of establishing a protective gas field for controlling the diffusion of oil fumes in an embodiment of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0019] Figure 1 This is a flowchart illustrating the multi-dimensional sensing and adjustment optimization method for kitchen appliance environmental parameters according to an embodiment of the present invention. Figure 1 As shown, the method includes: Collect data on cooking heat source temperature and cooking behavior; Based on the fluctuation pattern of cooking heat source temperature and the displacement trajectory of cooking behavior, the characteristics of cooking state are identified, and combined with the ratio of the rising velocity of oil fume particles to the velocity of surrounding airflow, spatiotemporal prediction information of oil fume movement is generated. Based on spatiotemporal prediction information, the cooking area is divided into multiple control blocks. A gradient air pressure control strategy is adopted to calculate the airflow guidance parameters of each control block and form a block airflow control scheme. Collect oil fume movement data from each control block. When an oil fume diffusion trend is detected, adjust the airflow parameters of adjacent control blocks according to the block airflow control scheme to establish a protective air field. Record the control effect of the protective air field on the oil fume, extract the correspondence between airflow parameters and control effect, generate optimal block airflow configuration information, and control the operation of environmental conditioning equipment based on the optimal block airflow configuration information.

[0020] In one optional implementation, based on the fluctuation pattern of the cooking heat source temperature and the displacement trajectory of the cooking behavior, cooking state characteristics are identified, and combined with the ratio of the rising velocity of oil fume particles to the velocity of the surrounding airflow, spatiotemporal prediction information of oil fume movement is generated, including: Collect cooking heat source temperature data, calculate the temperature change rate of adjacent sampling points, obtain temperature fluctuation curves, and determine the fluctuation pattern of cooking heat source temperature based on the frequency and peak amplitude of temperature change rate. Obtain the spatial coordinates of the cooking utensils, calculate the instantaneous velocity and instantaneous acceleration of the position coordinates, and determine the displacement trajectory of the cooking behavior based on the combined changes in the velocity and acceleration directions; By performing time-domain fusion of the abrupt change point of the fluctuation pattern with the motion component of the displacement trajectory, and identifying the cooking state characteristics based on the changing trends of the temperature gradient and motion component before and after the abrupt change point; Collect the surrounding airflow velocity at the time corresponding to the cooking state characteristics, and calculate the rising velocity of oil fume particles by combining the convection effect of the temperature field, and obtain the ratio relationship between the rising velocity of oil fume particles and the surrounding airflow velocity. Based on the fluctuation patterns of cooking state characteristics, displacement trajectories, and the gradient distribution of the ratio relationship in space, spatiotemporal prediction information for the movement of cooking fumes is generated.

[0021] In this embodiment, temperature data of the cooking heat source is first collected. An array of temperature sensors is arranged around the cooking heat source, and temperature data is collected every 100 milliseconds. For example, during a standard stir-fry process, the recorded temperature data sequence is: 120℃, 123℃, 128℃, 135℃, 142℃, 146℃, 148℃, 145℃, 143℃, 147℃, etc. Based on these temperature data, the rate of temperature change between adjacent sampling points is calculated. The rate of temperature change ΔT(t) at any time t is equal to the current temperature T(t) minus the previous temperature T(t-1) divided by the sampling time interval. Taking the above data as an example, the calculated temperature change rate sequence is: 30℃ / second, 50℃ / second, 70℃ / second, 70℃ / second, 40℃ / second, 20℃ / second, -30℃ / second, -20℃ / second, 40℃ / second, etc.

[0022] Frequency domain analysis was performed on the temperature change rate sequence to extract its frequency of change and peak amplitude. In practical applications, a sliding window technique was used, with a window size of 2 seconds and a step size of 0.5 seconds. For the data within each window, the number of peak occurrences of the temperature change rate and their corresponding amplitudes were counted. For example, within a 2-second window, three obvious temperature change rate peaks were detected, at 70℃ / second, -30℃ / second, and 40℃ / second, indicating that the temperature fluctuated frequently and significantly during this period, possibly corresponding to cooking operations such as stir-frying. Conversely, if there were fewer temperature change rate peaks and smaller amplitudes within the window, such as only two peaks at 20℃ / second and 10℃ / second, it might correspond to a gentle heating process.

[0023] By comparing and analyzing the temperature fluctuation characteristics at different times, several typical temperature fluctuation patterns of cooking heat sources are summarized: stable heating type (temperature rises slowly with small fluctuations in the rate of change), intermittent heating type (temperature fluctuates periodically with regular peaks and troughs in the rate of change), and intense stir-frying type (temperature fluctuates violently with frequent changes in the rate of change and large amplitudes).

[0024] Simultaneously, the spatial coordinates of the cooking appliance are also acquired. In this embodiment, a depth camera installed above the stovetop collects the three-dimensional coordinate data (x, y, z) of the cooking appliance (such as a pot) every 50 milliseconds. For example, the coordinate sequence recorded in a certain acquisition is: (50cm, 30cm, 10cm), (51cm, 31cm, 10cm), (53cm, 33cm, 11cm), (56cm, 36cm, 12cm), (58cm, 38cm, 12cm), etc. Based on these position coordinates, the instantaneous velocity and instantaneous acceleration of the cooking appliance are calculated. The instantaneous velocity is calculated by dividing the position difference between two adjacent acquisitions by the time interval, while the instantaneous acceleration is calculated by dividing the difference between two adjacent instantaneous velocities by the time interval.

[0025] By analyzing the combined changes in the instantaneous velocity and acceleration directions of cooking utensils, several typical displacement trajectories of cooking behaviors can be identified: linear movement (constant velocity direction, small acceleration), arc-shaped trajectory (smooth change in velocity direction, acceleration direction approximately perpendicular to the velocity direction), violent shaking (rapid changes in velocity and acceleration directions), and lifting away from the heat source (significantly positive velocity in the z-direction). For example, when the utensil's velocity is detected to exhibit periodic changes in the horizontal plane with gradually increasing amplitude, while its position in the z-direction remains essentially unchanged, this can be identified as a typical stir-frying action.

[0026] To accurately identify cooking state characteristics, abrupt changes in temperature fluctuation patterns are fused with the motion components of the displacement trajectory in the temporal domain. Specifically, when the time difference between a temperature abrupt change (rate of change exceeding ±80℃ / second) and a characteristic point of the displacement trajectory (such as a change in direction exceeding 60 degrees or a change in velocity exceeding 20cm / second) is less than 200 milliseconds, these two events are correlated. Subsequently, based on the temperature gradient and motion component change trends within 3 seconds before and after the abrupt change, the current cooking state characteristics are identified.

[0027] When the temperature is detected to rise sharply from 145℃ to 180℃ (the rate of change is 350℃ / second), and the cooking appliance exhibits a displacement trajectory of being thrown up and then falling (positive in the z direction first and then negative), it can be identified as a "tossing" operation; when the temperature suddenly drops from 160℃ to 120℃, and the position of the cooking appliance moves from the center of the heat source to the edge, it can be identified as a "removal from heat" operation.

[0028] Based on the identification of cooking state characteristics, the surrounding airflow velocity at corresponding moments is collected. An array of airflow velocity sensors installed above the cooking area measures the airflow velocity at different heights and horizontal positions. Airflow velocities measured at 10cm, 30cm, and 50cm directly above the heat source are 0.2m / s, 0.5m / s, and 0.3m / s, respectively. Combined with the acquired temperature field data, the rising velocity of the oil fume particles is calculated. Based on the principles of thermodynamics, when the heat source temperature is T℃, the theoretical initial rising velocity of the oil fume particles is related to T℃. -1 / 2 They are directly proportional. In practical applications, the system establishes a lookup table. For example, the initial rising velocity of oil fume particles at a temperature of 120℃ is approximately 0.3 m / s, and the rising velocity at a temperature of 180℃ is approximately 0.5 m / s.

[0029] By calculating the ratio of the rising velocity of oil fume particles to the velocity of the surrounding airflow at different spatial locations, the system obtained the spatial distribution of this key ratio. For example, at a height of 30cm directly above the heat source, when the "tossing" operation is detected, the rising velocity of the oil fume particles is 0.6m / s, the velocity of the surrounding airflow is 0.5m / s, and the ratio is 1.2; while at the same height 20cm horizontally from the heat source, this ratio decreases to 0.8.

[0030] Based on the identified cooking state characteristics, temperature fluctuation patterns, displacement trajectories, and gradient distribution of the ratio of oil fume velocity in space, spatiotemporal prediction information for oil fume movement is generated. This prediction information includes the trajectory, concentration distribution, and diffusion range of oil fume particles within the next 3-5 seconds. For example, when a "tossing" operation is detected, it is predicted that within 0.5 seconds after the operation, the oil fume will mainly concentrate in an area 40-60cm above the heat source and spread outwards to form a circular area with a radius of about 30cm; after 1.5 seconds, the oil fume will spread upwards to a height of 80-100cm, and the horizontal diffusion range will increase to a radius of 50cm.

[0031] In this embodiment, by sensing kitchen appliance environmental parameters in multiple dimensions, precise prediction and control of oil fume movement are achieved, demonstrating significant technical benefits. This method can adjust the operating parameters of the range hood in real time according to different cooking behaviors, improving oil fume capture efficiency and reducing energy consumption. Simultaneously, by accurately predicting the trajectory of oil fume movement, the operating strategy of the kitchen air circulation system can be optimized, improving indoor air quality. This method can also identify abnormal cooking states, promptly issuing safety alerts to prevent kitchen safety accidents. Furthermore, by establishing a mapping model between cooking behaviors and oil fume generation, it provides users with suggestions for optimizing their cooking behaviors, guiding them to develop healthier and more environmentally friendly cooking habits, and comprehensively improving the intelligence level of the kitchen environment and the user experience.

[0032] In one optional implementation, based on spatiotemporal prediction information, the cooking area is divided into multiple control blocks. A gradient pressure control strategy is adopted, and the airflow guidance parameters of each control block are calculated to form a block airflow control scheme, including: Based on spatiotemporal prediction information, the cooking area is divided into multiple control blocks using dynamic clustering. The temperature gradient and pressure gradient are calculated based on the residence time and diffusion rate of oil fume particles in each block. Collect oil fume concentration data for each control block, calculate the oil fume diffusion direction and diffusion rate by combining the temperature gradient change trend, and determine the oil fume movement trajectory based on the spatial distribution of the air pressure gradient. Based on the movement trajectory of the oil fume, an alternating high and low pressure gradient is established between adjacent control blocks. The inlet and outlet air flow rates of each control block are calculated, and the pressure gradient coefficient is determined based on the ratio of the inlet and outlet air flow rates. Calculate the airflow guidance parameters for each control block based on the pressure gradient coefficient, adjust the operating status of the air supply equipment to construct a directional airflow channel, and when the oil fume diffusion exceeds the preset diffusion range, adjust the air pressure step, record the adjustment effect of the air pressure step, and form a block airflow control scheme.

[0033] In a preferred embodiment, data from multiple sensors within the cooking area are first collected, including temperature data from a temperature sensor at five different heights (10cm, 30cm, 50cm, 70cm, and 100cm from the cooktop surface), and PM2.5 concentration data from 15 sampling points distributed throughout the cooking area. This data serves as the foundational input for spatiotemporal prediction information.

[0034] A dynamic clustering algorithm is used to divide the cooking area into four control blocks based on the oil fume concentration gradient and temperature distribution characteristics: a core cooking area (Area A), a cooking diffusion area (Area B), a transition area (Area C), and a peripheral area (Area D). Optionally, Area A is typically the area 0-40cm directly above the stove, Area B is the area 40-80cm around the stove, Area C is the area 80-150cm around the stove, and Area D is the outermost area. At least three temperature sensors and three oil fume concentration sensors are placed in each block to form a sensor network.

[0035] For each control block, the average residence time of oil fume particles was calculated. In the experimental environment, the residence time of oil fume in zone A was approximately 2-5 seconds, in zone B 5-10 seconds, in zone C 10-20 seconds, and in zone D 20-30 seconds. Simultaneously, the diffusion velocity of oil fume in each block was measured. Zone A had the fastest diffusion velocity, approximately 0.3-0.5 m / s, zone B 0.2-0.3 m / s, zone C 0.1-0.2 m / s, and zone D less than 0.1 m / s. Based on these data, the temperature gradient and pressure gradient values ​​for each block were calculated. The typical temperature gradient between zones A and B was approximately 15-25°C / m, and the pressure gradient was approximately 5-8 Pa / m.

[0036] Real-time data collection of cooking fume concentration in each control zone. Under standard cooking conditions, the PM2.5 concentration in zone A typically reaches 300-500 μg / m³. 3 Region B has a concentration of 150-300 μg / m³. 3 The concentration in region C is 50-150 μg / m 3 The concentration in region D is below 50 μg / m 3 The direction of oil fume diffusion is determined by the rate of change of the temperature gradient over a continuous 5-second period. When the temperature in area A rises rapidly (rate of change greater than 2°C / s), the upward diffusion trend of oil fumes strengthens; when there is lateral airflow in the surrounding environment (such as open doors and windows) causing the rate of temperature change in area B to exceed 1°C / s, oil fumes may diffuse laterally. The system calculates the main diffusion direction and rate of oil fumes by combining the temperature gradient change trends of each area.

[0037] The spatial distribution of air pressure gradients directly affects the trajectory of cooking fumes. By analyzing the air pressure differences between different zones, the main trajectory of the cooking fumes is determined. For example, when the air pressure difference between zone A and zone B reaches more than 5 Pa, and the air pressure in zone A is lower than that in zone B, the cooking fumes will mainly flow from zone B to zone A. The system plots the complete trajectory of the cooking fumes from generation to discharge, providing a basis for subsequent airflow control.

[0038] To construct an effective pressure gradient, an alternating high and low pressure structure is established between adjacent control blocks. A typical configuration is as follows: Zone A maintains the lowest pressure (relative pressure -5 Pa to -8 Pa), Zone B is set to relative pressure -2 Pa to -5 Pa, Zone C to relative pressure -1 Pa to -2 Pa, and Zone D to relative pressure 0 Pa to -1 Pa. This pressure gradient ensures that cooking fumes consistently accumulate in Zone A and are then exhausted. The system calculates the required inlet and outlet airflow rates for each block. The inlet-to-outlet airflow ratio is approximately 0.2:1 for Zone A, 0.5:1 for Zone B, 0.8:1 for Zone C, and 1.2:1 for Zone D. Based on these ratios, the pressure gradient coefficient is calculated.

[0039] The airflow guidance parameters for each control block are calculated based on the pressure gradient coefficient, including the supply air angle, supply air velocity, and exhaust air intensity. In this embodiment, an exhaust vent is installed above zone A, and the exhaust air intensity is set to 800-1000 m³ / h. 3 A ring-shaped air supply system is installed around Zone B, with an air supply angle of 45° pointing towards Zone A and an air supply velocity of 1.5-2.0 m / s. An auxiliary air supply device is installed in Zone C, with an air supply angle of 30° pointing towards Zone B and an air supply velocity of 1.0-1.5 m / s. An environmental airflow stabilization device is installed in Zone D to maintain a weak inward airflow (0.5-0.8 m / s). By adjusting these parameters, the system constructs a directional airflow channel, guiding the fumes to concentrate at the exhaust vent.

[0040] Continuous monitoring of the fume diffusion range; when the fume concentration detected by any sensor in area C exceeds 100 μg / m³ 3 If the concentration of any sensor in region D exceeds 50 μg / m³ for more than 10 seconds, or if the concentration of any sensor in region D exceeds 50 μg / m³, the concentration of any sensor in region D will exceed 50 μg / m³. 3 If the fume diffusion exceeds 5 seconds, it is determined that the fume diffusion has exceeded the preset range. At this time, the air pressure gradient is automatically adjusted, usually by increasing the pressure difference between zone A and zone B (e.g., reducing the pressure in zone A by 2 Pa), while simultaneously increasing the exhaust intensity (increasing it by 100-200 m³ / h) and adjusting the air supply angle in zone B (from 45° to 40°). The concentration change rate of each block is recorded after each adjustment. When the concentration decrease rate in zone C exceeds 30% / min and stabilizes, the current air pressure gradient configuration is recorded as an effective scheme.

[0041] The effects of multiple pressure gradient adjustments were evaluated, and the scheme with the highest smoke extraction efficiency (the fastest decrease in oil fume concentration in each zone) and lowest energy consumption was selected to form a zone airflow control scheme for this cooking scenario. This scheme includes the air pressure settings, supply air parameters, and exhaust air parameters for each zone, and can be saved as a cooking scenario template for use in similar cooking environments.

[0042] In this embodiment, by establishing a dynamic zoned air pressure control strategy, the flow of cooking fumes can be precisely guided, effectively preventing them from spreading to non-target areas. Gradient air pressure control can create directional airflow channels, improving fume collection efficiency. Through real-time monitoring and adaptive adjustment, the system can respond promptly to changes in operating conditions during cooking and dynamically optimize airflow organization. The solution also possesses self-learning capabilities, continuously improving control parameters by recording the effects of air pressure adjustments, thereby enhancing the system's adaptability and robustness. This zoned control method based on spatiotemporal prediction achieves more precise and energy-efficient fume control while reducing interference with the cooking process, improving overall fume removal efficiency and user experience.

[0043] In one optional implementation, based on the trajectory of the cooking fumes, an alternating high and low pressure gradient is established between adjacent control blocks. The inlet and outlet airflow rates of each control block are calculated, and the pressure gradient coefficient is determined based on the ratio of the inlet and outlet airflow rates, including: The system acquires the trajectory of cooking fumes and the location information of adjacent control blocks, calculates the spatial distance between control blocks, establishes a pressure transfer function based on the spatial distance, and generates the reference air pressure value and initial pressure increment for each control block. Based on the reference pressure value and the initial pressure increment, a pressure ladder with alternating high and low pressure is constructed between adjacent control blocks. The pressure attenuation coefficient of the pressure ladder is calculated, and the initial pressure ladder structure is formed according to the pressure attenuation coefficient. The inlet and outlet air flow rates of each control block under the initial pressure gradient structure are collected, the ratio of inlet to outlet air flow rates is calculated, the airflow accumulation state of each block is determined based on the ratio of inlet to outlet air flow rates, and the airflow regulation coefficient is calculated based on the airflow accumulation state. The oil fume concentration data of each control block is obtained, and the pressure correction amount is calculated in combination with the airflow regulation coefficient. The pressure increment in the pressure step is dynamically adjusted according to the pressure correction amount to generate the adjusted pressure step. Based on the adjusted pressure gradient, a multi-objective optimization function is constructed with airflow balance, system energy consumption, and airflow velocity as optimization objectives. The pressure gradient coefficient is obtained by solving the multi-objective optimization function.

[0044] In this embodiment, a multi-point sensor array is first used to acquire the trajectory data of the oil fume movement, and the flow path of the oil fume is collected by combining infrared imaging and gas concentration sensors. For a typical industrial kitchen, the space is divided into 10 control blocks, and each block is equipped with a pressure sensor, an airflow velocity sensor, and an oil fume concentration sensor. The spatial distance is determined by calculating the three-dimensional coordinate difference between adjacent control blocks. For example, the spatial distance between block A (3, 2, 1) and block B (4, 3, 1) is 1.414 meters.

[0045] Based on the acquired spatial distance data, a pressure transfer function was established. This function uses an inverse distance relationship to describe the pressure transfer efficiency: the transfer coefficient is 0.9 at a distance of 1 meter, and drops to 0.7 at a distance of 2 meters. Reference air pressure values ​​were set for 10 control blocks: -5 Pa for the kitchen work area, -20 Pa for the exhaust duct inlet, and other areas were assigned air pressure values ​​between -5 Pa and -20 Pa according to their relative positions. The initial pressure increment was set to ±2 Pa, with alternating changes between adjacent blocks.

[0046] When constructing the initial pressure gradient structure, a pressure attenuation coefficient is introduced, which is related to the distance between blocks and the number of obstacles. Measured data shows that the attenuation coefficient in open space is approximately 0.05 Pa / m, increasing to 0.12 Pa / m when obstacles are present. Taking blockchain ABCD as an example, the initial pressure configurations are -6 Pa, -8 Pa, -10 Pa, and -12 Pa, forming a linearly decreasing pressure gradient.

[0047] After completing the initial pressure gradient construction, the airflow monitoring phase begins. Airflow velocity is measured at the boundaries of each block using a hot-wire anemometer, and the inlet and outlet airflow rates are calculated. Under specific operating conditions, the inlet airflow rate for block B is 120 m³ / s. 3 / h, with an outlet flow rate of 100m³ / h. 3 / h, with an inflow-to-outflow ratio of 1.2, indicating airflow accumulation; the inflow rate for block C is 100m³ / h. 3 / h, with an outlet flow rate of 105m³ / h. 3 The inflow-to-outflow ratio is 0.95, indicating a slight loss of airflow. The ideal airflow ratio is set to 1.0 ± 0.05, and the airflow adjustment coefficient is calculated accordingly. The adjustment coefficient for block B is 0.8, and the adjustment coefficient for block C is 1.05.

[0048] The oil fume concentration data was collected using the light scattering method, recording the PM2.5 and VOCs concentrations in each block. The oil fume concentration in block B was 250 μg / m³. 3 200 μg / m 3 Based on the aforementioned airflow accumulation state, the system calculates a pressure correction of +1.5 Pa; the C concentration in the block is 180 μg / m³. 3 The pressure was below the threshold, and there was a slight loss of airflow, so the calculated pressure correction was -0.8 Pa. After applying these corrections, the air pressure in block B was adjusted to -9.5 Pa, and the air pressure in block C was adjusted to -9.2 Pa, breaking the original linear decreasing structure and forming an air pressure gradient that better reflects the actual distribution of cooking fumes.

[0049] Based on the adjusted pressure gradient, a multi-objective optimization function is constructed to solve for the pressure gradient coefficient. This function comprehensively considers three indicators: airflow balance, system energy consumption, and airflow velocity. Airflow balance is characterized by the standard deviation of the ratio of inflow to outflow in each block; the smaller the standard deviation, the higher the balance. System energy consumption is calculated by the power consumption of the exhaust fan and is proportional to the total pressure difference. The airflow velocity is required to achieve an effective capture velocity of 0.25-0.5 m / s in key areas (such as above the stove).

[0050] Through iterative optimization, the optimal pressure gradient coefficient was determined to be 0.08 Pa / m. 2 In practical applications, the system can dynamically adjust the pressure gradient coefficient according to the cooking conditions. During light cooking, the coefficient can be reduced to 0.05 Pa / m. 2 When subjected to intense stir-frying, the coefficient can increase to 0.12 Pa / m. 2It can also automatically adjust the center position of the pressure gradient according to changes in the cooking area, ensuring the directional guidance of cooking fumes. By constructing a precise pressure transmission model and air pressure gradient structure, it achieves refined control of the airflow field. Based on a multi-objective optimization pressure gradient adjustment method, it ensures effective fume control while considering system energy consumption. The solution effectively avoids airflow accumulation in local areas by monitoring the airflow accumulation state in real time and dynamically adjusting the pressure increment. Using airflow balance as the optimization objective improves the stability and reliability of the system. This air pressure control strategy based on the pressure transfer function not only improves the accuracy of fume collection but also achieves economic efficiency and high efficiency in system operation, providing reliable technical support for intelligent fume control.

[0051] like Figure 2 The diagram illustrates the process for controlling the diffusion of oil fumes and establishing a protective atmosphere in this embodiment.

[0052] In one optional implementation, data on the movement of oil fumes in each control block is collected. When an oil fume diffusion trend is detected, the airflow parameters of adjacent control blocks are adjusted according to the block airflow control scheme to establish a protective air field, including: The oil fume motion data of each control block is collected by an array of oil fume concentration sensors. The concentration gradient and rate of change of adjacent sampling points are calculated based on the airflow guidance parameters in the block airflow control scheme. The oil fume motion feature vector is established by combining the oil fume motion data. The oil fume diffusion trend is analyzed and detected based on the feature vector. According to the block airflow control scheme, the pressure transfer coefficient is calculated based on the detected oil fume diffusion trend, and the pressure value of each control block and the pressure gradient value between adjacent control blocks are set according to the pressure transfer coefficient. Collect airflow parameters for each control block, calculate the airflow field characteristics within the control block by combining airflow guidance parameters, and generate airflow parameter adjustment amounts for adjacent control blocks based on the airflow field characteristics. Adjust the supply and exhaust air parameters of adjacent control blocks according to the airflow parameter adjustment amount, update the pressure gradient value between blocks in real time, and when the airflow field characteristics of a block exceed the preset protection value, reset the pressure value and pressure gradient value of each control block according to the adjusted supply and exhaust air parameters to establish a protective air field.

[0053] This embodiment first deploys an array of oil fume concentration sensors in the kitchen space. This array consists of multiple miniature PM2.5 and VOC sensors, with at least three sensors installed in each control area, forming a sensor network covering the entire kitchen. Sampling period is 500 milliseconds, continuously collecting oil fume concentration data from each area to obtain PM2.5 concentration values, VOC concentration values, and their changing trends. For example, the sensor in the cooking area detects a PM2.5 concentration of 125 μg / m³. 3 The VOC concentration is 3.5 mg / m³. 3Furthermore, the growth rate reached 15% within 30 seconds, while the detection value in the adjacent food preparation area was 45 μg / m³. 3 and 1.2 mg / m 3 These data are recorded to form a dataset of oil fume movement.

[0054] The concentration gradient between adjacent sampling points is calculated based on the collected data by dividing the concentration difference between two adjacent sampling points by their physical distance. For example, if the cooking area and the food preparation area are 1.5 meters apart, the PM2.5 concentration gradient is (125-45) / 1.5 = 53.3 μg / m³. 3 / m. Simultaneously, the concentration change rate, i.e., the amount of concentration change per unit time, is calculated. The system records the PM2.5 concentration in the cooking area from 105 μg / m³ within 30 seconds. 3 Increased to 125 μg / m 3 The rate of change was 0.67 μg / m 3 / s.

[0055] A feature vector for oil fume movement is constructed by combining concentration data, concentration gradient, and rate of change. For each block, the feature vector includes parameters such as the PM2.5 concentration, VOC concentration, concentration gradient with adjacent blocks, and its own rate of change. The control system analyzes the oil fume diffusion trend based on these feature vectors. When the feature vector of a block shows that the concentration gradient direction points to the non-polluted area and the rate of change is consistently positive, it is determined that there is an oil fume diffusion trend.

[0056] The block airflow control scheme pre-sets airflow guidance parameters for each control block, including the location, angle, and airflow range of the air supply vents, as well as the location and exhaust capacity of the exhaust vents. For example, in the cooking area, the ceiling air supply vents are configured with an airflow velocity range of 0.3-0.8 m / s and an adjustable angle range of 15-45 degrees, while the side wall exhaust vents have an exhaust capacity of 800-2000 m³ / s. 3 / h. When the system detects a trend of cooking fumes spreading from the cooking area to the food preparation area, it calculates the pressure transfer coefficient based on the concentration gradient between the two areas. This coefficient represents the ratio of the expected pressure difference between adjacent areas to the concentration gradient. For example, when the concentration gradient is 53.3 μg / m³... 3 At a pressure of / m, the calculated pressure transfer coefficient is 0.15 Pa·m. 3 / μg means that a pressure difference of about 8Pa needs to be established between adjacent blocks.

[0057] The target pressure value for each control zone is set based on the calculated pressure transfer coefficient. For example, the cooking zone is set to -10 Pa (relative to atmospheric pressure), and the food preparation zone is set to -2 Pa, creating an airflow direction from the food preparation zone to the cooking zone with a pressure gradient of 5.3 Pa / m. Simultaneously, airflow parameters such as velocity, direction, and pressure are collected in real time using wind speed and pressure sensors installed within the control zones.

[0058] The control system combines preset airflow guidance parameters with real-time acquired airflow parameters to calculate the airflow field characteristics within the control block. These characteristics include indicators such as average wind speed, turbulence intensity, and airflow direction consistency within the block. For example, in the cooking area, the average wind speed is 0.5 m / s, the turbulence intensity is 20%, the airflow mainly flows towards the exhaust vent, and the airflow direction consistency is 75%. The system compares these characteristics with the ideal state required for the protective airfield and generates airflow parameter adjustment values.

[0059] The airflow parameter adjustment specifies the exact parameter values ​​that need to be adjusted for the supply and exhaust ventilation systems in each area. For example, when the average wind speed in the cooking area is lower than the required protection speed of 0.6 m / s, the system's adjustment includes increasing the supply air volume by 15% and adjusting the supply air angle from 25 degrees to 35 degrees. Correspondingly, the adjacent food preparation area needs to reduce the exhaust air volume by 10% to enhance the pressure gradient.

[0060] Based on the calculated adjustment values, the control system precisely adjusts the supply and exhaust air parameters by modifying the variable frequency fan speed, electric damper opening, and air supply angle in each zone. For example, the supply fan in the cooking area is adjusted from 45Hz to 52Hz to increase the supply air volume; simultaneously, the exhaust valve opening is increased from 65% to 85% to enhance exhaust capacity. In the food preparation area, the exhaust fan is reduced from 38Hz to 34Hz to decrease the exhaust air volume and increase the pressure difference with the cooking area.

[0061] After adjustment, the system monitors and updates the pressure gradient values ​​between blocks in real time. When the actual measured pressure gradient value deviates from the set value, or when the airflow characteristics of a block exceed the preset protection value, the system automatically triggers the protective air field reconstruction process. For example, when the concentration of cooking fumes increases in the food preparation area and the airflow consistency is less than 60%, the system determines that the protective air field has been damaged. It immediately recalculates and sets the pressure values ​​and pressure gradients of each block based on the latest supply and exhaust air parameters. For example, the pressure in the cooking area is adjusted to -12Pa, while the pressure in the food preparation area is maintained at -2Pa, increasing the pressure gradient to 6.7Pa / m, thus re-establishing a stronger protective air field and effectively blocking the diffusion of cooking fumes.

[0062] In one optional implementation, airflow parameters of each control block are collected, and airflow guidance parameters are combined to calculate the airflow field characteristics within the control block. Based on the airflow field characteristics, the airflow parameter adjustment amount for adjacent control blocks is generated, including: Collect airflow parameters for each control block, including wind speed data and pressure data; The direction of airflow is determined based on wind speed data, and the pressure change value is determined based on pressure data. The direction of airflow is compared with the airflow guidance parameters to obtain the airflow deviation. The characteristics of the airflow field in the control block are calculated based on the airflow deviation and the pressure change value. The correlation degree of airflow movement between adjacent control blocks is calculated based on the airflow field characteristics. The supply and exhaust air conditioning requirements of adjacent control blocks are determined based on the airflow movement correlation degree, and the airflow parameter adjustment amount of adjacent control blocks is generated.

[0063] In this embodiment, precise airflow control is achieved by collecting and analyzing airflow parameters from different control zones within the kitchen space. The kitchen space is functionally divided into several control zones, including a cooking area, a food preparation area, and a dining area. Each control zone is equipped with a sensor network system for real-time collection of airflow parameters.

[0064] The airflow parameter acquisition device includes an anemometer and a pressure sensor. The anemometer is a hot-wire anemometer with a sensitivity of 0.01 m / s and a measurement range of 0-20 m / s. The pressure sensor is a capacitive differential pressure sensor with an accuracy of ±0.5 Pa and a measurement range of -100 Pa to +100 Pa. The sensors are arranged in a grid pattern at the air inlets and outlets of the control block, as well as at key locations within the block, to ensure comprehensive acquisition of airflow parameters.

[0065] Airflow guidance parameters refer to the desired airflow direction and pressure distribution in each control zone, which are set by the system or defined by the user. For the cooking area, the airflow guidance parameters are usually set so that cooking fumes move upward and are exhausted through the exhaust system; for the food preparation area and dining area, the airflow guidance parameters are set so that fresh air is introduced from the air supply system and diffuses horizontally.

[0066] Airflow velocity vector data is acquired from wind speed sensors at a measurement frequency of 1 time / second to obtain the wind speed magnitude and direction at multiple points within the control block. The raw wind speed data is processed using a data smoothing and filtering algorithm to remove outliers and noise interference. Based on the processed wind speed data, a weighted average method is used to determine the overall airflow direction within the block. The weighting coefficients are adjusted according to the importance of the sensor locations: a weighting coefficient of 1.5 for sensors at critical locations and a weighting coefficient of 1.0 for sensors at general locations.

[0067] Pressure data processing also requires initial data filtering, using a moving average method to process the raw pressure data. The pressure change values ​​at each measuring point within adjacent sampling time intervals are calculated, and a pressure gradient distribution map is generated. The calculated airflow direction is then compared with preset airflow guidance parameters using a vector difference operation to obtain the airflow deviation vector. The magnitude of the deviation vector indicates the degree to which the airflow deviates from the expected direction, and the direction indicates the specific direction of deviation.

[0068] The airflow field characteristics are described in three dimensions: airflow turbulence intensity, airflow uniformity index, and pressure field stability. Airflow turbulence intensity is obtained by calculating the ratio of the standard deviation of wind speed to the average wind speed; the airflow uniformity index is determined by analyzing the dispersion of wind speed at each measuring point within the block; and pressure field stability is derived from time series analysis of pressure change values.

[0069] The correlation of airflow motion between adjacent control blocks is calculated based on the airflow exchange at the boundary. The wind speed vector and pressure difference at the boundary of adjacent blocks are analyzed to calculate the airflow flux and its direction. When the flux exceeds a preset threshold (e.g., 0.5m), the airflow flux is considered. 3 When the airflow velocity reaches a certain value (e.g., 0 / s), a significant airflow interaction is determined between the two blocks. The correlation degree of airflow motion ranges from 0 to 1, where 0 indicates no correlation and 1 indicates complete correlation. The correlation degree calculation takes into account factors such as flux magnitude, duration, and volatility.

[0070] The supply and exhaust air conditioning requirements are determined based on the correlation of airflow movement. When the correlation is higher than 0.7, the system determines that coordinated adjustment is required; when the correlation is between 0.3 and 0.7, a moderate level of coordination is implemented; when the correlation is lower than 0.3, independent adjustment is possible. The adjustment requirements also take into account the difference between the airflow field characteristics and the expected state; the greater the difference, the stronger the adjustment requirement.

[0071] An adaptive algorithm is used to generate airflow parameter adjustment values. A base adjustment value is calculated based on the difference between the airflow field characteristics and the expected state, and then corrected by considering the correlation effects of adjacent blocks. The adjustment values ​​include supply air volume adjustment values, exhaust air volume adjustment values, supply air angle adjustment values, and exhaust air angle adjustment values. For supply and exhaust air volume adjustments, percentage adjustment values ​​are calculated based on the relationship between the pressure difference and the expected pressure; for supply and exhaust air angle adjustments, angle adjustment values ​​are calculated based on the airflow motion deviation vector.

[0072] The adjustment command execution module receives the adjustment data and converts it into specific equipment control signals. Air supply system adjustment includes adjusting fan speed and guide vane angle; exhaust system adjustment includes adjusting exhaust fan speed and exhaust vent valve opening. A proportional-integral-derivative (PID) control algorithm is used to achieve smooth adjustment, avoiding discomfort caused by drastic fluctuations.

[0073] The multi-dimensional sensing and adjustment optimization method for kitchen appliance environmental parameters provided by this invention achieves precise control and intelligent adjustment of the airflow environment in the kitchen space. This method not only solves the problems of coarse adjustment and mutual interference between areas in traditional kitchen ventilation systems, but also allows for differentiated adjustments based on the actual needs of different zones. Based on the analysis of airflow field characteristics and the calculation of the correlation between adjacent zones, it can predict airflow change trends and adjust parameters in advance to avoid the diffusion of oil fumes and cross-contamination of odors. Simultaneously, the adaptive adjustment algorithm can continuously optimize control parameters according to environmental changes, reducing energy waste and improving user comfort. The overall solution achieves intelligent and refined management of the kitchen environment, significantly improving kitchen air quality and creating a healthy and comfortable cooking environment for users.

[0074] In one optional implementation, the control effect of the protective gas field on the cooking fumes is recorded, the correspondence between airflow parameters and control effects is extracted, optimal block airflow configuration information is generated, and the operation of the environmental conditioning equipment is controlled according to the optimal block airflow configuration information, including: Collect oil fume concentration data at the boundary of the protective gas field, calculate the spatial distribution and temporal variation of the oil fume concentration data, determine the boundary breach point based on the spatial distribution, calculate the oil fume diffusion intensity based on the temporal variation, and combine the boundary breach point and oil fume diffusion intensity to generate control effect data of the protective gas field. Establish a correspondence between the airflow parameters of each control block and the control effect data, extract the airflow parameter combination when the control effect data is optimal, and generate the optimal block airflow configuration information; Adjust the operating status of the environmental control equipment according to the optimal block airflow configuration information, and collect the control effect data after adjustment. When the control effect data decreases, update the airflow configuration information.

[0075] This embodiment records the control effect of the protective air field on cooking fumes, extracts the correspondence between airflow parameters and control effects, generates optimal block airflow configuration information, and thus achieves intelligent control of the operation of environmental control equipment. The protective air field refers to the airflow barrier formed by air supply and exhaust equipment in the kitchen space, used to prevent cooking fumes from spreading to non-cooking areas. The boundary of the protective air field is the interface between the airflow barrier and the surrounding air, and is a key area for evaluating the protective effect of the air field. In practical applications, the boundary of the protective air field is usually set as a closed curved surface extending outwards from the cooking area by a certain distance.

[0076] The oil fume concentration data acquisition employs a distributed sensor network, with oil fume concentration sensors evenly distributed at the boundary of the protective gas field. The sensors operate on the principle of light scattering, with a detection range of 0-1000 μg / m³. 3 The accuracy is ±5μg / m 3The sampling frequency is 5 times per minute. Sensors are arranged horizontally at 0.5 meters intervals and vertically at heights of 0.5 meters, 1 meter, and 1.5 meters, forming a three-dimensional monitoring network. Sensor data is transmitted in real-time to the central processing unit via a wireless network, enabling dynamic monitoring of oil fume concentration.

[0077] The spatial distribution calculation of oil fume concentration data employs an interpolation algorithm to expand the data from discrete sampling points into a continuous distribution field. Specifically, three-dimensional interpolation is performed on the data from each sampling point on the boundary of the protective air field to generate an oil fume concentration distribution map on the boundary surface. The spatial distribution data is updated every minute to reflect the dynamic changes in oil fume distribution. By comparing spatial distribution data from multiple consecutive frames, areas with consistently high oil fume concentrations can be identified; these areas are the boundary breach points.

[0078] The determination of the boundary breach point is based on the threshold judgment method. When the oil fume concentration in a certain area of ​​the boundary exceeds a preset threshold (such as 100 μg / m³), the boundary breach point is determined. 3 If the concentration of oil fume exceeds 30 seconds, the area is marked as a boundary breach point. To improve accuracy, the system also considers spatial continuity, i.e., the trend of oil fume concentration changes in adjacent areas, to avoid misjudgments due to sensor errors. Boundary breach points are divided into three levels according to severity: mild breach (100-200 μg / m³). 3 Moderate breakthrough (200-500 μg / m) 3 ) and severe breakthrough (>500 μg / m 3 ).

[0079] The calculation of oil fume diffusion intensity is based on time-varying value analysis. Oil fume concentration data is recorded for 5 consecutive minutes at each sampling point, and the rate of change between adjacent time points is calculated. A positive rate of change greater than a threshold (e.g., 20 μg / m³) is considered acceptable. 3 A rate of change of 1 / minute indicates that the oil fume is spreading rapidly; a positive rate of change but less than the threshold indicates that the oil fume is spreading slowly; a negative rate of change indicates that the oil fume concentration is decreasing and the protective effect is good. Based on the rate of change of each sampling point, a weighted average method is used to calculate the overall oil fume diffusion intensity. The weight coefficient is determined according to the importance of the sampling point location, with a weight of 1.5 for key locations (such as near the dining area) and a weight of 1.0 for general locations. The control effect data generation mechanism combines boundary breach point information with oil fume diffusion intensity for evaluation. Specifically, a scoring matrix is ​​constructed, where rows represent the severity of boundary breach points, columns represent the oil fume diffusion intensity level, and matrix elements are the corresponding combination effect scores. For example, when there are no boundary breach points and the oil fume diffusion intensity is negative, the score is 100 points; when there are severe breach points and the oil fume diffusion intensity is high, the score is 0 points. Through this scoring mechanism, control effect data ranging from 0 to 100 points is generated, with higher scores indicating better protective atmosphere effects.

[0080] The correspondence between airflow parameters and control effect data is established using data association analysis. Airflow parameter combinations and their corresponding control effect data under different operating conditions are recorded, forming airflow parameter-control effect data pairs. Airflow parameters include multi-dimensional data such as supply air volume, supply air angle, exhaust air volume, and exhaust air angle. By analyzing a large amount of historical data, the system identifies the airflow parameter characteristics corresponding to high control effect data, extracts frequently occurring parameter combinations, and generates parameter clusters.

[0081] The optimal airflow configuration information for each control block is generated based on cluster analysis results. The top 10% of control performance data are selected from historical data, and the corresponding airflow parameter combinations are extracted and their characteristics summarized. The summarization process considers the stability and adaptability of the parameters, discarding extreme values ​​and outlier combinations. The final optimal airflow configuration information for each control block includes the supply air volume range, supply air angle range, exhaust air volume range, and exhaust air angle range for each control block, as well as the ratios between these parameters. The configuration information is categorized and stored according to kitchen usage scenarios (such as high-oil cooking, slow simmering, etc.), forming a scenario-based configuration library.

[0082] The environmental control equipment employs a gradual adjustment strategy. Based on the current cooking scenario, the system retrieves the optimal airflow configuration information for the corresponding zone from the configuration library and compares it with the current operating parameters. To avoid user discomfort caused by sudden parameter changes, a progressive adjustment method is used, adjusting each parameter value step by step, with each adjustment not exceeding 20% ​​of the current value. The adjustment sequence is: first adjust the supply air system, then the exhaust system; first adjust the air volume, then the air direction. During the adjustment process, the control effect data of the protective air field is continuously monitored, forming a closed-loop feedback.

[0083] The system calculates the latest control performance data every minute and compares it with the baseline value before adjustment. When the control performance data increases, the current adjustment direction continues; when the control performance data decreases, the system pauses the current adjustment, reverts to the previous state, and attempts to adjust other parameters or change the adjustment direction. If the control performance data continues to decrease after three consecutive adjustments, the current scenario will be reassessed, and the system may switch to an alternative configuration.

[0084] In this embodiment, based on real-time monitoring and data analysis of oil fume concentration, weak points in the protective air field can be accurately identified, and airflow parameters can be intelligently adjusted to effectively control oil fume diffusion. Compared with traditional fixed parameter control, this method establishes a mapping relationship between airflow parameters and control effects, extracts the optimal configuration through historical data mining, and realizes the self-learning and evolution of the control strategy. Simultaneously, the closed-loop feedback mechanism ensures that the system can cope with dynamic changes during cooking and maintain the best protective effect. The overall solution significantly improves the intelligence level of kitchen air quality management, effectively solves the traditional problem of oil fume diffusion in kitchens, provides users with a healthier and more comfortable cooking environment, and reduces energy consumption through precise control, achieving a balance between environmental protection and comfort.

[0085] A second aspect of this invention provides a multi-dimensional sensing and adjustment optimization system for kitchen appliance environmental parameters, the system comprising: The first unit is used to collect data on cooking heat source temperature and cooking behavior. The second unit is used to identify cooking state characteristics based on the fluctuation pattern of cooking heat source temperature and the displacement trajectory of cooking behavior, and generate spatiotemporal prediction information of oil fume movement by combining the ratio of the rising velocity of oil fume particles to the velocity of the surrounding airflow. The third unit is used to divide the cooking area into multiple control blocks based on spatiotemporal prediction information, adopt a gradient air pressure control strategy, calculate the airflow guidance parameters of each control block, and form a block airflow control scheme. The fourth unit is used to collect the oil fume movement data of each control block. When the oil fume diffusion trend is detected, the airflow parameters of the adjacent control blocks are adjusted according to the block airflow control scheme to establish a protective air field. The fifth unit is used to record the control effect of the protective air field on the oil fume, extract the correspondence between airflow parameters and control effect, generate optimal block airflow configuration information, and control the operation of environmental conditioning equipment based on the optimal block airflow configuration information.

[0086] A third aspect of the present invention provides an electronic device, comprising: processor; Memory used to store processor-executable instructions; The processor is configured to invoke instructions stored in the memory to execute the aforementioned method.

[0087] A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the aforementioned method.

[0088] This invention can be a method, apparatus, system, and / or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for performing various aspects of the invention.

[0089] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for multi-dimensional sensing and adjustment optimization of kitchen appliance environmental parameters, characterized in that, include: Collect data on cooking heat source temperature and cooking behavior; Based on the fluctuation pattern of cooking heat source temperature and the displacement trajectory of cooking behavior, the characteristics of cooking state are identified, and combined with the ratio of the rising velocity of oil fume particles to the velocity of surrounding airflow, spatiotemporal prediction information of oil fume movement is generated. Based on spatiotemporal prediction information, the cooking area is divided into multiple control blocks. A gradient air pressure control strategy is adopted to calculate the airflow guidance parameters of each control block and form a block airflow control scheme. Collect oil fume movement data from each control block. When an oil fume diffusion trend is detected, adjust the airflow parameters of adjacent control blocks according to the block airflow control scheme to establish a protective air field. Record the control effect of the protective air field on the oil fume, extract the correspondence between airflow parameters and control effect, generate optimal block airflow configuration information, and control the operation of environmental conditioning equipment based on the optimal block airflow configuration information.

2. The method according to claim 1, characterized in that, Based on the fluctuation patterns of cooking heat source temperature and the displacement trajectory of cooking behavior, cooking state characteristics are identified. Combined with the ratio of the rising velocity of oil fume particles to the surrounding airflow velocity, spatiotemporal prediction information for oil fume movement is generated, including: Collect cooking heat source temperature data, calculate the temperature change rate of adjacent sampling points, obtain temperature fluctuation curves, and determine the fluctuation pattern of cooking heat source temperature based on the frequency and peak amplitude of temperature change rate. Obtain the spatial coordinates of the cooking utensils, calculate the instantaneous velocity and instantaneous acceleration of the position coordinates, and determine the displacement trajectory of the cooking behavior based on the combined changes in the velocity and acceleration directions; By performing time-domain fusion of the abrupt change point of the fluctuation pattern with the motion component of the displacement trajectory, and identifying the cooking state characteristics based on the changing trends of the temperature gradient and motion component before and after the abrupt change point; Collect the surrounding airflow velocity at the time corresponding to the cooking state characteristics, and calculate the rising velocity of oil fume particles by combining the convection effect of the temperature field, and obtain the ratio relationship between the rising velocity of oil fume particles and the surrounding airflow velocity. Based on the fluctuation patterns of cooking state characteristics, displacement trajectories, and the gradient distribution of the ratio relationship in space, spatiotemporal prediction information for the movement of cooking fumes is generated.

3. The method according to claim 1, characterized in that, Based on spatiotemporal prediction information, the cooking area is divided into multiple control blocks. A gradient pressure control strategy is adopted, and the airflow guidance parameters of each control block are calculated to form a block airflow control scheme, including: Based on spatiotemporal prediction information, the cooking area is divided into multiple control blocks using dynamic clustering. The temperature gradient and pressure gradient are calculated based on the residence time and diffusion rate of oil fume particles in each block. Collect oil fume concentration data for each control block, calculate the oil fume diffusion direction and diffusion rate by combining the temperature gradient change trend, and determine the oil fume movement trajectory based on the spatial distribution of the air pressure gradient. Based on the movement trajectory of the oil fume, an alternating high and low pressure gradient is established between adjacent control blocks. The inlet and outlet air flow rates of each control block are calculated, and the pressure gradient coefficient is determined based on the ratio of the inlet and outlet air flow rates. Calculate the airflow guidance parameters for each control block based on the pressure gradient coefficient, adjust the operating status of the air supply equipment to construct a directional airflow channel, and when the oil fume diffusion exceeds the preset diffusion range, adjust the air pressure step, record the adjustment effect of the air pressure step, and form a block airflow control scheme.

4. The method according to claim 1, characterized in that, Based on the trajectory of the cooking fumes, alternating high and low pressure gradients are established between adjacent control blocks. The inflow and outflow rates of each control block are calculated, and the pressure gradient coefficient is determined based on the ratio of the inflow and outflow rates, including: The system acquires the trajectory of cooking fumes and the location information of adjacent control blocks, calculates the spatial distance between control blocks, establishes a pressure transfer function based on the spatial distance, and generates the reference air pressure value and initial pressure increment for each control block. Based on the reference pressure value and the initial pressure increment, a pressure ladder with alternating high and low pressure is constructed between adjacent control blocks. The pressure attenuation coefficient of the pressure ladder is calculated, and the initial pressure ladder structure is formed according to the pressure attenuation coefficient. The inlet and outlet air flow rates of each control block under the initial pressure gradient structure are collected, the ratio of inlet to outlet air flow rates is calculated, the airflow accumulation state of each block is determined based on the ratio of inlet to outlet air flow rates, and the airflow regulation coefficient is calculated based on the airflow accumulation state. The oil fume concentration data of each control block is obtained, and the pressure correction amount is calculated in combination with the airflow regulation coefficient. The pressure increment in the pressure step is dynamically adjusted according to the pressure correction amount to generate the adjusted pressure step. Based on the adjusted pressure gradient, a multi-objective optimization function is constructed with airflow balance, system energy consumption, and airflow velocity as optimization objectives. The pressure gradient coefficient is obtained by solving the multi-objective optimization function.

5. The method according to claim 1, characterized in that, Collect oil fume movement data from each control block. When an oil fume diffusion trend is detected, adjust the airflow parameters of adjacent control blocks according to the block's airflow control scheme to establish a protective air field, including: The oil fume motion data of each control block is collected by an array of oil fume concentration sensors. The concentration gradient and rate of change of adjacent sampling points are calculated based on the airflow guidance parameters in the block airflow control scheme. The oil fume motion feature vector is established by combining the oil fume motion data. The oil fume diffusion trend is analyzed and detected based on the feature vector. According to the block airflow control scheme, the pressure transfer coefficient is calculated based on the detected oil fume diffusion trend, and the pressure value of each control block and the pressure gradient value between adjacent control blocks are set according to the pressure transfer coefficient. Collect airflow parameters for each control block, calculate the airflow field characteristics within the control block by combining airflow guidance parameters, and generate airflow parameter adjustment amounts for adjacent control blocks based on the airflow field characteristics. Adjust the supply and exhaust air parameters of adjacent control blocks according to the airflow parameter adjustment amount, update the pressure gradient value between blocks in real time, and when the airflow field characteristics of a block exceed the preset protection value, reset the pressure value and pressure gradient value of each control block according to the adjusted supply and exhaust air parameters to establish a protective air field.

6. The method according to claim 5, characterized in that, The airflow parameters of each control block are collected, and the airflow field characteristics within the control block are calculated in combination with the airflow guidance parameters. Based on the airflow field characteristics, the airflow parameter adjustment amounts for adjacent control blocks are generated, including: Collect airflow parameters for each control block, including wind speed data and pressure data; The direction of airflow is determined based on wind speed data, and the pressure change value is determined based on pressure data. The direction of airflow is compared with the airflow guidance parameters to obtain the airflow deviation. The characteristics of the airflow field in the control block are calculated based on the airflow deviation and the pressure change value. The correlation degree of airflow movement between adjacent control blocks is calculated based on the airflow field characteristics. The supply and exhaust air conditioning requirements of adjacent control blocks are determined based on the airflow movement correlation degree, and the airflow parameter adjustment amount of adjacent control blocks is generated.

7. The method according to claim 1, characterized in that, Record the control effect of the protective air field on cooking fumes, extract the correspondence between airflow parameters and control effects, generate optimal block airflow configuration information, and control the operation of environmental conditioning equipment based on the optimal block airflow configuration information, including: Collect oil fume concentration data at the boundary of the protective gas field, calculate the spatial distribution and temporal variation of the oil fume concentration data, determine the boundary breach point based on the spatial distribution, calculate the oil fume diffusion intensity based on the temporal variation, and combine the boundary breach point and oil fume diffusion intensity to generate control effect data of the protective gas field. Establish a correspondence between the airflow parameters of each control block and the control effect data, extract the airflow parameter combination when the control effect data is optimal, and generate the optimal block airflow configuration information; Adjust the operating status of the environmental control equipment according to the optimal block airflow configuration information, and collect the control effect data after adjustment. When the control effect data decreases, update the airflow configuration information.

8. A multi-dimensional sensing and adjustment optimization system for kitchen appliance environmental parameters, used to implement the method of any one of claims 1-7, characterized in that, include: The first unit is used to collect data on cooking heat source temperature and cooking behavior. The second unit is used to identify cooking state characteristics based on the fluctuation pattern of cooking heat source temperature and the displacement trajectory of cooking behavior, and generate spatiotemporal prediction information of oil fume movement by combining the ratio of the rising velocity of oil fume particles to the velocity of the surrounding airflow. The third unit is used to divide the cooking area into multiple control blocks based on spatiotemporal prediction information, adopt a gradient air pressure control strategy, calculate the airflow guidance parameters of each control block, and form a block airflow control scheme. The fourth unit is used to collect the oil fume movement data of each control block. When the oil fume diffusion trend is detected, the airflow parameters of the adjacent control blocks are adjusted according to the block airflow control scheme to establish a protective air field. The fifth unit is used to record the control effect of the protective air field on the oil fume, extract the correspondence between airflow parameters and control effect, generate optimal block airflow configuration information, and control the operation of environmental conditioning equipment based on the optimal block airflow configuration information.

9. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to invoke instructions stored in the memory to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the method described in any one of claims 1 to 7.

Images