Kitchen fume exhaust space vector control and air flow organization collaborative optimization management method and system

Abstract

This invention discloses a method and system for coordinated optimization management of kitchen exhaust space vector control and airflow organization, relating to the field of data processing technology. The invention constructs a kitchen space topology, deploys multiple sensors to collect data on oil fume concentration, temperature, wind speed, and equipment operation, and generates a structured environmental tensor through interpolation. It solves for a high-precision oil fume motion vector field, generating dynamic diffusion paths, locating the core oil fume area, dynamically marking personnel risk areas, and synthesizing the main diameter of the thermal plume. An LSTM model is used to predict equipment load and failure probability, generating a dynamic power consumption strategy. A multi-objective function is constructed, considering clearance rate, energy consumption, and comfort. A Pareto optimal solution set is output through a genetic algorithm, and a control scheme is dynamically selected according to operating conditions. Finally, the instructions are transformed into coordinated exhaust and replenishment air actions, and through real-time PID parameter tuning and closed-loop correction, energy consumption is reduced while improving oil fume clearance efficiency and precisely controlling the wind speed in the personnel area within a comfortable range.

Description

Technical Field

[0001] This invention belongs to the field of data processing technology, and specifically relates to a method and system for coordinated optimization management of kitchen exhaust space vector control and airflow organization. Background Technology

[0002] With the expansion of the catering industry and increasingly stringent environmental regulations, commercial kitchens face higher demands for air quality and energy efficiency management. Traditional ventilation systems generally suffer from the pain points of "high energy consumption and low precision"—exhaust volume is often estimated based on the number of stoves and fixed air volume, resulting in high energy waste during non-cooking periods; at the same time, the diffusion of cooking fumes is affected by factors such as the dynamic path of thermal plumes and interference from personnel activities, making it difficult for static ventilation schemes to effectively capture the core area of ​​cooking fumes, causing localized excessive fumes and occupational health risks. Therefore, it is still necessary to integrate environmental perception, fluid simulation, and intelligent decision-making technologies to achieve refined airflow organization and control.

[0003] In existing technologies, traditional fan speed regulation relies solely on simple temperature sensing or timing strategies, which cannot dynamically respond to the spatial diffusion characteristics of cooking fumes; localized exhaust leads to disordered airflow field, high retention rate of cooking fumes, and unbalanced airflow organization; kitchen exhaust systems lack energy efficiency synergy optimization mechanisms, resulting in serious energy waste. Summary of the Invention

[0004] (a) Technical problems to be solved

[0005] To address the problems in related technologies, this invention provides a method for coordinated optimization management of kitchen exhaust space vector control and airflow organization, in order to overcome the aforementioned technical problems existing in the prior art.

[0006] (II) Technical Solution

[0007] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution:

[0008] S1. Deploy multiple sensors based on kitchen space topology data; collect real-time environmental datasets and real-time kitchen operation data through multiple sensors;

[0009] S2. Based on the real-time environmental dataset, structured field data is obtained through the central difference method and Sobel operator; based on the structured field data, the final oil fume motion vector field is obtained by solving the dynamic equation; based on the final oil fume motion vector field, oil fume features are extracted and dynamic trajectory modeling is performed to obtain a dynamic vector map.

[0010] S3. Based on the real-time environmental dataset, threshold filtering of the oil fume concentration field is performed and cluster analysis is conducted to obtain the set of oil fume core areas;

[0011] The dynamic personnel zone is obtained through exposure risk assessment; based on the dynamic vector map, the thermal plume characteristics are quantified to obtain the main diameter of the thermal plume.

[0012] S4. Input the real-time kitchen operation data into the LSTM model trained using historical kitchen operation data to perform load prediction and failure probability prediction, and obtain the real-time dynamic power consumption strategy.

[0013] S5. Construct a multi-objective function based on a real-time dynamic power consumption strategy; based on the set of oil fume core areas, dynamic personnel areas, main diameter of thermal plumes, and the multi-objective function, obtain a Pareto optimal solution set through a multi-objective genetic algorithm; select the optimal solution from the Pareto optimal solution set according to real-time operating conditions.

[0014] S6. Transform the optimal solution into execution instructions, and perform coordinated optimization of airflow organization for exhaust control and make-up air control to obtain the final control instruction set;

[0015] S7. Perform deviation analysis on the execution effect data of the final control instruction set to obtain the control parameter correction amount; execute control based on the control parameter correction amount;

[0016] This invention collects kitchen environmental data in real time using multiple sensors, constructs a vector field for oil fume movement based on dynamic equations, and accurately identifies the core area of ​​oil fume, the area of ​​personnel activity, and the main path of the thermal plume. Based on an LSTM predictive dynamic power consumption strategy, it uses a multi-objective genetic algorithm to optimize the exhaust / makeup air scheme, generates collaborative control commands, and dynamically corrects parameters through closed-loop feedback, thereby improving the oil fume removal rate and reducing energy consumption and the response delay of the dynamic power consumption strategy. Closed-loop optimization ensures stability under complex operating conditions and reduces wind speed fluctuations in the personnel area. It achieves the effect of reducing energy consumption, improving oil fume removal efficiency, and accurately controlling the wind speed in the personnel area within a comfortable range.

[0017] Preferably, step S1 includes the following steps:

[0018] S11. By importing BIM models or scanning point clouds with lasers, collect precise coordinates of the stove, boundary coordinates of the personnel activity area, location and size of exhaust vents and air supply vents, as well as coordinates of obstacles, to obtain spatial topology data.

[0019] Establish a three-dimensional coordinate system, mark the positions of the stove area, personnel activity area and ventilation openings in the spatial topology data, and obtain a kitchen space coordinate mapping table;

[0020] S12. Deploy multiple sensors based on the kitchen space coordinate mapping table to obtain a sensor node location table; the multiple sensors include sensor types such as laser scattering oil fume sensor, three-dimensional ultrasonic anemometer, infrared temperature array and PM2.5 sensor;

[0021] All sensors in the sensor node location table are timestamped using the NTP protocol. Coordinate labels are added to each sampling point, and real-time data on oil fume concentration, wind speed, temperature, and PM2.5 are collected to obtain the raw sensor data stream. Energy consumption data, operating time, and equipment status data of the kitchen are collected to obtain real-time kitchen operation data.

[0022] S13. The original sensor data stream is reorganized by time slice segmentation, Kriging spatial interpolation is performed on the missing points in the original sensor data, and a structured tensor is constructed to obtain a real-time environmental dataset containing the oil fume concentration field, temperature field and wind speed vector field.

[0023] This invention constructs a millimeter-level spatial topology of the kitchen using BIM or laser scanning, deploys a multi-type sensor network based on a coordinate mapping table, and generates a structured environmental tensor using NTP timestamp synchronization and Kriging spatial interpolation; it achieves dynamic perception of oil fumes across the entire area, eliminates monitoring blind spots, and improves data integrity, laying a spatial data foundation for precise airflow control.

[0024] Preferably, step S2 includes the following steps:

[0025] S21. Unify the timestamps of all sensors and interpolate the discrete point data in the real-time environmental dataset into the grid to obtain the processed environmental data;

[0026] Based on the processed environmental data, the concentration gradient field, temperature gradient field, and wind speed gradient field were calculated using the central difference method and the Sobel operator, respectively, to obtain structured field data.

[0027] S22. Discretize the continuous equations in the structured field data into difference equations at grid points to obtain a set of discretized equations.

[0028] Calculate the concentration gradient, wind speed-temperature cross product term, and concentration-time derivative for each equation in the discretized equation set to obtain the current moment's oil fume motion vector field;

[0029] Add the κ-ε model correction term to the current moment's oil fume motion vector field to obtain the corrected oil fume motion vector field;

[0030] The final oil fume motion vector field is obtained by setting the wall boundary and the vent boundary of the modified oil fume motion vector field.

[0031] S23. Based on the final oil fume motion vector field, perform source strength calculation, source location and uncertainty analysis to obtain the oil fume source characteristics;

[0032] Based on the final oil fume motion vector field and oil fume source characteristics, particle tracking, thermal plume identification and diffusion direction analysis are performed on the oil fume source to obtain a dynamic vector map.

[0033] This invention calculates the concentration, temperature, and wind speed gradient fields using the central difference method and the Sobel operator, and corrects the boundary conditions using the κ-ε turbulence model to accurately solve the oil fume motion vector field. Based on particle tracking and thermal plume identification, it generates dynamic vector maps to achieve accurate prediction of oil fume diffusion paths. Compared with traditional models, it improves accuracy, eliminates airflow dead zones, and provides a core modeling foundation for precise wind control.

[0034] Preferably, step S3 includes the following steps:

[0035] S31. Standardize the concentration units of the oil fume concentration field in the real-time environmental dataset and match the timestamp of the final oil fume motion vector field to obtain the standardized oil fume concentration field.

[0036] Create a high-fume mask; label the standardized fume concentration field based on the high-fume mask to obtain a labeled concentration field;

[0037] S32. Set the neighborhood radius and minimum number of cluster points for the DBSCAN algorithm to obtain the parameters of the DBSCAN algorithm;

[0038] Cluster analysis of the labeled concentration field based on the parameters of the DBSCAN algorithm yields a group of spatially adjacent high-concentration points.

[0039] Noise points in spatially adjacent high-concentration point groups are removed, and the centroid position, equivalent radius, and peak concentration of each cluster are calculated to obtain the set of oil fume core areas.

[0040] S33. Based on the kitchen space topology combined with infrared positioning system thermal imaging dynamic tracking, the actual activity area of ​​personnel is obtained; the final oil fume motion vector field is superimposed on the actual activity area of ​​personnel, and the exposure index is calculated to obtain the real-time dynamic personnel area;

[0041] S34. By extracting the heat source of the stove from the dynamic vector diagram and calibrating the coefficients, the heat power of the stove is obtained; based on the heat power of the stove, the plume intensity in the dynamic vector diagram is calculated to obtain the plume intensity set;

[0042] A plume intensity threshold is set, and the plume intensities that are greater than the plume intensity threshold are filtered to obtain a high-intensity plume set; the plumes in the high-intensity plume set are then path-synthesized to obtain the main diameter of the thermal plume.

[0043] This invention uses high-concentration mask marking and DBSCAN spatial clustering to accurately locate the core area of ​​oil fume; combines infrared thermal imaging to dynamically track personnel positions and calculate real-time exposure indices to generate risk warning areas; and synthesizes the main diameter of the thermal plume based on thermal power calibration of plume intensity; thereby improving the targeted removal efficiency of oil fume sources and the speed of personnel risk response, and eliminating ventilation blind spots.

[0044] Preferably, step S4 includes the following steps:

[0045] S41. Collect historical energy consumption data, operating duration, and equipment status data to obtain historical operating data; classify the historical operating data into operating conditions based on the power change rate to obtain tagged historical operating data.

[0046] S42. Construct an LSTM model; set the weights of the LSTM model; train the LSTM model using historical running data, and combine the optimization algorithm during the training process to find the weights of the LSTM model and obtain the optimal solution; use the optimal solution as the weights of the LSTM model to obtain the optimized LSTM model.

[0047] S43. Input the real-time kitchen operation data into the final LSTM model to perform load prediction and fault probability prediction, and obtain the load prediction results and fault probability prediction results; based on the load prediction results and fault probability prediction results, generate a real-time dynamic power consumption strategy.

[0048] This invention uses an LSTM model to intelligently predict equipment load and failure probability, generating a dynamic power consumption strategy that includes fault avoidance, load response, and energy efficiency optimization; achieving fine-grained energy consumption control, reducing failure rate, saving energy during idle periods, and ensuring performance requirements during peak periods.

[0049] Preferably, step S5 includes the following steps:

[0050] S51. Unify the coordinates of the final oil fume motion vector field with the coordinates of the oil fume core area set, the dynamic personnel area, and the main diameter of the thermal plume into the same coordinate system, and perform timestamp alignment processing to obtain spatiotemporal aligned data.

[0051] Based on the coordinates of the core area of ​​oil fume and the coordinates of the dynamic personnel area in the spatiotemporally aligned data, the constraint boundary is extracted;

[0052] Based on the device parameter database, the device parameters are formatted to obtain physical limitation data;

[0053] S52. Construct a multi-objective function by minimizing total energy consumption, maximizing the clearance rate, and minimizing the deviation of wind speed from the comfort value in the personnel area; adjust the weight of total energy consumption in the multi-objective function based on a real-time dynamic power consumption strategy.

[0054] The upper limit of personnel concentration, vertical temperature difference constraint, physical limitation data, and constraint boundary are used as constraints for the multi-objective function; the fan speed and air delivery angle are used as decision variables for the multi-objective function.

[0055] S53. Find the Pareto front solution by combining a multi-objective genetic algorithm with a multi-objective function, and obtain the Pareto front solution set;

[0056] Collect real-time operating condition information; select the optimal solution from the Pareto optimal solution set based on the real-time operating condition information;

[0057] This invention constructs a three-objective function of fume removal rate, energy consumption, and comfort by aligning multi-source spatiotemporal data. Combined with equipment parameter constraints, it uses a multi-objective genetic algorithm to generate a Pareto optimal solution set. The strategy is dynamically selected according to the working conditions to reduce energy consumption while improving fume removal efficiency and accurately controlling the wind speed in the personnel area within a comfortable range.

[0058] Preferably, step S6 includes the following steps:

[0059] S61. Convert the optimal solution into execution instructions; obtain the actual exhaust system rotation speed based on the final oil fume motion vector field and the main diameter of the thermal plume.

[0060] Based on the actual exhaust system speed and the fan characteristic curve of the exhaust system, the exhaust scheme in the execution command is adjusted by PID to obtain the exhaust speed command.

[0061] S62. Based on the air replenishment scheme in the execution command, the joint angle is solved by solving the momentum equation and combining it with inverse kinematics, and the position of the servo motor is controlled to obtain the air replenishment speed command.

[0062] The exhaust fan speed command and the make-up air speed command together constitute the final control command set;

[0063] This invention dynamically calibrates the exhaust volume by using the oil fume motion vector field and the main diameter of the thermal plume, and generates precise speed commands by combining the PID parameter adjustment of the fan characteristic curve; the make-up air system drives the servo motor to deliver air in coordination based on the inverse solution of the momentum equation; it reduces the response delay of exhaust and make-up air, improves the matching degree of airflow organization, and eliminates the problem of oil fume retention caused by airflow turbulence.

[0064] Preferably, step S7 includes the following steps:

[0065] S71. Execute the instructions in the final control instruction set and collect the execution effect data to obtain the actual execution effect data; compare the actual execution effect data with the expected effect of the final control instruction set to obtain the deviation result;

[0066] S72. Perform PID correction based on the deviation results to obtain the control parameter correction amount; execute control based on the control parameter correction amount.

[0067] This invention generates deviation results by comparing real-time collected execution data with expected results, and uses PID closed-loop correction to dynamically adjust control parameters; thereby achieving continuous improvement in control accuracy, and maintaining stable energy consumption and oil fume removal efficiency during long-term operation, solving the control failure problem caused by operating condition drift in traditional systems.

[0068] The kitchen exhaust space vector control and airflow organization collaborative optimization management system is used to implement the above-mentioned kitchen exhaust space vector control and airflow organization collaborative optimization management method. It includes a sensor deployment and data acquisition module, a fume motion modeling and dynamic trajectory generation module, a fume core area identification and risk area positioning module, an equipment operation prediction and energy efficiency strategy generation module, a multi-objective collaborative optimization and decision generation module, and a control command execution and closed-loop feedback correction module.

[0069] The sensor deployment and data acquisition module is used for digital modeling and real-time data acquisition of the kitchen space. It acquires stove coordinates, boundaries of the activity area, ventilation vent locations, and obstacle information through BIM or laser scanning point clouds, constructs a three-dimensional spatial coordinate system, and generates a coordinate mapping table. Based on this, it deploys devices such as laser scattering fume sensors and three-dimensional ultrasonic anemometers to form a sensor node network. It synchronizes timestamps via the NTP protocol, collects fume concentration, wind speed, temperature, PM2.5, and equipment operation data, and generates a raw sensor data stream. The data is then segmented into time slices and spatially interpolated to construct a structured tensor dataset containing a fume concentration field, a temperature field, and a wind speed vector field.

[0070] The oil fume motion modeling and dynamic trajectory generation module is used for the quantitative analysis of oil fume motion patterns. It calculates the concentration gradient field, temperature gradient field, and wind speed gradient field using the central difference method and the Sobel operator to form structured field data. Combining the discretization of fluid dynamics equations, it introduces a κ-ε turbulence model to correct boundary conditions, outputting a high-precision oil fume motion vector field. Through oil fume source feature extraction and particle tracking and thermal plume identification, it generates a dynamic vector map, intuitively displaying the oil fume diffusion path and intensity changes.

[0071] The oil fume core area identification and risk area positioning module is used to realize dynamic monitoring of oil fume hotspots and personnel risks. After standardizing the oil fume concentration field, a high oil fume mask is generated through threshold filtering. The DBSCAN clustering algorithm is applied to identify spatially adjacent high-concentration clusters, and the centroid position and equivalent radius are calculated to form an oil fume core area set. Combined with infrared thermal imaging to track personnel activities, the exposure index is calculated by superimposing the oil fume motion vector field, and the dynamic personnel risk area is output. By extracting the heat source of the stove to calibrate the plume intensity, high-intensity plumes are screened and the main diameter of the thermal plume is synthesized, providing critical path basis for ventilation control.

[0072] The equipment operation prediction and energy efficiency strategy generation module uses machine learning to optimize equipment operation strategies; it collects historical energy consumption, operating duration and equipment status data, and classifies operating conditions according to power change rate; it trains LSTM model to predict real-time load and failure probability, and combines optimization algorithm to generate dynamic power consumption strategy, including three types of mechanisms: fault avoidance, load response and energy efficiency optimization, to achieve a balance between equipment safety and energy saving.

[0073] The multi-objective collaborative optimization and decision generation module integrates environmental and operational data to achieve global optimization; it unifies the spatiotemporal coordinates of the oil fume vector field, oil fume core area, personnel activity area, and thermal plume path, and extracts physical constraint boundaries; it constructs a multi-objective function with the objectives of "minimizing energy consumption, maximizing removal rate, and minimizing wind speed deviation in personnel area", takes fan speed and air delivery angle as decision variables, solves the Pareto front solution set through a multi-objective genetic algorithm, and dynamically selects the optimal solution based on real-time operating conditions;

[0074] The control command execution and closed-loop feedback correction module is responsible for command conversion and system optimization; it converts the optimal solution into exhaust and replenishment air control commands, and the exhaust system adjusts the speed of the fan based on the fan characteristic curve through PID; the replenishment air system drives the servo motor through the inverse solution of the momentum equation; after execution, it collects the actual effect data, compares it with the expected value to generate deviation results, and forms a closed-loop feedback by correcting the control parameters through PID, so as to ensure that the airflow organization and collaborative optimization effect is continuously improved.

[0075] (III) Beneficial Effects

[0076] The present invention has the following beneficial effects:

[0077] This invention achieves dynamic perception and accurate modeling, solving the problem of spatial diffusion blind spots. Through multi-sensor spatial topology deployment and Kriging spatial interpolation technology, it constructs accurate three-dimensional tensors of oil fume concentration field, temperature field, and wind speed field, solving the problem that traditional single sensors cannot track the migration path of oil fumes. Combined with the solution of dynamic equations corrected by the κ-ε turbulence model, it realizes dynamic prediction of oil fume motion vector field, achieving improved accuracy compared to static CFD models.

[0078] This invention achieves targeted control of oil fume sources and proactive risk avoidance for personnel; it identifies the core area of ​​oil fumes based on the DBSCAN clustering algorithm and generates a dynamic risk map by integrating infrared thermal imaging personnel tracking; it accurately captures the main path of heat source diffusion on the stove through thermal plume main path synthesis technology, thereby improving the directional suction efficiency of the exhaust system; and it has a real-time exposure index calculation function for personnel activity areas, which shortens the oil fume retention time and effectively reduces occupational health risks.

[0079] This invention achieves synergistic improvement in energy efficiency and equipment lifespan; it utilizes the LSTM operating condition prediction model to accurately identify peak, steady-state, and idle periods to generate dynamic power consumption strategies, reduces equipment loss rate through fault avoidance mechanisms, avoids overload tripping through load response mechanisms, and achieves energy savings through energy efficiency optimization mechanisms; and significantly reduces energy consumption compared to traditional timing control strategies.

[0080] This invention achieves airflow organization balance through multi-objective collaborative optimization. By constructing a three-objective function of clearance rate, energy consumption, and comfort, and combining it with a multi-objective genetic algorithm to generate a Pareto optimal solution set, the clearance rate is maximized during the peak cooking period, and the wind speed comfort control in the personnel area is prioritized during the idle period. Through a dynamic switching mechanism of the global energy consumption optimal solution, the exhaust and makeup air systems are coordinated to reduce the airflow organization turbulence rate.

[0081] This invention generates an instruction set based on PID tuning of the wind turbine characteristic curve and inverse solution of the momentum equation. After execution, the control parameters are automatically corrected through real-time deviation analysis. The system achieves closed-loop optimization, which continuously improves the matching degree between the control strategy and the actual operating conditions, thereby improving long-term operational stability.

[0082] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0083] To more clearly illustrate the technical solutions of the embodiments of the invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For those skilled in the art, the drawings can be obtained from these drawings without creative effort.

[0084] Figure 1 This is a flowchart illustrating the collaborative optimization management method for kitchen smoke exhaust space vector control and airflow organization according to the present invention.

[0085] Figure 2 This is a schematic diagram of the modules of the kitchen smoke exhaust space vector control and airflow organization collaborative optimization management system of the present invention. Detailed Implementation

[0086] The technical solutions of the embodiments of the invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the invention, and not all embodiments. Based on the embodiments of the invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the invention.

[0087] In the description of this invention, it should be understood that the terms "opening", "upper", "lower", "top", "middle", "inner", etc., which indicate orientation or positional relationship, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the invention.

[0088] Example 1:

[0089] Please see Figure 1 This invention discloses a method for coordinated optimization management of kitchen exhaust space vector control and airflow organization, comprising the following steps:

[0090] S1. Deploy multiple sensors based on kitchen space topology data; collect real-time environmental datasets and real-time kitchen operation data through multiple sensors;

[0091] S1 includes the following steps:

[0092] S11. Collect precise coordinates of the stove, boundary coordinates of the personnel activity area (polygon vertex set), location and size of exhaust / make-up air vents (including installation height), and coordinates of obstacles (kitchen cabinets / equipment / columns) by importing BIM model or laser scanning point cloud (accuracy ±5cm) to obtain spatial topology data.

[0093] Establish a three-dimensional coordinate system (the origin is usually set in the corner of the kitchen), and mark the positions of the stove area, the activity area and the ventilation opening in the spatial topology data to obtain a kitchen spatial coordinate mapping table;

[0094] S12. Deploy multiple sensors based on the kitchen space coordinate mapping table to obtain a sensor node location table; the multiple sensors include sensor types such as laser scattering oil fume sensor, three-dimensional ultrasonic anemometer, infrared temperature array and PM2.5 sensor;

[0095] All sensors in the sensor node location table are timestamped using the NTP protocol. Coordinate labels are added to each sampling point, and real-time data on oil fume concentration, wind speed, temperature, and PM2.5 are collected to obtain the raw sensor data stream. Energy consumption data, operating time, and equipment status data of the kitchen are collected to obtain real-time kitchen operation data.

[0096] S13. The original sensor data stream is reorganized by time slice segmentation, Kriging spatial interpolation is performed on the missing points in the original sensor data, and a structured tensor is constructed to obtain a real-time environmental dataset containing the oil fume concentration field, temperature field and wind speed vector field.

[0097] S2. Based on the real-time environmental dataset, structured field data is obtained through the central difference method and Sobel operator; based on the structured field data, the final oil fume motion vector field is obtained by solving the dynamic equation; oil fume features are extracted and combined with the final oil fume motion vector field to perform dynamic trajectory modeling, resulting in a dynamic vector map.

[0098] S2 includes the following steps:

[0099] S21. Unify the timestamps of all sensors and interpolate the discrete point data in the real-time environmental dataset into the grid to obtain the processed environmental data;

[0100] Based on the processed environmental data, the concentration gradient field, temperature gradient field, and wind speed gradient field were calculated using the central difference method and the Sobel operator, respectively, to obtain structured field data.

[0101] S22. Discretize the continuous equations in the structured field data into difference equations at grid points to obtain a set of discrete equations (each grid point has an independent equation).

[0102] Calculate the concentration gradient, wind speed-temperature cross product term, and concentration-time derivative for each equation in the discretized equation set to obtain the current moment's oil fume motion vector field;

[0103] Add the κ-ε model correction term to the current moment's oil fume motion vector field to obtain the corrected oil fume motion vector field;

[0104] The final oil fume motion vector field is obtained by setting the wall boundary and the vent boundary of the modified oil fume motion vector field.

[0105] S23. Based on the final oil fume motion vector field, perform source strength calculation, source location and uncertainty analysis to obtain the oil fume source characteristics;

[0106] Based on the final oil fume motion vector field and oil fume source characteristics, particle tracking, thermal plume identification and diffusion direction analysis are performed on the oil fume source to obtain a dynamic vector map.

[0107] S3. Based on the real-time environmental dataset, threshold filtering of the oil fume concentration field is performed and cluster analysis is conducted to obtain the set of oil fume core areas;

[0108] The dynamic personnel zone is obtained through exposure risk assessment; based on the dynamic vector map, the thermal plume characteristics are quantified to obtain the main diameter of the thermal plume.

[0109] S3 includes the following steps:

[0110] S31. Standardize the concentration units of the oil fume concentration field in the real-time environmental dataset and match the timestamp of the final oil fume motion vector field to obtain the standardized oil fume concentration field.

[0111] Create a high-fume mask, such as one where the fume concentration exceeds 50 mg / m³; label the standardized fume concentration field based on the high-fume mask to obtain a labeled concentration field.

[0112] S32. Set the neighborhood radius (experienced value at the kitchen scale) and minimum number of cluster points for the DBSCAN algorithm to obtain the parameters of the DBSCAN algorithm;

[0113] Cluster analysis of the labeled concentration field based on the parameters of the DBSCAN algorithm yields a group of spatially adjacent high-concentration points.

[0114] Noise points in spatially adjacent high-concentration point groups are removed, and the centroid position, equivalent radius, and peak concentration of each cluster are calculated to obtain the set of oil fume core areas.

[0115] S33. Based on the kitchen space topology combined with infrared positioning system thermal imaging dynamic tracking, the actual activity area of ​​personnel is obtained; the final oil fume motion vector field is superimposed on the actual activity area of ​​personnel, and the exposure index is calculated to obtain the real-time dynamic personnel area;

[0116] S34. By extracting the heat source of the stove from the dynamic vector diagram and calibrating the coefficients, the heat power of the stove is obtained; based on the heat power of the stove, the plume intensity in the dynamic vector diagram is calculated to obtain the plume intensity set;

[0117] A plume intensity threshold is set, and the plume intensities that are greater than the plume intensity threshold are filtered to obtain a high-intensity plume set; the plumes in the high-intensity plume set are then path-synthesized to obtain the main diameter of the thermal plume.

[0118] S4. Train the LSTM model using historical kitchen operation data to obtain the final LSTM model; input the real-time kitchen operation data into the final LSTM model to perform load prediction and fault probability prediction to obtain the real-time dynamic power consumption strategy.

[0119] S4 includes the following steps:

[0120] S41. Collect historical energy consumption data, operating duration, and equipment status data to obtain historical operating data; the energy consumption data is: {timestamp, device ID, power (kW)}, the operating duration is: {start time, end time, operating type}, and the equipment status is: {device ID, timestamp, operating status, fault code}.

[0121] Historical operating data is divided into operating conditions based on the power change rate to obtain tagged historical operating data; the operating conditions are as follows: if power > 0.5 kW / s: operating condition = "high-intensity period", elif 0.1 < power ≤ 0.5: operating condition = "steady state", else: operating condition = "idle";

[0122] S42. Construct an LSTM model; set the weights of the LSTM model; train the LSTM model using historical running data, and combine the optimization algorithm during the training process to find the weights of the LSTM model and obtain the optimal solution; use the optimal solution as the weights of the LSTM model to obtain the optimized LSTM model.

[0123] S43. Input the real-time kitchen operation data into the final LSTM model to perform load prediction and fault probability prediction, and obtain the load prediction results and fault probability prediction results; based on the load prediction results and fault probability prediction results, generate a real-time dynamic power consumption strategy.

[0124] Under the fault avoidance mechanism, when the probability of equipment failure exceeds 70%, the power during the peak operating period is limited to 80% of the rated value, the power during steady-state operation is reduced to 60%, and the power during the idle period is limited to 20% (fault isolation is achieved through step-by-step power reduction).

[0125] Under the load response mechanism, when the predicted peak power exceeds 8kW, the system maintains full power operation during the stir-frying period, reduces the steady-state power to 80%, and limits the power to 40% during the idle period (prioritizing the performance of the core cooking stage).

[0126] Under the energy efficiency optimization mechanism, during normal operation, the power is fully utilized during the stir-frying period (to meet thermodynamic requirements), the power is reduced to 70% during steady-state operation, and the power is limited to 30% during idle periods (to achieve a 30% conventional energy-saving effect).

[0127] S5. Construct a multi-objective function based on a real-time dynamic power consumption strategy; based on the final oil fume motion vector field, oil fume core area set, dynamic personnel area, main diameter of thermal plume, and multi-objective function, obtain a Pareto optimal solution set through a multi-objective genetic algorithm; select the optimal solution from the Pareto optimal solution set according to real-time operating conditions.

[0128] S5 includes the following steps:

[0129] S51. Unify the coordinates of the final oil fume motion vector field with the coordinates of the oil fume core area set, the dynamic personnel area, and the main diameter of the thermal plume into the same coordinate system, and perform timestamp alignment processing to obtain spatiotemporal aligned data.

[0130] Based on the coordinates of the core area of ​​oil fume and the coordinates of the dynamic personnel area in the spatiotemporally aligned data, the constraint boundary is extracted;

[0131] Based on the equipment parameter database (wind turbine power curve, angle range, etc.), the equipment parameters are formatted to obtain physical constraint data; the physical constraint data is used to set physical constraints for the equipment in multi-objective optimization.

[0132] S52. A multi-objective function is constructed by minimizing total energy consumption, maximizing clearance rate, and minimizing the deviation of wind speed from the comfort value in the personnel area; the multi-objective function is specifically as follows:

[0133] Minimize F ( x ) = [ f 1(x) , f 2(x) , f 3(x) ]

[0134] Among them, Minimize F ( x ) represents minimizing a multi-objective function. f 1(x) =Σ(fan power + make-up air system power)*Δ t Total energy consumption, Δ t Indicates the time step;

[0135] f 2(x) = -(∂C / ∂t)* V zone ∂C / ∂t represents the partial derivative of pollutant concentration C with respect to time t; it indicates the rate of change of pollutant concentration at a given instant. In a ventilation system, we prefer this value to be negative (concentration is decreasing). The larger the absolute value of (∂C / ∂t), the faster the pollutants are removed. The unit is mg / m³ / s. V zone Indicates the volume of the kitchen;

[0136] f 3(x) =Σ|vperson - vcomfort|, where vperson represents the actual wind speed in the personnel area. This is the actual wind speed calculated by sensors or simulation in the area where people are active (e.g., at the height and position of a person standing or sitting). It is determined by the fan speed and the angle of the air outlet, and the unit is meters per second (m / s). vcomfort represents the comfortable wind speed, which is a preset, ideal wind speed value. The range of wind speeds that people feel comfortable with varies depending on the season and activity level. For example, in winter, the comfortable wind speed may be lower (e.g., 0.15 m / s), while in summer it may be slightly higher (e.g., 0.25 m / s). vcomfort is this target value, and the unit is meters per second (m / s).

[0137] x As decision variables, x = [ n 1, n 2,..., n i ,... n k , i 1, i 2,..., i j ,..., i m ],in n i Indicates the first i The rotational speed of each fan k This indicates the total number of wind turbines. i j Indicates the first j The angle of the air vent m Indicates the total number of air outlets;

[0138] The weight of total energy consumption in the multi-objective function is adjusted based on a real-time dynamic power consumption strategy. Specifically, the weight coefficients of each sub-objective in the multi-objective function are dynamically adjusted according to the operating condition type (peak season, steady state, idle period) in the real-time dynamic power consumption strategy. w i Weighted aggregation can be used to solve a single-objective function or for individual ranking in multi-objective genetic algorithms. F weighted(x) = w 1* f 1(x) + w 2* f 2(x) + w 3* f 3(x) The weighting adjustment strategy is: increase during periods of speculative frenzy. f 2(x) The weights (i.e.) w 2 increases), steady-state period increases f 1(x) The weights (i.e.) w 1 increase), idle period improved f 3(x) The weights (i.e.) w 3 increase);

[0139] The upper limit of personnel concentration, vertical temperature difference constraint, physical limitation data, and constraint boundary are used as constraints for the multi-objective function; the fan speed and air delivery angle are used as decision variables for the multi-objective function.

[0140] S53. Find the Pareto front solution by combining a multi-objective genetic algorithm with a multi-objective function, and obtain the Pareto front solution set;

[0141] The specific steps of the multi-objective genetic algorithm include:

[0142] S531. Randomly generate an initial population containing N individuals, each individual representing a set of decision variables. x (Combination of fan speed and air delivery angle); Set maximum number of iterations

[0143] S532. Calculate the multi-objective function value for each individual in the population. F ( x );

[0144] Individuals in the population are stratified and ordered according to Pareto dominance;

[0145] Within the same non-dominated layer, calculate the crowding distance for each individual in the objective function space;

[0146] Parent individuals are selected based on non-dominance level and crowding, and crossover and mutation operations are performed to generate offspring populations.

[0147] The parent and offspring populations are merged, and non-dominated sorting and crowding calculations are performed. The top N individuals are selected as the new generation population.

[0148] S533, repeat S532 until the maximum number of iterations is reached, and finally output the non-dominated solution set as the Pareto front solution set;

[0149] S54. Collect real-time operating condition information; select the optimal solution from the Pareto optimal solution set based on the real-time operating condition information; if the operating condition is stir-frying, prioritize the solution with a high clearing rate; if the operating condition is steady state, prioritize the solution with low energy consumption; if the operating condition is idle, prioritize the solution with high comfort.

[0150] S6. The optimal solution is converted into execution instructions, and the airflow organization of exhaust control and make-up air control is optimized in coordination based on the final oil fume motion vector field and the main diameter of the thermal plume to obtain the final control instruction set.

[0151] S6 includes the following steps:

[0152] S61. Convert the optimal solution into execution instructions; obtain the actual exhaust system rotation speed based on the final oil fume motion vector field and the main diameter of the thermal plume.

[0153] Based on the actual exhaust system speed and the exhaust system fan characteristic curve (maximum air volume / power ratio), the exhaust scheme in the execution command is adjusted by PID to obtain the exhaust speed command;

[0154] S62. Based on the air supply scheme in the execution command, the joint angle is solved by solving the momentum equation and combining it with inverse kinematics, and the position control of the servo motor is used to obtain the air supply speed command; specifically, the air supply angle decision variable in the optimal solution is used. i j The angle of the air supply louver joint is solved by inverse kinematics. The specific solution process is based on the wind momentum equation M = r * A * v 2 sin i j Combined with the desired air delivery speed v and angle i j The required joint angle α for the servo motor to rotate is calculated by reverse calculation, and the formula is α = g( i j , v This is achieved through servo motor position control, which generates the air supply speed command; where M represents torque. r Let A represent the air density, A represent the effective force-bearing area of ​​the air supply louver joint, and g() represent the inverse kinematic mapping function.

[0155] The exhaust fan speed command and the make-up air speed command together constitute the final control command set;

[0156] S7. Perform deviation analysis on the execution effect data of the final control instruction set to obtain the control parameter correction amount; execute control based on the control parameter correction amount;

[0157] S7 includes the following steps:

[0158] S71. Execute the instructions in the final control instruction set and collect the execution effect data to obtain the actual execution effect data; compare the actual execution effect data with the expected effect of the final control instruction set to obtain the deviation result;

[0159] S72. Perform PID correction based on the deviation results to obtain the control parameter correction amount; execute control through the control parameter correction amount.

[0160] Example 2:

[0161] Please see Figure 2 The kitchen exhaust space vector control and airflow organization collaborative optimization management system is used to implement the above-mentioned kitchen exhaust space vector control and airflow organization collaborative optimization management method. It includes a sensor deployment and data acquisition module, a fume motion modeling and dynamic trajectory generation module, a fume core area identification and risk area positioning module, an equipment operation prediction and energy efficiency strategy generation module, a multi-objective collaborative optimization and decision generation module, and a control command execution and closed-loop feedback correction module.

[0162] The sensor deployment and data acquisition module is used for digital modeling and real-time data acquisition of the kitchen space. It acquires stove coordinates, boundaries of the activity area, ventilation vent locations, and obstacle information through BIM or laser scanning point clouds, constructs a three-dimensional spatial coordinate system, and generates a coordinate mapping table. Based on this, it deploys devices such as laser scattering fume sensors and three-dimensional ultrasonic anemometers to form a sensor node network. It synchronizes timestamps via the NTP protocol, collects fume concentration, wind speed, temperature, PM2.5, and equipment operation data, and generates a raw sensor data stream. The data is then segmented into time slices and spatially interpolated to construct a structured tensor dataset containing a fume concentration field, a temperature field, and a wind speed vector field.

[0163] The oil fume motion modeling and dynamic trajectory generation module is used for the quantitative analysis of oil fume motion patterns. It calculates the concentration gradient field, temperature gradient field, and wind speed gradient field using the central difference method and the Sobel operator to form structured field data. Combining the discretization of fluid dynamics equations, it introduces a κ-ε turbulence model to correct boundary conditions, outputting a high-precision oil fume motion vector field. Through oil fume source feature extraction and particle tracking and thermal plume identification, it generates a dynamic vector map, intuitively displaying the oil fume diffusion path and intensity changes.

[0164] The oil fume core area identification and risk area positioning module is used to realize dynamic monitoring of oil fume hotspots and personnel risks. After standardizing the oil fume concentration field, a high oil fume mask is generated through threshold filtering. The DBSCAN clustering algorithm is applied to identify spatially adjacent high-concentration clusters, and the centroid position and equivalent radius are calculated to form an oil fume core area set. Combined with infrared thermal imaging to track personnel activities, the exposure index is calculated by superimposing the oil fume motion vector field, and the dynamic personnel risk area is output. By extracting the heat source of the stove to calibrate the plume intensity, high-intensity plumes are screened and the main diameter of the thermal plume is synthesized, providing critical path basis for ventilation control.

[0165] The equipment operation prediction and energy efficiency strategy generation module uses machine learning to optimize equipment operation strategies; it collects historical energy consumption, operating duration and equipment status data, and classifies operating conditions according to power change rate; it trains LSTM model to predict real-time load and failure probability, and combines optimization algorithm to generate dynamic power consumption strategy, including three types of mechanisms: fault avoidance, load response and energy efficiency optimization, to achieve a balance between equipment safety and energy saving.

[0166] The multi-objective collaborative optimization and decision generation module integrates environmental and operational data to achieve global optimization; it unifies the spatiotemporal coordinates of the oil fume vector field, oil fume core area, personnel activity area, and thermal plume path, and extracts physical constraint boundaries; it constructs a multi-objective function with the objectives of "minimizing energy consumption, maximizing removal rate, and minimizing wind speed deviation in personnel area", takes fan speed and air delivery angle as decision variables, solves the Pareto front solution set through a multi-objective genetic algorithm, and dynamically selects the optimal solution based on real-time operating conditions;

[0167] The control command execution and closed-loop feedback correction module is responsible for command conversion and system optimization; it converts the optimal solution into exhaust and replenishment air control commands, and the exhaust system adjusts the speed of the fan based on the fan characteristic curve through PID; the replenishment air system drives the servo motor through the inverse solution of the momentum equation; after execution, it collects the actual effect data, compares it with the expected value to generate deviation results, and forms a closed-loop feedback by correcting the control parameters through PID, so as to ensure that the airflow organization and collaborative optimization effect is continuously improved.

[0168] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0169] The preferred embodiments of the invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention.

Claims

1. A method for coordinated optimization management of kitchen smoke exhaust space vector control and airflow organization, characterized in that, Includes the following steps: S1. Deploy multiple sensors based on kitchen space topology data; collect real-time environmental datasets and real-time kitchen operation data through multiple sensors; S2. Based on real-time environmental datasets, structured field data are obtained using the central difference method and the Sobel operator; Based on structured field data, the final motion vector field of oil fume is obtained by solving the dynamic equations; Based on the final motion vector field of the oil fume, the features of the oil fume are extracted and dynamic trajectory modeling is performed to obtain a dynamic vector map; S3. Based on the real-time environmental dataset, threshold filtering of the oil fume concentration field is performed and cluster analysis is conducted to obtain the set of oil fume core areas; Dynamic personnel zones are obtained through exposure risk assessment; Based on the dynamic vector map, thermal plume features are quantized to obtain the main diameter of the thermal plume. S3 includes the following steps: S31. Standardize the concentration units of the oil fume concentration field in the real-time environmental dataset and match the timestamp of the final oil fume motion vector field to obtain the standardized oil fume concentration field. Create a high-fume mask; label the standardized fume concentration field based on the high-fume mask to obtain a labeled concentration field; S32. Set the neighborhood radius and minimum number of cluster points for the DBSCAN algorithm to obtain the parameters of the DBSCAN algorithm; Cluster analysis of the labeled concentration field based on the parameters of the DBSCAN algorithm yields a group of spatially adjacent high-concentration points. Noise points in spatially adjacent high-concentration point groups are removed, and the centroid position, equivalent radius, and peak concentration of each cluster are calculated to obtain the set of oil fume core areas. S33. Based on the kitchen space topology combined with infrared positioning system thermal imaging dynamic tracking, the actual activity area of ​​personnel is obtained; the final oil fume motion vector field is superimposed on the actual activity area of ​​personnel, and the exposure index is calculated to obtain the real-time dynamic personnel area; S34. By extracting the heat source of the stove from the dynamic vector diagram and calibrating the coefficients, the heat power of the stove is obtained; based on the heat power of the stove, the plume intensity in the dynamic vector diagram is calculated to obtain the plume intensity set; A plume intensity threshold is set, and the plume intensities that are greater than the plume intensity threshold are filtered to obtain a high-intensity plume set; the plumes in the high-intensity plume set are then path-synthesized to obtain the main diameter of the thermal plume. S4. Input the real-time kitchen operation data into the LSTM model trained using historical kitchen operation data to perform load prediction and failure probability prediction, and obtain the real-time dynamic power consumption strategy. S4 includes the following steps: S41. Collect historical energy consumption data, operating duration, and equipment status data to obtain historical operating data; classify the historical operating data into operating conditions based on the power change rate to obtain tagged historical operating data. S42. Construct an LSTM model; set the weights of the LSTM model; train the LSTM model using historical running data, and combine the optimization algorithm during the training process to find the weights of the LSTM model and obtain the optimal solution; use the optimal solution as the weights of the LSTM model to obtain the optimized LSTM model. S43. Input the real-time kitchen operation data into the final LSTM model to perform load prediction and fault probability prediction, and obtain the load prediction results and fault probability prediction results; based on the load prediction results and fault probability prediction results, generate a real-time dynamic power consumption strategy. S5. Construct a multi-objective function based on a real-time dynamic power consumption strategy; based on the set of oil fume core areas, dynamic personnel areas, main diameter of thermal plumes, and the multi-objective function, obtain a Pareto optimal solution set through a multi-objective genetic algorithm; select the optimal solution from the Pareto optimal solution set according to real-time operating conditions. S6. Transform the optimal solution into execution instructions, and perform coordinated optimization of airflow organization for exhaust control and make-up air control to obtain the final control instruction set; S7. Perform deviation analysis on the execution effect data of the final control instruction set to obtain the control parameter correction amount; execute control based on the control parameter correction amount.

2. The method for coordinated optimization management of kitchen exhaust space vector control and airflow organization according to claim 1, characterized in that, S1 includes the following steps: S11. By importing BIM models or scanning point clouds with lasers, collect precise coordinates of the stove, boundary coordinates of the personnel activity area, location and size of exhaust vents and air supply vents, as well as coordinates of obstacles, to obtain spatial topology data. Establish a three-dimensional coordinate system, mark the positions of the stove area, personnel activity area and ventilation openings in the spatial topology data, and obtain a kitchen space coordinate mapping table; S12. Deploy multiple sensors based on the kitchen space coordinate mapping table to obtain a sensor node location table; the multiple sensors include sensor types such as laser scattering oil fume sensor, three-dimensional ultrasonic anemometer, infrared temperature array and PM2.5 sensor; All sensors in the sensor node location table are timestamped using the NTP protocol. Coordinate labels are added to each sampling point, and real-time data on oil fume concentration, wind speed, temperature, and PM2.5 are collected to obtain the raw sensor data stream. Energy consumption data, operating time, and equipment status data of the kitchen are collected to obtain real-time kitchen operation data. S13. The original sensor data stream is reorganized by time slice segmentation, Kriging spatial interpolation is performed on the missing points in the original sensor data, and a structured tensor is constructed to obtain a real-time environmental dataset containing the oil fume concentration field, temperature field and wind speed vector field.

3. The method for coordinated optimization management of kitchen exhaust space vector control and airflow organization according to claim 1, characterized in that, S2 includes the following steps: S21. Unify the timestamps of all sensors and interpolate the discrete point data in the real-time environmental dataset into the grid to obtain the processed environmental data; Based on the processed environmental data, the concentration gradient field, temperature gradient field, and wind speed gradient field were calculated using the central difference method and the Sobel operator, respectively, to obtain structured field data. S22. Discretize the continuous equations in the structured field data into difference equations at grid points to obtain a set of discretized equations. Calculate the concentration gradient, wind speed-temperature cross product term, and concentration-time derivative for each equation in the discretized equation set to obtain the current moment's oil fume motion vector field; Add the κ-ε model correction term to the current moment's oil fume motion vector field to obtain the corrected oil fume motion vector field; The final oil fume motion vector field is obtained by setting the wall boundary and the vent boundary of the modified oil fume motion vector field. S23. Based on the final oil fume motion vector field, perform source strength calculation, source location and uncertainty analysis to obtain the oil fume source characteristics; Based on the final oil fume motion vector field and oil fume source characteristics, particle tracking, thermal plume identification, and diffusion direction analysis are performed on the oil fume source to obtain a dynamic vector map.

4. The method for coordinated optimization management of kitchen exhaust space vector control and airflow organization according to claim 1, characterized in that, S5 includes the following steps: S51. Unify the coordinates of the final oil fume motion vector field with the coordinates of the oil fume core area set, the dynamic personnel area, and the main diameter of the thermal plume into the same coordinate system, and perform timestamp alignment processing to obtain spatiotemporal aligned data. Based on the coordinates of the core area of ​​oil fume and the coordinates of the dynamic personnel area in the spatiotemporally aligned data, the constraint boundary is extracted; Based on the device parameter database, the device parameters are formatted to obtain physical limitation data; S52. Construct a multi-objective function by minimizing total energy consumption, maximizing the clearance rate, and minimizing the deviation of wind speed from the comfort value in the personnel area; adjust the weight of total energy consumption in the multi-objective function based on a real-time dynamic power consumption strategy. The upper limit of personnel concentration, vertical temperature difference constraint, physical limitation data, and constraint boundary are used as constraints for the multi-objective function; the fan speed and air delivery angle are used as decision variables for the multi-objective function. S53. Find the Pareto front solution by combining a multi-objective genetic algorithm with a multi-objective function, and obtain the Pareto front solution set; Collect real-time operating condition information; select the optimal solution from the Pareto optimal solution set based on the real-time operating condition information.

5. The method for coordinated optimization management of kitchen exhaust space vector control and airflow organization according to claim 1, characterized in that, S6 includes the following steps: S61. Convert the optimal solution into execution instructions; obtain the actual exhaust system rotation speed based on the final oil fume motion vector field and the main diameter of the thermal plume. Based on the actual exhaust system speed and the fan characteristic curve of the exhaust system, the exhaust scheme in the execution command is adjusted by PID to obtain the exhaust speed command. S62. Based on the air replenishment scheme in the execution command, the joint angle is solved by solving the momentum equation and combining it with inverse kinematics, and the position of the servo motor is controlled to obtain the air replenishment speed command. The exhaust fan speed command and the make-up air speed command together constitute the final control command set.

6. The method for coordinated optimization management of kitchen exhaust space vector control and airflow organization according to claim 1, characterized in that, S7 includes the following steps: S71. Execute the instructions in the final control instruction set and collect the execution effect data to obtain the actual execution effect data; compare the actual execution effect data with the expected effect of the final control instruction set to obtain the deviation result; S72. Perform PID correction based on the deviation results to obtain the control parameter correction amount; execute control through the control parameter correction amount.

7. A kitchen exhaust space vector control and airflow organization collaborative optimization management system, characterized in that, The method for coordinated optimization management of kitchen exhaust space vector control and airflow organization as described in any one of claims 1-6 includes a sensor deployment and data acquisition module, an oil fume motion modeling and dynamic trajectory generation module, an oil fume core area identification and risk area positioning module, an equipment operation prediction and energy efficiency strategy generation module, a multi-objective coordinated optimization and decision generation module, and a control command execution and closed-loop feedback correction module.

8. A storage medium, characterized in that, It stores a program that, when executed by a processor, implements the kitchen exhaust space vector control and airflow organization collaborative optimization management method as described in any one of claims 1-6.

Images