Energy-saving control method and system for ultra-low lampblack emission all-in-one machine and medium

Abstract

The invention relates to the technical field of energy-saving control, and discloses an energy-saving control method and system for an ultra-low lampblack emission all-in-one machine and a medium. The method comprises the following steps: collecting oil fume parameters through multiple sensors, and obtaining concentration, rotating speed, power, temperature and pollutant data; performing feature extraction and classification on the parameters, identifying a cooking scene and determining control parameters; performing energy consumption optimization calculation based on the scene and the parameter to obtain a control instruction; and adjusting the instruction through the hierarchical structure, and evaluating the operation state to obtain energy-saving feedback data. By intelligently identifying the cooking scene and dynamically optimizing the control parameters, the optimal balance between the purification efficiency and the energy consumption is realized. Layered control and a multi-dimensional evaluation mechanism are adopted, and cooperative work and real-time optimization of equipment are ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of energy-saving control, in particular to an energy-saving control method and system for an oil fume ultra-low emission integrated machine and a medium. BACKGROUND

[0002] Currently, the oil fume purification equipment in the catering industry usually adopts a separation processing mode of the extractor hood and the oil fume purifier, that is, the oil fume is collected by the extractor hood and then transmitted to the oil fume purifier outside the building through the flue for processing. This traditional oil fume processing mode generally has the characteristics of long oil fume pipeline and large equipment space occupation. A general oil fume purification system includes multiple components such as an extractor hood, a smoke exhaust pipeline, a fan, and an electrostatic purification device. These components are installed separately, which not only increases the installation difficulty but also occupies a large amount of space. At the same time, the control mode of the traditional oil fume purification equipment is mostly simple on-off control or timing control, that is, the equipment operating parameters such as fan speed and purification intensity are fixed or can only be manually adjusted, lacking an intelligent automatic control mechanism.

[0003] However, this traditional oil fume processing mode has obvious deficiencies. First, due to the use of fixed parameter control, the working parameters cannot be dynamically adjusted according to the actual cooking situation, and the energy consumption cannot be reduced during light cooking, while the purification effect may be poor during heavy cooking. Second, the collaboration between devices is poor, and each component works independently, lacking overall energy efficiency optimization control, resulting in serious energy waste. Third, the smoke exhaust pipeline is long, the installation is complex, and it needs to be cleaned regularly, with high maintenance cost. Fourth, the traditional oil fume purification equipment lacks real-time monitoring and feedback mechanism, and cannot adjust the control strategy in time according to the purification effect, resulting in unstable purification effect. Especially in the intensive area of the catering industry, the problem of non-compliance of oil fume emission is prominent, which not only affects the environmental quality but also easily causes complaints from surrounding residents, causing trouble to the operation of catering enterprises.

[0004] In view of the above deficiencies, a new type of equipment that integrates the extractor hood and the purifier and has intelligent energy-saving control function is urgently needed. This equipment should be able to sense the oil fume situation in real time, automatically adjust the control parameters according to different cooking scenes, and achieve the optimal balance between energy consumption and purification effect. At the same time, it also needs to have the parameter self-optimization ability, constantly improve the control strategy through multi-dimensional data analysis, and adapt to various cooking environments and use habits. In addition, the components of the equipment should realize collaborative control to form an organic whole, maximize the use of energy and reduce waste. A complete monitoring and feedback mechanism is also essential. Only through continuous state monitoring and performance evaluation can the equipment maintain a long-term stable and efficient energy-saving operation state, and truly solve the dual problems of oil fume emission and energy consumption. SUMMARY

[0005] The application provides an energy-saving control method and system for an oil fume ultra-low emission integrated machine, which realizes optimal balance between purification efficiency and energy consumption by intelligently identifying cooking scenes and dynamically optimizing control parameters. The layered control and multi-dimensional evaluation mechanism are adopted to ensure the collaborative work and real-time optimization of the equipment.

[0006] In a first aspect, the application provides an energy-saving control method for an oil fume ultra-low emission integrated machine, which comprises: collecting oil fume related parameters by a plurality of sensors arranged in the oil fume ultra-low emission integrated machine to obtain oil fume concentration data, fan speed data, equipment power data, temperature data and pollutant concentration data; performing feature extraction and classification processing on the oil fume related parameters to obtain a scene category representing the current kitchen cooking state and a corresponding control parameter combination; performing energy consumption optimization calculation based on the scene category and the control parameter combination to obtain a target control instruction; executing equipment adjustment through a layered control structure and evaluating and analyzing the running state data to obtain energy-saving control feedback data.

[0007] In a first implementation of the first aspect, the collecting of the oil fume related parameters by the plurality of sensors arranged in the oil fume ultra-low emission integrated machine to obtain the oil fume concentration data, the fan speed data, the equipment power data, the temperature data and the pollutant concentration data comprises: real-time monitoring of the oil fume at the air inlet position by an oil fume concentration sensor to obtain the oil fume concentration data; collecting the temperatures of the kitchen environment, the air inlet and the air outlet by a temperature sensor to obtain the temperature data; measuring the current and voltage at the equipment power inlet by a power monitoring module to obtain the equipment power data; monitoring the rotation speed of the centrifugal fan by a fan speed sensor to obtain the fan speed data; detecting the pollutant content in the oil fume gas by a gas composition analyzer to obtain the pollutant concentration data; and performing digital processing and outlier filtering on the oil fume concentration data, the temperature data, the equipment power data, the fan speed data and the pollutant concentration data to obtain the oil fume related parameters.

[0008] In a second implementation form of the first aspect, the feature extraction and classification processing on the oil fume related parameters to obtain the scene category representing the current kitchen cooking state and the corresponding control parameter combination comprises: performing standardization processing on the oil fume related parameters to obtain standardized feature data with unified value range; inputting the standardized feature data into a support vector machine classifier to obtain the category and probability value of the current cooking scene; dividing the current cooking state into an idle mode, a preparation mode, a light cooking mode, a medium cooking mode or a heavy cooking mode according to the category; performing time smoothing processing on the cooking scene category to obtain a stable scene judgment result; selecting a corresponding basic control parameter according to the stable scene judgment result to obtain an initial control parameter combination comprising a fan rotating speed value, a purification unit working intensity value and a heat exchange system working intensity value; and performing dynamic adjustment on the initial control parameter combination according to the environmental temperature and the change rate of the oil fume concentration to obtain the corresponding control parameter combination.

[0009] In a third implementation form of the first aspect, the energy consumption optimization calculation based on the scene category and the control parameter combination to obtain the target control instruction comprises: setting a fan rotating speed range, a purification unit working intensity range and a heat exchange system working intensity range according to the scene category to obtain a control parameter optimization interval; performing energy consumption calculation on the fan rotating speed value, the purification unit working intensity value and the heat exchange system working intensity value in the control parameter combination to obtain a current energy consumption value; calculating the required minimum purification efficiency according to the oil fume concentration data and the pollutant concentration data to obtain a purification constraint condition; adjusting the fan rotating speed value in the control parameter optimization interval and calculating the energy consumption change rate after adjustment to obtain a fan energy consumption optimization value; adjusting the purification unit working intensity value and the heat exchange system working intensity value in the control parameter optimization interval to obtain a minimum energy consumption combination that meets the purification constraint condition; and integrating the fan energy consumption optimization value and the minimum energy consumption combination into a control instruction to obtain the target control instruction.

[0010] In a fourth implementation form of the first aspect, the adjusting the purification unit working intensity value and the heat exchange system working intensity value in the control parameter optimization interval to obtain the lowest energy consumption combination under the purification constraint condition comprises: discretely sampling the purification unit working intensity value in a range from a minimum value to a maximum value according to a set step size to obtain a purification unit working intensity sampling point set; discretely sampling the heat exchange system working intensity value in a range from a minimum value to a maximum value according to a set step size to obtain a heat exchange system working intensity sampling point set; performing orthogonal combination on the purification unit working intensity sampling point set and the heat exchange system working intensity sampling point set to obtain a working intensity parameter combination matrix; calculating an energy consumption value and a purification efficiency value of each combination point in the working intensity parameter combination matrix to obtain a combination point performance evaluation result; screening a combination point set satisfying the purification constraint condition from the combination point performance evaluation result to obtain an effective control parameter subset; and searching for a parameter combination with the lowest energy consumption in the effective control parameter subset to obtain the lowest energy consumption combination.

[0011] In a fifth implementation form of the first aspect, the orthogonal combination of the purification unit working intensity sampling point set and the heat exchange system working intensity sampling point set to obtain a working intensity parameter combination matrix comprises: determining a row and column number of an orthogonal test table according to a size of the purification unit working intensity sampling point set and a size of the heat exchange system working intensity sampling point set to obtain an orthogonal test design scheme; distributing sampling points in the purification unit working intensity sampling point set into corresponding columns of the orthogonal test table according to an equal interval principle to obtain test level values of the purification unit working intensity; distributing sampling points in the heat exchange system working intensity sampling point set into corresponding columns of the orthogonal test table according to an equal interval principle to obtain test level values of the heat exchange system working intensity; performing orthogonal combination arrangement on the test level values to generate a test combination scheme to obtain optimized combination points with reduced test times; calculating an energy consumption contribution degree and a purification efficiency contribution degree corresponding to each of the optimized combination points to obtain a parameter sensitivity analysis result; and supplementally sampling the optimized combination points based on the parameter sensitivity analysis result to obtain the working intensity parameter combination matrix.

[0012] In a sixth implementation form of the first aspect, the adjusting the target control instruction through the hierarchical control structure and the evaluating and analyzing the running state data to obtain the energy-saving control feedback data comprises: decomposing the target control instruction into decision layer instruction, coordination layer instruction and execution layer instruction to obtain control tasks of each layer; transmitting the coordination layer instruction to each subsystem controller through a control bus to obtain a fan control instruction, an oil-water separation control instruction, a filtration control instruction, a purification control instruction and a heat exchange control instruction; adjusting corresponding physical component parameters according to the execution layer instruction by each execution unit to obtain fan speed adjustment, purification unit working intensity adjustment and heat exchange system working intensity adjustment; collecting adjusted equipment running state information to obtain real-time energy consumption data, purification efficiency data and equipment health state data; performing multi-dimensional evaluation on the real-time energy consumption data, the purification efficiency data and the equipment health state data to obtain performance evaluation indexes; comparing and analyzing the performance evaluation indexes with expected targets to obtain the energy-saving control feedback data.

[0013] In a second aspect, the application provides an energy-saving control system for an oil fume ultra-low emission all-in-one machine, comprising: a collection module configured to collect oil fume related parameters through a plurality of sensors arranged in the oil fume ultra-low emission all-in-one machine to obtain oil fume concentration data, fan speed data, equipment power data, temperature data and pollutant concentration data; a classification module configured to perform feature extraction and classification processing on the oil fume related parameters to obtain a scene category representing a current kitchen cooking state and a corresponding control parameter combination; a calculation module configured to perform energy consumption optimization calculation based on the scene category and the control parameter combination to obtain a target control instruction; an adjusting module configured to adjust the target control instruction through a hierarchical control structure and evaluate and analyze running state data to obtain energy-saving control feedback data.

[0014] In a third aspect, a computer readable storage medium is provided, which stores instructions when executed on a computer, causes the computer to perform the energy-saving control method for an oil fume ultra-low emission all-in-one machine.

[0015] In the technical scheme provided in the application, the multiple sensors arranged in the oil fume ultra-low emission all-in-one machine collect oil fume related parameters in real time, obtain oil fume concentration data, fan speed data, equipment power data, temperature data and pollutant concentration data, so that the system can comprehensively master the equipment operation state and the oil fume condition and provide a complete data basis for subsequent processing. These multi-dimensional and multi-type sensing data realize accurate perception of the cooking environment and solve the control blind area problem of traditional equipment due to insufficient information acquisition. Feature extraction and classification processing are performed on the collected oil fume related parameters, the system can accurately identify the current cooking state of the kitchen, divide it into different scene categories such as idle mode, preparation mode, light cooking mode, medium cooking mode or heavy cooking mode, and automatically match the corresponding control parameter combination. This scene-based intelligent classification algorithm is closely combined with the actual cooking process, so that the control system can adaptively adjust according to the actual situation, breaking through the limitations of traditional fixed parameter control. Based on the identified scene category and the initial control parameter combination, the system performs energy consumption optimization calculation, finds out the lowest energy consumption parameter combination that meets the purification requirements through analysis of the relationship between energy consumption and purification efficiency under different parameter combinations, and generates target control instructions. In this process, the optimization algorithm and the specific oil fume purification technical features support each other, considering multiple factors such as oil fume concentration, pollutant type and equipment characteristics, realizing high consistency between theoretical calculation and actual working condition. Finally, the optimized target control instructions are transmitted to each execution unit through the hierarchical control structure to realize accurate adjustment of the equipment, and the running state data is evaluated and analyzed to generate energy-saving control feedback data. The hierarchical control structure ensures the orderly execution of instructions and the cooperative work between components, and the feedback evaluation mechanism provides real-time verification of the control effect, forming a complete closed-loop control to ensure that the system can continuously optimize the operating parameters. The hardware equipment provides the physical basis for data collection and execution control, while the algorithm realizes intelligent processing and decision optimization of data, especially in oil fume purification, the algorithm features are optimized for the generation law, purification principle and energy consumption characteristics of oil fume, so that the entire system can achieve maximum energy saving while ensuring ultra-low emission, effectively solving the technical problems of high energy consumption and unstable purification effect of traditional oil fume treatment equipment. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor based on these drawings.

[0017] Figure 1 An embodiment of the energy-saving control method for the oil fume ultra-low emission all-in-one machine in the embodiments of the present application is shown in the figure. Figure 2 An embodiment of the energy-saving control system for the oil fume ultra-low emission all-in-one machine in the embodiments of the present application is shown. DETAILED DESCRIPTION

[0018] The embodiments of the present application provide an energy-saving control method and system for an oil fume ultra-low emission all-in-one machine, and a medium. The terms "first", "second", "third", "fourth" and the like (if any) in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the term "comprising" or "having" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0019] For ease of understanding, the specific flow of the embodiments of the present application is described below. Please refer to Figure 1 An embodiment of the energy-saving control method for the oil fume ultra-low emission all-in-one machine in the embodiments of the present application includes the following steps. Step S101, collecting oil fume related parameters through a plurality of sensors arranged in the oil fume ultra-low emission all-in-one machine to obtain oil fume concentration data, fan speed data, device power data, temperature data and pollutant concentration data; Step S102, performing feature extraction and classification processing on the oil fume related parameters to obtain a scene category representing a current kitchen cooking state and a corresponding control parameter combination; Step S103, performing energy consumption optimization calculation based on the scene category and the control parameter combination to obtain a target control instruction; Step S104, executing device adjustment through a hierarchical control structure for the target control instruction, and evaluating and analyzing the running state data to obtain energy-saving control feedback data.

[0020] It can be understood that the execution subject of the present application can be an energy-saving control system for an oil fume ultra-low emission all-in-one machine, and can also be a terminal or a server, which is not limited here. The embodiments of the present application take a server as an execution subject for example.

[0021] Specifically, the oil fume related parameters are collected by multiple sensors installed in the oil fume ultra-low emission integrated machine, including oil fume concentration data, fan speed data, equipment power data, temperature data, and pollutant concentration data. The oil fume ultra-low emission integrated machine is equipped with various sensing devices such as oil fume concentration sensors, temperature sensors, power monitoring modules, fan speed sensors, and gas composition analyzers. The oil fume concentration sensor is installed at the air inlet position to monitor the oil fume concentration in real time, with a sampling frequency of once per second. The temperature sensors are installed at the kitchen environment, air inlet, and air outlet positions to collect temperature data at the corresponding positions. The power monitoring module is connected at the device power inlet to calculate the actual power consumption data of the device by measuring the current and voltage values. The fan speed sensor is directly installed on the centrifugal fan to monitor the fan speed data in real time. The gas composition analyzer is used to detect the pollutant content in the oil fume, including volatile organic compounds and particulate matter data. The data collected by these sensors is converted into standard digital signals by the data acquisition module and subjected to digital processing and outlier filtering to form a complete set of oil fume related parameter data.

[0022] The oil fume related parameters are subjected to feature extraction and classification processing to obtain the scene category representing the current kitchen cooking state and the corresponding control parameter combination. The collected oil fume related parameters are standardized to unify different dimension data into the same value range. The standardization processing uses the z-score method, which subtracts the mean value from the original data and divides it by the standard deviation to obtain standardized feature data with uniform value range. Then, the standardized feature data is input into the support vector machine classifier for processing. The support vector machine classifier uses the radial basis kernel function to map the input feature data to a high-dimensional feature space through the previously trained model parameters, and finds the optimal classification hyperplane in this space to obtain the category and probability value of the current cooking scene. According to the classification result, the current cooking state is divided into five basic modes: idle mode (no cooking activity), preparation mode (starting to prepare cooking), light cooking mode (such as boiling, stewing, etc.), medium cooking mode (such as ordinary stir-frying), or heavy cooking mode (such as explosive frying, frying). To avoid unstable control caused by frequent scene category switching, time smoothing processing is performed on the cooking scene category, i.e., when the recognition result changes, it needs to be consistent for three consecutive new recognition results to confirm the scene change, thereby obtaining a stable scene judgment result. According to the stable scene judgment result, the corresponding basic control parameters are selected from the pre-set control strategy library, including fan speed value, purification unit working intensity value, and heat exchange system working intensity value, to form an initial control parameter combination. Finally, the initial control parameter combination is dynamically adjusted according to the environmental temperature and oil fume concentration change rate to obtain the final control parameter combination.

[0023] Energy consumption optimization calculations are performed based on scenario categories and control parameter combinations to obtain target control commands. This step first sets the fan speed range, purification unit workload range, and heat exchange system workload range according to the scenario category, forming a control parameter optimization interval. Then, energy consumption calculations are performed on the fan speed, purification unit workload, and heat exchange system workload values ​​in the control parameter combinations to obtain the energy consumption value under the current configuration. Simultaneously, the minimum required purification efficiency is calculated based on oil fume concentration data and pollutant concentration data to determine purification constraints. Within the determined control parameter optimization interval, the fan speed value is first adjusted, and the energy consumption change rate before and after the adjustment is calculated to obtain the optimized fan energy consumption value. Next, the purification unit workload and heat exchange system workload values ​​are adjusted within the control parameter optimization interval. Specifically, the purification unit workload and heat exchange system workload values ​​are discretely sampled within their respective minimum to maximum ranges according to a set step size to obtain corresponding sampling point sets. These two sampling point sets are orthogonally combined to generate a workload parameter combination matrix. Then, the energy consumption value and purification efficiency value of each combination point in the parameter combination matrix are calculated to form the combination point performance evaluation result. From the evaluation results, a set of combination points that meet the purification constraints is selected to obtain a subset of effective control parameters. The parameter combination with the lowest energy consumption is then identified within this subset, determining the lowest energy consumption combination. Finally, the optimized energy consumption value of the fan and the lowest energy consumption combination are integrated into a unified control command to obtain the target control command.

[0024] The target control commands are executed through a hierarchical control structure to adjust the equipment, and the operating status data is evaluated and analyzed to obtain energy-saving control feedback data. This step adopts a hierarchical control structure, including a decision-making layer, a coordination layer, and an execution layer. First, the target control commands are decomposed into control tasks at different levels, forming decision-making layer commands, coordination layer commands, and execution layer commands. The coordination layer commands are transmitted to the controllers of each subsystem via the control bus, and converted into specific control commands such as fan control commands, oil-water separation control commands, filtration control commands, purification control commands, and heat exchange control commands. Each execution unit adjusts the corresponding physical component parameters according to the execution layer commands to achieve specific operations such as adjusting the fan speed, the workload of the purification unit, and the workload of the heat exchange system. After the equipment is adjusted and running, the system collects the adjusted equipment operating status information to obtain real-time energy consumption data, purification efficiency data, and equipment health status data. These data are evaluated from multiple dimensions to calculate various indicators reflecting equipment performance, forming performance evaluation indicators. The performance evaluation indicators are compared and analyzed with the expected targets to obtain energy-saving control feedback data, which will be used for parameter optimization in the next control cycle.

[0025] In one specific embodiment, the process of performing step S101 may specifically include the following steps: The oil fume concentration sensor is used to monitor the oil fume at the inlet position in real time, and the oil fume concentration data is obtained. The temperature sensor is used to collect the temperature of the kitchen environment, the inlet and the outlet, and the temperature data is obtained. The power monitoring module is used to measure the current and voltage at the device power inlet, and the device power data is obtained. The fan speed sensor is used to monitor the rotation speed of the centrifugal fan, and the fan speed data is obtained. The gas component analyzer is used to detect the pollutant content in the oil fume gas, and the pollutant concentration data is obtained. The oil fume concentration data, temperature data, device power data, fan speed data and pollutant concentration data are digitally processed and filtered for outliers, and the oil fume related parameters are obtained.

[0026] Specifically, the energy-saving control method for the oil fume ultra-low emission all-in-one machine first collects oil fume related parameters through multiple sensors, which are the basis data for subsequent control decisions. The oil fume concentration sensor is used to monitor the oil fume at the inlet position in real time, and the oil fume concentration data is obtained. The sensor works on the principle of light scattering, that is, it uses the scattering effect of oil fume particles on light to measure the concentration of oil fume. The specific process is that the infrared light source emits light through the gas containing oil fume, and the oil fume particles scatter the light. The scattered light intensity received by the photodetector is proportional to the oil fume concentration. The sensor converts the received light signal into an electrical signal, and through the built-in conversion circuit, the electrical signal is converted into a digital signal, outputting the real-time oil fume concentration value, with the unit of mg / m³. The sampling frequency is set to once per second to ensure real-time data. The temperature sensor is used to collect the temperature of the kitchen environment, the inlet and the outlet, and the temperature data is obtained. Three temperature sensors are installed in the oil fume ultra-low emission all-in-one machine, located in the kitchen environment, the inlet and the outlet. These sensors use thermistor temperature sensors, which work on the principle that the resistance value of the thermistor changes with temperature. When the ambient temperature changes, the resistance value of the sensor changes accordingly, and the control circuit calculates the current temperature by measuring the change in resistance value. The collection frequency is every 3 seconds, and the temperature data output by the sensor is in Celsius, with a data accuracy of ±0.1℃. The temperature difference between the inlet and the outlet is an important indicator of heat recovery efficiency, and the working effect of the heat exchange system can be evaluated by calculating the temperature difference.

[0027] The power monitoring module measures the current and voltage at the power input of the equipment to obtain power data. The module includes current and voltage sensors. The current sensor, based on the Hall effect, determines the current flowing through a conductor by measuring changes in the magnetic field around it; the voltage sensor directly measures the potential difference across the circuit. The power monitoring module multiplies the collected current and voltage values ​​to calculate the equipment's real-time power consumption, expressed in watts (W). Power data is collected once per second, recording both the total power and the power consumption of each major component (fan, purification unit, heat exchange system). This power data provides direct evidence for energy optimization; by analyzing power changes under different operating conditions, the most energy-efficient combination of operating parameters can be identified.

[0028] The rotational speed of the centrifugal fan is monitored by a fan speed sensor to obtain fan speed data. The fan speed sensor, employing a Hall effect sensor or photoelectric encoder, is mounted on the fan shaft and generates one or more pulse signals per revolution. The control circuit calculates the fan speed in revolutions per minute (rpm) by counting the number of pulses received per unit time. Fan speed data is collected twice per second to ensure accurate monitoring of the fan's operating status. Fan speed directly affects the fume extraction effect and system energy consumption, making it a crucial parameter of the control system. A gas composition analyzer is used to detect the pollutant content in the fume gas, obtaining pollutant concentration data. The gas composition analyzer includes various gas sensors for detecting volatile organic compounds (VOCs), particulate matter (PM2.5, PM10), and other pollutants in the fume. The VOCs sensor uses a semiconductor gas-sensitive element; when specific gas molecules are adsorbed onto the sensor surface, their conductivity changes, thus detecting the gas concentration. The particulate matter sensor uses the principle of light scattering, similar to the working method of the fume concentration sensor. The gas composition analyzer samples every 5 seconds, outputting data including the concentration values ​​of various pollutants, in units of mg / m³ or μg / m³. Pollutant concentration data are a direct indicator for evaluating purification effectiveness and a crucial basis for developing purification control strategies.

[0029] The oil fume concentration data, temperature data, equipment power data, fan speed data and pollutant concentration data are digitally processed and filtered for abnormal values to obtain oil fume related parameters. The digital processing includes signal conversion, data format standardization and time stamp addition. The abnormal value filtering mainly adopts a method combining median filtering and amplitude limiting filtering. The median filtering is to take all data in a sliding window (usually 5 data points), sort them by size and take the middle value as valid data, which can effectively filter out impulse noise; the amplitude limiting filtering is to set a reasonable change range, when the change of adjacent two sampling data exceeds the range, it is determined as abnormal data and is rejected. For example, in the normal cooking process, the change rate of oil fume concentration usually does not exceed 0.5 mg / m³·s, if it exceeds this threshold, it may be caused by sensor failure or interference. The data after abnormal value filtering is smoother and more reliable, providing accurate input for subsequent feature extraction and classification processing.

[0030] In a specific embodiment, the process of performing step S102 can specifically include the following steps: The oil fume related parameters are standardized to obtain standardized feature data with uniform value range; The standardized feature data is input into a support vector machine classifier to obtain the category and probability value of the current cooking scene; The current cooking state is divided into idle mode, preparation mode, light cooking mode, medium cooking mode or heavy cooking mode according to the category; The cooking scene category is time-smoothed to obtain a stable scene judgment result; According to the stable scene judgment result, the corresponding basic control parameters are selected to obtain an initial control parameter combination including fan speed value, purification unit working intensity value and heat exchange system working intensity value; The initial control parameter combination is dynamically adjusted according to the change rate of environmental temperature and oil fume concentration to obtain the corresponding control parameter combination.

[0031] Specifically, feature extraction and classification processing are performed on these parameters to identify the current cooking scene and determine the corresponding control strategy. First, the oil fume related parameters are standardized to obtain standardized feature data with uniform value range. Standardization is necessary because different parameters have different dimensions and numerical ranges. For example, oil fume concentration data is usually in the range of 0-10 mg / m³, temperature data is in the range of 20-100 °C, fan speed data is in the range of 0-3000 rpm, equipment power data is in the range of 0-1000 W, and pollutant concentration data has different units and ranges depending on the pollutant. The z-score method is used for standardization, which calculates the difference between each parameter value and the mean of the parameter, and then divides it by the standard deviation of the parameter, so that all parameters are converted to a distribution with a mean of 0 and a standard deviation of 1. For example, for oil fume concentration data, calculate the average concentration value and standard deviation over a period of time (e.g. 10 minutes), then subtract the average value from the current concentration value and divide by the standard deviation to get the standardized oil fume concentration feature value. The same processing method applies to other parameters, resulting in a vector containing multiple standardized features, with approximately the same value range for each feature, which is beneficial for subsequent classification algorithm processing. The standardized feature data is input into a support vector machine classifier to obtain the category and probability value of the current cooking scene. Support vector machine (SVM) is a supervised learning algorithm for data classification. In this method, the support vector machine classifier has been pre-trained with a large amount of labeled data and can determine the current cooking scene based on the input standardized feature data. The core idea of support vector machine is to find an optimal hyperplane in the feature space that correctly separates different classes of sample points and maximizes the geometric interval of the classification boundary. This method uses radial basis function (RBF) as the kernel function to map the original feature space to a higher dimensional space to handle non-linear classification problems. In the classification process, the standardized feature data is input into the trained SVM model, which calculates the distance of the data point to each classification boundary and converts it to the probability value of each category, and finally outputs the category with the highest probability as the judgment result of the current cooking scene, and gives the probability value of the judgment to evaluate the credibility of the judgment.

[0032] The current cooking state is classified into idle mode, preparation mode, light cooking mode, medium cooking mode or heavy cooking mode according to the category. The five modes correspond to different cooking activity states and oil fume generation situations: the idle mode indicates that there is no cooking activity in the kitchen, and the oil fume concentration is usually below 0.1 mg / m³; the preparation mode indicates that the kitchen starts to prepare cooking, such as washing food, preparing seasonings, etc., and the oil fume concentration is between 0.1-0.3 mg / m³; the light cooking mode indicates that cooking activities such as boiling and stewing are carried out, which produce less oil fume, and the oil fume concentration is between 0.3-0.8 mg / m³; the medium cooking mode indicates that cooking activities such as ordinary stir-frying are carried out, which produce moderate oil fume, and the oil fume concentration is between 0.8-1.5 mg / m³; the heavy cooking mode indicates that cooking activities such as explosive frying and frying are carried out, which produce a large amount of oil fume, and the oil fume concentration is higher than 1.5 mg / m³. In addition to the oil fume concentration, each mode has a typical value of other characteristic parameters, such as temperature data, power data, etc., and the SVM classifier comprehensively considers all characteristic parameters to perform mode recognition.

[0033] The cooking scene categories are time-smoothed to obtain stable scene judgment results. Due to fluctuations in sensor data, combined with short-term changes in the cooking process itself, directly using the original output of the SVM classifier may result in frequent switching of cooking scene categories, which in turn causes frequent adjustment of control parameters, which is not conducive to the stable operation of the equipment. Time smoothing aims to eliminate such fluctuations and improve the stability of scene judgment. The specific processing method is: when a change in the cooking scene category is detected, the control strategy is not immediately switched, but a period of time (such as 15 seconds) is continuously observed. Only when the judgment results are consistent for multiple times (such as 3 times) is the scene confirmed to have switched, and the control strategy is updated. At the same time, for the judgment results with low probability values (such as less than 0.6), the original scene category is maintained until a higher confidence judgment is obtained. Time smoothing is equivalent to filtering the original classification results in the time dimension, removing the influence of short-term fluctuations, and retaining the trend of continuous and stable changes. According to the stable scene judgment results, the corresponding basic control parameters are selected to obtain the initial control parameter combination, which includes the fan speed value, the purification unit working intensity value, and the heat exchange system working intensity value. Each cooking scene corresponds to a set of preset basic control parameters, which are determined through a large number of experiments and optimization, and can reduce energy consumption as much as possible while ensuring purification effect. For the idle mode, the fan speed is set to 20% of the rated speed, the purification unit working intensity is set to 30%, and the heat exchange system working intensity is set to 30%; for the preparation mode, the fan speed is set to 40% of the rated speed, the purification unit working intensity is set to 40%, and the heat exchange system working intensity is set to 50%; for the light cooking mode, the fan speed is set to 60% of the rated speed, the purification unit working intensity is set to 60%, and the heat exchange system working intensity is set to 70%; for the medium cooking mode, the fan speed is set to 80% of the rated speed, the purification unit working intensity is set to 80%, and the heat exchange system working intensity is set to 90%; for the heavy cooking mode, the fan speed is set to 100% of the rated speed, the purification unit working intensity is set to 100%, and the heat exchange system working intensity is set to 100%. These preset parameters are based on the amount of oil fume generated and the characteristics of pollutants under different cooking scenes, ensuring effective capture and purification of oil fume while avoiding energy waste.

[0034] The initial control parameter combination is dynamically adjusted according to the change rate of the ambient temperature and the oil fume concentration to obtain a corresponding control parameter combination. The preset basic control parameters are designed for typical working conditions, and there are differences in actual use environment and cooking habits, so it is necessary to dynamically adjust according to real-time environmental parameters. The adjustment process mainly considers two factors: ambient temperature and oil fume concentration change rate. When the ambient temperature is higher than the preset threshold (such as 30℃), the working strength of the heat exchange system needs to be increased to strengthen the heat recovery and cooling effect of the oil fume; when the oil fume concentration change rate is large (such as more than 0.5mg / m³·min), it indicates that the cooking activity is rapidly heating up or changing, and the fan speed and purification unit working strength need to be increased in advance to cope with the increasing oil fume load. The dynamic adjustment adopts proportional regulation method, that is, according to the difference between the ambient temperature and the reference temperature, the difference between the oil fume concentration change rate and the reference change rate, the control parameter value is adjusted in proportion. For example, when the ambient temperature is 5℃ higher than the reference value, the working strength of the heat exchange system is increased by 10%; when the oil fume concentration change rate is 0.3mg / m³·min higher than the reference value, the fan speed and the working strength of the purification unit are each increased by 15%. The adjusted parameter combination not only considers the basic scene requirements, but also adapts to the actual environmental changes, realizing more accurate control.

[0035] When the cooking activity in the kitchen starts, the oil fume concentration rises rapidly from 0.2mg / m³ to 1.2mg / m³, and the temperature data shows that the inlet temperature rises by 15℃, and the pollutant concentration data also increases accordingly. After standardization processing, these original data form a standardized feature vector, which is input into the SVM classifier. The classifier judges that the current scene is a moderate cooking mode, and the probability value is 0.85. After time smoothing processing, it is confirmed that the scene has been switched from the preparation mode to the moderate cooking mode. The control system selects the corresponding basic control parameters: the fan speed is set to 80% of the rated value, the purification unit working strength is set to 80%, and the heat exchange system working strength is set to 90%. Since the oil fume concentration change rate reaches 0.8mg / m³·min, which is much higher than the reference value of 0.4mg / m³·min, the system dynamically adjusts the basic control parameters and increases the fan speed and the working strength of the purification unit by 10% each. The final control parameter combination is: the fan speed is 90% of the rated value, the purification unit working strength is 90%, and the heat exchange system working strength is 90%. This control method based on scene recognition and dynamic adjustment solves the problem that the traditional fixed parameter control cannot adapt to different cooking scenes, ensures the purification effect, avoids energy waste, and realizes the goal of energy-saving control.

[0036] In a specific embodiment, the process of performing step S103 can specifically include the following steps: According to the scene category, set the fan speed range, purification unit working intensity range and heat exchange system working intensity range, and obtain the control parameter optimization interval; Calculate the energy consumption of the fan speed value, purification unit working intensity value and heat exchange system working intensity value in the control parameter combination, and obtain the current energy consumption value; According to the oil fume concentration data and the pollutant concentration data, calculate the required minimum purification efficiency, and obtain the purification constraint condition; Adjust the fan speed value in the control parameter optimization interval, and calculate the energy consumption change rate after adjustment, to obtain the fan energy consumption optimization value; Adjust the purification unit working intensity value and the heat exchange system working intensity value in the control parameter optimization interval, to obtain the lowest energy consumption combination that meets the purification constraint condition; Integrate the fan energy consumption optimization value and the lowest energy consumption combination into the control instruction, to obtain the target control instruction.

[0037] Specifically, the fan speed range, the purification unit working intensity range, and the heat exchange system working intensity range are set according to the scene category to obtain the control parameter optimization interval. For different scene categories, the optimization interval of the control parameter is different, because the amount and characteristics of the oil fume generated under different cooking scenes are different, and the corresponding control strategy is needed. Specifically, for the idle mode, the fan speed range is set to 10%-30% of the rated speed, the purification unit working intensity range is 20%-40%, and the heat exchange system working intensity range is 20%-40%; for the preparation mode, the fan speed range is set to 30%-50% of the rated speed, the purification unit working intensity range is 30%-50%, and the heat exchange system working intensity range is 40%-60%; for the light cooking mode, the fan speed range is set to 50%-70% of the rated speed, the purification unit working intensity range is 50%-70%, and the heat exchange system working intensity range is 60%-80%; for the medium cooking mode, the fan speed range is set to 70%-90% of the rated speed, the purification unit working intensity range is 70%-90%, and the heat exchange system working intensity range is 80%-100%; for the heavy cooking mode, the fan speed range is set to 90%-100% of the rated speed, the purification unit working intensity range is 90%-100%, and the heat exchange system working intensity range is 90%-100%. The setting of these parameter ranges is based on a large number of experimental tests and optimization analysis, ensuring that there is enough adjustment space under various cooking scenes. The fan speed value, the purification unit working intensity value, and the heat exchange system working intensity value in the control parameter combination are calculated for energy consumption to obtain the current energy consumption value. Energy consumption calculation is the core of energy-saving control, and by establishing the relationship model between the control parameters and the energy consumption, the energy consumption under different parameter combinations can be predicted. Energy consumption calculation considers three main components: the fan, the purification unit, and the heat exchange system. The energy consumption of the fan is proportional to the cube of the speed, i.e., the energy consumption increases by eight times when the fan speed increases by one time; the energy consumption of the purification unit is linearly related to the working intensity, i.e., the energy consumption increases by 10% when the working intensity increases by 10%; the energy consumption of the heat exchange system is sub-linearly related to the working intensity, i.e., the energy consumption increases by about 8% when the working intensity increases by 10%. The total energy consumption is the weighted sum of the energy consumption of the three components, among which the energy consumption of the fan accounts for the largest proportion, usually 50%-70% of the total energy consumption, so the optimization of the fan speed has the greatest impact on the total energy consumption. The energy consumption calculation uses a combination of lookup table and interpolation method, first querying the preset energy consumption table according to the working parameters of each component, and then using linear interpolation method to calculate the energy consumption for parameter values not in the table. In this way, the energy consumption value under the current control parameter combination can be quickly and accurately obtained.

[0038] The minimum purification efficiency required is calculated according to the oil fume concentration data and the pollutant concentration data, and the purification constraint condition is obtained. The purification efficiency is an important indicator for measuring the purification effect of oil fume, and is defined as the reduction ratio of the pollutant concentration before and after purification. In the energy-saving control process, it is necessary to ensure that the purification efficiency meets the minimum requirement, which is dynamically adjusted according to the current oil fume situation. The calculation process includes: first, analyzing the current oil fume concentration and pollutant composition, the higher the oil fume concentration, the higher the minimum purification efficiency required; second, considering the type and harm degree of pollutants, for oil fume with high content of harmful substances such as VOCs and PM2.5, higher purification efficiency is required; finally, combined with the requirements of environmental standards, the final purification constraint condition is determined. Under normal circumstances, the minimum purification efficiency is set between 85%-99%, 85% for light cooking mode, 90% for moderate cooking mode, and more than 95% for heavy cooking mode. This dynamically adjusted purification constraint condition not only ensures that the air quality meets the standard, but also avoids unnecessary energy consumption.

[0039] The fan speed value is adjusted within the control parameter optimization interval, and the adjusted energy consumption change rate is calculated to obtain the fan energy consumption optimization value. The fan is the largest energy-consuming component in the oil fume ultra-low emission integrated machine, and its speed directly affects the oil fume capture effect and energy consumption. The optimization process uses a variable step search method. First, a rough search is performed within the set fan speed range with a large step size (e.g., 5% of the rated speed). The energy consumption and purification efficiency at each speed point are calculated to find the lowest energy consumption point that meets the purification efficiency requirement. Then, a fine search is performed near the point with a small step size (e.g., 1% of the rated speed) to determine the final fan energy consumption optimization value. During the search process, the relationship between fan speed and purification efficiency is considered. If the fan speed is too low, it will cause some oil fume to escape, reducing the purification efficiency. If the fan speed is too high, although it can improve the capture rate, the energy consumption increases significantly, and the marginal improvement in purification efficiency is small. By balancing these two factors, the fan speed value that meets the purification efficiency requirement and maximally saves energy is found. The purification unit working intensity value and the heat exchange system working intensity value are adjusted within the control parameter optimization interval to obtain the lowest energy consumption combination that meets the purification constraint. After determining the fan speed optimization value, the working parameters of the purification unit and the heat exchange system need to be further optimized. This optimization process uses a grid search method. The purification unit working intensity and the heat exchange system working intensity are discretely sampled within their respective optimization intervals according to the set step size to form a two-dimensional parameter grid. For each grid point, the total energy consumption and purification efficiency at the current fan speed are calculated, and all parameter combinations that meet the purification constraint are selected. Then, from these effective parameter combinations, the combination with the lowest energy consumption is found as the final optimization result. It is important to note that there is a coupling relationship between the working parameters of the purification unit and the heat exchange system. The working intensity of the heat exchange system affects the oil fume temperature, which in turn affects the working efficiency of the purification unit. Therefore, this mutual influence needs to be considered during the optimization process, rather than simply optimizing each parameter independently.

[0040] The fan energy consumption optimization value and the lowest energy consumption combination are integrated into control instructions to obtain target control instructions. Through the previous optimization calculation, the optimization values of the fan speed, the purification unit working intensity, and the heat exchange system working intensity are obtained. These optimization parameters need to be integrated into control instructions that can be directly executed by the device. The integration process includes: first, converting the parameter values into specific control quantities, such as converting the fan speed percentage into the frequency value of the frequency converter, converting the purification unit working intensity into the voltage value of the high-voltage power supply, and converting the heat exchange system working intensity into the flow value of the circulating pump; then, considering the smooth transition of parameter adjustment to avoid parameter mutation impacting the device, designing a gradual change process for parameters with large change amplitudes; finally, generating control instructions in a standard format, including the target values of each control parameter, the adjustment timing, and the priority marker. These control instructions are passed to each execution unit through a hierarchical control structure to achieve precise control of the device.

[0041] In a specific embodiment, the process of adjusting the purification unit operating intensity value and the heat exchange system operating intensity value within the control parameter optimization interval can specifically include the following steps: Discretely sampling the purification unit operating intensity value within the minimum value to the maximum value range according to a set step size to obtain a purification unit operating intensity sampling point set; Discretely sampling the heat exchange system operating intensity value within the minimum value to the maximum value range according to a set step size to obtain a heat exchange system operating intensity sampling point set; Orthogonally combining the purification unit operating intensity sampling point set and the heat exchange system operating intensity sampling point set to obtain an operating intensity parameter combination matrix; Calculating the energy consumption value and the purification efficiency value of each combination point in the operating intensity parameter combination matrix to obtain a combination point performance evaluation result; Screening a combination point set that satisfies the purification constraint condition from the combination point performance evaluation result to obtain an effective control parameter subset; Finding the parameter combination with the lowest energy consumption in the effective control parameter subset to obtain a lowest energy consumption combination.

[0042] Specifically, the purification unit working intensity value is discretely sampled within the minimum to maximum range with a set step size, resulting in a set of purification unit working intensity sampling points. The purification unit working intensity refers to the working state of the purification device, expressed in percentage, usually ranging from 20% (minimum) to 100% (maximum). Discrete sampling is a method of dividing the continuously changing working intensity into a finite number of discrete points for study, and the set step size determines the sampling precision. In actual operation, different sampling step sizes are used according to different cooking scenarios: for idle mode and preparation mode, a larger step size (such as 10%) is used for coarse sampling; for light cooking mode and moderate cooking mode, a medium step size (such as 5%) is used; for heavy cooking mode, a smaller step size (such as 2%) is used for fine sampling. The sampling process starts from the minimum value within the set range, increases by one step each time until the maximum value is reached, forming a series of discrete sampling points. For example, for moderate cooking mode, the purification unit working intensity range is 70%-90%, the sampling step size is 5%, and the sampling point set is {70%, 75%, 80%, 85%, 90%}, a total of 5 points. The heat exchange system working intensity value is discretely sampled within the minimum to maximum range with a set step size, resulting in a set of heat exchange system working intensity sampling points. The heat exchange system working intensity refers to the working state of the heat exchange device, also expressed in percentage, ranging from 30% (minimum) to 100% (maximum). The main function of the heat exchange system is to recover the heat in the oil fume, reduce the exhaust temperature, and improve energy utilization efficiency. Similar to purification unit sampling, heat exchange system sampling also sets different step sizes according to cooking scenarios, and the sampling process is the same. For example, for moderate cooking mode, the heat exchange system working intensity range is 80%-100%, the sampling step size is 5%, and the sampling point set is {80%, 85%, 90%, 95%, 100%}, a total of 5 points. This discrete sampling method converts the continuous parameter space into a set of finite discrete points, greatly reducing the complexity of the search space, making optimization calculations feasible within a limited time.

[0043] The working intensity parameter combination matrix is obtained by orthogonal combination of the purification unit working intensity sampling point set and the heat exchange system working intensity sampling point set. Orthogonal combination refers to combining all possible values of two parameters two by two to form a two-dimensional matrix, and each element in the matrix represents a parameter combination. The purpose of orthogonal combination is to comprehensively explore the parameter space and find the optimal parameter combination. The specific operation is to take the purification unit working intensity sampling point set as the rows of the matrix and the heat exchange system working intensity sampling point set as the columns of the matrix, and each position formed by the intersection of the two is a parameter combination point. Continuing the above example, the purification unit working intensity sampling point set has 5 points and the heat exchange system working intensity sampling point set has 5 points, and 5x5=25 combination points are formed by orthogonal combination to form the working intensity parameter combination matrix. Organizing these combination points in matrix form facilitates subsequent batch calculation and comparison. Orthogonal combination can systematically explore the possibility of all parameter combinations and avoid missing the optimal solution. The energy consumption value and purification efficiency value of each combination point in the working intensity parameter combination matrix are calculated to obtain the performance evaluation results of the combination points. For each parameter combination point in the matrix, two key indicators need to be calculated: energy consumption value and purification efficiency value. The energy consumption value calculation considers the power consumption of the purification unit and the heat exchange system under a certain working intensity, as well as their mutual influence. The purification efficiency value calculation is based on the oil smoke concentration, pollutant concentration and working state of each component to evaluate the actual effect of the parameter combination on oil smoke purification. The calculation process uses the pre-established performance model or table lookup method to calculate the energy consumption value and purification efficiency value according to the current working parameters. For example, for the combination point with a purification unit working intensity of 80% and a heat exchange system working intensity of 90%, the energy consumption value is 220W and the purification efficiency value is 93% by table lookup and interpolation calculation. After calculation, a performance evaluation result is generated for each combination point, including parameter combination, energy consumption value and purification efficiency value. These evaluation results form a two-dimensional table, which facilitates subsequent screening and comparison.

[0044] The combination point set satisfying the purification constraint condition is screened from the combination point performance evaluation results, and an effective control parameter subset is obtained. The purification constraint condition refers to the minimum efficiency requirement that must be met by oil fume purification. This requirement is dynamically determined according to the current oil fume concentration and pollutant situation. The screening process is to traverse the performance evaluation results of all combination points, check whether the purification efficiency value of each point meets or exceeds the required minimum purification efficiency. If it meets the requirement, the combination point is added to the effective control parameter subset; if it does not meet the requirement, the combination point is excluded. For example, assuming that the minimum purification efficiency required by the current oil fume situation is 90%, then in the previous example, the combination point with a purification unit working strength of 80% and a heat exchange system working strength of 90% has a purification efficiency of 93%, which exceeds the requirement of 90%, and is therefore retained in the effective control parameter subset. After screening, all combination points that do not meet the purification requirement are excluded, and the remaining combination points constitute the effective control parameter subset. These combination points can all meet the purification performance requirement, and the difference lies in the energy consumption.

[0045] The combination point with the lowest energy consumption is searched for in the effective control parameter subset, and a lowest energy consumption combination is obtained. The goal of this step is to find the operating parameters with the lowest energy consumption under the premise of ensuring purification effect, so as to achieve the best energy saving effect. The searching process is to traverse all combination points in the effective control parameter subset, compare their energy consumption values, and find the combination point with the smallest energy consumption value. If there are multiple combination points with the same energy consumption value and the smallest value, other factors (such as the margin of purification efficiency) can be further considered to determine the final selection. The finally determined parameter combination is the lowest energy consumption combination, which contains two parameters: the purification unit working strength value and the heat exchange system working strength value. This set of parameters will be part of the control instruction to guide the operation of the equipment and maximize the energy saving effect under the condition of meeting the purification requirement.

[0046] In a specific embodiment, the process of performing the orthogonal combination step on the purification unit working strength sampling point set and the heat exchange system working strength sampling point set can specifically include the following steps: According to the size of the purification unit working strength sampling point set and the size of the heat exchange system working strength sampling point set, the number of rows and columns of the orthogonal test table is determined, and an orthogonal test design scheme is obtained; The sampling points in the purification unit working strength sampling point set are distributed into the corresponding columns of the orthogonal test table according to the equal interval principle, and test level values of the purification unit working strength are obtained; The sampling points in the heat exchange system working strength sampling point set are distributed into the corresponding columns of the orthogonal test table according to the equal interval principle, and test level values of the heat exchange system working strength are obtained; The test level values are arranged in orthogonal combination to generate a test combination scheme, and an optimized combination point with reduced test times is obtained; Calculate the energy consumption contribution degree and purification efficiency contribution degree corresponding to each optimization combination point to obtain the parameter sensitivity analysis result; Based on the parameter sensitivity analysis result, the optimization combination points are supplemented with sampling to obtain the working intensity parameter combination matrix.

[0047] Specifically, according to the size of the purification unit working intensity sampling point set and the size of the heat exchange system working intensity sampling point set, the number of rows and columns of the orthogonal test table is determined to obtain the orthogonal test design scheme. Orthogonal test design is an efficient test method that can obtain comprehensive parameter influence information while reducing the number of tests. In this method, the number of rows of the orthogonal test table depends on the number of levels of the purification unit working intensity, and the number of columns depends on the number of levels of the heat exchange system working intensity. For example, for the moderate cooking mode, the purification unit working intensity sampling point set contains 5 points (70%, 75%, 80%, 85%, 90%), and the heat exchange system working intensity sampling point set also contains 5 points (80%, 85%, 90%, 95%, 100%), so the number of rows and columns of the orthogonal test table is 5x5. According to the orthogonal test theory, it is not necessary to perform all 25 tests, but to select representative combinations for testing. The orthogonal test design scheme usually selects the L25(56) orthogonal table, i.e., a 25-row 6-column orthogonal table, in which the first two columns are used to arrange the two factors. The sampling points in the purification unit working intensity sampling point set are distributed to the corresponding columns of the orthogonal test table according to the equal interval principle to obtain the test level values of the purification unit working intensity. The equal interval principle means that the sampling points are distributed in the corresponding columns of the orthogonal test table according to uniform spacing to ensure that the test points cover the entire parameter space. Specifically, the 5 sampling points of the purification unit working intensity (70%, 75%, 80%, 85%, 90%) are sequentially filled into the first column of the orthogonal test table, corresponding to 5 test levels. Each level appears the same number of times in the orthogonal table, ensuring the balance of the test. In this way, the first column of the orthogonal test table contains all possible values of the purification unit working intensity, each value as a test level.

[0048] The sampling points in the heat exchange system working intensity sampling point set are distributed to the corresponding columns of the orthogonal test table according to the equal interval principle to obtain the test level values of the heat exchange system working intensity. Similarly, the 5 sampling points of the heat exchange system working intensity (80%, 85%, 90%, 95%, 100%) are sequentially filled into the second column of the orthogonal test table to form 5 test levels. Similarly, each level appears the same number of times in the orthogonal table, ensuring the balance of the test. The second column of the orthogonal test table contains all possible values of the heat exchange system working intensity, each value as a test level. At this time, the first two columns of the orthogonal test table have been filled, representing the test levels of the purification unit working intensity and the heat exchange system working intensity.

[0049] The test level values are arranged in an orthogonal combination to generate a test combination scheme, and an optimized combination point is obtained to reduce the number of tests. According to the design principle of the orthogonal test table, the levels of different factors are combined to form a series of test points. For an L25(56) orthogonal table, although there are 5 levels for each of the two factors, theoretically, 5x5=25 tests are required. However, the orthogonal test theory shows that only 25 carefully designed tests are required to obtain information equivalent to a complete test. The core of the orthogonal test is "balance" and "representativeness", that is, each level of each factor appears the same number of times in the test, and the combination of each factor level is representative and covers the entire test space. In this way, the generated test combination scheme contains 25 optimized combination points, each composed of a purification unit work intensity value and a heat exchange system work intensity value, such as (70%, 80%) and (75%, 85%). Compared with the complete combination scheme, these optimized combination points greatly reduce the number of parameter combinations that need to be evaluated, while maintaining the representativeness of the test.

[0050] The energy consumption contribution degree and the purification efficiency contribution degree corresponding to each optimized combination point are calculated to obtain the parameter sensitivity analysis results. For each optimized combination point, two key indicators need to be calculated: energy consumption contribution degree and purification efficiency contribution degree. Energy consumption contribution degree refers to the degree of influence of the parameter setting of the combination point on total energy consumption, and purification efficiency contribution degree refers to the degree of influence of the parameter setting of the combination point on purification efficiency. The calculation method is to obtain the energy consumption value and purification efficiency value of each combination point through model prediction or table lookup interpolation, and then calculate the average energy consumption value and average purification efficiency value of each level of each factor through variance analysis method, and then calculate the contribution degree of each factor to energy consumption and purification efficiency. For example, for the purification unit work intensity, the average energy consumption and average purification efficiency of its 5 levels (70%, 75%, 80%, 85%, 90%) are calculated, and the dispersion degree of these average values is calculated to obtain the contribution degree of the purification unit work intensity to energy consumption and purification efficiency. Similarly, the same calculation is performed for the heat exchange system work intensity. In this way, the parameter sensitivity analysis results are obtained, that is, the degree of influence of each parameter on energy consumption and purification efficiency. These results help to identify which parameter has a greater influence on the objective function, thereby guiding the subsequent parameter optimization.

[0051] Based on the results of parameter sensitivity analysis, supplementary sampling is performed on the optimized combination points to obtain the working intensity parameter combination matrix. The results of parameter sensitivity analysis show the influence degree of different parameters on energy consumption and purification efficiency, and thus the region requiring supplementary sampling can be determined. The principle of supplementary sampling is that for the parameters with higher sensitivity, more intensive sampling is performed in the region with high contribution degree; and for the parameters with lower sensitivity, sparse sampling is adopted. For example, if the analysis shows that the working intensity of the purification unit in the region of 75%-85% has great influence on energy consumption and purification efficiency, additional intensive sampling is performed in this region, such as adding intermediate points of 77.5%, 82.5%, etc.; and for the region with less influence, the original sampling density is maintained. After supplementary sampling, the original optimized combination points are combined to form a more comprehensive working intensity parameter combination matrix. This matrix contains not only the representative combination points generated by orthogonal test design, but also the targeted supplementary sampling points based on the results of parameter sensitivity analysis, thereby improving the accuracy of parameter optimization while maintaining the calculation efficiency.

[0052] In a specific embodiment, the process of performing step S104 can specifically include the following steps: decomposing the target control instruction into decision layer instruction, coordination layer instruction and execution layer instruction to obtain control tasks of each layer; transmitting the coordination layer instruction to each subsystem controller through the control bus to obtain fan control instruction, oil-water separation control instruction, filtration control instruction, purification control instruction and heat exchange control instruction; adjusting the corresponding physical component parameters according to the execution layer instruction by each execution unit to obtain fan speed adjustment, purification unit working intensity adjustment and heat exchange system working intensity adjustment; collecting the running state information of the adjusted equipment to obtain real-time energy consumption data, purification efficiency data and equipment health state data; performing multi-dimensional evaluation on the real-time energy consumption data, purification efficiency data and equipment health state data to obtain performance evaluation index; comparing and analyzing the performance evaluation index with the expected target to obtain energy-saving control feedback data.

[0053] Specifically, the target control instruction is decomposed into decision layer instruction, coordination layer instruction and execution layer instruction to obtain control tasks of each layer. The hierarchical control structure is a commonly used complex system control architecture, which divides control functions into different levels according to the degree of abstraction, and each level is responsible for control tasks of different granularity. The decision layer instruction is the highest level control instruction, which contains the overall goal and strategy of control, such as setting the target value, priority and timing requirement of each parameter, etc. The coordination layer instruction is the middle layer control instruction, which is responsible for converting the abstract instruction of the decision layer into specific operation instruction of each subsystem, and coordinating the linkage relationship between different subsystems. The execution layer instruction is the bottom layer control instruction, which directly acts on the hardware driver unit to control the action of physical components. The instruction decomposition process adopts a top-down manner, first extracts the fan speed value, purification unit work intensity value and heat exchange system work intensity value in the target control instruction as the decision layer instruction; then according to the internal structure and control protocol of the equipment, converts these parameter values into control instructions of each subsystem, such as converting the fan speed value into the frequency setting value of the frequency converter, converting the purification unit work intensity value into the voltage setting value of the high-voltage power supply, etc., to form the coordination layer instruction; finally, the coordination layer instruction is further refined into bottom layer commands such as PWM signal, on-off control, analog output, etc., to form the execution layer instruction.

[0054] The coordination layer instruction is transmitted to each subsystem controller through the control bus to obtain the fan control instruction, oil-water separation control instruction, filtration control instruction, purification control instruction and heat exchange control instruction. The control bus is a communication channel connecting the central control unit and each subsystem controller, which adopts a standard industrial communication protocol such as CAN bus, Modbus or RS-485, etc. When the coordination layer instruction is transmitted through the control bus, a specific data frame format is adopted, which contains fields such as destination address, instruction type, parameter value, check code, etc. Each subsystem controller receives and parses the corresponding instruction according to its own address. The fan control instruction is the instruction for controlling the fan speed, which contains parameters such as target speed, acceleration time, deceleration time, etc. The oil-water separation control instruction is the instruction for controlling the working state of the oil-water separation unit, which contains parameters such as electric field intensity, discharge frequency, etc. The filtration control instruction is the instruction for controlling the working state of the filtration unit, which contains parameters such as filter layer selection, filtration intensity, etc. The purification control instruction is the instruction for controlling the working state of the purification unit, which contains parameters such as catalyst temperature, ultraviolet light intensity, etc. The heat exchange control instruction is the instruction for controlling the working state of the heat exchange system, which contains parameters such as heat exchange liquid flow, circulating pump speed, etc. These specific control instructions are received and processed by each subsystem controller to prepare for subsequent execution layer operation.

[0055] The corresponding physical component parameters are adjusted according to the execution layer instructions by each execution unit, to obtain fan speed adjustment, purification unit work intensity adjustment, and heat exchange system work intensity adjustment. The execution unit is a hardware drive unit that directly controls the physical component, including frequency converters, relays, thyristors, stepper motor drivers, etc. The fan execution unit adjusts the frequency converter output frequency according to the fan control instruction to realize accurate control of the fan speed; the oil-water separation execution unit adjusts the output voltage of the high-voltage power supply according to the oil-water separation control instruction to control the oil-water separation efficiency; the filtration execution unit controls the start-stop state of different filter layers according to the filtration control instruction to optimize the filtration effect; the purification execution unit adjusts the working state of the catalyst heating circuit and the ultraviolet light source according to the purification control instruction to control the purification intensity; and the heat exchange execution unit adjusts the circulating pump speed and the three-way valve opening according to the heat exchange control instruction to control the heat exchange efficiency. These execution units change the working parameters of the physical components to realize adjustment of the overall running state of the equipment. In order to ensure smooth transition and avoid parameter mutation impacting the equipment, the execution unit adopts a ramp change or step adjustment method when adjusting the parameters, such as gradually changing the fan speed from the current value to the target value, with a change rate controlled within 5% per second. The adjusted equipment running state information is collected to obtain real-time energy consumption data, purification efficiency data, and equipment health state data. The equipment running state information collection is completed by a sensor network distributed in each part of the equipment. Real-time energy consumption data collection measures the power consumption of each component through current and voltage sensors, and then calculates the total energy consumption; purification efficiency data collection calculates the removal rate by comparing the oil smoke concentration and pollutant concentration at the inlet and outlet; equipment health state data collection includes temperature, vibration, noise, pressure difference, etc. of each component, which is used to monitor the running condition and life prediction of the equipment. The data collection adopts a timing sampling method, with important parameters such as oil smoke concentration and power sampled once per second, and secondary parameters such as temperature and vibration sampled once every 5-10 seconds. The collected raw data is processed through filtering, calibration, unit conversion, etc. to form a standard format of state information data packet, including data identification, data value, time stamp, quality mark, etc. These data are transmitted to the data processing unit through the internal communication network, to prepare for subsequent performance evaluation.

[0056] The performance evaluation index is obtained by multi-dimensional evaluation of real-time energy consumption data, purification efficiency data and equipment health status data. Multi-dimensional evaluation refers to comprehensive evaluation of the equipment running state from different angles, including energy efficiency dimension, purification effect dimension and reliability dimension. The energy efficiency dimension evaluation mainly focuses on energy consumption data, calculates unit time energy consumption, unit fume treatment energy consumption and other indicators, and evaluates the energy utilization efficiency of the equipment; the purification effect dimension evaluation mainly focuses on purification efficiency data, calculates fume removal rate, removal rate of various pollutants and other indicators, and evaluates the purification performance of the equipment; the reliability dimension evaluation mainly focuses on equipment health status data, calculates component temperature margin, vibration level, noise level and other indicators, and evaluates the stability and service life of the equipment. The evaluation process adopts a weighted average method, weights are allocated according to the importance of each indicator under different working conditions, and then a weighted comprehensive score is calculated. For example, in the heavy cooking mode, the weight of the purification effect index is higher; in the light cooking mode, the weight of the energy efficiency index is higher. In this way, a set of evaluation indexes reflecting the overall performance of the equipment are obtained, including comprehensive energy efficiency index, purification effect index and reliability index.

[0057] The energy-saving control feedback data is obtained by comparing the performance evaluation index with the expected target. The expected target refers to the performance index set in advance according to the current cooking scene, environmental conditions and user demand, such as energy efficiency target, purification efficiency target, etc. The comparison analysis process includes calculation of the deviation of the actual index from the target index, the change trend of the deviation and the source analysis of the deviation. The deviation calculation adopts the relative error method, i.e. (actual value-target value) / target value; the change trend of the deviation is determined by comparing the current deviation with the historical deviation, to judge whether the performance is improving or deteriorating; the source analysis of the deviation is to determine which part has the greatest impact on the total deviation by decomposing the contribution of each component. The energy-saving control feedback data includes these analysis results, and adjustment suggestions generated based on the results, such as the need to increase or decrease the value of a certain parameter, the need to change the direction of the control strategy, etc. These feedback data will be used for parameter optimization in the next control cycle, forming a closed-loop control, continuously adjusting and improving the control effect, and realizing dynamic optimization.

[0058] The above describes the energy-saving control method for the oil fume ultra-low emission all-in-one machine in the embodiments of the present application, and the following describes the energy-saving control system for the oil fume ultra-low emission all-in-one machine in the embodiments of the present application. Please refer to Figure 2 An embodiment of the energy-saving control system for the oil fume ultra-low emission all-in-one machine in the embodiments of the present application includes: The acquisition module is configured to acquire oil fume related parameters through a plurality of sensors arranged in the oil fume ultra-low emission all-in-one machine, to obtain oil fume concentration data, fan speed data, equipment power data, temperature data and pollutant concentration data. The classification module is configured to perform feature extraction and classification processing on the oil fume related parameters, so as to obtain a scene category representing a current kitchen cooking state and a corresponding control parameter combination. The calculation module is configured to perform energy consumption optimization calculation based on the scene category and the control parameter combination, so as to obtain a target control instruction. The adjustment module is configured to execute equipment adjustment through a hierarchical control structure according to the target control instruction, and to perform evaluation and analysis on the running state data, so as to obtain energy saving control feedback data.

[0059] The application further provides a computer readable storage medium, which can be a non-volatile computer readable storage medium or a volatile computer readable storage medium, and the computer readable storage medium stores instructions, and when the instructions are executed on a computer, the computer performs the steps of the energy saving control method for the oil fume ultra-low emission all-in-one machine.

[0060] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, system and unit can refer to the corresponding processes in the foregoing method embodiments, and will not be described here.

[0061] The integrated unit, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the application or the whole or part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a device for energy saving control of an oil fume ultra-low emission all-in-one machine (which can be a personal computer, a server or a network device) to execute all or part of the steps of the method described in each embodiment of the application. The foregoing storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk and various program code storage media.

[0062] The above embodiments are only used to illustrate the technical solutions of the application, rather than limit them; although the application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the application.

Claims

1. An energy-saving control method for an integrated ultra-low emission kitchen fume generator, characterized in that, The method includes: Multiple sensors installed inside the integrated ultra-low emission fume machine collect relevant parameters of the fume, obtaining data on fume concentration, fan speed, equipment power, temperature, and pollutant concentration. The oil fume-related parameters are subjected to feature extraction and classification processing to obtain the scene category and corresponding control parameter combination representing the current kitchen cooking state; Energy consumption optimization calculations are performed based on the scenario category and control parameter combination to obtain the target control command; The target control commands are executed through a hierarchical control structure to adjust the equipment, and the operating status data is evaluated and analyzed to obtain energy-saving control feedback data.

2. The energy-saving control method for an integrated ultra-low emission fume generator according to claim 1, characterized in that, The process involves collecting oil fume-related parameters through multiple sensors installed within the integrated ultra-low emission oil fume unit, obtaining oil fume concentration data, fan speed data, equipment power data, temperature data, and pollutant concentration data, including: The oil fume concentration data is obtained by real-time monitoring of the oil fume at the air inlet using an oil fume concentration sensor. The temperature data is obtained by collecting the temperature of the kitchen environment, air inlet, and air outlet through temperature sensors; The power data of the device is obtained by measuring the current and voltage at the power input of the device through the power monitoring module; The rotational speed of the centrifugal fan is monitored by a fan speed sensor to obtain the fan speed data; The pollutant concentration data are obtained by detecting the pollutant content in the oil fume gas using a gas composition analyzer. The oil fume concentration data, temperature data, equipment power data, fan speed data, and pollutant concentration data are digitally processed and outlier filtered to obtain the oil fume-related parameters.

3. The energy-saving control method for an integrated ultra-low emission fume extractor according to claim 1, characterized in that, The process of extracting and classifying the oil fume-related parameters to obtain a scene category representing the current kitchen cooking state and a corresponding combination of control parameters includes: The oil fume-related parameters are standardized to obtain standardized feature data with uniform value ranges; The standardized feature data is input into a support vector machine classifier to obtain the category and probability value of the current cooking scenario; Based on the categories described, the current cooking state is divided into idle mode, preparation mode, light cooking mode, medium cooking mode, or heavy cooking mode. Time smoothing is applied to cooking scene categories to obtain stable scene judgment results; Based on the stable scenario judgment result, select the corresponding basic control parameters to obtain an initial control parameter combination that includes the fan speed value, the purification unit working intensity value and the heat exchange system working intensity value. The initial control parameter combination is dynamically adjusted by adjusting the rate of change of ambient temperature and oil fume concentration to obtain the corresponding control parameter combination.

4. The energy-saving control method for an integrated ultra-low emission fume extractor according to claim 1, characterized in that, The energy consumption optimization calculation based on the scenario category and control parameter combination to obtain the target control command includes: Based on the scenario category, the fan speed range, the purification unit working intensity range, and the heat exchange system working intensity range are set to obtain the control parameter optimization range; Energy consumption is calculated for the fan speed, purification unit workload, and heat exchange system workload in the control parameter combination to obtain the current energy consumption value. The minimum required purification efficiency is calculated based on the oil fume concentration data and pollutant concentration data, thus obtaining the purification constraints. Within the optimized range of the control parameters, the fan speed is adjusted, and the energy consumption change rate after adjustment is calculated to obtain the optimized energy consumption value of the fan. Within the optimized range of the control parameters, the working intensity values ​​of the purification unit and the heat exchange system are adjusted to obtain the lowest energy consumption combination that meets the purification constraints. The optimized energy consumption value and the minimum energy consumption combination of the wind turbine are integrated into a control command to obtain the target control command.

5. The energy-saving control method for an integrated ultra-low emission fume extractor according to claim 4, characterized in that, The step of adjusting the working intensity values ​​of the purification unit and the heat exchange system within the optimization range of the control parameters to obtain the lowest energy consumption combination that meets the purification constraints includes: The working intensity value of the purification unit is discretely sampled within the range of minimum to maximum value according to a set step size to obtain the sampling point set of the working intensity of the purification unit. The working intensity value of the heat exchange system is discretely sampled within the range of minimum to maximum value according to a set step size to obtain the sampling point set of the working intensity of the heat exchange system. The working intensity sampling point set of the purification unit and the working intensity sampling point set of the heat exchange system are orthogonally combined to obtain the working intensity parameter combination matrix. Calculate the energy consumption value and purification efficiency value of each combination point in the working intensity parameter combination matrix to obtain the performance evaluation result of the combination point; From the combined point performance evaluation results, a set of combined points that meet the purification constraints is selected to obtain an effective control parameter subset. The lowest energy consumption parameter combination is obtained by finding the parameter combination with the lowest energy consumption in the subset of effective control parameters.

6. The energy-saving control method for an integrated ultra-low emission fume extractor according to claim 5, characterized in that, The orthogonal combination of the sampling point set of the working intensity of the purification unit and the sampling point set of the working intensity of the heat exchange system yields a working intensity parameter combination matrix, including: Based on the size of the sampling point set of the working intensity of the purification unit and the size of the sampling point set of the working intensity of the heat exchange system, the number of rows and columns of the orthogonal experimental table is determined, and the orthogonal experimental design scheme is obtained. The sampling points of the working intensity sampling point set of the purification unit are distributed into the corresponding columns of the orthogonal test table according to the principle of equal spacing to obtain the test level value of the working intensity of the purification unit. The sampling points of the heat exchange system working intensity sampling point set are distributed into the corresponding columns of the orthogonal test table according to the principle of equal spacing to obtain the test level value of the heat exchange system working intensity. The test level values ​​are orthogonally combined to generate test combination schemes, and the optimal combination points that reduce the number of tests are obtained. Calculate the energy consumption contribution and purification efficiency contribution corresponding to each of the optimized combination points to obtain the parameter sensitivity analysis results; Based on the parameter sensitivity analysis results, additional sampling is performed on the optimized combination points to obtain the working intensity parameter combination matrix.

7. The energy-saving control method for an integrated ultra-low emission fume extractor according to claim 1, characterized in that, The process of executing the target control command through a hierarchical control structure to adjust the equipment and evaluating and analyzing the operating status data to obtain energy-saving control feedback data includes: The target control instructions are decomposed into decision-making layer instructions, coordination layer instructions, and execution layer instructions to obtain control tasks at each level. The coordination layer instructions are transmitted to the controllers of each subsystem via the control bus to obtain fan control instructions, oil-water separation control instructions, filtration control instructions, purification control instructions and heat exchange control instructions; Each execution unit adjusts the corresponding physical component parameters according to the execution layer instructions, thereby adjusting the fan speed, the working intensity of the purification unit, and the working intensity of the heat exchange system. Collect and adjust equipment operating status information to obtain real-time energy consumption data, purification efficiency data, and equipment health status data; The real-time energy consumption data, purification efficiency data, and equipment health status data are evaluated from multiple dimensions to obtain performance evaluation indicators; The energy-saving control feedback data is obtained by comparing and analyzing the performance evaluation indicators with the expected targets.

8. An energy-saving control system for an integrated ultra-low emission kitchen fume generator, characterized in that, An energy-saving control method for an integrated ultra-low emission fume generator as described in any one of claims 1-7, wherein the energy-saving control system for the integrated ultra-low emission fume generator comprises: The data acquisition module is used to collect oil fume-related parameters through multiple sensors installed in the integrated ultra-low emission oil fume machine, and obtain oil fume concentration data, fan speed data, equipment power data, temperature data and pollutant concentration data; The classification module is used to extract features and classify the oil fume-related parameters to obtain the scene category and corresponding control parameter combination representing the current kitchen cooking state; The calculation module is used to perform energy consumption optimization calculations based on the scenario category and the combination of control parameters to obtain the target control command; The adjustment module is used to execute the target control command through a hierarchical control structure to adjust the equipment, and to evaluate and analyze the operating status data to obtain energy-saving control feedback data.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is run by the processor, it causes the processor to execute the energy-saving control method for an integrated ultra-low emission fume generator as described in any one of claims 1 to 7.

Images