A method, system, device and medium for controlling variable frequency operation of a fan

Abstract

The embodiments of the present specification provide a method, system, device and medium for controlling the variable frequency operation of a fan, the method being executed by a processor, including obtaining food data of food to be processed, the food data including at least one of food type and storage characteristics; determining operating parameters of the processing equipment and / or the fan equipment based on the food data and the power consumption characteristics of the processing equipment; generating control instructions based on the operating parameters, and sending the control instructions to the fan equipment to control the fan equipment to determine the working parameters and perform fume extraction based on the control instructions according to the fume detection results during the processing.

Description

Technical Field

[0001] The present specification relates to the field of food processing, and in particular to a method, system, device and medium for controlling variable frequency operation of a fan. Background Art

[0002] In traditional food processing technology, the operating parameters of processing equipment or fan equipment often rely on the operator's experience and intuition, resulting in a lack of scientific and accurate setting of operating parameters. This not only fails to guarantee the taste and quality of food, but also may cause waste of oil products and food safety hazards. In addition, traditional processing methods do not involve intelligent control of fans for oil fume extraction and auxiliary monitoring of whether food and oil products have deteriorated.

[0003] Therefore, it is necessary to provide a method, system, device and medium for controlling the variable frequency operation of the fan. By optimizing the operating parameters, the efficiency of the fan equipment in extracting oil fumes and the quality of food processing can be improved. At the same time, it can assist in monitoring the quality of food and oil products, making the food processing process more intelligent and ensuring the safety of food processing. Summary of the invention

[0004] One or more embodiments of the present specification provide a method for controlling variable frequency operation of a fan, the method being executed by a processor, the method comprising: acquiring food data of food to be processed, the food data comprising at least one of food type and storage characteristics; determining operating parameters of the processing equipment and / or the fan equipment based on the food data and power consumption characteristics of the processing equipment; generating a control instruction based on the operating parameters, and sending the control instruction to the fan equipment to control the fan equipment to determine the operating parameters and perform fume extraction based on the control instruction according to the fume detection result during the processing.

[0005] One or more embodiments of the present specification provide a system for controlling variable frequency operation of a fan, the system comprising a processor, an image sensing unit, and a smoke detection unit that are communicatively connected, the processor being configured to: obtain food data of food to be processed, the food data comprising at least one of food type and storage characteristics; determine operating parameters of the processing equipment and / or the fan equipment based on the food data and power consumption characteristics of the processing equipment; generate control instructions based on the operating parameters, and send the control instructions to the fan equipment to control the fan equipment to determine working parameters and perform fume extraction based on the control instructions according to a result of fume detection during processing.

[0006] One or more embodiments of the present specification provide a device for controlling variable frequency operation of a fan, characterized in that the device includes at least one memory and at least one processor, the at least one memory is used to store computer instructions, and the at least one processor executes the computer instructions or part of the instructions to implement a method for controlling variable frequency operation of a fan.

[0007] One or more embodiments of the present specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a method for controlling variable frequency operation of a fan. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0009] Figure 1 It is an application scenario diagram of the method for controlling the variable frequency operation of a fan according to some embodiments of this specification;

[0010] Figure 2 is a system module diagram of a system for controlling variable frequency operation of a fan according to some embodiments of this specification;

[0011] Figure 3 is an exemplary flow chart of a method for controlling variable frequency operation of a fan according to some embodiments of this specification;

[0012] Figure 4 is an exemplary flow chart of generating first warning information according to some embodiments of this specification;

[0013] Figure 5 is an exemplary schematic diagram of a first prediction model according to some embodiments of this specification;

[0014] Figure 6 This is an exemplary flowchart of generating second warning information according to some embodiments of this specification. DETAILED DESCRIPTION

[0015] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0016] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0017] Figure 1 It is an application scenario diagram of the method for controlling the variable frequency operation of a fan according to some embodiments of this specification.

[0018] The application scenario may include a processor 110, an image sensing unit 120, a smoke detection unit 130, a network 140, a processing device 150, and a fan device 160, etc.

[0019] The processor 110 is configured to apply the method of controlling the variable frequency operation of the fan in various application scenarios. For example, the processor 110 determines the operating parameters of the processing equipment and / or the fan device based on the food data and the power consumption characteristics of the processing equipment. For another example, the processor 110 generates a control instruction based on the operating parameters, sends the control instruction to the fan device, determines the working parameters based on the control instruction, and performs oil fume extraction.

[0020] The processing equipment 150 refers to equipment for processing food. The fan equipment 160 refers to equipment for extracting oil smoke. In some embodiments, the processing equipment includes at least one of an electric cooker, a frying pan, etc. The fan equipment includes at least one of a centrifugal fan, an axial flow fan, etc.

[0021] The image sensing unit 120 is configured to obtain the characteristics of oil surface bubbles, oil color, and oil surface fluctuations when the processing equipment 150 processes food.

[0022] The smoke detection unit 130 is configured to obtain a smoke detection result and a smoke characteristic of the smoke sucked by the fan device 160 .

[0023] The network 140 is configured to implement data interaction between the processor 110 and other units or devices in the application scenario diagram and to obtain network interaction data. In some embodiments, the processor 110 can also obtain data uploaded by the user through the network 140.

[0024] In a typical application scenario, the image sensing unit 120 obtains the characteristics of oil bubbles, oil color, and oil surface fluctuations when the processing equipment 150 processes food, the smoke detection unit 130 obtains the oil smoke detection results and oil smoke characteristics of the oil smoke sucked by the fan device 160, and the image sensing unit 120 and the smoke detection unit 130 upload the obtained data to the network 140. The network 140 obtains network interaction data and sends the data obtained by the image sensing unit 120 and the smoke detection unit 130, the food data uploaded by the user, the power consumption characteristics uploaded by the processing equipment 150, and the network interaction data to the processor 150.

[0025] The processor 150 determines the operating parameters of the processing equipment 150 and / or the fan device 160 based on the food material data and the power consumption characteristics, generates a control instruction based on the operating parameters, and sends the control instruction to the fan device 160 to control the fan device 160 to determine the operating parameters and perform fume extraction based on the control instruction according to the fume detection result. The processor 150 also determines the internal deterioration risk of the food material based on the food material data, the fume characteristics, and the oil surface bubble characteristics. The processor 150 also determines the viscosity of the oil product based on the color of the oil product and the oil surface fluctuation characteristics.

[0026] For detailed description of the above, please refer to Figures 2 to 6 Related description.

[0027] Figure 2 It is a system module diagram of a system for controlling variable frequency operation of a fan according to some embodiments of this specification.

[0028] In some embodiments, Figure 2 As shown, the system 200 for controlling the variable frequency operation of a fan includes a processor 110 , an image sensing unit 220 , and a smoke detection unit 230 , which are communicatively connected.

[0029] The processor 110 is configured to process data from at least one unit of the system 200 for controlling variable frequency operation of a fan or an external data source. In some embodiments, the processor may include a central processing unit (CPU), an application specific integrated circuit (ASIC), a graphics processing unit (GPU), a digital signal processor (DSP), a microprocessor, etc., or any combination thereof.

[0030] In some embodiments, the processor 110 may be communicatively coupled to the image sensing unit 220, the smoke detection unit 230, and the processing equipment and the fan equipment.

[0031] In some embodiments, the processor 110 is also configured to obtain food data of the food to be processed; determine the operating parameters of the processing equipment and / or the fan equipment based on the food data and the power consumption characteristics of the processing equipment; generate control instructions based on the operating parameters, and send the control instructions to the fan equipment, determine the working parameters based on the control instructions and perform oil fume extraction.

[0032] In some embodiments, the system 200 for controlling variable frequency operation of a fan may further include a memory configured to store data, information, or instructions related to the system 200 for controlling variable frequency operation of a fan.

[0033] The image sensing unit 220 refers to a unit capable of collecting and analyzing images. In some embodiments, the image sensing unit 220 includes a camera, an image analyzer, and the like.

[0034] In some embodiments, the image sensing unit 220 is configured to obtain the characteristics of oil surface bubbles, oil color, and oil surface fluctuations during the processing. The image sensing unit 220 can be set at any position around the processing equipment where the oil surface can be photographed.

[0035] The smoke detection unit 230 is a unit for detecting oil smoke related data. In some embodiments, the smoke detection unit 230 includes a smoke sensor, a component detector, and the like.

[0036] In some embodiments, the smoke detection unit 230 is configured to obtain the oil smoke detection result and the oil smoke characteristics. The smoke detection unit 230 may be disposed in the fan device.

[0037] In some embodiments, the system 200 for controlling variable frequency operation of a fan executes a method for controlling variable frequency operation of a fan through the processor 110 .

[0038] By controlling the fan variable frequency operation system, the fan equipment can be intelligently controlled to extract oil fumes, thereby improving the efficiency of the fan equipment in extracting oil fumes.

[0039] Figure 3 is an exemplary flow chart of a method for controlling variable frequency operation of a fan according to some embodiments of this specification. In some embodiments, process 300 may be executed by a processor. Figure 3 As shown, process 300 includes the following steps.

[0040] Step 310, obtaining food data of the food to be processed.

[0041] The food to be processed refers to food waiting to be processed. In some embodiments, the food to be processed includes at least one of vegetables, meat, pasta, etc.

[0042] Ingredient data refers to data related to the ingredients to be processed. In some embodiments, the ingredient data includes at least one of ingredient type and storage characteristics. The ingredient type includes at least one of staple food, vegetarian food, and meat.

[0043] The storage characteristics are used to characterize the storage process of the food to be processed. In some embodiments, the storage characteristics include at least one of storage temperature and storage duration.

[0044] In some embodiments, the processor may obtain the food material data by obtaining user input or the like.

[0045] Step 320, based on the food data and the power consumption characteristics of the processing equipment, determine the operating parameters of the processing equipment and / or the fan equipment.

[0046] For information on processing equipment and fan equipment, see Figure 1 and its related description.

[0047] The power usage characteristics are used to reflect the power usage of the processing equipment during normal processing. In some embodiments, the power usage characteristics include at least one of power consumption, minimum power, and maximum power. In some embodiments, the processor obtains the power usage characteristics of the processing equipment through the processing equipment.

[0048] The operating parameters refer to parameters that indicate the operation of the processing equipment and / or the fan equipment. In some embodiments, the operating parameters include the power range of the fan equipment, the oil temperature curve of the processing equipment, etc.

[0049] The power range refers to the power range that the fan equipment can use for oil fume extraction.

[0050] In some embodiments, the processor may select the power of the fan device for extracting the oil smoke from the power range according to the oil smoke detection result during the processing, so as to extract the oil smoke. For the description of this part, please refer to step 330.

[0051] The oil temperature curve refers to a curve that characterizes the change of the oil temperature required for processing the food to be processed over time. In some embodiments, the abscissa of the oil temperature curve includes time, and the ordinate includes the oil temperature.

[0052] In some embodiments, the processor determines the operating parameters by various methods based on the food material data and the power consumption characteristics of the processing equipment. For example, the processor determines the reference operating parameters as the operating parameters by querying the reference operating parameters corresponding to the food material data and the power consumption characteristics in the parameter table based on the food material data and the power consumption characteristics.

[0053] In some embodiments, the processor constructs a parameter table based on historical data. For example, the processor selects the historical processing process of the historical food to be processed in which the state after processing meets the standard as reference data, and enters the food data and power consumption characteristics corresponding to the reference data into the parameter table, and counts the actual operating parameters corresponding to the reference data, and enters the actual operating parameters that meet the screening conditions into the parameter table as reference operating parameters. The screening conditions include the most times used. The actual operating parameters refer to the operating parameters actually used in the historical processing process.

[0054] In some embodiments, the processor determines whether the state of the food to be processed after processing meets the standard based on the content of the ingredients contained in the food to be processed after processing. For example, if the ratio of the number of ingredients with the content meeting the standard to the total number of ingredients after processing exceeds a preset ratio, the processor determines that the state of the food to be processed after processing meets the standard. Among them, the content of the ingredient meets the standard means that the content of the ingredient exceeds the preset content value corresponding to the ingredient. One ingredient corresponds to one preset content value. The preset content value and the preset ratio are preset based on historical experience.

[0055] Exemplarily, if the ingredients contained in the food to be processed after processing include fat, protein, iron and trace elements, among which the content of fat, protein and iron meets the standard, then the ratio of the number of ingredients with meeting the standard to the total number of ingredients is 75%, which exceeds the preset ratio of 70%, then the processor determines that the state of the food to be processed meets the standard after processing.

[0056] In some embodiments, the content of each component of the food to be processed after processing can be obtained by manual detection or other methods.

[0057] In some embodiments, the processor predicts the inner temperature of the food to be processed based on the food type, storage characteristics, surface temperature of the food to be processed, thawing environment characteristics and thawing time, and determines the oil temperature curve based on the food type, surface temperature, inner temperature and electricity consumption characteristics.

[0058] The surface temperature refers to the temperature of the surface of the food to be processed. In some embodiments, a temperature monitoring device may be provided in the processing equipment. The temperature monitoring device is used to collect the surface temperature of the food to be processed and send it to the processor. The processor may also obtain the surface temperature of the food to be processed by manual detection or the like. Among them, the temperature monitoring device includes at least one of a temperature sensor, a thermometer, a thermometer, etc.

[0059] Thawing environment characteristics refer to data that characterize the environment when the food to be processed is thawed. In some embodiments, the thawing environment characteristics include at least one of thawing method, thawing temperature, and thawing humidity. Among them, the thawing method includes at least one of thawing in water or thawing in air. Thawing temperature and thawing humidity refer to the temperature and humidity of the environment when the food to be processed is thawed. For example, if the thawing method is thawing in water, the thawing temperature is the water temperature. If the thawing method is thawing in the air, the thawing temperature and thawing humidity are the temperature and humidity of the air.

[0060] The thawed time refers to the time from the beginning of thawing of the food to be processed to the current moment.

[0061] In some embodiments, the thawing method is determined according to actual thawing needs. The thawing temperature, thawing humidity, and thawing time can be obtained by instrument collection or obtaining user input. Instrument collection includes using instruments such as thermometers, hygrometers, and timers that are communicatively connected to the processor to obtain the thawing temperature, thawing humidity, and thawing time, and uploading the thawing temperature, thawing humidity, and thawing time to the processor.

[0062] Internal temperature refers to the temperature inside the food to be processed.

[0063] In some embodiments, the processor determines the inner layer temperature in a variety of ways based on the food type, storage characteristics, surface temperature, thawing environment characteristics, and thawing time. For example, the processor queries a preset temperature curve corresponding to the food type, storage characteristics, surface temperature, and thawing environment characteristics in a temperature relationship library based on the food type, storage characteristics, surface temperature, and thawing environment characteristics, and determines the inner layer temperature of the food to be processed based on the thawing time and the preset temperature curve.

[0064] In some embodiments, the temperature relationship library includes multiple data groups and preset temperature curves corresponding to different data groups. Among them, a single data group includes food type, storage characteristics, surface temperature and thawing environment characteristics. The preset temperature curve refers to a curve that characterizes the change of inner layer temperature with thawing time, the horizontal axis includes the thawing time, and the vertical axis includes the inner layer temperature.

[0065] In some embodiments, the processor queries the inner layer temperature corresponding to the thawing time in the preset temperature curve based on the thawing time, and confirms the inner layer temperature as the inner layer temperature of the food to be processed.

[0066] In some embodiments, the processor can build a temperature relationship library based on historical data and / or experimental data. The experimental data is obtained through a large number of experiments. Exemplarily, the experimental process includes: for the ingredients to be processed with different food types, storage characteristics and surface temperatures, thawing under different thawing environments, measuring the changes in the inner layer temperature of the ingredients to be processed as the thawing time increases, and building a preset temperature curve based on the measurement results. Among them, the inner layer temperature of the ingredients to be processed during the experiment can be obtained by measuring the temperature of the inside of the ingredients to be processed based on equipment such as temperature sensors.

[0067] In some embodiments, the processor can also determine the target database based on the food type, construct a vector to be matched based on storage characteristics, thawing environment characteristics and thawing time, calculate the similarity between the vector to be matched and multiple target vectors in the target database, determine multiple association vectors based on the similarity, and determine the inner layer temperature based on the inner layer temperature values ​​corresponding to the multiple association vectors.

[0068] It is understandable that the historical inner layer temperatures in the temperature relationship library are obtained through experiments, and the experimental environment is relatively simple. In actual situations, the environment for processing food is more complex, and during the thawing process of food, the thawing environment characteristics may change, so a large amount of historical data is needed to correct the data obtained through experiments.

[0069] The target database includes multiple target vectors and inner layer temperatures corresponding to different target vectors. The target vector refers to a feature vector constructed based on historical storage characteristics, historical thawing environment characteristics, and historical thawing time. In some embodiments, the processor determines the target databases corresponding to different food types based on historical data. For example, the processor selects multiple historical processing processes of the same food type to be processed from the historical data, constructs a target vector based on the historical storage characteristics, historical thawing environment characteristics, and historical thawing time corresponding to each historical processing process in the multiple historical processing processes, and uses the obtained multiple target vectors as the target vectors in the target database corresponding to the food type, and uses the historical inner layer temperature in the historical processing process corresponding to the target vector as the inner layer temperature corresponding to the target vector.

[0070] In some embodiments, the similarity between vectors may be negatively correlated to the distance between the vectors. The vector distance includes the Euclidean distance and the like.

[0071] In some embodiments, the processor sorts the multiple target vectors according to the similarity based on the similarity, and determines the target vectors that meet the association condition as the association vector. The association condition includes an order higher than the preset order bit in the similarity sorting. The preset order bit is pre-set based on the data processing load of the processor, and the greater the data processing load, the later the preset order bit. The data processing load refers to the maximum amount of data that the processor can process per unit time.

[0072] In some embodiments, the processor may determine the inner layer temperature in a variety of ways based on the inner layer temperature values ​​corresponding to the plurality of association vectors. For example, the processor may determine the mean of the inner layer temperature values ​​corresponding to the plurality of association vectors as the inner layer temperature of the food to be processed.

[0073] In some embodiments, the processor may also determine the inner temperature of the food to be processed by weighting based on the inner temperature values ​​corresponding to the multiple association vectors, wherein the weight of the inner temperature value is related to the similarity and environmental difference between the corresponding association vector and the vector to be matched.

[0074] The environmental difference is used to characterize the degree of difference between the historical thawing environmental features in the association vector and the thawing environmental features in the vector to be matched. In some embodiments, the processor can calculate the vector distance between the sub-vector composed of the historical thawing environmental features of the association vector and the sub-vector composed of the thawing environmental features of the vector to be matched, and confirm the vector distance as the environmental difference between the association vector and the vector to be matched.

[0075] For example, the processor may determine the weight of the inner layer temperature value through a preset algorithm based on the similarity and environmental difference between the association vector corresponding to the inner layer temperature value and the vector to be matched. The preset algorithm is shown in the following formula (1):

[0076] Among them, Q is the weight of the inner temperature value, C is the environmental difference between the association vector corresponding to the inner temperature value and the vector to be matched, S is the similarity between the association vector corresponding to the inner temperature value and the vector to be matched, and w1 is the order of magnitude constant. The order of magnitude constant is used to adjust the value of the weight of the inner temperature value to less than 1. The order of magnitude constant is preset based on historical experience.

[0077] In some embodiments, the processor may calculate a weighted average of the inner layer temperature values ​​corresponding to the plurality of correlation vectors, and determine the weighted average as the inner layer temperature.

[0078] Based on the inner layer temperature values ​​corresponding to the multiple correlation vectors, the inner layer temperature is weighted and determined, which can improve the accuracy of determining the inner layer temperature. Considering that the thawing environment characteristics have a greater impact on the inner layer temperature, the weight of the inner layer temperature value is determined based on the thawing environment characteristics, which can further improve the accuracy of determining the inner layer temperature.

[0079] According to the food type, a target database that better matches the current food to be processed can be determined. Compared with using the temperature relationship library to determine the inner layer temperature, the method of using the target database to determine the inner layer temperature of the food to be processed can determine the inner layer temperature that better matches the actual complex thawing environment.

[0080] In some embodiments, the processor determines the oil temperature curve based on the food type, surface temperature, inner temperature, and power consumption characteristics. For example, the processor determines the historical oil temperature curve corresponding to the food type, surface temperature, inner temperature, and power consumption characteristics by querying a preset oil temperature table, and determines the historical oil temperature curve as the current oil temperature curve.

[0081] The preset oil temperature table is constructed based on historical data, including multiple groups of historical food types, historical surface temperatures, historical inner temperatures, historical electricity consumption characteristics, and historical oil temperature curves corresponding to different groups.

[0082] Taking the surface temperature and inner temperature of the food to be processed into consideration when determining the oil temperature curve can select a more targeted oil temperature curve, thereby ensuring the taste of the food to be processed after processing, avoiding food waste, and avoiding repeated processing to improve cooking efficiency.

[0083] Step 330, generating a control instruction based on the operating parameters, and sending the control instruction to the fan device to control the fan device to determine the operating parameters and perform fume extraction based on the control instruction according to the fume detection result during the processing.

[0084] The control instruction refers to an instruction for controlling the operation of the wind turbine device. In some embodiments, the processor may convert the power interval in the operating parameter into a machine instruction, and send the machine instruction as the control instruction to the wind turbine device.

[0085] The oil fume detection result refers to the relevant data obtained by detecting the oil fume generated during the processing. In some embodiments, the oil fume detection result includes the intensity of the oil fume, etc. The oil fume detection result is obtained by the smoke detection unit and sent to the processor.

[0086] The working parameters refer to the parameters used by the fan device to extract oil smoke. In some embodiments, the working parameters include the power of the fan device.

[0087] In some embodiments, the processor selects a power from the power range as a working parameter based on the smoke intensity in the smoke detection result and the power range in the control instruction, and controls the fan device to extract the smoke based on the working parameter. The greater the smoke intensity, the greater the power selected by the processor in the power range.

[0088] In some embodiments, the processor may convert the oil temperature curve in the operating parameters into machine instructions, and send the machine instructions as processing instructions to the processing equipment to control the processing equipment to process the food to be processed according to the oil temperature curve.

[0089] According to the food data of the food to be processed and the power consumption characteristics of the processing equipment, more targeted operating parameters can be determined, so as to improve the processing quality of the food to be processed and reduce the loss of food ingredients. At the same time, the power of the fan equipment can be selected from the operating parameters based on the oil fume detection results, which can effectively absorb the oil fume while avoiding excessive use of the fan equipment and reducing costs.

[0090] Figure 4 is an exemplary flow chart of generating the first warning information according to some embodiments of this specification. Figure 4 As shown, process 400 includes the following steps.

[0091] Step 410, obtain the characteristics of oil smoke through the smoke detection unit deployed in the fan equipment, and obtain the characteristics of oil surface bubbles through the image sensor unit. For the description of the smoke detection unit and the image sensor unit, see Figure 1 and Figure 2 and its related description.

[0092] The oil smoke feature refers to a feature related to the oil smoke. In some embodiments, the oil smoke feature includes oil smoke components, etc. The oil smoke feature is acquired by the smoke detection unit and sent to the processor.

[0093] The oil surface bubble feature refers to a feature related to the bubbles on the oil surface, for example, at least one of the distribution and size of the bubbles. In some embodiments, the image sensing unit can acquire an image of the oil surface, extract the oil surface bubble feature in the image, and send it to the processor.

[0094] Step 420, based on the food type, storage characteristics, oil smoke characteristics, and oil bubble characteristics, determine the internal deterioration risk of the food to be processed.

[0095] For information on food type and storage characteristics, please refer to the description of step 310.

[0096] The internal spoilage risk is used to characterize the possibility that the food to be processed has deteriorated internally before processing. In some embodiments, the internal spoilage risk can be represented by a numerical range of 0-1, and an internal spoilage risk of 1 indicates that the food to be processed has deteriorated before processing.

[0097] In some embodiments, the processor can determine the internal spoilage risk in a variety of ways based on the food type, storage characteristics, oil fume characteristics, and oil bubble characteristics. For example, the processor can construct a spoilage vector based on the food type, storage characteristics, oil fume characteristics, and oil bubble characteristics, calculate the similarity between the spoilage vector and multiple reference spoilage vectors in the spoilage risk database, and use the historical internal spoilage risk corresponding to the reference spoilage vector that meets the similarity condition as the internal spoilage risk of the food to be processed. The spoilage vector refers to a feature vector constructed based on the food type, storage characteristics, oil fume characteristics, and oil bubble characteristics. The similarity condition includes the highest similarity of the vectors.

[0098] In some embodiments, the spoilage risk database is constructed based on historical data, including multiple reference spoilage vectors and historical internal spoilage risks corresponding to different reference spoilage vectors. The reference spoilage vector refers to a feature vector constructed based on historical food type, historical storage characteristics, historical oil smoke characteristics, and historical oil surface bubble characteristics.

[0099] In some embodiments, the processor may determine the historical internal spoilage risk based on the historical spoilage components of the historical food to be processed. For example, the processor calculates the ratio of the content of each historical spoilage component to the content threshold corresponding to the historical spoilage component based on multiple historical spoilage components of the historical food to be processed, and determines the average of the multiple ratios obtained as the internal spoilage risk.

[0100] The historical spoiled components refer to the components that may have spoiled in the historical food materials to be processed. In some embodiments, the historical spoiled components are preset based on historical experience. The content of the historical spoiled components is obtained by manual detection or other methods.

[0101] In some embodiments, the content threshold corresponding to each historical spoilage component is preset based on historical experience. If the ratio of the content of a single historical spoilage component to the content threshold corresponding to the historical spoilage component exceeds the preset spoilage threshold, the processor directly determines that the historical internal spoilage risk is 1. The preset spoilage threshold is preset based on historical experience, such as 80%.

[0102] In some embodiments, the processor may also determine the internal spoilage risk through the first prediction model based on the food type, storage characteristics, oil smoke characteristics, and oil bubble characteristics. Figure 5 and its related description.

[0103] Step 430: In response to the internal deterioration risk meeting the deterioration condition, generate and send first warning information.

[0104] The spoilage condition refers to a condition used to determine whether the food to be processed has spoiled internally before processing. In some embodiments, the spoilage condition includes that the risk of internal spoilage is not less than a risk threshold. The risk threshold is set based on historical experience or actual needs.

[0105] The first warning information refers to warning information used to remind the user that the food to be processed has deteriorated. In some embodiments, the first warning information includes sound information, text information, etc. The processor can send the first warning information to a terminal device (e.g., a mobile phone, a computer, etc.) or a prompt device (e.g., a display, a speaker, etc.) used by the user to warn the user.

[0106] Since the deterioration of the food to be processed will cause abnormal bubbles to appear on the oil surface when cooking the food, and the oil fume composition will also change. Based on the oil fume composition and the characteristics of the bubbles on the oil surface, it is possible to promptly detect whether the food to be processed has deteriorated and issue an early warning to the user. This is more convenient than directly detecting whether the food to be processed has deteriorated, and is conducive to the subsequent replacement or inspection of the food to be processed.

[0107] Figure 5 It is a schematic diagram of the structure of the first prediction model shown in some embodiments of this specification.

[0108] In some embodiments, Figure 5 As shown, the processor can determine the internal spoilage risk 530 through the first prediction model 520 based on the food type 511 , storage characteristics 512 , oil smoke characteristics 513 , and oil bubble characteristics 514 .

[0109] For information on food types, storage characteristics, oil smoke characteristics, and oil bubble characteristics, see Figure 3 and Figure 4 Related description.

[0110] The first prediction model refers to a model for determining the risk of internal deterioration. In some embodiments, the first prediction model is a machine learning model, such as any one or combination of a deep neural network (DNN) model or other custom model structures.

[0111] In some embodiments, the input of the first prediction model includes food type, storage characteristics, oil smoke characteristics, and oil bubble characteristics, and the output may include internal spoilage risk.

[0112] In some embodiments, the input of the first prediction model may further include the surface temperature 515 and the inner temperature 516 of the food to be processed. For the description of the surface temperature and the inner temperature, please refer to the relevant description of step 320.

[0113] The same kind of food has different internal spoilage risks at different surface temperatures and internal temperatures. When determining the internal spoilage risk through the first prediction model, the correlation between the surface temperature and the internal temperature and the internal spoilage of the food is taken into account, which can improve the accuracy of the determined internal spoilage risk.

[0114] In some embodiments, the processor trains the first prediction model based on the first training data set by a gradient descent method or the like. The first training data set includes a first training sample and a first label corresponding to the first training sample. The first training sample includes the sample food type, sample storage characteristics, sample oil smoke characteristics, and sample oil bubble characteristics during the processing of the sample food to be processed, and the first label includes the historical internal deterioration risk corresponding to the sample food to be processed.

[0115] In some embodiments, the processor can obtain the first training sample and the first label from historical data. For example, the processor uses the historical food to be processed as the sample food to be processed, and uses the historical food type, historical storage characteristics, historical oil fume characteristics, and historical oil bubble characteristics during the processing of the sample food to be processed as the first training sample, and determines the first label based on the internal deterioration of the sample food to be processed. The internal deterioration includes internal deterioration and non-deterioration. If the internal deterioration, the first label is 1. If the internal deterioration is not, the first label is 0.

[0116] In some embodiments, the first prediction model is trained by: inputting a plurality of first training samples with first labels into an initial first prediction model, constructing a loss function through the first labels and the prediction results of the initial first prediction model, iteratively updating the initial first prediction model based on the loss function, and completing the training of the first prediction model when the loss function of the initial first prediction model satisfies a preset condition. The preset conditions include convergence of the loss function, the number of iterations reaching a set value, etc.

[0117] In some embodiments, if the input of the first prediction model can also include the surface temperature and the inner temperature of the food to be processed, the first training sample also includes the sample surface temperature and the sample inner temperature during the processing of the sample food. The method of obtaining the sample surface temperature and the sample inner temperature is similar to the method of obtaining the first training sample.

[0118] By processing data such as oil fume characteristics and oil surface bubble characteristics through the first prediction model, the self-learning ability of the machine learning model can be used to find patterns from a large amount of data, obtain the correlation between data such as oil fume characteristics and oil surface bubble characteristics and internal deterioration risks, and improve the accuracy and efficiency of determining internal deterioration risks.

[0119] Figure 6is an exemplary flow chart of generating the second warning information according to some embodiments of this specification. Figure 6 As shown, process 600 includes the following steps.

[0120] Step 610, the color of the oil and the fluctuation characteristics of the oil surface during the processing are obtained through the image sensor unit. For the description of the image sensor unit, see Figure 1 and Figure 2 and its related description.

[0121] The oil color refers to the color of the oil used in the current processing, for example, at least one of yellow-brown, yellow-brown, etc.

[0122] The oil surface fluctuation characteristics refer to data related to the surface fluctuation of the oil product, for example, at least one of the wavelength and frequency of the waves formed by the fluctuations at various locations on the surface of the oil product.

[0123] In some embodiments, the image sensing unit can acquire an image of the oil surface, and extract the oil color and oil surface fluctuation characteristics in the image and send them to the processor.

[0124] Step 620, determining the viscosity of the oil based on the oil surface fluctuation characteristics and the oil surface bubble characteristics.

[0125] Oil viscosity refers to data used to characterize the viscosity of oil. In some embodiments, oil viscosity can be represented by a numerical value, etc. The higher the numerical value, the higher the oil viscosity.

[0126] In some embodiments, the processor may determine the oil viscosity based on the oil surface fluctuation characteristics and the oil surface bubble characteristics. For example, the processor determines the reference oil viscosity corresponding to the oil surface fluctuation characteristics and the oil surface bubble characteristics by querying the viscosity table based on the oil surface fluctuation characteristics and the oil surface bubble characteristics, and confirms the reference oil viscosity as the current oil viscosity.

[0127] In some embodiments, the viscosity table is constructed based on experimental data, including multiple groups of oil surface fluctuation characteristics and oil surface bubble characteristics and reference oil viscosity corresponding to different groups. The experimental process includes: manually marking the viscosity of different oils to obtain reference oil viscosity of different oils, heating different oils, recording the oil surface fluctuation characteristics and oil surface bubble characteristics during the heating process, and recording the reference oil viscosity, oil surface fluctuation characteristics and oil surface bubble characteristics of each oil into the viscosity table.

[0128] Step 630, predicting the oil rancidity risk based on historical oil composition, oil color, oil viscosity, and oil smoke characteristics.

[0129] Historical oil composition refers to the composition of oil obtained in the past. Oil composition refers to the composition of oil used in the current processing process, including at least one of fatty acids or hydrocarbons.

[0130] In some embodiments, the historical oil composition includes the oil composition detected in the previous oil composition detection of the oil used in the current processing process. The oil composition detection is obtained by using a composition detector and other methods. It is understandable that the oil composition obtained in the previous oil composition detection has the highest reliability.

[0131] The oil rancidity risk is used to characterize the possibility of oil rancidity. In some embodiments, the oil rancidity risk can be represented by a numerical range of 0-1, and the oil rancidity risk is 1, indicating that the oil has become rancid.

[0132] Oil rancidity refers to the deterioration (e.g., discoloration, taste change) of oil due to the action of microorganisms, enzymes, oxygen, etc. If the result of the oil component test of the oil includes components that may appear when the oil is rancid, the processor determines that the oil is rancid. The components that may appear when the oil is rancid are preset based on historical experience.

[0133] In some embodiments, the processor can determine the oil rancidity risk in a variety of ways based on historical oil composition, oil color, oil viscosity and oil fume characteristics. For example, the processor constructs an oil vector based on the historical oil composition, oil color, oil viscosity and oil fume characteristics corresponding to the current oil, and calculates the similarity between the oil vector and the reference oil vector in the rancidity risk database, and confirms the historical oil rancidity risk corresponding to the reference oil vector that meets the similarity condition as the oil rancidity risk of the current oil. The oil vector refers to a feature vector constructed based on historical oil composition, oil color, oil viscosity and oil fume characteristics. For an explanation of the similarity condition, see step 420 and its related description.

[0134] In some embodiments, the rancidity risk database is acquired based on clustering of historical data. For example, the processor clusters the historical oil products in the historical data based on the historical oil product composition at the first historical time and the historical oil product color, historical oil product viscosity and historical oil fume characteristics at the second historical time, and constructs a reference oil product vector based on the clustered historical oil product composition, historical oil product color, historical oil product viscosity and historical oil fume characteristics, and uses the historical oil product rancidity risk corresponding to the historical oil product as the historical oil product rancidity risk corresponding to the reference oil product vector. Among them, the first historical time is earlier than the second historical time. The reference oil product vector refers to a feature vector constructed based on the historical oil product composition, historical oil product color, historical oil product viscosity and historical oil fume characteristics.

[0135] In some embodiments, the processor may obtain the results of multiple oil component tests of multiple historical similar oil products within a preset time period, calculate the ratio of the number of oil rancidity occurrences in the multiple oil component tests to the total number of oil component tests, and use the ratio as the historical oil rancidity risk corresponding to the historical oil product. Historical similar oil products refer to oil products of the same or similar type as historical oil products. The preset time period is pre-set based on historical experience, such as one week after the first historical time and earlier than the second historical time.

[0136] In some embodiments, the processor may determine the risk of oil rancidity through a second prediction model based on historical oil composition, oil color, oil viscosity, and oil smoke characteristics.

[0137] The second prediction model refers to a model for determining the risk of oil rancidity. In some embodiments, the second prediction model is a machine learning model, such as any one or combination of a deep neural network (DNN) model or other custom model structures.

[0138] In some embodiments, the input of the second prediction model includes historical oil composition, oil color, oil viscosity, and oil smoke characteristics, and the output includes the risk of oil rancidity.

[0139] In some embodiments, the input of the second prediction model also includes the detection time of historical oil components and historical processing data of a preset historical period. The preset historical period is preset based on historical experience, for example, the preset historical period includes the time period from the detection time of the previous oil component detection to the current time.

[0140] Historical processing data refers to data related to the completed historical processing process within a preset historical period. In some embodiments, the historical processing data may include historical food types, historical surface temperatures, historical inner layer temperatures, and historical oil temperature curves corresponding to multiple historical processing processes completed within the preset historical period. For an explanation of food types, surface temperatures, inner layer temperatures, and oil temperature curves, see Figure 2 Related description.

[0141] Inputting the historical oil component detection time and the historical processing data of the preset historical time period into the second prediction model can take into account the possibility of oil rancidity caused by changes in time and the possibility of oil rancidity caused by past processing when determining the oil rancidity risk, thereby improving the accuracy of determining the oil rancidity risk.

[0142] In some embodiments, the processor may train the second prediction model based on the second training data set, and the training process is similar to the training process of the first prediction model. For instructions on training the first prediction model, see Figure 5 and its related description.

[0143] In some embodiments, the second training data set includes a second training sample and a second label corresponding to the second training sample. The second training sample includes a sample historical oil product composition of the sample oil product at a first historical time and a sample oil product color, a sample oil product viscosity, and a sample oil smoke characteristic of the sample oil product at a second historical time. The second label includes the historical oil product rancidity risk corresponding to the sample oil product. The second training sample and the second label are determined based on historical data. The method for determining the historical oil product rancidity risk corresponding to the sample oil product is similar to the method for determining the historical oil product rancidity risk corresponding to the historical oil product, and its implementation method refers to the method for determining the historical oil product rancidity risk corresponding to the historical oil product.

[0144] In some embodiments, if the input of the second prediction model can also include the detection time of historical oil product components and historical processing data of a preset historical period, the second training sample also includes the first historical time corresponding to the sample oil product and the sample historical processing data between the first historical time and the second historical time.

[0145] Using the second prediction model to determine the rancidity risk of oil products can realize automatic prediction of the rancidity risk of oil products, improve the accuracy and efficiency of determining the rancidity risk of oil products, and facilitate users to monitor or replace oil products to ensure the quality of food processing.

[0146] Step 640: In response to the rancidity risk of the oil product meeting the rancidity condition, generate and send a second warning message.

[0147] Rancidity conditions refer to conditions used to determine whether an oil product has become rancid. In some embodiments, the rancidity conditions include the rancidity risk of the oil product being no less than a rancidity threshold. In some embodiments, the rancidity threshold is set based on historical experience or actual needs.

[0148] The second warning information refers to warning information used to remind the user that the oil product has gone rancid. In some embodiments, the second warning information includes sound information, text information, etc. The processor can send the second warning information to a terminal device or prompt device used by the user to warn the user.

[0149] The more solutes contained in the oil, the more likely it is to become rancid. Since the viscosity of the oil can reflect the current solute content of the oil, the risk of oil rancidity can be quickly predicted through data such as oil viscosity, thereby providing timely warnings.

[0150] It should be noted that the above descriptions of process 300, process 400 and process 600 are only for example and illustration, and do not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0151] Some embodiments of the present specification also provide a device for controlling the variable frequency operation of a fan, characterized in that the device includes at least one memory and at least one processor, the at least one memory is used to store computer instructions, and the at least one processor executes the computer instructions or part of the instructions to implement the method for controlling the variable frequency operation of a fan described in any of the above embodiments.

[0152] Some embodiments of the present specification also provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method for controlling the variable frequency operation of a fan as described in any one of the above embodiments.

[0153] Furthermore, certain features, structures or characteristics in one or more embodiments of this specification may be appropriately combined.

[0154] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0155] If there is any inconsistency or conflict between the descriptions, definitions, and / or usage of terms in the materials cited in this specification and the contents described in this specification, the descriptions, definitions, and / or usage of terms in this specification shall prevail.

Claims

1. A method for controlling the variable frequency operation of a fan, characterized in that: The method is executed by a processor, and the method includes: Acquiring food data of the food to be processed, wherein the food data includes at least one of food type and storage characteristics; Determine the operating parameters of the processing equipment and / or the fan equipment based on the food data and the power consumption characteristics of the processing equipment; A control instruction is generated based on the operating parameters, and the control instruction is sent to the fan device to control the fan device to determine the operating parameters and perform fume extraction based on the control instruction according to the fume detection result during the processing.

2. The method according to claim 1, characterized in that The operating parameters include an oil temperature curve, and the operating parameters of the processing equipment and / or the fan equipment are determined based on the food data and the power consumption characteristics of the processing equipment, including: Predicting the inner temperature of the food to be processed based on the food type, the storage characteristics, the surface temperature of the food to be processed, the thawing environment characteristics, and the thawing time; The oil temperature curve is determined based on the food type, the surface temperature, the inner layer temperature, and the power consumption characteristics.

3. The method according to claim 1, characterized in that The method further comprises: Acquiring oil smoke characteristics through a smoke detection unit deployed in the fan device, and acquiring oil surface bubble characteristics through an image sensing unit; Determining the internal deterioration risk of the food to be processed based on the food type, the storage characteristics, the oil smoke characteristics, and the oil surface bubble characteristics; In response to the internal deterioration risk satisfying a deterioration condition, first warning information is generated and sent.

4. The method according to claim 3, characterized in that: The method further comprises: Acquiring the color of the oil and the fluctuation characteristics of the oil surface during the processing by the image sensing unit; and Determining the viscosity of the oil product based on the oil surface fluctuation characteristics and the oil surface bubble characteristics; Predicting the risk of oil rancidity based on historical oil composition, oil color, oil viscosity, and oil smoke characteristics; In response to the rancidity risk of the oil product meeting the rancidity condition, a second warning message is generated and sent.

5. A system for controlling variable frequency operation of a fan, characterized in that: The system includes a processor, an image sensing unit, and a smoke detection unit that are communicatively connected, wherein the processor is configured to: Acquiring food data of the food to be processed, wherein the food data includes at least one of food type and storage characteristics; Determine the operating parameters of the processing equipment and / or the fan equipment based on the food data and the power consumption characteristics of the processing equipment; A control instruction is generated based on the operating parameters, and the control instruction is sent to the fan device to control the fan device to determine the operating parameters and perform fume extraction based on the control instruction according to the fume detection result during the processing.

6. The system according to claim 5, characterized in that The operating parameters include an oil temperature curve, and the processor is further configured to: Predicting the inner temperature of the food to be processed based on the food type, the storage characteristics, the surface temperature of the food to be processed, the thawing environment characteristics, and the thawing time; The oil temperature curve is determined based on the food type, the surface temperature, the inner layer temperature, and the power consumption characteristics.

7. The system according to claim 5, characterized in that The processor is further configured to: Acquiring oil smoke characteristics through the smoke detection unit, and acquiring oil surface bubble characteristics through the image sensing unit; Determining the internal deterioration risk of the food to be processed based on the food type, the storage characteristics, the oil smoke characteristics, and the oil surface bubble characteristics; In response to the internal deterioration risk satisfying a deterioration condition, first warning information is generated and sent.

8. The system according to claim 7, characterized in that The processor is further configured to: Acquiring the color of the oil and the fluctuation characteristics of the oil surface during the processing by the image sensing unit; and Determining the viscosity of the oil product based on the oil surface fluctuation characteristics and the oil surface bubble characteristics; Predicting the risk of oil rancidity based on historical oil composition, oil color, oil viscosity, and oil smoke characteristics; In response to the rancidity risk of the oil product meeting the rancidity condition, a second warning message is generated and sent.

9. A device for controlling the variable frequency operation of a fan, characterized in that: The device includes at least one memory and at least one processor, wherein the at least one memory is used to store computer instructions, and the at least one processor executes the computer instructions or part of the instructions to implement the method for controlling variable frequency operation of a fan according to any one of claims 1-4.

10. A computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method for controlling variable frequency operation of a fan as claimed in any one of claims 1 to 4.

Images