A control method, control device and medium of an extractor hood

Abstract

The application discloses a control method and device of an extractor hood and a medium, the extractor hood comprising a main box, a fan, an oil fume filter screen and a filter screen cleaning structure in the main box; the control method firstly acquires cooking operation data of the extractor hood, then constructs an oil stain index recognition model corresponding to the oil fume filter screen, then inputs the average oil fume concentration, the peak oil fume concentration, the cumulative oil fume concentration, the motor speed, the cooking duration, the surface oil stain thickness of the oil fume filter screen and the air pressure difference of both sides of the oil fume filter screen in a first time corresponding to the extractor hood into the oil stain index recognition model, outputs the filter screen oil stain index corresponding to the oil fume filter screen, and finally controls the rotation of the oil fume filter screen and / or controls the water outlet of the filter screen cleaning structure to clean the oil fume filter screen. By using the method, dynamic intelligent centrifugal cleaning based on the cooking habit of a user is realized, and the cleaning efficiency is effectively improved.

Description

Technical Field

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

[0002] As an essential kitchen appliance, the main function of a range hood is to remove cooking fumes and keep the kitchen air fresh. However, traditional range hoods suffer from problems such as infrequent cleaning, lack of smart features, and absence of feedback mechanisms.

[0003] Currently, cleaning solutions for range hoods on the market mainly fall into two categories: one is automatic cleaning technology that uses timed cleaning or simple oil stain detection, and the other is the traditional method that relies on manual cleaning by the user. However, these solutions have significant drawbacks: automatic cleaning technology cannot intelligently adjust according to the user's actual cooking habits; manual cleaning is cumbersome, costly, and often difficult for users to clean in a timely manner. Therefore, how to achieve intelligent cleaning technology based on user cooking habits, improve cleaning efficiency, and reduce user maintenance costs has become a pressing technical problem for the industry. Summary of the Invention

[0004] This invention provides a control method, control device, and medium for a range hood, enabling dynamic intelligent centrifugal cleaning based on user cooking habits, improving cleaning efficiency, reducing resource waste and user maintenance costs, and extending the service life of the fume filter and the entire range hood.

[0005] In a first aspect, embodiments of the present invention provide a control method for a range hood, the range hood including a main unit box, and a fan, a fume filter and a filter cleaning structure located inside the main unit box; The fume filter is located on the air inlet side of the fan; the output shaft of the fan is mechanically connected to the middle of the fume filter; the water outlet direction of the filter cleaning structure is oriented towards the surface of the fume filter. The control method includes: Acquire the cooking operation data of the range hood; wherein the cooking operation data of the range hood includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides within a first time period; Construct an oil stain index identification model corresponding to the oil fume filter screen; The average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood within the first time period are input into the oil stain index recognition model, and the filter oil stain index corresponding to the oil fume filter is output. Based on the oil stain index of the oil fume filter, the rotation of the oil fume filter is controlled, and / or the water outlet of the filter cleaning structure is controlled to clean the oil fume filter.

[0006] Optionally, an oil stain index identification model corresponding to the oil fume filter is constructed, including: Obtain first training data for training the oil stain index recognition model; wherein, the first training data includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides during the second time period; The first training data is divided into a first training set and a first test set; The parameters of the oil pollution index recognition model are debugged using the first training set, and the training results of the oil pollution index recognition model are evaluated using the first test set. When the training results of the oil pollution index recognition model meet the first preset condition, the training of the oil pollution index recognition model is determined to be complete.

[0007] Optionally, after inputting the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides into the oil stain index recognition model, and before outputting the filter oil stain index corresponding to the oil fume filter, the method further includes: The average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood within the first time period are standardized. The average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood corresponding to the first time period after standardization are subjected to feature screening processing to obtain the surface oil stain thickness of the oil fume filter, airflow pressure difference on both sides, and cumulative oil fume concentration.

[0008] Optionally, based on the oil stain index corresponding to the oil fume filter, the rotation of the oil fume filter is controlled, and / or the water outlet of the filter cleaning structure is controlled to clean the oil fume filter, including: When the oil stain index of the oil fume filter is greater than or equal to the first preset oil stain index threshold and less than the second preset oil stain index threshold, the oil fume filter is controlled to rotate to clean the oil fume filter.

[0009] Optionally, based on the oil stain index corresponding to the oil fume filter, the rotation of the oil fume filter is controlled, and / or the water outlet of the filter cleaning structure is controlled to clean the oil fume filter, including: When the oil stain index of the filter screen corresponding to the oil fume filter screen is greater than or equal to the second preset oil stain index threshold, the oil fume filter screen is controlled to rotate, and the water outlet of the filter screen cleaning structure is controlled to clean the oil fume filter screen.

[0010] Optionally, the control method further includes: Construct a cooking intensity recognition model corresponding to the range hood; The average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood within the first time period are input into the cooking intensity recognition model, and the cooking intensity index corresponding to the range hood is output. Based on the cooking intensity index corresponding to the range hood, the rotation of the fume filter is controlled to centrifugally separate the oil stains attached to the fume filter.

[0011] Optionally, a cooking intensity recognition model corresponding to the range hood is constructed, including: Acquire second training data for training the cooking intensity recognition model; wherein the second training data includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides within a third time period; The second training data is divided into a second training set and a second test set; The parameters of the cooking intensity recognition model are adjusted using the second training set, and the training results of the cooking intensity recognition model are evaluated using the second test set. When the training results of the cooking intensity recognition model meet the second preset condition, the training of the cooking intensity recognition model is determined to be complete.

[0012] Optionally, after inputting the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides into the cooking intensity recognition model, and before outputting the cooking intensity index corresponding to the range hood, the method further includes: The average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood within the first time period are standardized. The average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood within the first time period after standardization are subjected to feature screening processing to obtain the average oil fume concentration, peak oil fume concentration, motor speed, and cooking duration of the range hood.

[0013] Secondly, embodiments of the present invention also provide a control device for a range hood, the range hood including a main unit housing, and a fan, an oil fume filter and a filter cleaning structure located inside the main unit housing; The fume filter is located on the air inlet side of the fan; the output shaft of the fan is mechanically connected to the middle of the fume filter; the water outlet direction of the filter cleaning structure is oriented towards the surface of the fume filter. The control device includes: The operation data acquisition module is used to acquire the cooking operation data of the range hood; wherein, the cooking operation data of the range hood includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides within a first time period; The first model building module is used to build an oil pollution index recognition model corresponding to the oil fume filter screen. The oil stain index recognition module is used to input the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter and airflow pressure difference on both sides of the range hood into the oil stain index recognition model, and output the filter oil stain index corresponding to the oil fume filter. The filter cleaning control module is used to control the rotation of the fume filter and / or control the water output of the filter cleaning structure to clean the fume filter based on the filter oil stain index corresponding to the fume filter.

[0014] Thirdly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the control method for a range hood as described in any of the first aspects.

[0015] The beneficial effects of the embodiments of the present invention are as follows: 1. Achieve dynamic intelligent centrifugal cleaning based on user cooking habits. After the cooking process is completed, through data fusion from multiple sensors and based on the cooking operation data of the range hood and the corresponding oil stain index recognition model, it can realize real-time detection and accurate judgment of the oil stain index of the fume filter. Based on the detection results corresponding to the pollution level of the fume filter, it automatically matches the corresponding intelligent cleaning strategy. This intelligent cleaning strategy is not triggered at a fixed period, nor is it a fixed program that is unchanging. Instead, it can automatically adjust the cleaning intensity according to the oil stains generated by the user's cooking habits. For example, it can automatically adjust the water output parameters of the filter cleaning structure corresponding to the cleaning mode, and automatically adjust whether the fume filter rotates and its rotation speed. In this way, it can achieve efficient and automatic cleaning of the fume filter and convenient control. 2. The oil stain index recognition model can comprehensively reflect the oil stain adhesion, clogging, and performance degradation of the fume filter. The output filter oil stain index can more accurately reflect the true pollution level of the fume filter, greatly improving the comprehensiveness and accuracy of the pollution level assessment of the fume filter. It can truly reflect the actual pollution pattern of the fume filter under different cooking scenarios, realize the accurate quantification and real-time judgment of the pollution status of the fume filter, and provide reliable data support for intelligent reminders to clean the fume filter and optimize the operation strategy of the range hood, effectively ensuring the fume purification effect. 3. The cooking intensity recognition model can comprehensively reflect the amount of oil fumes produced, the heat level, and the duration of cooking. The output cooking intensity index can also more accurately reflect the actual suction and exhaust efficiency of the range hood, greatly improving the comprehensiveness and accuracy of the range hood's operation assessment. It fits the actual scenario and can realize real-time quantification and adaptive judgment of cooking intensity, providing intelligent adjustment basis for the range hood's motor speed, air volume, pressure boosting, and cleaning functions, improving suction and exhaust effect, reducing noise and energy consumption, and realizing on-demand operation and intelligent control. 4. Standardize and feature-filter the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood within the first time period to determine the core feature data related to the model's output. This will help to further iteratively optimize the model and improve the accuracy of its output.

[0016] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the overall structure of a range hood provided in an embodiment of the present invention; Figure 2 This is an enlarged structural schematic diagram of a main unit chassis provided in an embodiment of the present invention; Figure 3 This is a flowchart illustrating a control method for a range hood provided in an embodiment of the present invention; Figure 4 This is a flowchart illustrating another control method for a range hood provided in an embodiment of the present invention; Figure 5 This is a flowchart illustrating another control method for a range hood provided in an embodiment of the present invention; Figure 6 This is a flowchart illustrating another control method for a range hood provided in an embodiment of the present invention; Figure 7 This is a flowchart illustrating another control method for a range hood provided in an embodiment of the present invention; Figure 8 This is a schematic diagram of the structure of a control device for a range hood provided in an embodiment of the present invention; Figure 9 This is a schematic diagram of the structure of a terminal device provided in an embodiment of the present invention. Detailed Implementation

[0019] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0020] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0021] Figure 1 This is a schematic diagram of the overall structure of a range hood provided in an embodiment of the present invention. Figure 2 This is an enlarged structural diagram of a main unit chassis provided in an embodiment of the present invention, as shown below. Figure 1 and Figure 2 As shown, the range hood includes a main unit 10, and a fan, a fume filter 40, and a filter cleaning structure 50 located inside the main unit 10; the fume filter 40 is located on the air inlet side of the fan; the output shaft of the fan is mechanically connected to the middle of the fume filter 40; the water outlet direction of the filter cleaning structure 50 is arranged towards the surface of the fume filter 40.

[0022] First, a brief explanation of the structure and working principle of this range hood will be given. (Continue to refer to...) Figure 1 and Figure 2 The range hood includes a main unit housing 10, a fan, an oil fume filter 40, and a filter cleaning structure 50, all of which are located inside the main unit housing 10. Exemplarily, the range hood also includes a smoke collection hood, with the main unit housing 10 positioned above it. Exemplarily, the fan includes a motor 20, an impeller structure, and a volute structure 30, with the impeller structure located inside the volute structure 30. The output shaft of the motor 20 can be mechanically connected to the center of the impeller structure. When the motor 20 is operating, its output shaft directly drives the impeller structure to rotate stably inside the volute structure 30. The high-speed rotation of the impeller structure creates negative pressure suction, drawing oil fumes from the kitchen cooking environment into the duct and discharging them through the volute structure 30, thus efficiently completing the range hood's smoke extraction process.

[0023] Furthermore, since the fume filter 40 is located on the air inlet side of the fan, it can filter and intercept oil stains before the oily gas enters the fan, significantly reducing oil stains adhering to the impeller and volute, lowering the risk of internal clogging, reducing the frequency of cleaning and maintenance, ensuring unobstructed airflow, stabilizing exhaust volume and smoke extraction effect, and extending the service life of the entire machine. For example, the fume filter 40 can be located on the side of the fan closer to the motor 20; for example, both the fume filter 40 and the motor 20 can be located on the air inlet side of the fan. For example, the output shaft of the motor 20 can also be mechanically connected to the middle of the fume filter 40. That is, the output shaft of the motor 20 is mechanically connected to the middle of the impeller structure in the fan and the middle of the fume filter 40, respectively. This integrated coaxial connection structure between the fan and the fume filter 40 is more compact and stable, reducing component vibration and noise, while ensuring uniform airflow, improving oil fume separation and extraction efficiency, simplifying assembly, and enhancing the overall reliability of the machine.

[0024] The water outlet of the filter cleaning structure 50 is directed towards the surface of the fume filter 40. This means that the external cleaning water flowing from the filter cleaning structure 50 can be sprayed onto the surface of the fume filter 40, thereby achieving efficient and automatic cleaning of the fume filter 40 with convenient control, preventing excessive adhesion of grease particles from the fume gas to the surface of the fume filter 40. In simpler terms, this embodiment enables precise and comprehensive spray rinsing of the fume filter 40 during the cleaning process, efficiently removing grease from its surface without disassembly, simplifying the cleaning process and improving cleaning effectiveness and ease of use. Furthermore, exemplarily, the range hood may also include a liquid pump 61; the inlet of the liquid pump 61 is connected to an external water supply system, and the outlet of the liquid pump 61 is connected to the inlet of the filter cleaning structure 50, with the outlet of the filter cleaning structure 50 corresponding to the surface of the fume filter 40. The liquid pump 61 provides power to circulate external cleaning water, injecting it into the corresponding filter cleaning structure 50, ensuring a stable water supply to the filter cleaning structure 50, and enabling automatic control of the spray cleaning process. For example, Figure 1 and Figure 2 The filter cleaning structure 50 shown can be a structure consisting of a water supply pipe and a spray outlet. One end of the water supply pipe can be directly connected to the liquid pump 61, or one end of the water supply pipe can be indirectly connected to the liquid pump 61 via a solenoid valve assembly or the like. Figure 1 and Figure 2 The structure and connection relationship of the filter cleaning structure 50 shown are for illustrative purposes only and are not intended to be limiting.

[0025] For example, the range hood also includes a cooking mode. In the cooking mode, the control system of the range hood can correspondingly control the motor 20 to work. The output shaft of the motor 20 can also directly drive the oil fume filter 40 to rotate continuously. At this time, the oil fume filter 40 can also be understood as a rotating filter to construct a dynamic rotating separation net system. When the oil fume airflow passes through the oil fume filter 40, the oil fume filter 40, during its rotation, causes collisions, adsorption, and centrifugal separation of oil mist particles in the oil fume airflow. That is, the high-speed rotation of the oil fume filter 40 can achieve centrifugal separation of oil fumes, trapping most of the oil stains on the surface of the oil fume filter 40, thereby reducing the amount of oil fumes entering the duct. In other words, the oil fume filter 40 can filter and intercept oil stains before the oil fume gas enters the fan.

[0026] Furthermore, the range hood also includes a cleaning mode. In cleaning mode, the control system can control not only the water flow rate and time of the filter cleaning structure 50, but also the rotation speed and direction of the fume filter 40, allowing for more precise cleaning of the filter 40. In this mode, the fume filter 40 can be understood as a rotating filter. When the external cleaning water from the filter cleaning structure 50 is sprayed onto the surface of the fume filter 40, the filter 40 is simultaneously rotated. Centrifugal force is used to remove grease and grime from the surface and mesh of the filter 40, improving its self-cleaning effect. Furthermore, the spray position corresponding to the filter cleaning structure 50 changes as the fume filter 40 rotates, forming a multi-angle, no-dead-angle spray coverage, effectively avoiding cleaning blind spots, ensuring that all areas of the fume filter 40 are rinsed by the spray water flow, and also improving the oil stain removal effect, making stubborn oil stains easier to wash away, significantly improving the comprehensiveness and cleaning efficiency of self-cleaning. That is, the spraying process of the filter cleaning structure 50 can also be coordinated with the rotational movement of the fume filter 40, and the flowing water can efficiently remove stubborn residual oil stains on the fume filter 40, ensuring that the fume filter 40 is thoroughly rinsed. For example, the control system of this range hood can control the fume filter 40 to rotate around the output shaft of the motor 20, with the preset central axis being the axis of the output shaft of the motor 20.

[0027] Furthermore, the range hood may also include a ring-shaped support structure 62. One end of the ring-shaped support structure 62 is mechanically connected to the side of the motor 20, and the other end is mechanically connected to the side plate of the volute structure 30. In other words, the ring-shaped support structure 62 connects the side of the motor 20 and the side plate of the volute structure 30. Thus, the ring-shaped support structure 62 provides stable support for the motor 20 and the fan, fixing their relative positions and preventing displacement. This effectively improves the overall rigidity of the internal structure of the range hood, reduces operational vibration and noise, and extends its service life. It is understandable that the ring-shaped support structure 62, connected between the motor 20 and the fan, also prevents interference with moving parts such as the duct and impeller, further ensuring the normal operation of the range hood. The ring shape of the ring-shaped support structure 62 can also provide uniform support at multiple points for the motor 20 and the fan, significantly improving the overall structural strength and operational stability of the range hood. Furthermore, the opening of the annular support structure 62 facing the fume filter 40 is funnel-shaped, and the fume filter 40 is located within the area corresponding to the funnel-shaped opening. Thus, the annular support structure 62 can further optimize the airflow path, reduce airflow turbulence and resistance, improve the efficiency of fume intake and exhaust, and enhance the smoke extraction effect. It should also be noted that in this embodiment, the fume filter 40 is limited to being located inside the main unit housing 10. For example, the range hood can be a centrifugal range hood, and the fume filter 40 can also be a centrifugal fume filter. When oil stains accumulate on the surface and mesh of the fume filter 40, it can be effectively cleaned subsequently. For example, the annular support structure 62 can include multiple connecting rods 621, each connecting rod 621 connecting to the side of the motor 20 and the side plate of the volute structure 30, respectively, providing multi-point uniform support between the motor 20 and the fan. For example, the annular support structure 62 can be understood as the support structure corresponding to the motor 20, and the annular support structure 62 can also be understood as the support structure corresponding to the oil fume filter 40.

[0028] Optionally, continue to refer to Figure 1 and Figure 2 The range hood also includes an oil collector 63; the oil collector 63 is annular in shape, and is concentrically arranged with the oil fume filter 40, and is located on the outside of the oil fume filter 40.

[0029] Specifically, the oil collector 63 is concentrically arranged with the fume filter 40, and the oil collector 63 is located on the outside of the fume filter 40. This outer arrangement of the oil collector 63 can accurately collect the oil that falls off the fume filter 40 during the centrifugal oil-spinning process in cooking mode, preventing oil from splashing onto the internal components of the range hood such as the air duct, motor 20, and fan, effectively preventing secondary pollution and ensuring the cleanliness of the internal structure of the range hood. Furthermore, the oil collector 63 can also be reused as a spray water collector. That is, the outer arrangement of the oil collector 63 can also accurately collect the wastewater generated during the spray cleaning process of the fume filter 40 in cleaning mode, preventing excessive wastewater residue inside the main unit 10. In addition, the concentric ring arrangement of the oil collector 63 fits closely with the fume filter 40, forming a complete guide and collection area for oil and wastewater, greatly improving the oil collection efficiency and reducing the accumulation of oil residue. Meanwhile, one side of the oil collector 63 is mechanically connected to the annular support structure 62, and the other side is mechanically connected to the side plate of the volute structure 30. This achieves a reliable and fixed structural connection, further strengthening the overall structural integrity between the annular support structure 62 and the fan, improving the overall operational stability of the machine, and reducing vibration and noise. This structural design also integrates the oil collection function with the structural support function, without occupying additional duct space, without affecting the exhaust airflow, simplifying the internal layout, and facilitating centralized cleaning of oil stains later. This significantly improves the self-cleaning ability, hygiene, and ease of maintenance of the range hood.

[0030] Optionally, continue to refer to Figure 1 and Figure 2 The range hood also includes an oil cup; the oil collector 63 is also equipped with a liquid return hole, through which the wastewater liquid after cleaning and the oil sludge separated by centrifugation can enter the duct volute and flow into the oil cup through the relevant oil passage inside the range hood, so that users can handle it conveniently.

[0031] In addition, the range hood may include other structures, which will not be described in detail in this embodiment.

[0032] Figure 3 This is a flowchart illustrating a control method for a range hood according to an embodiment of the present invention. This control method is applicable to situations where the oil fume filter is intelligently and adaptively cleaned after the cooking process. The control method can be executed by a control device for the range hood, which can be implemented in hardware and / or software and can be configured in a control board. Figure 3 As shown, the control method includes: S110. Obtain the cooking operation data of the range hood; wherein, the cooking operation data of the range hood includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides within the first time period.

[0033] Specifically, the cooking operation data of a range hood can reflect the user's cooking habits, the effectiveness of fume extraction, and the level of grease buildup. For example, "first time" can be understood as a specific period during the cooking process, or it can be understood as a specific time period selected by the user. (Continue to refer to...) Figure 1 and Figure 2 Multiple detection modules can be installed near the fume filter 40. For example, these modules may include, but are not limited to, a grease thickness detection module, an airflow pressure difference detection module, a fume concentration detection module, a motor speed detection module, and a cooking time detection module. Subsequently, these modules can be used to acquire real-time or periodic data on the user's cooking habits, the fume extraction status inside the range hood, and the grease adhesion status of the fume filter 40. The cooking operation data of the range hood should include key indicators such as the average fume concentration, peak fume concentration, cumulative fume concentration, motor speed, cooking duration, surface grease thickness of the fume filter, and airflow pressure difference on both sides within the first time period. This facilitates a multi-dimensional quantitative assessment of the user's cooking habits, the fume extraction status inside the range hood, and the grease adhesion status of the fume filter 40. Furthermore, the cooking operation data may also include, for example, the number of peak fume concentrations, motor speed settings, range hood start / stop times, and the number of times the fan is manually adjusted.

[0034] Understandably, the thickness of the oil stains on the surface of the fume filter 40 reflects the degree of oil adhesion. The thicker the oil stains, the easier it is to clog the fume filter 40. The airflow pressure difference on both sides of the fume filter 40 reflects the unobstructed state of the air duct. The greater the airflow pressure difference, the more severe the clogging of the fume filter 40. The average oil fume concentration, peak oil fume concentration, and cumulative oil fume concentration of the fume filter 40 reflect the total amount of oil accumulation and the degree of pollution. The higher the cumulative oil fume concentration, the less the oil fume separation capacity of the fume filter 40 matches the current oil fume extraction efficiency. The motor speed inside the range hood reflects the extraction capacity. The cooking time of the range hood reflects the user's cooking habits. These are all key factors in determining whether the fume filter 40 needs to be cleaned.

[0035] For example, the oil stain thickness detection module can be used to obtain the surface oil stain thickness of the fume filter 40. For example, the oil stain thickness detection module can be an oil stain thickness sensor, which may include, but is not limited to, an optical oil film thickness detection sensor, a capacitive oil film thickness detection sensor, and an ultrasonic oil film thickness detection sensor disposed on or near the surface of the fume filter 40. The surface oil stain thickness of the fume filter 40 is obtained by calculating the oil film thickness. For example, the airflow pressure difference detection module can be used to obtain the airflow pressure difference across the fume filter 40. For example, the airflow pressure difference detection module can be an airflow pressure difference sensor, which may include a first pressure detection sensor disposed on the air inlet side of the fume filter 40 and a second pressure detection sensor disposed on the air outlet side of the fume filter 40. The airflow pressure difference across the fume filter 40 is obtained by calculating the pressure difference detected by the first and second pressure detection sensors. For example, the fume concentration detection module can be used to obtain the cumulative fume concentration of the fume filter 40. For example, the oil fume concentration detection module can be an oil fume concentration sensor. The oil fume concentration sensor can include, but is not limited to, an optical particulate sensor and an oil fume concentration detection sensor disposed on or near the surface of the oil fume filter 40. By calculating the oil fume concentration and its changes, the average oil fume concentration, peak oil fume concentration, and cumulative oil fume concentration corresponding to the oil fume filter 40 are obtained. For example, the motor speed detection module can be used to obtain the motor speed of the range hood. For example, the motor speed detection module can be a speed sensor. And, for example, the cooking time detection module can be used to obtain the cooking duration of the range hood. For example, the cooking time detection module can be a timer.

[0036] S120. Construct an oil pollution index identification model corresponding to the oil fume filter.

[0037] Specifically, this oil stain index recognition model can use multiple data points from the cooking operation data of the range hood as multi-dimensional inputs. By fusing and quantitatively fitting these data points with corresponding physical characteristics, a model capable of accurately outputting the filter oil stain index is constructed. Furthermore, this oil stain index recognition model can comprehensively reflect the oil stain adhesion, clogging, and performance degradation of the oil fume filter. The output filter oil stain index can more accurately reflect the true pollution level of the oil fume filter, significantly improving the comprehensiveness and accuracy of the pollution level assessment. It can truly reflect the actual pollution patterns of the oil fume filter under different cooking scenarios, achieving precise quantification and real-time judgment of the oil fume filter's pollution status. This provides reliable data support for intelligent reminders for cleaning the oil fume filter and optimizing the range hood's operating strategy, effectively ensuring the oil fume purification effect, reducing motor load and energy consumption, and extending the service life of the oil fume filter and the entire range hood.

[0038] It should also be noted that S110 is the step of acquiring cooking operation data, and S120 is the step of constructing the oil stain index identification model. S110 can be executed first and then S120, or S120 can be executed first and then S110, or S110 and S120 can be executed simultaneously. In this embodiment, there are no specific requirements or special limitations on the execution order of S110 and S120. This is only an example for illustration.

[0039] S130: Input the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides into the oil stain index recognition model for the first time period corresponding to the range hood, and output the filter oil stain index corresponding to the oil fume filter.

[0040] Specifically, the input to this oil stain index recognition model is the cooking operation data of the range hood, and the output is the oil stain index of the oil fume filter. In other words, this oil stain index recognition model analyzes and processes the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides within the first time period, and performs multi-parameter fusion calculations. It can output a filter oil stain index that comprehensively characterizes the oil stain adhesion, clogging, and performance degradation of the oil fume filter. It can comprehensively reflect the cooking conditions, equipment operating status, and physical pollution characteristics of the oil fume filter, making the pollution assessment more in line with actual use scenarios, and the judgment results more accurate and reliable. It realizes the quantification and real-time monitoring of the pollution status of the oil fume filter, which helps to accurately trigger cleaning or replacement reminders, optimize equipment operation strategies, improve oil fume purification effects, reduce operating resistance and energy consumption, and extend the overall service life of the range hood. Furthermore, after each cleaning of the fume filter, the data on the filter's grease index, corresponding cleaning strategy, and cleaning effect can be archived. This data can be used in subsequent iterations of the grease index recognition model to further improve its output accuracy. Additionally, after the grease index recognition model is updated, the range hood can be turned off, and upon the next startup, the grease index recognition model will continue to iterate and update, better meeting the user's cooking habits and cleaning needs.

[0041] S140. Based on the oil stain index of the corresponding oil fume filter, control the rotation of the oil fume filter and / or control the water outlet of the filter cleaning structure to clean the oil fume filter.

[0042] Specifically, this embodiment essentially involves the steps of selecting a graded cleaning strategy and executing a centrifugal cleaning process to collaboratively achieve intelligent cleaning management of the fume filter. For example, multiple pollution level thresholds can be preset experimentally, such as a first preset oil stain index threshold, a second preset oil stain index threshold, and a third preset oil stain index threshold. The first preset oil stain index threshold is less than the second preset oil stain index threshold, and the second preset oil stain index threshold is less than the third preset oil stain index threshold. Subsequently, the relationship and range between the filter oil stain index output by the oil stain index recognition model and the first, second, and third preset oil stain index thresholds can be determined to achieve precise control of the fume filter cleaning. Furthermore, based on the filter oil stain index corresponding to the fume filter and the determined pollution levels of the fume filter (light, medium, and heavy), corresponding cleaning parameter combinations can be preset for different pollution levels. For example, the water flow rate and duration of the filter cleaning structure can be adjusted accordingly, as can the rotation speed of the fume filter. Thus, when the external cleaning water from the filter cleaning structure sprays onto the surface of the fume filter, the filter rotates simultaneously, utilizing centrifugal force to remove oil and dirt adhering to the surface and mesh of the filter, improving self-cleaning effectiveness. Furthermore, exemplarily, based on the oil stain index of the fume filter, the water flow rate, direction, spray type, and alternation duration of the filter cleaning structure can be adjusted accordingly. This embodiment is merely an example and not intended to be limiting.

[0043] The technical solution in this invention provides a dynamic centrifugal range hood based on user cooking habits, achieving dynamic intelligent centrifugal cleaning based on user cooking habits. After the cooking process is completed, through data fusion from multiple sensors, and based on the range hood's cooking operation data and the corresponding oil stain index recognition model, it can achieve real-time detection and accurate judgment of the oil stain index of the fume filter. Based on the detection results corresponding to the oil stain condition of the fume filter, it automatically matches a corresponding intelligent cleaning strategy. This intelligent cleaning strategy is not triggered at a fixed period, nor is it a fixed, unchanging program. Instead, it automatically adjusts the cleaning intensity according to the oil stains generated by the user's cooking habits. For example, it automatically adjusts the water output parameters of the filter cleaning structure corresponding to the cleaning mode, and automatically adjusts the rotation of the fume filter. The rotation speed is controlled to achieve efficient and automatic cleaning of the fume filter, which is easy to control. This prevents excessive grease particles from adhering to the filter surface, reduces the rotational resistance of the filter during cooking, and ensures the oil-fume separation efficiency of the filter, the load supply capacity of the motor, and the overall suction and exhaust efficiency of the range hood. This improves cleaning efficiency and reduces resource consumption and user maintenance costs. In other words, while ensuring the cleaning effect of the fume filter, it avoids resource waste caused by ineffective cleaning, as well as over-cleaning or under-cleaning. It also achieves a dynamic balance between the exhaust efficiency of the range hood and energy saving and noise reduction, further extending the service life of the fume filter and the range hood as a whole. In addition, users do not need to disassemble the fume filter for manual cleaning periodically, improving the user maintenance experience.

[0044] Optionally, based on the oil stain index corresponding to the oil fume filter, the rotation of the oil fume filter is controlled, and / or the water outlet of the filter cleaning structure is controlled to clean the oil fume filter, including: when the oil stain index corresponding to the oil fume filter is greater than or equal to a first preset oil stain index threshold and less than a second preset oil stain index threshold, the rotation of the oil fume filter is controlled to clean the oil fume filter.

[0045] Specifically, when the oil stain index of the oil fume filter is greater than or equal to the first preset oil stain index threshold and less than the second preset oil stain index threshold, the oil fume filter can be considered to be slightly polluted. In this case, a basic centrifugal cleaning process can be performed in the cleaning mode. That is, the surface oil stains of the oil fume filter can be peeled off by the centrifugal force generated by the high-speed rotation of the oil fume filter.

[0046] Optionally, based on the oil stain index corresponding to the oil fume filter, the rotation of the oil fume filter and / or the water discharge from the filter cleaning structure are controlled to clean the oil fume filter. This includes: controlling the rotation of the oil fume filter and controlling the water discharge from the filter cleaning structure when the oil stain index corresponding to the oil fume filter is greater than or equal to a second preset oil stain index threshold, to clean the oil fume filter.

[0047] Specifically, when the oil stain index of the oil fume filter is greater than or equal to the second preset oil stain index threshold and less than the third preset oil stain index threshold, the oil fume filter can be considered to be moderately polluted. In this case, the standard centrifugal cleaning process can be performed in the cleaning mode. That is, the centrifugal force generated by the high-speed rotation of the oil fume filter can be used to peel off the surface oil stains of the oil fume filter. Based on the centrifugal action, the filter cleaning structure is linked to assist in dissolving the surface oil stains of the oil fume filter.

[0048] Furthermore, for example, when the oil stain index of the oil fume filter is greater than or equal to the third preset oil stain index threshold, the oil fume filter can be considered to be heavily polluted. In this case, a deep centrifugal cleaning process can be performed in the cleaning mode. That is, the centrifugal force generated by the high-speed rotation of the oil fume filter can be used to peel off the surface oil stains of the oil fume filter. Based on the centrifugal action, the filter cleaning structure is linked to assist in dissolving the surface oil stains of the oil fume filter. At this time, it is also necessary to appropriately extend the rotation time of the oil fume filter and the water output time of the filter cleaning structure. High-frequency pulse oscillation can also be used to further enhance the oil stain removal effect.

[0049] Based on this, after cleaning the fume filter, the oil stain index recognition model can output the corresponding oil stain index of the fume filter again, and determine whether the oil stain index of the fume filter has recovered to a safe range below the first preset oil stain index threshold. For example, if the oil stain index of the fume filter output by the oil stain index recognition model recovers to below the first preset oil stain index threshold, the cleaning mode can be ended. For example, if the oil stain index of the fume filter output by the oil stain index recognition model does not recover to below the first preset oil stain index threshold, an enhanced cleaning process is automatically triggered, and a higher-level cleaning strategy is re-matched. For example, after performing a medium cleaning process, if the oil stain index of the fume filter does not recover to below the first preset oil stain index threshold, a heavy cleaning process is performed again until the oil stain index of the fume filter output by the oil stain index recognition model recovers to below the first preset oil stain index threshold. In this way, real-time feedback control of the cleaning process of the fume filter in the range hood is achieved.

[0050] Figure 4 This is a flowchart illustrating another control method for a range hood provided in this embodiment of the invention. This embodiment is an optimization based on the above embodiment. Optionally, an oil stain index identification model corresponding to the oil fume filter is constructed, including: Acquire first training data for training the oil stain index recognition model; wherein, the first training data includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides during the second time period; The first training data is divided into a first training set and a first test set; The parameters of the oil pollution index identification model were debugged using the first training set, and the training results of the oil pollution index identification model were evaluated using the first test set. When the training results of the oil pollution index identification model meet the first preset condition, the training of the oil pollution index identification model is considered complete.

[0051] For details not covered in this embodiment, please refer to the above embodiments. Figure 4 As shown, the control method includes: S210. Obtain cooking operation data of the range hood; wherein, the cooking operation data of the range hood includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides within the first time period.

[0052] S220. Obtain first training data for training the oil stain index recognition model; wherein the first training data includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides during the second time period.

[0053] Specifically, the first training data can be understood as historical cooking data of the range hood, while the cooking operation data can be understood as real-time cooking data of the range hood in operation. The acquisition of the first training data can be referred to the above embodiment, and will not be repeated here. For example, the second time can be understood as a certain period of time during the previous cooking process, and the first time can also be understood as a period of time before the current cooking moment. It should also be noted that the first training data can be applied to the construction of the oil stain index recognition model, while the cooking operation data is applied after the oil stain index recognition model is constructed, specifically to the actual acquisition of the oil stain index of the corresponding oil fume filter.

[0054] S230. Divide the first training data into a first training set and a first test set.

[0055] Specifically, the first training data can be divided into a first training set and a first test set according to a preset ratio. For example, the preset ratio can be determined according to the training process of the oil pollution index identification model, such as 7:3.

[0056] S240. Debug the parameters of the oil pollution index recognition model using the first training set, and evaluate the training results of the oil pollution index recognition model using the first test set.

[0057] Specifically, the data corresponding to the first training set is input into the oil stain index recognition model, which can output the filter oil stain index recognized by the model for the first training set. By comparing the filter oil stain index recognized by the model for the first training set with the actual filter oil stain index of the first training set, if the filter oil stain index recognized by the model for the first training set is different from the actual filter oil stain index of the first training set, the parameters of the oil stain index recognition model need to be readjusted until the filter oil stain index recognized by the model for the first training set is the same as or close to the actual filter oil stain index of the first training set.

[0058] Furthermore, by inputting the data corresponding to the first test set into the oil stain index recognition model, the model can output the filter oil stain index recognized by the model for the first test set. By comparing the filter oil stain index recognized by the model for the first test set with the actual filter oil stain index of the first test set, if the filter oil stain index recognized by the model for a large number of data in the first test set is the same as the actual filter oil stain index of the first test set, then the training result of the oil stain index recognition model is good. If the filter oil stain index recognized by the model for a large number of data in the first test set is different from the actual filter oil stain index of the first test set, then the training result of the oil stain index recognition model is poor, and the parameters of the oil stain index recognition model need to be readjusted using the first training set.

[0059] S250. When the training results of the oil pollution index identification model meet the first preset condition, the training of the oil pollution index identification model is determined to be complete.

[0060] The first preset condition is determined based on the training process and application of the oil stain index recognition model. For example, the first preset condition can be a proportional threshold or a proportional range. For example, the first preset condition can be adjusted by changing the hyperparameters to achieve a classification accuracy ≥95%. Specifically, when the training result meets the first preset condition, that is, when the oil stain index recognition model outputs the filter oil stain index for the first test set based on a large amount of data, and the model's identification is the same as the actual filter oil stain index for the first test set, it can be determined that the oil stain index recognition model has been successfully trained and can be applied to identify the filter oil stain index of oil fume filters after unknown cooking times or after the next cooking time.

[0061] S260: Input the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides into the oil stain index recognition model for the first time period corresponding to the range hood, and output the filter oil stain index corresponding to the oil fume filter.

[0062] S270. Based on the oil stain index of the corresponding oil fume filter, control the rotation of the oil fume filter and / or control the water outlet of the filter cleaning structure to clean the oil fume filter.

[0063] Optionally, after inputting the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides into the oil stain index recognition model for the first time period corresponding to the range hood, before outputting the filter oil stain index corresponding to the oil fume filter, the following steps are included: standardizing the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides for the first time period corresponding to the range hood; performing feature filtering on the standardized average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides for the first time period corresponding to the range hood to obtain the surface oil thickness of the oil fume filter, airflow pressure difference on both sides, and cumulative oil fume concentration.

[0064] Specifically, this embodiment is essentially a process of analyzing and processing the cooking operation data of the range hood input into the oil stain index recognition model. The average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood within the first time period are standardized. For example, the numerical data can be normalized according to the interval [0, 1]. For example, the time-related data can be quantized into numerical labels according to a two-hour interval. For example, the encoding of the typological data can be processed using binary vectorization. Subsequently, feature filtering is performed on the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood corresponding to the first time period after standardization. This is to remove low-relevance features to reduce the amount of computation. For example, the core features can be screened out by using the Pearson correlation coefficient. These core features refer to the data in the cooking operation data of the range hood that are mainly related to the oil stain adhesion of the oil fume filter, such as the surface oil stain thickness of the oil fume filter, the airflow pressure difference on both sides, and the cumulative oil fume concentration.

[0065] In addition, based on the obtained surface oil stain thickness H of the fume filter, the airflow pressure difference ΔP on both sides, and the cumulative oil fume concentration C acc The control system of this range hood can output the filter oil stain index FI corresponding to the fume filter through an oil stain index recognition model. This filter oil stain index FI comprehensively reflects the degree of oil accumulation, changes in filter ventilation resistance, and the decline in smoke extraction efficiency. The value of the filter oil stain index FI can be used to quantitatively determine whether the fume filter needs to be cleaned, thus enabling adaptive graded control of the fume filter's cleaning. Furthermore, this embodiment can also quantify the surface oil stain thickness H, the airflow pressure difference ΔP on both sides, and the accumulated oil fume concentration C through the oil stain index recognition model. acc The relationship between these three core characteristics and the filter oil stain index FI is calculated using the formula FI = k1 × H + k2 × ΔP + k3 × C. acc +FI0 indirectly yields the filter oil stain index FI, which is derived from the surface oil stain thickness H, the airflow pressure difference ΔP on both sides, and the cumulative oil fume concentration C. acc These three key indicators, quantified using normalized weighting coefficients, accurately and comprehensively reflect the actual contamination level of the fume filter, avoiding bias from single-parameter judgments and making cleanliness assessments more scientific and reasonable. This calculation formula can also be used to assess the accuracy of the output of the oil stain index identification model. FI0 can be understood as the influence of remaining cooking operation data on the filter's oil stain index FI, in addition to the three core characteristics of the filter's surface oil thickness, airflow pressure difference across the filter, and accumulated oil fume concentration. Furthermore, the value of FI0 is relatively small and negligible.

[0066] In addition, k1 represents the weighting coefficient corresponding to the surface oil thickness H, which can also be understood as the first weighting coefficient; k2 represents the weighting coefficient corresponding to the airflow pressure difference ΔP on both sides, which can also be understood as the second weighting coefficient; and k3 represents the cumulative oil fume concentration C. acc The corresponding weighting coefficient, k3, can also be understood as the third weighting coefficient. By setting these three weighting coefficients, k1, k2, and k3, and ensuring their sum is 1, the influence of each factor parameter can be flexibly adjusted according to the model and usage scenario, improving the applicability and versatility of the control strategy. Furthermore, the values ​​of these three weighting coefficients, k1, k2, and k3, can be gradually optimized in each iteration of the oil stain index identification model; therefore, the values ​​of these three weighting coefficients are not entirely the same in each iteration. This filter oil stain index FI enables more intelligent and precise self-cleaning control, effectively ensuring the unobstructed flow of the oil fume filter, maintaining the stable operation of the range hood, reducing manual maintenance, and improving the overall reliability and economic efficiency of the machine.

[0067] Figure 5This is a flowchart illustrating another control method for a range hood provided in this embodiment of the invention. This embodiment is an optimization based on the above embodiment. Optionally, the control method further includes: Construct a cooking intensity recognition model for range hoods; The average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood in the first time period are input into the cooking intensity recognition model, and the cooking intensity index corresponding to the range hood is output. The rotation of the oil fume filter is controlled according to the cooking intensity index corresponding to the range hood, so as to centrifugally separate the oil stains attached to the oil fume filter.

[0068] For details not covered in this embodiment, please refer to the above embodiments. Figure 5 As shown, the control method includes: S310. Obtain cooking operation data of the range hood; wherein, the cooking operation data of the range hood includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides within the first time period.

[0069] S320. Construct a cooking intensity recognition model corresponding to the range hood.

[0070] Specifically, this cooking intensity recognition model can use multiple data points from the cooking operation data of the range hood as multi-dimensional inputs. By fusing and quantitatively fitting these data points with corresponding physical characteristics, it constructs a model that can accurately output a cooking intensity index. Furthermore, this model comprehensively reflects the amount of smoke generated, the heat level, and the duration of cooking. The output cooking intensity index more accurately reflects the actual extraction efficiency of the range hood, significantly improving the comprehensiveness and accuracy of the range hood's operational status assessment. It aligns with real-world scenarios, enabling real-time quantification and adaptive judgment of cooking intensity. This provides intelligent adjustment criteria for the range hood's motor speed, airflow, pressure boosting, and cleaning functions, improving extraction efficiency, reducing noise and energy consumption, and achieving on-demand operation and intelligent control.

[0071] It should also be noted that S310 is the step of acquiring cooking operation data, and S320 is the step of constructing the cooking intensity recognition model. S310 can be executed first and then S320, or S320 can be executed first and then S310, or S310 and S320 can be executed simultaneously. In this embodiment, there are no specific requirements or special limitations on the execution order of S310 and S320. This is only an example for illustration.

[0072] S330: Input the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood into the cooking intensity recognition model, and output the cooking intensity index corresponding to the range hood.

[0073] Specifically, the input to this cooking intensity recognition model is the cooking operation data of the range hood, and the output is the cooking intensity index corresponding to the range hood. For example, "first time" can be understood as a certain period during the cooking process, or it can be understood as a specific period selected by the user. In other words, this cooking intensity recognition model analyzes and processes the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides within the first time period corresponding to the range hood, and performs multi-parameter fusion calculations. It can output a cooking intensity index that comprehensively characterizes the amount of oil fume generated, the heat level, and the duration of cooking with the range hood. This index accurately reflects different cooking scenarios such as stir-frying, simmering, and gentle boiling, achieving real-time quantification and adaptive judgment of cooking intensity. It provides precise adjustment basis for the range hood's airflow, speed, and pressure boosting functions, achieving the effect of oil fume removal as cooking progresses, intelligent noise reduction, and energy saving, thus improving the overall intelligence level of the machine and the user experience.

[0074] S340: Based on the cooking intensity index corresponding to the range hood, control the rotation of the oil fume filter to centrifugally separate the oil stains attached to the oil fume filter.

[0075] Specifically, this embodiment essentially involves selecting a graded cleaning strategy and executing a centrifugal oil-spinning process. This collaboratively achieves intelligent oil removal management of the fume filter. Throughout the cooking process, it continuously monitors changes in the rotation speed of the fume filter and the cooking intensity, ensuring that the filter's rotation speed is adjusted in real-time to match the equipment's operating status and actual cooking needs. This adaptive adjustment optimizes energy consumption and operating noise while maintaining effective oil fume separation, and better suits the personalized cooking habits of different users. For example, multiple intensity level thresholds can be preset experimentally, such as a first preset intensity index threshold, a second preset intensity index threshold, and a third preset intensity index threshold. The first preset intensity index threshold is less than the second preset intensity index threshold, and the second preset intensity index threshold is less than the third preset intensity index threshold. Subsequently, the relationship and range between the cooking intensity index output by the cooking intensity recognition model and the first, second, and third preset intensity index thresholds can be determined to achieve precise control of oil removal from the fume filter. Furthermore, based on the cooking intensity index corresponding to the range hood and the determined low, medium, and high cooking intensity levels, the rotation speed of the fume filter can be automatically matched to different cooking intensities. For example, the rotation speed of the fume filter can be adjusted accordingly. In this way, centrifugal force can be used to shake off the oil and dirt adhering to the surface and mesh of the fume filter, reducing the amount of oil adhering to the surface of the fume filter before spray cleaning and improving the self-cleaning effect.

[0076] For example, when the cooking intensity index corresponding to the range hood is greater than or equal to the first preset intensity index threshold and less than the second preset intensity index threshold, it can be considered that the range hood corresponds to low-smoke cooking scenarios such as steaming, boiling, and soup making. In this case, a low-intensity centrifugal separation process can be performed in the cleaning mode. That is, the surface oil stains of the oil fume filter can be peeled off by the centrifugal force generated by the high-speed rotation of the oil fume filter. For example, the rotation speed of the oil fume filter can be 400r / min, which can reduce energy consumption and noise while ensuring the basic smoke exhaust effect.

[0077] For example, when the cooking intensity index corresponding to the range hood is greater than or equal to the second preset intensity index threshold and less than the third preset intensity index threshold, it can be considered that the range hood corresponds to a medium-intensity cooking scenario such as home-style stir-frying. In this case, the cleaning mode can perform a medium-intensity centrifugal separation process, that is, the surface oil stains of the oil fume filter can be peeled off by the centrifugal force generated by the high-speed rotation of the oil fume filter. For example, the rotation speed of the oil fume filter can be 800r / min, which is suitable for the scenario of rapid discharge of medium-intensity oil fumes.

[0078] For example, when the cooking intensity index corresponding to the range hood is greater than or equal to the third preset intensity index threshold, it can be considered that the range hood corresponds to high-oil-fume cooking scenarios such as stir-frying and deep-frying. In this case, the cleaning mode can perform a high-intensity centrifugal separation process, that is, the centrifugal force generated by the high-speed rotation of the oil fume filter can be used to peel off the surface oil stains of the oil fume filter. For example, the rotation speed of the oil fume filter can be 1200r / min, which can effectively deal with high oil fume concentration scenarios and prevent oil fume diffusion.

[0079] In addition, it should be noted that the specific rotation speed of the fume filter is only an example and is not limited. For instance, the rotation speed of the fume filter can be determined through bench testing to measure the fume separation efficiency, noise level, and energy consumption at different rotation speeds. With the goal of "separation efficiency ≥90%, noise ≤65dB, and optimal energy consumption," the optimal rotation speed for each cooking intensity level can be fitted. Furthermore, the rotation speed of the fume filter can be continuously optimized and iterated based on actual user data and cooking conditions.

[0080] S350. Construct an oil pollution index identification model corresponding to the oil fume filter.

[0081] It should also be noted that S320 and S350 are steps for constructing the oil stain index recognition model. S330 and S340 following S320 can be applied to the cooking process of the range hood, and S360 and S370 following S350 can be applied to the cleaning process of the range hood after cooking. S320 can be executed first and then S350, or S350 can be executed first and then S320, or S320 and S350 can be executed simultaneously. In this embodiment, there are no specific requirements or special limitations on the execution order of S320 and S350. This is only an example for illustration. The execution order of S330 and S340 can be before S360 and S370, which is consistent with the cooking process and the cleaning process after cooking of the range hood.

[0082] Furthermore, in this embodiment, throughout the cooking process, based on the cooking operation data of the range hood and the cooking intensity index output by the cooking intensity recognition model, different rotation speeds of the fume filter are matched to achieve adaptive adjustment of cooking intensity and fume filter rotation speed, improving oil fume separation effect and reducing energy consumption. After cooking, based on the cooking operation data of the range hood and the oil stain index output by the oil stain index recognition model, different rotation speeds of the fume filter and different water output modes of the filter cleaning structure are matched to achieve precise, on-demand cleaning, avoiding ineffective cleaning and improving cleaning efficiency. The S320, S330 to S340 models use a cooking intensity recognition model and the corresponding cooking intensity index of the range hood as one independent intelligent control logic. The S350, S360 to S370 models use an oil stain index recognition model and the corresponding oil stain index of the fume filter as another independent intelligent control logic. These two independent intelligent control logics work together to form a complete closed loop from adaptive adjustment and adaptive purification during the cooking process to intelligent and precise cleaning after cooking. Through multi-sensor fusion technology, the oil stain adhesion of the fume filter is monitored throughout the entire process. Combined with the recognition of user cooking habits, intelligent strategy matching is achieved. At the same time, feedback information such as cleaning status and maintenance reminders can be output to improve user experience, increase cleaning efficiency, reduce resource consumption, and extend the service life of the equipment.

[0083] S360: Input the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides into the oil stain index recognition model for the first time period corresponding to the range hood, and output the filter oil stain index corresponding to the oil fume filter.

[0084] S370. Based on the oil stain index of the corresponding oil fume filter, control the rotation of the oil fume filter and / or control the water outlet of the filter cleaning structure to clean the oil fume filter.

[0085] Figure 6 This is a flowchart illustrating another control method for a range hood provided in this embodiment of the invention. This embodiment is an optimization based on the above embodiment. Optionally, the control method further includes: Construct a cooking intensity recognition model for range hoods; The average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood in the first time period are input into the cooking intensity recognition model, and the cooking intensity index corresponding to the range hood is output. The rotation of the oil fume filter is controlled according to the cooking intensity index corresponding to the range hood, so as to centrifugally separate the oil stains attached to the oil fume filter.

[0086] Furthermore, a cooking intensity recognition model corresponding to the range hood is constructed, including: Acquire second training data for training the cooking intensity recognition model; wherein the second training data includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides within a third time period; The second training data is divided into a second training set and a second test set; The parameters of the cooking intensity recognition model were debugged using the second training set, and the training results of the cooking intensity recognition model were evaluated using the second test set. When the training results of the cooking intensity recognition model meet the second preset condition, the training of the cooking intensity recognition model is considered complete.

[0087] For details not covered in this embodiment, please refer to the above embodiments. Figure 6 As shown, the control method includes: S401. Obtain the cooking operation data of the range hood; wherein, the cooking operation data of the range hood shall include at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides within the first time period.

[0088] S402. Obtain second training data for training the cooking intensity recognition model; wherein the second training data includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides within a third time period.

[0089] Specifically, the second training data can be understood as historical cooking data of the range hood, while the cooking operation data can be understood as real-time cooking data of the range hood in operation. The acquisition of the second training data can be referred to the above embodiment, and will not be repeated here. For example, the third time can be understood as a certain period of time during the previous cooking process, and the first time can be understood as a certain period of time before the current cooking moment. It should also be noted that the second training data can be applied to the construction of the cooking intensity recognition model, while the cooking operation data is applied to the actual acquisition of the cooking intensity index corresponding to the range hood after the cooking intensity recognition model has been constructed. Furthermore, the first training data and the second training data can be understood as the same data, differing only in the type of model subsequently input.

[0090] S403. Divide the second training data into a second training set and a second test set.

[0091] Specifically, the second training data can be divided into a second training set and a second test set according to a preset ratio. For example, the preset ratio can be determined according to the training process of the cooking intensity recognition model, such as 7:3.

[0092] S404. Debug the parameters of the cooking intensity recognition model using the second training set, and evaluate the training results of the cooking intensity recognition model using the second test set.

[0093] Specifically, the data corresponding to the second training set is input into the cooking intensity recognition model, which can output the cooking intensity index recognized by the model for the second training set. By comparing the cooking intensity index recognized by the model for the second training set with the actual cooking intensity index of the second training set, if the cooking intensity index recognized by the model for the second training set is different from the actual cooking intensity index of the second training set, the parameters of the cooking intensity recognition model need to be readjusted until the cooking intensity index recognized by the model for the second training set is the same as or close to the actual cooking intensity index of the second training set.

[0094] Furthermore, by inputting the data corresponding to the second test set into the cooking intensity recognition model, the model can output a cooking intensity index for the second test set. By comparing the cooking intensity index output by the cooking intensity recognition model for the second test set with the actual cooking intensity index of the second test set, if the cooking intensity index output by the cooking intensity recognition model for the second test set for a large number of data in the second test set is the same as the actual cooking intensity index of the second test set, then the training result of the cooking intensity recognition model is good. If the cooking intensity index output by the cooking intensity recognition model for the second test set for a large number of data in the second test set is different from the actual cooking intensity index of the second test set, then the training result of the cooking intensity recognition model is poor, and the parameters of the cooking intensity recognition model need to be readjusted using the second training set.

[0095] S405. When the training results of the cooking intensity recognition model meet the second preset condition, the training of the cooking intensity recognition model is determined to be complete.

[0096] Specifically, the second preset condition is determined based on the training process and application of the cooking intensity recognition model. For example, the second preset condition can be a proportional threshold or a proportional range. For example, the second preset condition can be adjusted by changing the hyperparameters to achieve a classification accuracy ≥95%. Specifically, when the training result meets the second preset condition—that is, when the cooking intensity recognition model outputs the same cooking intensity index for the second test set as the actual cooking intensity index for the second test set—it can be determined that the cooking intensity recognition model has been successfully trained and can be applied to identify the cooking intensity index of the range hood during an unknown cooking process or the next cooking process.

[0097] S406. Input the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood into the cooking intensity recognition model, and output the cooking intensity index corresponding to the range hood.

[0098] S407. Based on the cooking intensity index corresponding to the range hood, control the rotation of the oil fume filter to centrifugally separate the oil stains attached to the oil fume filter.

[0099] S408. Construct an oil stain index identification model corresponding to the oil fume filter.

[0100] S409. Input the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides into the oil stain index recognition model for the first time period corresponding to the range hood, and output the filter oil stain index corresponding to the oil fume filter.

[0101] S410. Based on the oil stain index of the corresponding oil fume filter, control the rotation of the oil fume filter and / or control the water outlet of the filter cleaning structure to clean the oil fume filter.

[0102] Optionally, after inputting the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood into the cooking intensity recognition model, before outputting the cooking intensity index corresponding to the range hood, the following steps are included: standardizing the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood within the first time period; performing feature filtering on the standardized average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood within the first time period to obtain the average oil fume concentration, peak oil fume concentration, motor speed, and cooking duration of the range hood.

[0103] Specifically, this embodiment is essentially a process of analyzing and processing the cooking operation data of the range hood input into the cooking intensity recognition model. The average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood within the first time period are standardized. For example, the numerical data can be normalized according to the interval [0, 1]. For example, the time-related data can be quantized into numerical labels according to a two-hour interval. For example, the encoding of the type-related data can be processed using binary vectorization. Subsequently, feature filtering is performed on the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood in the first time period after standardization. This is to remove low-relevance features to reduce computational load. For example, core features can be selected by using the Pearson correlation coefficient. These core features refer to the data in the cooking operation data of the range hood that are mainly related to the cooking intensity of the range hood, such as the average oil fume concentration, peak oil fume concentration, motor speed, and cooking duration.

[0104] And, based on the obtained average oil fume concentration C of the range hood avg Peak oil fume concentration C peakThe range hood's control system, taking into account the motor speed F and cooking duration T, can output a cooking intensity index CI through a cooking intensity recognition model. This CI comprehensively reflects the oil buildup, fume extraction efficiency, and user cooking habits. The value of the CI quantifies whether the centrifugal oil separation process of the fume filter needs to be activated, thus enabling the filter to pre-remove some of the attached oil. Furthermore, this embodiment can also quantify the average fume concentration C using the cooking intensity recognition model. avg Peak oil fume concentration C peak The relationship between the four core characteristics—motor speed F, cooking duration T, and cooking intensity index CI—is expressed by the formula CI = α × C. avg +β×C peak The cooking intensity index CI is indirectly derived from +δ×F+γ×T+CI0, and the average oil fume concentration C is calculated from it. avg Peak oil fume concentration C peak The four key indicators—motor speed (F), cooking duration (T), and cooking frequency—are comprehensively quantified using normalized weighting coefficients. This accurately and comprehensively reflects the actual oil stain condition of the range hood, avoiding bias from single-parameter judgments and making cleaning assessments more scientific and reasonable. This calculation formula can also be used to assess the accuracy of the cooking intensity recognition model's output. CI0 can be understood as the influence of the remaining cooking operation data on the cooking intensity index CI, excluding the four core characteristics of the range hood: average oil fume concentration, peak oil fume concentration, motor speed, and cooking duration. The value of CI0 is relatively small and can be ignored.

[0105] In addition, α represents the average oil fume concentration C. avg The corresponding weighting coefficient, α, can also be understood as the fourth weighting coefficient, and β represents the peak oil fume concentration C. peak The corresponding weighting coefficients are as follows: β can be understood as the fifth weighting coefficient; δ represents the weighting coefficient corresponding to the motor speed F, which can also be understood as the sixth weighting coefficient; and γ represents the weighting coefficient corresponding to the cooking duration T, which can also be understood as the seventh weighting coefficient. By setting these four weighting coefficients α, β, δ, and γ, and ensuring that their sum is 1, the influence of each factor parameter can be flexibly adjusted according to the model and usage scenario, improving the applicability and versatility of the control strategy. Furthermore, the values ​​of these four weighting coefficients α, β, δ, and γ can be gradually optimized in each iteration of the cooking intensity recognition model, and the values ​​of these four weighting coefficients are not exactly the same in each iteration. This cooking intensity index CI enables more intelligent and precise control of the rotation speed of the fume filter, effectively ensuring the unobstructed flow of the fume filter, maintaining the stable operation of the range hood, reducing manual maintenance, and improving the overall reliability and economic efficiency of the machine.

[0106] Figure 7 This is a flowchart illustrating another control method for a range hood provided in an embodiment of the present invention, as shown below. Figure 7 As shown, the range hood is turned on / started, and cooking operation data is acquired throughout the cooking process. This data includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference between the two sides within a first time period. Then, based on a pre-built cooking intensity recognition model, a cooking intensity index corresponding to the range hood can be output, and subsequent cooking intensity determination can be performed. For example, if the cooking intensity index corresponding to the range hood is greater than or equal to a first preset intensity index threshold and less than a second preset intensity index threshold, the range hood can be considered to correspond to low-oil-fume cooking scenarios such as steaming, boiling, and simmering, or to correspond to a low-intensity mode. In this case, the rotation speed of the oil fume filter can be adjusted to 400 r / min. For example, when the cooking intensity index corresponding to the range hood is greater than or equal to the second preset intensity index threshold and less than the third preset intensity index threshold, the range hood can be considered to correspond to a medium-smoke cooking scenario such as stir-frying, or a medium-intensity mode. In this case, the rotation speed of the fume filter can be increased to 800 r / min. For example, when the cooking intensity index corresponding to the range hood is greater than or equal to the third preset intensity index threshold, the range hood can be considered to correspond to a high-smoke cooking scenario such as stir-frying or deep-frying, or a high-intensity mode. In this case, the rotation speed of the fume filter can be further increased to 1200 r / min. Furthermore, throughout the cooking process, the cooking operation data of the range hood can be acquired in real time, and the rotation speed of the fume filter can be adjusted in real time according to the cooking intensity index corresponding to the range hood output by the model, to better match actual cooking needs.

[0107] Then, after the cooking process is completed, the range hood can enter standby mode. Afterwards, based on a pre-built oil stain index recognition model, the oil stain index of the corresponding fume filter can be output, and subsequent filter contamination determination can be performed. For example, if the oil stain index of the corresponding fume filter output by the model is less than a first preset oil stain index threshold, then no cleaning mode is required. For example, if the oil stain index of the corresponding fume filter output by the model is greater than or equal to the first preset oil stain index threshold and less than the second preset oil stain index threshold, then the fume filter can be considered lightly contaminated, and a basic centrifugal cleaning process can be performed in cleaning mode. For example, if the oil stain index of the corresponding fume filter output by the model is greater than or equal to the second preset oil stain index threshold and less than the third preset oil stain index threshold, then the fume filter can be considered moderately contaminated, and a standard centrifugal cleaning process can be performed in cleaning mode. For example, if the oil stain index of the oil fume filter output by the model is greater than or equal to the third preset oil stain index threshold, the oil fume filter can be considered heavily polluted, and a deep centrifugal cleaning process can be performed in the cleaning mode. Based on this, after cleaning the oil fume filter, the cooking operation data of the range hood can be acquired again, and the corresponding intelligent cleaning strategy can be adjusted in real time according to the oil stain index of the oil fume filter output by the model. It is then determined whether the calculated oil stain index of the oil fume filter has recovered to a safe range below the first preset oil stain index threshold, that is, whether the calculated oil stain index of the oil fume filter meets the standard. If yes, the cleaning mode can be ended; if not, the cleaning strategy needs to be rematched, for example, a higher-level cleaning strategy, until the calculated oil stain index of the oil fume filter recovers to below the first preset oil stain index threshold. Finally, after the cleaning mode is completed, the range hood can be turned off.

[0108] Figure 8 This is a schematic diagram of the structure of a control device for a range hood provided in an embodiment of the present invention, as shown below. Figure 1 and Figure 2 As shown, the range hood includes a main unit 10, and inside the main unit 10 are a fan, an oil fume filter 40, and a filter cleaning structure 50. The oil fume filter 40 is located on the air inlet side of the fan. The output shaft of the fan is mechanically connected to the middle of the oil fume filter 40. The water outlet of the filter cleaning structure 50 is oriented towards the surface of the oil fume filter 40. The control device of this range hood is suitable for intelligent adaptive cleaning of the oil fume filter after the cooking process. The control device of this range hood can be implemented in hardware and / or software, and is generally configured in a control board. Figure 8 As shown, the control device includes: The operation data acquisition module 510 is used to acquire the cooking operation data of the range hood; wherein, the cooking operation data of the range hood includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides within a first time period; the first model construction module 520 is used to construct an oil stain index recognition model corresponding to the oil fume filter; the oil stain index recognition module 530 is used to input the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides within the first time period corresponding to the range hood into the oil stain index recognition model, and output the filter oil stain index corresponding to the oil fume filter; the filter cleaning control module 540 is used to control the rotation of the oil fume filter and / or control the water outlet of the filter cleaning structure to clean the oil fume filter according to the filter oil stain index corresponding to the oil fume filter.

[0109] The technical solution in this invention provides a dynamic centrifugal range hood based on user cooking habits, achieving dynamic intelligent centrifugal cleaning based on user cooking habits. After the cooking process is completed, through data fusion from multiple sensors, and based on the range hood's cooking operation data and the corresponding oil stain index recognition model, it can achieve real-time detection and accurate judgment of the oil stain index of the fume filter. Based on the detection results corresponding to the oil stain condition of the fume filter, it automatically matches a corresponding intelligent cleaning strategy. This intelligent cleaning strategy is not triggered at a fixed period, nor is it a fixed, unchanging program. Instead, it automatically adjusts the cleaning intensity according to the oil stains generated by the user's cooking habits. For example, it automatically adjusts the water output parameters of the filter cleaning structure corresponding to the cleaning mode, and automatically adjusts the rotation of the fume filter. The rotation speed is controlled to achieve efficient and automatic cleaning of the fume filter, which is easy to control. This prevents excessive grease particles from adhering to the filter surface, reduces the rotational resistance of the filter during cooking, and ensures the oil-fume separation efficiency of the filter, the load supply capacity of the motor, and the overall suction and exhaust efficiency of the range hood. This improves cleaning efficiency and reduces resource consumption and user maintenance costs. In other words, while ensuring the cleaning effect of the fume filter, it avoids resource waste caused by ineffective cleaning, as well as over-cleaning or under-cleaning. It also achieves a dynamic balance between the exhaust efficiency of the range hood and energy saving and noise reduction, further extending the service life of the fume filter and the range hood as a whole. In addition, users do not need to disassemble the fume filter for manual cleaning periodically, improving the user maintenance experience.

[0110] Based on the above technical solution, optionally, the first model construction module 520 may specifically include a first data acquisition unit, a first data partitioning unit, a first training and testing unit, and a first model judgment unit. The first data acquisition unit is used to acquire first training data for training the oil stain index recognition model; wherein, the first training data includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides within a second time period; the first data partitioning unit is used to partition the first training data into a first training set and a first testing set; the first training and testing unit is used to debug the parameters of the oil stain index recognition model using the first training set, and to evaluate the training results of the oil stain index recognition model using the first testing set; the first model judgment unit is used to determine that the training of the oil stain index recognition model is complete when the training results of the oil stain index recognition model meet a first preset condition.

[0111] Optionally, the control device further includes a first standardization unit and a first feature filtering unit. The first standardization unit is used to standardize the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides within a first time period corresponding to the range hood. The first feature filtering unit is used to perform feature filtering on the standardized average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides within a first time period corresponding to the range hood, to obtain the surface oil thickness of the oil fume filter, airflow pressure difference on both sides, and cumulative oil fume concentration.

[0112] Optionally, the filter cleaning control module 540 may specifically include a first filter cleaning control unit, which is used to control the oil fume filter to rotate in order to clean the oil fume filter when the oil stain index of the filter corresponding to the oil fume filter is greater than or equal to a first preset oil stain index threshold and less than a second preset oil stain index threshold.

[0113] Optionally, the filter cleaning control module 540 may specifically include a second filter cleaning control unit. The second filter cleaning control unit is used to control the rotation of the fume filter and control the water outlet of the filter cleaning structure to clean the fume filter when the filter oil stain index corresponding to the fume filter is greater than or equal to a second preset oil stain index threshold.

[0114] Optionally, the control device further includes a second model building module, an intensity index recognition module, and a centrifugal separation control module. The second model building module is used to build a cooking intensity recognition model corresponding to the range hood. The intensity index recognition module is used to input the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood into the cooking intensity recognition model and output the cooking intensity index corresponding to the range hood. The centrifugal separation control module is used to control the rotation of the oil fume filter according to the cooking intensity index corresponding to the range hood, so as to centrifugally separate the oil stains attached to the oil fume filter.

[0115] Optionally, the second model construction module may specifically include a second data acquisition unit, a second data partitioning unit, a second training and testing unit, and a second model judgment unit. The second data acquisition unit is used to acquire second training data for training the cooking intensity recognition model. The second training data includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides within a third time period. The second data partitioning unit is used to partition the second training data into a second training set and a second testing set. The second training and testing unit is used to debug the parameters of the cooking intensity recognition model using the second training set and to evaluate the training results of the cooking intensity recognition model using the second testing set. The second model judgment unit is used to determine that the training of the cooking intensity recognition model is complete when the training results of the cooking intensity recognition model meet a second preset condition.

[0116] Optionally, the control device further includes a second standardization unit and a second feature filtering unit. The second standardization unit is used to standardize the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood within a first time period. The second feature filtering unit is used to perform feature filtering on the standardized average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood within the first time period to obtain the average oil fume concentration, peak oil fume concentration, motor speed, and cooking duration of the range hood.

[0117] The control device for the range hood provided in the embodiments of the present invention can execute the control method for the range hood provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0118] Figure 9 This is a schematic diagram of the structure of a terminal device provided in an embodiment of the present invention, such as... Figure 9As shown, the terminal device provided in this embodiment of the invention includes: one or more processors 71 and a storage device 72; the processors 71 in the terminal device may be one or more. Figure 9 Taking a processor 71 as an example; storage device 72 is used to store one or more programs; when one or more programs are executed by one or more processors 71, the one or more processors 71 implement the control method of the range hood as provided in any of the embodiments of the present invention.

[0119] The terminal device may also include an input device 73 and an output device 74.

[0120] The processor 71, storage device 72, input device 73, and output device 74 in this terminal device can be connected via a bus or other means. Figure 9 Taking the example of a connection between China and Israel via a bus.

[0121] The storage device 72 in the terminal device serves as a readable storage medium and can be used to store one or more programs. These programs can be software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the range hood control method provided in this embodiment of the invention (e.g., attached...). Figure 8 The cleaning control device of the range hood shown includes the following modules: an operation data acquisition module 510, used to acquire cooking operation data of the range hood; wherein, the cooking operation data of the range hood includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides within a first time period; a first model construction module 520, used to construct an oil stain index recognition model corresponding to the oil fume filter; an oil stain index recognition module 530, used to input the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides within the first time period corresponding to the range hood into the oil stain index recognition model, and output the filter oil stain index corresponding to the oil fume filter; and a filter cleaning control module 540, used to control the rotation of the oil fume filter and / or control the water outlet of the filter cleaning structure to clean the oil fume filter according to the filter oil stain index corresponding to the oil fume filter. The processor 71 executes various functional applications and data processing of the terminal device by running software programs, instructions and modules stored in the storage device 72, thereby realizing the control method of the range hood in the above method embodiment.

[0122] Storage device 72 may include a stored program area and a stored data area, wherein the stored program area may store the operating system and applications required for at least one function; the stored data area may store data created based on the use of the device, etc. Furthermore, storage device 72 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, storage device 72 may further include memory remotely located relative to processor 71, and this remote memory may be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0123] Input device 73 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the device. Output device 74 may include display devices such as a display screen.

[0124] Furthermore, when one or more programs included in the aforementioned device are executed by one or more processors 71, the programs perform the following operations: Acquire cooking operation data of the range hood; the cooking operation data of the range hood shall include at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter and airflow pressure difference on both sides in the first time period; Construct an oil pollution index identification model for oil fume filters; The average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood within the first time period are input into the oil stain index recognition model, and the filter oil stain index corresponding to the oil fume filter is output. Based on the oil stain index of the corresponding oil fume filter, control the rotation of the oil fume filter and / or control the water outlet of the filter cleaning structure to clean the oil fume filter.

[0125] This invention also provides a readable storage medium storing a computer program thereon, which, when executed by a processor, performs a control method for a range hood provided in any one of the embodiments of this invention. The control method includes: Acquire cooking operation data of the range hood; the cooking operation data of the range hood shall include at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter and airflow pressure difference on both sides in the first time period; Construct an oil pollution index identification model for oil fume filters; The average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood within the first time period are input into the oil stain index recognition model, and the filter oil stain index corresponding to the oil fume filter is output. Based on the oil stain index of the corresponding oil fume filter, control the rotation of the oil fume filter and / or control the water outlet of the filter cleaning structure to clean the oil fume filter.

[0126] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a readable storage medium. A readable storage medium can take many forms, including but not limited to: electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable CD-ROMs, optical storage devices, magnetic storage devices, or any suitable combination thereof. A readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0127] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0128] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, radio frequency (RF), etc., or any suitable combination thereof.

[0129] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including but not limited to a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0130] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0131] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A control method for a range hood, characterized in that, The range hood includes a main unit housing, and a fan, a fume filter, and a filter cleaning structure located inside the main unit housing; The fume filter is located on the air inlet side of the fan; the output shaft of the fan is mechanically connected to the middle of the fume filter; the water outlet direction of the filter cleaning structure is oriented towards the surface of the fume filter. The control method includes: Acquire the cooking operation data of the range hood; wherein the cooking operation data of the range hood includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides within a first time period; Construct an oil stain index identification model corresponding to the oil fume filter screen; The average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood within the first time period are input into the oil stain index recognition model, and the filter oil stain index corresponding to the oil fume filter is output. Based on the oil stain index of the oil fume filter, the rotation of the oil fume filter is controlled, and / or the water outlet of the filter cleaning structure is controlled to clean the oil fume filter.

2. The control method according to claim 1, characterized in that, Constructing an oil stain index identification model corresponding to the oil fume filter includes: Obtain first training data for training the oil stain index recognition model; wherein, the first training data includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides during the second time period; The first training data is divided into a first training set and a first test set; The parameters of the oil pollution index recognition model are debugged using the first training set, and the training results of the oil pollution index recognition model are evaluated using the first test set. When the training results of the oil pollution index recognition model meet the first preset condition, the training of the oil pollution index recognition model is determined to be complete.

3. The control method according to claim 1, characterized in that, After inputting the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference between the two sides into the oil stain index recognition model, before outputting the filter oil stain index corresponding to the oil fume filter, the following steps are also included: The average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood within the first time period are standardized. The average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood corresponding to the first time period after standardization are subjected to feature screening processing to obtain the surface oil stain thickness of the oil fume filter, airflow pressure difference on both sides, and cumulative oil fume concentration.

4. The control method according to claim 1, characterized in that, Based on the oil stain index corresponding to the oil fume filter, the rotation of the oil fume filter is controlled, and / or the water outlet of the filter cleaning structure is controlled to clean the oil fume filter, including: When the oil stain index of the oil fume filter is greater than or equal to the first preset oil stain index threshold and less than the second preset oil stain index threshold, the oil fume filter is controlled to rotate to clean the oil fume filter.

5. The control method according to claim 1, characterized in that, Based on the oil stain index corresponding to the oil fume filter, the rotation of the oil fume filter is controlled, and / or the water outlet of the filter cleaning structure is controlled to clean the oil fume filter, including: When the oil stain index of the filter screen corresponding to the oil fume filter screen is greater than or equal to the second preset oil stain index threshold, the oil fume filter screen is controlled to rotate, and the water outlet of the filter screen cleaning structure is controlled to clean the oil fume filter screen.

6. The control method according to claim 1, characterized in that, The control method also includes: Construct a cooking intensity recognition model corresponding to the range hood; The average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood within the first time period are input into the cooking intensity recognition model, and the cooking intensity index corresponding to the range hood is output. Based on the cooking intensity index corresponding to the range hood, the rotation of the fume filter is controlled to centrifugally separate the oil stains attached to the fume filter.

7. The control method according to claim 6, characterized in that, Constructing a cooking intensity recognition model corresponding to the range hood includes: Acquire second training data for training the cooking intensity recognition model; wherein the second training data includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil thickness of the oil fume filter, and airflow pressure difference on both sides within a third time period; The second training data is divided into a second training set and a second test set; The parameters of the cooking intensity recognition model are adjusted using the second training set, and the training results of the cooking intensity recognition model are evaluated using the second test set. When the training results of the cooking intensity recognition model meet the second preset condition, the training of the cooking intensity recognition model is determined to be complete.

8. The control method according to claim 6, characterized in that, After inputting the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference between the two sides into the cooking intensity recognition model, before outputting the cooking intensity index corresponding to the range hood, the following steps are also included: The average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood within the first time period are standardized. The average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides of the range hood within the first time period after standardization are subjected to feature screening processing to obtain the average oil fume concentration, peak oil fume concentration, motor speed, and cooking duration of the range hood.

9. A control device for a range hood, characterized in that, The range hood includes a main unit housing, and a fan, a fume filter, and a filter cleaning structure located inside the main unit housing; The fume filter is located on the air inlet side of the fan; the output shaft of the fan is mechanically connected to the middle of the fume filter; the water outlet direction of the filter cleaning structure is oriented towards the surface of the fume filter. The control device includes: The operation data acquisition module is used to acquire the cooking operation data of the range hood; wherein, the cooking operation data of the range hood includes at least the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter, and airflow pressure difference on both sides within a first time period; The first model building module is used to build an oil pollution index recognition model corresponding to the oil fume filter screen. The oil stain index recognition module is used to input the average oil fume concentration, peak oil fume concentration, cumulative oil fume concentration, motor speed, cooking duration, surface oil stain thickness of the oil fume filter and airflow pressure difference on both sides of the range hood into the oil stain index recognition model, and output the filter oil stain index corresponding to the oil fume filter. The filter cleaning control module is used to control the rotation of the fume filter and / or control the water output of the filter cleaning structure to clean the fume filter based on the filter oil stain index corresponding to the fume filter.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the control method for the range hood as described in any one of claims 1-8.

Images