Intelligent range hood based on multi-dimensional data fusion and dynamic threshold control
By using multi-dimensional data fusion and dynamic threshold control in the range hood, the existing range hood control methods and poor user adaptability are solved, and intelligent operation and efficient smoke removal effects are achieved.
Patent Information
- Application Number
- CN202510355698.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-25
- Publication Date
- 2025-06-20
AI Technical Summary
The existing range hood has cumbersome control methods, poor user adaptability, and has not achieved intelligent operation. It is impossible to automatically adjust the working status according to actual needs and environmental changes during the cooking process.
The intelligent hood is adopted based on multi-dimensional data fusion and dynamic threshold control. Multi-source environmental data is collected through sound sensing, light signal sensing, human body sensing and smoke sensing modules, and data processing and logic control are used for the main control module to generate control commands to automatically adjust the working state of the hood.
It improves judgment accuracy and environmental adaptability, improves user experience, energy efficiency and safety, realizes intelligent operation, reduces false triggers, and adapts to different kitchen environments and usage scenarios.
Smart Images
Figure CN120176151A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of kitchen equipment, and in particular to an intelligent range hood based on multi-dimensional data fusion and dynamic threshold control. Background Art
[0002] Traditional range hoods usually use a physical control switch component installed on the machine body, and users need to manually control the various working functions of the range hood, such as turning the lighting on and off, adjusting the brightness, and starting, stopping and adjusting the wind speed of the fan, etc. This operation method is relatively cumbersome, requiring users to frequently interrupt their work to operate the control panel during cooking, which not only affects the continuity and convenience of cooking, but may also cause inconvenience in operation or inaccurate control due to greasy or wet hands.
[0003] In order to improve this situation, some range hoods have introduced infrared detection technology, trying to control the range hood by identifying the movements of human hands. However, this type of technology still has many limitations in practical applications. On the one hand, users need to remember and accurately make specific gestures or gestures, which has a large learning cost for different users and is difficult to adapt quickly; on the other hand, the recognition accuracy and response speed of infrared detection technology may be affected by multiple factors such as ambient light, hand obstructions (such as gloves, sleeves), and user movement habits, resulting in poor control effects. More importantly, this control method based on gesture recognition still relies on the user's active operation, and does not truly realize the intelligent operation of the range hood, that is, automatically adjusting the working state according to the actual needs and environmental changes during the cooking process.
[0004] Therefore, the range hoods in the prior art have shortcomings in terms of control methods, such as cumbersome operation and poor user adaptability, and a more convenient, intelligent and user-friendly control solution is urgently needed to improve user experience and cooking efficiency. Summary of the invention
[0005] The purpose of the present invention is to solve the problems of complicated operation and poor user adaptability in the control method of range hoods in the prior art, and to provide an intelligent range hood based on multi-dimensional data fusion and dynamic threshold control.
[0006] In order to achieve the above invention object, the present invention adopts the following technical scheme:
[0007] Intelligent range hood based on multi-dimensional data fusion and dynamic threshold control, comprising a range hood body and a control system arranged on the range hood body. The control system includes an input module, a main control module and an execution module. The signal input end and the signal output end of the main control module are respectively connected to the input module and the execution module. The input module includes a sound sensing module for collecting sound signals in the environment, a light signal sensing module for detecting changes in ambient light intensity, a motion sensing module for monitoring the human body and human movements, and a smoke sensing module for detecting the smoke concentration in the air. The main control module is responsible for data processing, logical control and decision-making, receives multi-source environmental data from the input module, and conducts comprehensive analysis through a data fusion algorithm to generate control instructions. The execution module includes a lighting module and an exhaust module, and executes corresponding operations according to the instructions of the main control module, such as automatically starting the exhaust function when detecting smoke or abnormal movements, or turning on the lighting function when the light is insufficient.
[0008] The intelligent range hood of the present invention integrates multiple data inputs such as sound sensing, light signal sensing, human body sensing and smoke sensing. This multi-dimensional data fusion enables the main control module to more comprehensively understand the kitchen environment, so as to make more accurate judgments. Compared with the prior art, by fusing multiple data inputs for intelligent judgment and control, the present invention not only improves the judgment accuracy and environmental adaptability, but also enhances the user experience, energy efficiency and safety.
[0009] Further solution: The detection data of the motion sensing module includes the human presence state, the relative distance of the human body, and the human body posture. The detection data of the sound sensing module includes the sound type and the sound decibel. The main control module presets a sound threshold, a distance threshold, a reference posture, and a reference sound. The control instruction includes a fan start instruction. The data fusion algorithm includes the following control logic: When any of the following conditions is met, the main control module generates a fan start instruction: Condition A, all of the following three sub-conditions are met simultaneously: the human body posture matches the preset reference posture, the relative distance of the human body reaches or exceeds the preset distance threshold, and the sound type matches the preset reference sound; Condition B, both of the following two sub-conditions are met simultaneously: the human body posture matches the preset reference posture, and the smoke concentration reaches or exceeds the preset smoke concentration threshold. This solution can more accurately identify the actual behavior of the user (such as whether cooking) by fusing multi-dimensional data such as human body posture, relative distance, and sound type, thereby reducing false triggers and improving the judgment accuracy. The main control module presets parameters such as a sound threshold, a distance threshold, a reference posture, and a reference sound, and makes dynamic judgments in combination with real-time detection data. Through dynamic threshold control, the system can adapt to different kitchen environments and usage scenarios. For example, in a noisy environment, the system can avoid accidentally starting the fan due to background noise through the dual judgment of sound decibel and sound type; in low light conditions, the system can automatically turn on the lighting according to the data of the light signal sensing module. This dynamic adaptability enables the device to better cope with complex and changing environments.
[0010] Further, the sound threshold is set as threshold a, threshold b, and threshold c, and a < b < c is satisfied; the control instruction includes a gear-up instruction, a gear-down instruction, and a shutdown instruction. The data fusion algorithm includes the following control logic: If the sound data rises from threshold a to threshold b, or from threshold b to threshold c, a gear-up instruction is generated; if the sound data drops from threshold c to threshold b, or from threshold b to threshold a, a gear-down instruction is generated; if the sound data is lower than threshold a, or the smoke concentration is lower than the preset smoke concentration threshold, a shutdown instruction is generated. By introducing multi-level sound thresholds and hierarchical control instructions, a more refined, dynamic, and intelligent control logic is achieved.
[0011] Further, the reference sound includes a stir-frying sound.
[0012] Further, the main control module is provided with a signal conditioning circuit and a preset reference frequency domain. It is connected to the sound induction module through the signal conditioning circuit to extract the frequency domain of the sound signal and compare it with the reference frequency domain to determine whether the sound types are the same. This solution uses frequency domain analysis technology or time domain analysis technology to identify specific sound types, such as the stir-frying sound. It improves the accuracy of sound recognition, enabling the range hood to automatically start or shift gears when the user performs operations that generate a large amount of oil fumes, such as stir-frying, thus more effectively removing the oil fumes. This solution converts the characteristics of the sound signal into values for comparison, and the comparison method is simple and direct.
[0013] Further, the main control module is provided with a frequency domain analysis program and a frequency domain feature matching program. The frequency domain analysis program converts the time domain sound signal into frequency domain features, and the frequency domain feature matching program compares the detected sound frequency domain features with the preset reference frequency domain of the stir-frying sound to determine whether they match. Further, the reference postures include cooking postures and smoking postures.
[0014] Alternatively, the main control module is provided with a signal conditioning circuit and a preset reference time domain waveform. It is connected to the sound induction module through the signal conditioning circuit and extracts the time domain waveform of the sound signal through the signal conditioning circuit, and determines whether the sound type of the sound signal judged by the main control module is the same as the reference sound by comparing the time domain waveform of the sound signal with the reference time domain waveform. This solution uses waveform comparison technology, which has the characteristics of small computational amount and short response time.
[0015] Further, the control system includes a first automatic lighting mode and a second automatic lighting mode. The main control module presets a light threshold. The human presence state includes two types: yes and no. In the first automatic lighting mode, when the light data is lower than the light threshold and it is detected that the human presence state is "yes", the main control module generates a night light start instruction. When the light data reaches the light threshold or it is detected that the human presence state is "no", the main control module generates a night light off instruction; in the second automatic lighting mode, when the light data is lower than the light threshold, the main control module generates a night light start instruction. When the light data reaches the threshold, the main control module generates a night light off instruction. In this solution, the control system includes a first automatic lighting mode and a second automatic lighting mode, which can automatically turn on or off the night light according to the light data and the human presence state. This design not only facilitates the user's operation in low light conditions but also saves energy.
[0016] Further, the motion sensing module includes a millimeter-wave radar sensing module group. There are at least two groups in the millimeter-wave radar sensing module group. One group is arranged on the front end face of the range hood body, and the other group is arranged on the lower end face of the range hood body. Description of the Drawings
[0017] Figure 1 is the overall schematic diagram of the intelligent range hood;
[0018] Figure 2 is the schematic diagram of the control system;
[0019] Figure 3 is the system block diagram of the control system.
[0020] Label description:
[0021] The main body of the range hood 1, the millimeter-wave radar sensing module 2, the sound sensor 3, the photosensitive sensor 4, and the smoke sensor 5. Specific implementation mode
[0022] The technical solution of the present invention will be further described below with reference to the accompanying drawings:
[0023] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by "upper", "lower", "left", "right", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention.
[0024] See Figures 1-3 As shown, the present invention discloses an intelligent range hood based on multi-dimensional data fusion and dynamic threshold control, including the main body of the range hood 1 and a control system provided on the main body of the range hood 1. The control system includes an input module, a main control module, and an execution module. The signal input end and the signal output end of the main control module are respectively connected to the input module and the execution module. The input module includes a sound sensing module for collecting sound signals in the environment, a light signal sensing module for detecting changes in ambient light intensity, a motion sensing module for monitoring the human body and human movements, and a smoke sensing module for detecting the smoke concentration in the air. The main control module is responsible for data processing, logic control, and decision-making judgment, receives multi-source environmental data from the input module, and performs comprehensive analysis through a data fusion algorithm to generate control instructions. The execution module includes a lighting module and an exhaust module, and performs corresponding operations according to the instructions of the main control module, such as automatically starting the exhaust function when detecting smoke or abnormal movement, or turning on the lighting function when the light is insufficient.
[0025] The detection data of the above motion sensing module include the human presence state, the relative distance of the human body, and the human body posture. The detection data of the sound sensing module include the sound type and the sound decibel. The main control module presets a sound threshold, a distance threshold, a reference posture, and a reference sound. The control instruction includes a fan start instruction. The data fusion algorithm includes the following control logic: When any of the following conditions is met, the main control module generates a fan start instruction: Condition A, while meeting the following three sub-conditions: the human body posture matches the preset reference posture, the relative distance of the human body reaches or exceeds the preset distance threshold, and the sound type matches the preset reference sound; Condition B, while meeting the following two sub-conditions: the human body posture matches the preset reference posture, and the smoke concentration reaches or exceeds the preset smoke concentration threshold. This solution can more accurately identify the actual behavior of the user (such as whether cooking) by fusing multi-dimensional data such as human body posture, relative distance, and sound type, thereby reducing false triggers and improving the judgment accuracy. The main control module presets parameters such as a sound threshold, a distance threshold, a reference posture, and a reference sound, and makes a dynamic judgment in combination with the real-time detection data. Through dynamic threshold control, the system can adapt to different kitchen environments and usage scenarios. For example, in a noisy environment, the system can avoid accidentally starting the fan due to background noise through the dual judgment of the sound decibel and the sound type; when the light is insufficient, the system can automatically turn on the lighting according to the data of the light signal sensing module. This dynamic adaptability enables the device to better cope with complex and changeable environments.
[0026] The above sound threshold is set to threshold a, threshold b, and threshold c, and satisfies a < b < c; the control instruction includes a gear-up instruction, a gear-down instruction, and a shutdown instruction. The data fusion algorithm includes the following control logic: If the sound data rises from threshold a to threshold b, or from threshold b to threshold c, a gear-up instruction is generated; if the sound data drops from threshold c to threshold b, or from threshold b to threshold a, a gear-down instruction is generated; if the sound data is lower than threshold a, or the smoke concentration is lower than the preset smoke concentration threshold, a shutdown instruction is generated. By introducing multi-level sound thresholds and hierarchical control instructions, a more refined, dynamic, and intelligent control logic is achieved.
[0027] The above reference sound includes the stir-frying sound.
[0028] The above main control module is provided with a signal conditioning circuit and presets a reference frequency domain. It is connected to the sound sensing module through the signal conditioning circuit to extract the frequency domain of the sound signal and compare it with the reference frequency domain to determine whether the sound types are consistent. This solution improves the judgment accuracy and enhances the environmental adaptability by introducing the stir-frying sound recognition function and the frequency domain analysis technology.
[0029] The above-mentioned main control module is provided with a frequency-domain analysis program and a frequency-domain feature matching program. The frequency-domain analysis program converts the time-domain sound signal into frequency-domain features, and the frequency-domain feature matching program compares the detected sound frequency-domain features with the preset reference frequency domain of the stir-frying sound to determine whether they match.
[0030] The above-mentioned main control module is provided with a signal conditioning circuit, and a reference time-domain waveform is preset. It is connected to the sound induction module through the signal conditioning circuit to extract the time-domain waveform of the sound signal and compare it with the reference time-domain waveform to determine whether the sound types are the same.
[0031] The above-mentioned reference postures include cooking postures and smoking postures.
[0032] The above-mentioned control system includes a first automatic lighting mode and a second automatic lighting mode. The main control module presets a light threshold. The human presence state includes "yes" and "no". In the first automatic lighting mode, when the light data is lower than the light threshold and it is detected that the human presence state is "yes", the main control module generates a night light start instruction. When the light data reaches the light threshold or it is detected that the human presence state is "no", the main control module generates a night light off instruction; in the second automatic lighting mode, when the light data is lower than the light threshold, the main control module generates a night light start instruction. When the light data reaches the threshold, the main control module generates a night light off instruction.
[0033] The above-mentioned motion sensing module includes a millimeter-wave radar sensing module 2. There are at least two groups of the millimeter-wave radar sensing module 2. One group is arranged on the front end face of the range hood body 1, and the other group is arranged on the lower end face of the range hood body 1.
[0034] The above-mentioned sound induction module includes a sound sensor 3. The sound sensor 3 is any one of an electret microphone, an optical fiber microphone, a capacitive microphone, a moving coil microphone, and a piezoelectric microphone.
[0035] The above-mentioned smoke sensing module is a smoke sensor 5. The optical signal sensing module at least includes a photosensitive sensor 4.
[0036] The intelligent range hood of the present invention integrates various data inputs such as sound induction, optical signal induction, human body induction, and smoke induction. This multi-dimensional data fusion enables the main control module to more comprehensively understand the kitchen environment, thereby making more accurate judgments. By fusing various data inputs for intelligent judgment and control, not only the judgment accuracy and environmental adaptability are improved, but also the user experience, energy efficiency, and safety are enhanced.
[0037] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the various embodiments, reference can be made to each other. According to the disclosure and teachings of the above specification, those skilled in the art to which the present invention pertains can also make changes and modifications to the above-described embodiments. Therefore, the present invention is not limited to the specific embodiments disclosed and described above, and some modifications and changes to the present invention should also fall within the protection scope of the claims of the present invention. In addition, although some specific terms are used in this specification, these terms are only for convenience of description and do not constitute any limitation to the present invention.
Claims
1. An intelligent range hood based on multi-dimensional data fusion and dynamic threshold control, characterized in that: It includes a range hood body and a control system arranged on the range hood body, and the control system includes: An input module, including a sound sensing module for collecting sound signals in the environment, a light signal sensing module for detecting changes in ambient light intensity, a motion sensing module for monitoring the human body and human movements, and a smoke sensing module for detecting the smoke concentration in the air; A main control module, whose signal input end is connected to the input module, is responsible for data processing, logic control and decision-making judgment, receives multi-source environmental data from the input module, and performs comprehensive analysis through a data fusion algorithm to generate control instructions; An execution module, whose signal is connected to the output end of the main control module, includes a lighting module and an exhaust module, and performs corresponding operations according to the instructions of the main control module. For example, when detecting smoke or abnormal movement, it automatically starts the exhaust function, or turns on the lighting function when the light is insufficient.
2. The intelligent range hood according to claim 1, characterized in that: The detection data of the motion sensing module includes the human presence state, the relative distance of the human body and the human body posture, the detection data of the sound sensing module includes the sound type and the sound decibel, the main control module presets a sound threshold, a distance threshold, a reference posture and a reference sound, the control instruction includes a fan start instruction, and the data fusion algorithm includes the following control logic: When any of the following conditions is met, the main control module generates a fan start instruction: Condition A, while meeting the following three sub-conditions: The human body posture matches the preset reference posture, The relative distance of the human body reaches or exceeds the preset distance threshold, The sound type matches the preset reference sound; Condition B, while meeting the following two sub-conditions: The human body posture matches the preset reference posture, The smoke concentration reaches or exceeds the preset smoke concentration threshold.
3. The intelligent range hood according to claim 2, characterized in that: The sound threshold is set to threshold a, threshold b and threshold c, and a < b < c is satisfied; the control instructions include a gear-up instruction, a gear-down instruction and a shutdown instruction, and the data fusion algorithm includes the following control logic: If the sound data rises from threshold a to threshold b, or from threshold b to threshold c, a gear-up instruction is generated; If the sound data drops from threshold c to threshold b, or from threshold b to threshold a, a gear-down instruction is generated; If the sound data is lower than threshold a, or the smoke concentration is lower than the preset smoke concentration threshold, a shutdown instruction is generated.
4. The intelligent range hood according to claim 2, characterized in that: The reference sound includes the stir-frying sound.
5. The intelligent range hood according to claim 2, characterized in that: The main control module is provided with a signal conditioning circuit and presets a reference frequency domain, and is connected to the sound sensing module through the signal conditioning circuit to extract the frequency domain of the sound signal and compare it with the reference frequency domain to judge whether the sound types are the same.
6. The intelligent range hood according to claim 5, characterized in that: The main control module is provided with a frequency domain analysis program and a frequency domain feature matching program. The frequency domain analysis program converts the time-domain sound signal into frequency domain features, and the frequency domain feature matching program compares the detected sound frequency domain features with the preset stir-frying sound reference frequency domain to judge whether they match.
7. The intelligent range hood according to claim 2, characterized in that: The main control module is provided with a signal conditioning circuit and a preset reference time domain waveform. The main control module is connected to the sound sensing module through the signal conditioning circuit to extract the time domain waveform of the sound signal and compare it with the reference time domain waveform to determine whether the sound type is consistent.
8. The intelligent range hood according to claim 2, characterized in that: The reference postures include a cooking posture and a smoking posture.
9. The intelligent range hood according to claim 1, characterized in that: The control system includes a first automatic lighting mode and a second automatic lighting mode, the main control module is preset with a light threshold, and the human presence status includes two types: yes and no. In the first automatic lighting mode, when the light data is lower than the light threshold and the human presence status is detected as "yes", the main control module generates a night light start instruction, and when the light data reaches the light threshold or the human presence status is detected as "no", the main control module generates a night light shut-down instruction; In the second automatic lighting mode, when the light data is lower than the light threshold, the main control module generates a night light start instruction, and when the light data reaches the threshold, the main control module generates a night light turn off instruction.
10. The intelligent range hood according to claim 1, characterized in that: The motion sensing module includes at least two groups of millimeter wave radar sensing modules, which are respectively arranged on the front end surface and the lower end surface of the range hood body.