A control system and method for a bladeless air moving device based on multi-sensor data

Abstract

The present application relates to a kind of based on multi-sensor data's bladeless ventilation device control system and method, system includes bladeless fan body, air quality monitoring module, infrared pyroelectric sensor, infrared distance sensor, air purification module and controller.By fusing user presence state detection, infrared heat signal and distance data processing, user position distribution modeling based on Gaussian kernel density estimation and Markov chain user behavior prediction method, real-time perception user in the scene state and spatial position change.Controller according to environmental comfort index model and user position prediction result, self-adaptive adjustment wind speed mode and air purification intensity, realize with user active area as core dynamic directional air supply and accurate purification control.The present application improves indoor air management efficiency and user experience, give consideration to comfort, energy saving and health, applicable to family, office and various application scenarios.

Description

Technical Field

[0001] This invention belongs to the field of ventilation device technology, specifically relating to a control system and method for a bladeless ventilation device based on multi-sensor data. Background Technology

[0002] As people's demands for indoor air quality and personalized comfort continue to rise, traditional ventilation equipment such as fans and air conditioners are no longer sufficient to meet the needs of refined control and health-oriented usage scenarios. Especially in relatively enclosed spaces such as homes and offices, users not only want to obtain suitable airflow adjustment, but also want to achieve effective improvement in air quality at the same time.

[0003] While some existing bladeless ventilation devices achieve safe and low-noise air delivery in terms of structure, they generally suffer from problems such as limited control methods, unintelligent response, and limited purification effects. For example, some devices can only achieve simple wind speed adjustment based on a single sensor (such as a temperature sensor), failing to comprehensively consider user location, changes in air quality, and environmental comfort. This results in a disconnect between wind speed control and purification mode, affecting both user experience and energy efficiency.

[0004] Furthermore, in air purification, existing equipment often relies on fixed filtration modes, lacking the ability to intelligently identify and adjust responses to different pollution levels, which can easily lead to wasted filter media resources or insufficient purification capacity. At the same time, the lack of predictive mechanisms also limits the system's ability to proactively adapt to changes in user behavior and environmental conditions.

[0005] In the prior art, Chinese patent CN110030703A discloses an indoor air quality control system and method based on personnel positioning detection. The system includes a data acquisition system, a computer system, and an indoor environment control system. The data acquisition system includes a personnel counter, an infrared array sensor, and an air quality sensor module. The indoor environment control system includes an overall main ventilation and purification system and a local area ventilation and purification system. The overall main ventilation and purification system performs overall indoor ventilation and purification based on the total number of people in the room transmitted to the computer system. The local area ventilation and purification system determines whether to activate the local area ventilation and purification system based on the data transmitted to the computer system from the infrared array sensor and the air quality sensor module.

[0006] However, this solution still has the following shortcomings: First, its personnel detection methods mainly rely on total headcount and whether an area is occupied, lacking refined identification of individual user locations, relative activity states, and spatial behavior trends. This results in coarse-grained system control, making it difficult to achieve personalized air supply or purification responses. Second, the control method is a passive response based on current detection results, without incorporating intelligent predictive models. It cannot proactively adjust based on user behavior patterns or air pollution trends, impacting comfort and system efficiency. Furthermore, this solution is primarily applied to large indoor ventilation systems, resulting in complex structures and low integration, making it difficult to adapt to smaller ventilation equipment such as bladeless fans.

[0007] Therefore, there is an urgent need to provide a new type of ventilation device that combines multi-source sensing, intelligent prediction and adaptive control, which can achieve deep integration of wind speed adjustment and purification functions based on the user's actual presence, air quality level and behavioral trends, thereby improving air purification efficiency, energy saving and user experience. Summary of the Invention

[0008] The purpose of this invention is to overcome the shortcomings of the prior art by providing a control system and method for a bladeless ventilation device based on multi-sensor data.

[0009] The objective of this invention can be achieved through the following technical solutions:

[0010] This invention provides a control system for a bladeless ventilation device based on multi-sensor data, comprising:

[0011] The main control module, based on a high-performance microcontroller (MCU), is used to receive data from various sensors, perform data preprocessing, fusion analysis and control strategy calculations, and output ventilation control signals.

[0012] The sensor module includes: a human body sensing submodule for detecting the user's presence and relative position, the human body sensing submodule including a pyroelectric infrared sensor and an infrared distance sensor; an environmental sensing submodule for real-time acquisition of ambient temperature, humidity, and duct pressure information, the environmental sensing submodule including a temperature and humidity sensor and a pressure sensor; and an air quality monitoring submodule for monitoring the concentration of particulate matter and volatile organic compounds in the air, the air quality monitoring submodule including a PM2.5 sensor and a VOC sensor.

[0013] The control execution module is used to control the bladeless ventilation device according to the ventilation control signal output by the main control module;

[0014] The air purification module includes a coarse filter layer, a medium filter layer, and a high-efficiency filter layer, which are used to automatically switch purification modes according to the air quality level under the control of the control and execution module.

[0015] Furthermore, the control execution module includes: a PWM drive submodule, used to adjust the speed of the brushless motor of the bladeless ventilation device according to the wind speed control signal output by the main control module, so as to realize stepless adjustment of the wind speed; a purification control submodule, used to control the working status and filtration level of the air purification module; and a communication submodule, used to realize system status uploading and remote control command reception via Bluetooth or WiFi.

[0016] Furthermore, the main control module is equipped with a multi-sensor data fusion algorithm. Based on the user status, environmental parameters, and air quality information collected by the sensor modules, it constructs a user presence status model, an environmental comfort index model, and an air pollution level model. Based on a fuzzy logic controller and a predictive adjustment algorithm, it outputs control commands such as wind speed and purification intensity to achieve intelligent adjustment and energy consumption optimization of the ventilation device.

[0017] Another aspect of the present invention provides a bladeless ventilation device control method based on multi-sensor data control system as described above, comprising the following steps:

[0018] The sensor module collects human body sensing data, environmental parameter data, and air quality data respectively.

[0019] The main control module preprocesses the data collected by the sensor module;

[0020] The main control module performs fusion calculations on the preprocessed data to construct a user presence status model, an environmental comfort index model, and an air pollution level model.

[0021] Based on the constructed user presence state model, environmental comfort index model, and air pollution level model, the main control module, combined with a fuzzy logic controller, performs decision calculations on wind speed and purification intensity control variables to generate control commands.

[0022] The control execution module drives the PWM drive module to adjust the speed of the brushless motor according to the control instructions output by the main control module, and links the air purification module to perform the corresponding filtration level switching operation.

[0023] The communication submodule uploads environmental status parameters and equipment operating status to the mobile terminal and receives remote control commands from users to enable system status monitoring and intervention.

[0024] Furthermore, the human body sensing data includes infrared thermal signal data acquired by a pyroelectric infrared sensor and distance data between the user and the ventilation device acquired by an infrared distance sensor.

[0025] The environmental parameter data includes ambient temperature and humidity data obtained by temperature and humidity sensors, and duct pressure data obtained by pressure sensors.

[0026] The air quality data includes the concentration data of inhalable particulate matter in the air obtained by the PM2.5 sensor, and the concentration data of volatile organic compounds in the air obtained by the VOC sensor.

[0027] Furthermore, the main control module preprocesses the data collected by the sensor module, specifically including:

[0028] Denoising is performed on various raw sensor data, and Kalman filtering or moving average algorithms are used to eliminate short-term interference signals and abnormal fluctuations.

[0029] Add timestamp information to the denoised data and write it to the sensor fusion buffer according to data category for subsequent fusion operation calls.

[0030] Furthermore, the process of constructing the user presence state model is as follows:

[0031] At multiple sampling times, infrared thermal signal intensity data P of the area surrounding the user is acquired using a pyroelectric infrared sensor. i And acquire distance data between the user and the device through an infrared distance sensor. i , where i is the sampling sequence number;

[0032] For infrared thermal signal intensity data sequence {P i A sliding window averaging filter is performed to eliminate short-term jitter interference, resulting in a smooth thermal signal sequence. The formula is:

[0033]

[0034] Where w is the width of the sliding window, P j Represents the intensity of the infrared thermal signal at time j. The intensity of the infrared thermal signal at time i after smoothing;

[0035] The processed smooth thermal signal sequence With the set threshold P th Compare, when satisfied At that time, it is determined that the user exists within the detection range of the device at the current sampling moment;

[0036] Based on the time series of user presence Combined with its corresponding distance data D tk The Gaussian kernel density estimation method is used to fit the user occurrence probability distribution f(D) as a user relative location probability model to estimate the user's main activity range in space [D]. min D max ],in, D represents the time sequence of a user's existence.tk Let f(D) represent the distance between the user and the ventilation device at time tk, and let f(D) be the probability distribution function of the user's location fitted by the Gaussian kernel density estimation method. min D max Let f(D) be the minimum and maximum distances between user activity ranges determined by probability distribution f(D).

[0037] Assuming the user persists, a first-order Markov chain is used to analyze the user position change sequence {D}. tk Establish the transition probability matrix:

[0038] P ij =Pr(D t+1 =d j |D t =d i )

[0039] Among them, P ij This indicates that the user distance is d at time t. i When the distance to the user arriving at time t+1 is d j The transition probability, D t D t+1 Let Pr(·) represent the distances between the user and the ventilation device at time t and time t+1, respectively, and let Pr(·) represent the probability operator.

[0040] Based on the transition probability matrix P of the Markov chain, predict the user's possible position state at the next moment.

[0041] Furthermore, the environmental comfort index model is as follows:

[0042]

[0043] C env (t)=w1·f temp (T env (t))+w2·f lumid (H env (t))+w3·f pressure (P env (t))

[0044] Among them, I comfort (t) represents the environmental comfort index at time t, C env (t) is the environmental comfort factor at time t, C envmin C envmax The minimum and maximum values ​​of the preset environmental comfort factor are defined by w1, w2, and w3, which are weighting coefficients that are adaptively adjusted based on user behavior data and environmental changes. env (t), H env (t), P env(t) represents the ambient temperature, ambient humidity, and duct pressure at time t, respectively; f temp (T env (t)), f lumid (H env (t)), f pressure (P env (t) represents the influence functions of ambient temperature, ambient humidity, and duct pressure on the comfort factor, respectively, and the formula is:

[0045]

[0046] Where, k temp Let α be the sensitivity constant for temperature changes. temp T is an adjustment factor for the impact of temperature changes on comfort. opt The most comfortable temperature for the human body, ΔT env (t)=T env (t)-T env (t-1) is the instantaneous rate of change of temperature; β humid γ represents the sensitivity of humidity to the comfort factor. humid H is an influencing factor of the cumulative effect of humidity. min The minimum comfortable threshold for humidity. This represents the time-cumulative effect of humidity, i.e., the integral of humidity from time 0 to time t, reflecting the long-term influence of humidity; P opt The pressure that the human body is most comfortable with, δ pressure γ are regulating factors.

[0047] Furthermore, the air pollution level model is as follows:

[0048] A pollution (t)=w4·f PM2.5 (C PM2.5 (t))+w5·f VOC (C VOC (t))

[0049]

[0050] Among them, A pollution (t) represents the air pollution level index at time t, C PM2.5 (t), C VOC (t) represents the concentrations of inhalable particulate matter and volatile organic compounds at time t, w4 and w5 are weighting coefficients, and f PM2.5 (C PM2.5 (t)), f VOC (C VOC (t) represents the influence functions of inhalable particulate matter concentration and volatile organic compound concentration on the air pollution level index, respectively, k PM2.5C is the adjustment parameter for the sensitivity of PM2.5 concentration changes to the pollution index. PM2.5,opt For the optimal reference concentration of PM2.5, β VOC C is the scaling factor for the effect of VOC concentration on the pollution index. VOC,min This is the minimum safe threshold for VOCs.

[0051] Furthermore, the main control module, based on the constructed user presence state model, environmental comfort index model, and air pollution level model, and in conjunction with a fuzzy logic controller, performs decision calculations on the wind speed and purification intensity control variables to generate control commands, specifically including:

[0052] Acquire sensor data at the current moment, and calculate the current environmental comfort index I based on the sensor data at the current moment and the constructed user presence state model, environmental comfort index model, and air pollution level model. comfort (t) and air pollution level index A Pollution (t), and based on the Markov chain transition matrix P constructed in the user presence state model, predict the user's position state S at the next time step. t+1 ;

[0053] The environmental comfort index I comfort (t), Air Pollution Level Index A pollution (t) and the predicted user's position state S at the next time step. t+1 As input variables, they are fed into the fuzzy logic controller for fuzzy inference. The fuzzy rules include:

[0054]

[0055] Wherein, Filter Mode(t) is the purification mode of the air purification module at time t, High-efficiency means that the air purification module is controlled to use a high-efficiency filter layer, Medium-efficiency means that the air purification module is controlled to use a medium-efficiency filter layer, Low-efficiency means that the air purification module is controlled to use a coarse filter layer, A1 and A2 are the first preset value and the second preset value, respectively, and A1>A2.

[0056]

[0057] Where WindSpeed(t) is the speed mode of the brushless motor of the bladeless ventilation device at time t, High, Medium, Low and Close represent high speed, medium speed, low speed and closed respectively, I1 is the preset environmental comfort value and D is the preset distance threshold.

[0058] Compared with the prior art, the present invention has the following advantages:

[0059] (1) This invention features an air quality monitoring module and a human body sensor module connected to the fan body. The controller adjusts the fan speed based on the human body's position and air quality parameters. This design allows the fan to operate in a closed loop of intelligent control, rather than in a fixed manner. It achieves dynamic optimization of wind speed and purification intensity to align with the human breathing and activity zones, enhancing user comfort, improving purification efficiency, and avoiding resource waste.

[0060] (2) This invention integrates an air quality monitoring module and a purification module, and automatically adjusts the purification intensity based on air quality data. The controller determines the activation and intensity adjustment of the purification mode based on real-time air quality monitoring data, thereby ensuring that the air purification effect meets the current environmental requirements, avoiding resource waste under a fixed purification mode, and improving the intelligence and efficiency of air quality control.

[0061] (3) This invention uses a human body sensing module to accurately detect the presence and location of the user, and dynamically adjusts the wind speed in combination with environmental parameters. The adjustment of wind speed is based not only on environmental data such as temperature and humidity, but also on the user's real-time activity status and location, so that the device can adapt to the user's needs in a more personalized way, provide a more comfortable indoor air environment, and avoid the unsuitability of traditional fans in fixed wind speed mode.

[0062] (4) This invention uses a multi-sensor data fusion algorithm to simultaneously collect and analyze information such as user distance, ambient temperature and humidity, and air quality, and comprehensively judges the environmental comfort level and air pollution level based on this information. Based on a fuzzy logic controller and a predictive adjustment algorithm, the control system can intelligently adjust the wind speed and purification intensity to ensure that the equipment always maintains the optimal working state, improve the intelligence level and automatic adaptability of the equipment, and enhance the user experience.

[0063] (5) This invention eliminates short-term jitter interference by performing sliding window averaging filtering on the infrared thermal signal intensity data sequence, thereby improving the stability and accuracy of the infrared thermal signal. This processing technology effectively improves the reliability of the signal, avoids misjudgment caused by environmental changes or signal fluctuations, and thus enhances the device's accuracy in recognizing the user's presence, avoiding misjudgment and missed judgment.

[0064] (6) This invention employs a Gaussian kernel density estimation method, combining the user's infrared thermal signal data and distance data to fit a relative position probability model of the user. This technique can estimate the user's main activity range in space, thereby helping the device predict the user's activity range and behavior patterns. In this way, the device can not only identify the user's location but also understand its possible activity area, providing more accurate information for subsequent adjustment and control. A transition probability matrix is ​​established using a first-order Markov chain for the user's position change sequence, thereby predicting the user's possible position at the next moment. This Markov chain-based prediction mechanism enables the device to understand the user's dynamic position changes in real time and make response adjustments in advance based on the prediction results, further improving the device's intelligence and adaptability. Attached Figure Description

[0065] Figure 1 This is a diagram of the overall system architecture of the present invention;

[0066] Figure 2 This is a schematic diagram of the bladeless ventilation device of the present invention;

[0067] Figure 3 This is a flowchart of the control method of the present invention. Detailed Implementation

[0068] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. 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.

[0069] Example 1:

[0070] This embodiment provides a control system for a bladeless ventilation device based on multi-sensor data, such as... Figure 1 As shown, it includes:

[0071] The main control module, based on a high-performance microcontroller (MCU), is used to receive data from various sensors, perform data preprocessing, fusion analysis and control strategy calculations, and output ventilation control signals.

[0072] The sensor module includes: a human body sensing submodule, used to detect the user's presence and relative position, which includes a pyroelectric infrared sensor and an infrared distance sensor; an environmental sensing submodule, used to collect real-time information on ambient temperature, humidity, and duct pressure, which includes a temperature and humidity sensor and a pressure sensor; and an air quality monitoring submodule, used to monitor the concentration of particulate matter and volatile organic compounds in the air, which includes a PM2.5 sensor and a VOC sensor.

[0073] The control execution module is used to control the bladeless ventilation device according to the ventilation control signal output by the main control module; wherein, the bladeless ventilation device is as follows: Figure 2 As shown.

[0074] The air purification module includes a coarse filter layer, a medium filter layer, and a high-efficiency filter layer, which are used to automatically switch purification modes according to the air quality level under the control of the control and execution module.

[0075] The control execution module includes: a PWM drive submodule, used to adjust the speed of the brushless motor of the bladeless ventilation device according to the wind speed control signal output by the main control module, so as to realize stepless adjustment of the wind speed; a purification control submodule, used to control the working status and filtration level of the air purification module; and a communication submodule, used to realize system status uploading and remote control command reception via Bluetooth or WiFi.

[0076] The main control module is equipped with a multi-sensor data fusion algorithm. Based on the user status, environmental parameters and air quality information collected by the sensor modules, it constructs a user presence status model, an environmental comfort index model and an air pollution level model. Based on a fuzzy logic controller and a predictive adjustment algorithm, it outputs control commands such as wind speed and purification intensity to achieve intelligent adjustment and energy consumption optimization of the ventilation device.

[0077] Example 2:

[0078] This embodiment provides a bladeless ventilation device control method based on multi-sensor data in the bladeless ventilation device control system described above. Figure 3 As shown, it includes the following steps:

[0079] Step S1: The sensor module collects human body sensing data, environmental parameter data, and air quality data respectively;

[0080] Step S2: The main control module preprocesses the data collected by the sensor module;

[0081] Step S3: The main control module performs fusion calculations on the preprocessed data to construct a user presence status model, an environmental comfort index model, and an air pollution level model;

[0082] Step S4: Based on the constructed user presence state model, environmental comfort index model, and air pollution level model, the main control module, combined with the fuzzy logic controller, performs decision calculations on the wind speed and purification intensity control variables to generate control commands.

[0083] Step S5: The control execution module drives the PWM drive module to adjust the speed of the brushless motor according to the control instructions output by the main control module, and links the air purification module to perform the corresponding filtration level switching operation.

[0084] Step S6: The communication submodule uploads environmental status parameters and device operating status to the mobile terminal and receives remote control commands from the user to realize system status monitoring and intervention operations.

[0085] Human body sensing data includes infrared thermal signal data acquired by pyroelectric infrared sensors and distance data between the user and the ventilation device acquired by infrared distance sensors;

[0086] Environmental parameter data includes ambient temperature and humidity data obtained from temperature and humidity sensors, as well as duct pressure data obtained from pressure sensors.

[0087] Air quality data includes concentrations of inhalable particulate matter in the air obtained from PM2.5 sensors, and concentrations of volatile organic compounds in the air obtained from VOC sensors.

[0088] The main control module preprocesses the data collected by the sensor module, specifically including:

[0089] Denoising is performed on various raw sensor data, and Kalman filtering or moving average algorithms are used to eliminate short-term interference signals and abnormal fluctuations.

[0090] Add timestamp information to the denoised data and write it to the sensor fusion buffer according to data category for subsequent fusion operation calls.

[0091] The process of constructing the user presence state model is as follows:

[0092] At multiple sampling times, infrared thermal signal intensity data P of the area surrounding the user is acquired using a pyroelectric infrared sensor. i And acquire distance data between the user and the device through an infrared distance sensor. i , where i is the sampling sequence number;

[0093] For infrared thermal signal intensity data sequence {P i A sliding window averaging filter is performed to eliminate short-term jitter interference, resulting in a smooth thermal signal sequence. The formula is:

[0094]

[0095] Where w is the width of the sliding window, P j Represents the intensity of the infrared thermal signal at time j. The intensity of the infrared thermal signal at time i after smoothing;

[0096] The processed smooth thermal signal sequence With the set threshold P th Compare, when satisfied At that time, it is determined that the user exists within the detection range of the device at the current sampling moment;

[0097] Based on the time series of user presence Combined with its corresponding distance data D tk The Gaussian kernel density estimation method is used to fit the user occurrence probability distribution f(D) as a user relative location probability model to estimate the user's main activity range in space [D]. min D max ],in, D represents the time sequence of a user's existence. tk Let f(D) represent the distance between the user and the ventilation device at time tk, and let f(D) be the probability distribution function of the user's location fitted by the Gaussian kernel density estimation method. min D max Let f(D) be the minimum and maximum distances between user activity ranges determined by probability distribution f(D).

[0098] Assuming the user persists, a first-order Markov chain is used to analyze the user position change sequence {D}. tk Establish the transition probability matrix:

[0099] P ij =Pr(D t+1 =d j |D t =d i )

[0100] Among them, P ij This indicates that the user distance is d at time t. i When the distance to the user arriving at time t+1 is d j The transition probability, D t D t+1 Let Pr(·) represent the distances between the user and the ventilation device at time t and time t+1, respectively, and let Pr(·) represent the probability operator.

[0101] Based on the transition probability matrix P of the Markov chain, predict the user's possible position state at the next moment.

[0102] The environmental comfort index model is as follows:

[0103]

[0104] C env (t)=w1·f temp (T env (t))+w2·f lumid (H env (t))+w3·f pressure (P env (t))

[0105] Among them, I comfort (t) represents the environmental comfort index at time t, C env (t) is the environmental comfort factor at time t, C envmin C envmax The minimum and maximum values ​​of the preset environmental comfort factor are defined by w1, w2, and w3, which are weighting coefficients that are adaptively adjusted based on user behavior data and environmental changes. env (t), H env (t), P env (t) represents the ambient temperature, ambient humidity, and duct pressure at time t, respectively; f temp (T env (t)), f lumid (H env (t)), f pressure (P env (t) represents the influence functions of ambient temperature, ambient humidity, and duct pressure on the comfort factor, respectively, and the formula is:

[0106]

[0107] Where, k temp Let α be the sensitivity constant for temperature changes. temp T is an adjustment factor for the impact of temperature changes on comfort. opt The most comfortable temperature for the human body, ΔT env (t)=T env (t)-T env (t-1) is the instantaneous rate of change of temperature; β humid γ represents the sensitivity of humidity to the comfort factor. humid H is an influencing factor of the cumulative effect of humidity. min The minimum comfortable threshold for humidity. This represents the time-cumulative effect of humidity, i.e., the integral of humidity from time 0 to time t, reflecting the long-term influence of humidity; P opt The pressure that the human body is most comfortable with, δ pressure γ are regulating factors.

[0108] Among them, w1, w2, and w3 are weighting coefficients that are adaptively adjusted based on user behavior data and environmental changes, specifically including:

[0109] Through a human body sensing module and a user operation recording module, the system collects user interactions such as switching devices on and off, adjusting wind speed, and moving positions in real time, forming a behavior label dataset. After each user operation or automatic system adjustment, the system records the environmental conditions such as temperature, humidity, and pollution index. Based on the time-series correlation between user behavior and environmental conditions, a loss function is defined to account for the deviation between the predicted environmental comfort value and the user's actual operating preferences. Using optimization algorithms such as stochastic gradient descent (SGD), the weights w1, w2, and w3 are iteratively updated to make the comfort value output by the model as consistent as possible with the user's actual behavioral preferences. Whenever the system accumulates a certain number of user behavior samples or the environmental changes significantly, a weight retraining mechanism is triggered to further improve prediction accuracy.

[0110] The air pollution level model is as follows:

[0111] A pollution (t)=w4·f PM2.5 (C PM2.5 (t))+w5·f VOC (C VOC (t))

[0112]

[0113] Among them, A pollution (t) represents the air pollution level index at time t, C PM2.5 (t), C VOC (t) represents the concentrations of inhalable particulate matter and volatile organic compounds at time t, w4 and w5 are weighting coefficients, and f PM2.5 (C PM2.5 (t)), f VOC (C VOC (t) represents the influence functions of inhalable particulate matter concentration and volatile organic compound concentration on the air pollution level index, respectively, k PM2.5 C is the adjustment parameter for the sensitivity of PM2.5 concentration changes to the pollution index. PM2.5,opt For the optimal reference concentration of PM2.5, β VOC C is the scaling factor for the effect of VOC concentration on the pollution index. VOC,mim This is the minimum safe threshold for VOCs.

[0114] Based on the constructed user presence state model, environmental comfort index model, and air pollution level model, the main control module, combined with a fuzzy logic controller, performs decision calculations on the control variables of wind speed and purification intensity, and generates control commands, specifically including:

[0115] Acquire sensor data at the current moment, and calculate the current environmental comfort index I based on the sensor data at the current moment and the constructed user presence state model, environmental comfort index model, and air pollution level model.comfort (t) and air pollution level index A pollution (t), and based on the Markov chain transition matrix P constructed in the user presence state model, predict the user's position state S at the next time step. t+1 ;

[0116] The environmental comfort index I comfort (t), Air Pollution Level Index A pollution (t) and the predicted user's position state S at the next time step. t+1 As input variables, they are fed into the fuzzy logic controller for fuzzy inference. The fuzzy rules include:

[0117]

[0118] Wherein, Filter Mode(t) is the purification mode of the air purification module at time t, High-efficiency means that the air purification module is controlled to use a high-efficiency filter layer, Medium-efficiency means that the air purification module is controlled to use a medium-efficiency filter layer, Low-efficiency means that the air purification module is controlled to use a coarse filter layer, A1 and A2 are the first preset value and the second preset value, respectively, and A1>A2.

[0119] That is, if the air pollution level index A pollution If (t) is greater than the first preset value, then the air purification module will use a high-efficiency filter layer; if the air pollution level index A pollution If (t) is less than or equal to the first preset value and greater than the second preset value, then the air purification module will use a medium-efficiency filter layer. If the air pollution level index A pollution If (t) is less than or equal to the second preset value, then the air purification module is controlled to use a coarse filter layer;

[0120]

[0121] Where WindSpeed(t) is the speed mode of the brushless motor of the bladeless ventilation device at time t, High, Medium, Low and Close represent high speed, medium speed, low speed and closed respectively, I1 is the preset environmental comfort value and D is the preset distance threshold.

[0122] That is, if the environmental comfort index is less than or equal to the first preset value and the predicted user location is less than the preset distance threshold, the bladeless ventilation device is controlled to operate in high-speed mode to provide a strong airflow to meet the heat dissipation needs of the user when using it at close range; if the environmental comfort index is less than or equal to the first preset value and the predicted user location is greater than or equal to the preset distance threshold, the control device operates in medium-speed mode to maintain a moderate airflow to balance comfort and energy consumption; if the environmental comfort index is greater than the first preset value and the predicted user location is less than the preset distance threshold, the control device operates in low-speed mode to avoid causing discomfort to the user at close range under high comfort levels; if the environmental comfort index is greater than the first preset value and the predicted user location is greater than or equal to the preset distance threshold, the ventilation device is turned off to save energy and prevent excessive interference with the user.

[0123] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0124] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A control method for a bladeless ventilation device based on a multi-sensor data control system, characterized in that, The system includes: The main control module, based on a high-performance microcontroller (MCU), is used to receive data from various sensors, perform data preprocessing, fusion analysis and control strategy calculations, and output ventilation control signals. The sensor module includes: a human body sensing submodule for detecting the user's presence and relative position, the human body sensing submodule including a pyroelectric infrared sensor and an infrared distance sensor; an environmental sensing submodule for real-time acquisition of ambient temperature, humidity, and duct pressure information, the environmental sensing submodule including a temperature and humidity sensor and a pressure sensor; and an air quality monitoring submodule for monitoring the concentration of particulate matter and volatile organic compounds in the air, the air quality monitoring submodule including a PM2.5 sensor and a VOC sensor. The control execution module is used to control the bladeless ventilation device according to the ventilation control signal output by the main control module; The air purification module includes a coarse filter layer, a medium filter layer, and a high-efficiency filter layer, which are used to automatically switch the purification mode according to the air quality level under the control of the control and execution module. The method includes the following steps: The sensor module collects human body sensing data, environmental parameter data, and air quality data respectively. The main control module preprocesses the data collected by the sensor module; The main control module performs fusion calculations on the preprocessed data to construct a user presence status model, an environmental comfort index model, and an air pollution level model. Based on the constructed user presence state model, environmental comfort index model, and air pollution level model, the main control module, combined with a fuzzy logic controller, performs decision calculations on wind speed and purification intensity control variables to generate control commands. The control execution module drives the PWM drive module to adjust the speed of the brushless motor according to the control instructions output by the main control module, and links the air purification module to perform the corresponding filtration level switching operation. The communication submodule uploads environmental status parameters and equipment operating status to the mobile terminal and receives remote control commands from users to enable system status monitoring and intervention. The environmental comfort index model is as follows: in, For a moment t The environmental comfort index, For a moment t Environmental comfort factor, These are the preset minimum and maximum values ​​of the environmental comfort factor; , These are weighting coefficients that are adaptively adjusted based on user behavior data and environmental changes. , , They are time points t Ambient temperature, ambient humidity, and duct pressure; , , These are the influence functions of ambient temperature, ambient humidity, and duct pressure on the comfort factor, respectively, and the formula is: in, Let be the sensitivity constant for temperature changes. This is an adjustment factor for the impact of temperature changes on comfort. The most comfortable temperature for the human body The instantaneous rate of change of temperature; Sensitivity to the effect of humidity on comfort factors. The influencing factor of the cumulative effect of humidity. The minimum comfortable threshold for humidity. This refers to the cumulative effect of humidity over time, i.e., from time 0 to time 1. t Humidity integral reflects the long-term effects of humidity; This is the pressure that the human body is most comfortable with. , As a regulating factor; The process of constructing the user presence state model is as follows: At multiple sampling times, infrared thermal signal intensity data of the area surrounding the user are acquired using a pyroelectric infrared sensor. P i And to acquire distance data between the user and the device through an infrared distance sensor. D i ,in i The sampling sequence number; For infrared thermal signal intensity data sequences { P i A sliding window averaging filter is performed to eliminate short-term jitter interference, resulting in a smooth thermal signal sequence. The formula is: in, For the width of the sliding window, Indicates the first j Infrared thermal signal intensity at time [time] For the smoothed first i The intensity of the infrared thermal signal at any given moment; The processed smooth thermal signal sequence { } and set threshold P th Compare, when satisfied > P th At that time, it is determined that the user exists within the detection range of the device at the current sampling moment; Based on the time series of user presence Combined with its corresponding distance data D tk The Gaussian kernel density estimation method is used to fit the user occurrence probability distribution. f(D) As a user relative location probability model, it estimates the user's main activity range in space. D min , D max ],in, This represents a sequence of time points in time when a user exists. D tk Indicates at time tk Distance between the user and the ventilation system f(D) The user location probability distribution function is fitted by the Gaussian kernel density estimation method. D min , D max To pass through the probability distribution f(D) The minimum and maximum distances within a defined user activity range; Assuming the user persists, a first-order Markov chain is used to analyze the user location change sequence. D tk Establish the transition probability matrix: in, Indicates at time t User distance is At that time, arrival time The user's distance is The transition probability, Representing time respectively t and time Distance between the user and the ventilation system Represents probability operators; Based on the transition probability matrix of Markov chains, predict the user's possible position state at the next moment; The main control module, based on the constructed user presence state model, environmental comfort index model, and air pollution level model, and combined with a fuzzy logic controller, performs decision calculations on the wind speed and purification intensity control variables to generate control commands, specifically including: Acquire sensor data at the current moment, and calculate the current environmental comfort index based on the sensor data at the current moment and the constructed user presence state model, environmental comfort index model, and air pollution level model. Air pollution level index Based on the Markov chain transition matrix P constructed in the user presence state model, the system predicts the user's position state at the next time step. S t+1 ; The environmental comfort index Air pollution level index And the predicted location and state of the user in the next moment. S t+1 As input variables, they are fed into the fuzzy logic controller for fuzzy inference. The fuzzy rules include: in, Let t be the purification mode of the air purification module. This indicates that the air purification module uses a high-efficiency filter layer. This indicates that the air purification module uses a medium-efficiency filter layer. This indicates that the air purification module uses a coarse filter layer. , These are the first preset value and the second preset value, respectively. ; in, The speed mode of the brushless motor of the bladeless ventilation device at time t. , , , These represent high speed, medium speed, low speed, and off, respectively. To preset the environmental comfort value, This is a preset distance threshold.

2. The bladeless ventilation device control method of the bladeless ventilation device control system based on multi-sensor data according to claim 1, characterized in that, The main control module preprocesses the data collected by the sensor module, specifically including: Denoising is performed on various raw sensor data, and Kalman filtering or moving average algorithms are used to eliminate short-term interference signals and abnormal fluctuations. Add timestamp information to the denoised data and write it to the sensor fusion buffer according to data category for subsequent fusion operation calls.

3. The bladeless ventilation device control method of the bladeless ventilation device control system based on multi-sensor data according to claim 1, characterized in that, The air pollution level model is as follows: in, Let be the air pollution level index at time t. , Let be the concentrations of inhalable particulate matter and volatile organic compounds at time t. , These are the weighting coefficients. , These are the effects of inhalable particulate matter concentration and volatile organic compound concentration on the air pollution level index, respectively. This is a parameter used to adjust the sensitivity of PM2.5 concentration changes to the pollution index. This is the optimal reference concentration for PM2.

5. This is the scaling factor for the effect of VOC concentration on the pollution index. This is the minimum safe threshold for VOCs.

Images