Intelligent control method for purifier filter screen

Abstract

The invention relates to the field of intelligent control, in particular to an intelligent control method for a purifier filter screen, and the method comprises the steps: collecting and preprocessing the monitoring data of the filter screen, and building a quick response mechanism for sudden pollution; and on the basis of the quick response mechanism, an optimization mechanism of a feed-forward gain coefficient aiming at filter screen blockage is further established, and finally, the filter screen is intelligently controlled through the optimized control model, so that continuous, dynamic and intelligent control on the air purifier is realized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and particularly to an intelligent control method for a purifier filter screen. Background Art

[0002] With the improvement of people's requirements for indoor air quality, air purifiers have become common household appliances in modern families. Air purifiers filter pollutants in the air, such as particulate matter (PM2.5, PM10), formaldehyde, volatile organic compounds (VOC), etc., through filters, thereby improving indoor air quality. The filter screen is the core component of an air purifier, and its performance directly affects the purification effect. Currently, most common air purifiers on the market adopt a control system based on the PID control algorithm. The PID controller calculates the deviation between the measured value of an indoor air quality sensor (such as a PM2.5 sensor) and the set value, and outputs a control signal through the operations of three links: proportional (P), integral (I), and derivative (D), to adjust the fan speed of the air purifier, thereby controlling the purification rate. Due to its advantages such as simple structure and easy parameter adjustment, the PID control algorithm has been widely used in the field of industrial control. In the traditional PID air purifier control system, its PID parameters (proportional coefficient , integral coefficient , derivative coefficient ) are usually fixed, or only simply adjusted according to a single index (such as PM2.5 concentration). This control method cannot fully adapt to the complex and changeable indoor environment and the changes in the filter screen state, resulting in the control performance of the air purifier being difficult to reach the optimal level. Specifically, there is a core problem in the existing PID air purifier control system: the parameters are fixed or the adjustment is not flexible, resulting in its inability to simultaneously take into account the rapid response to sudden pollution and the effective compensation for filter screen clogging, thereby affecting the purification efficiency of the air purifier and the user experience.

[0003] Specifically, when the indoor pollutant concentration suddenly increases (for example, due to activities such as opening windows, smoking, cooking, etc.), the PID controller with fixed parameters mainly relies on the error signal (i.e., the difference between the target concentration and the actual concentration) to adjust the fan speed. Since the PID controller lacks the ability to "predict" the change trend of the pollutant concentration, its response is often lagged, resulting in the indoor air quality not being effectively improved for a period of time. Simply increasing the proportional coefficient can indeed speed up the response speed, but it is prone to cause system overshoot (i.e., excessive wind speed adjustment) and oscillation, affecting the user experience.

[0004] On the other hand, as the air purifier filter is continuously used, pollutant particles will gradually accumulate on the filter, resulting in filter clogging and increased wind resistance. Filter clogging will change the dynamic characteristics of the air purifier system, making the original PID parameters no longer applicable. If the PID controller cannot adjust the integral coefficient in a timely and accurate manner to adapt to this change, it will lead to a decline in control performance and a reduction in purification efficiency. However, traditional PID controllers usually do not consider the filter state or only make simple parameter adjustments based on the cumulative usage time of the filter, unable to accurately reflect the actual clogging situation of the filter, resulting in poor control effects.

[0005] In summary, the problem with the existing PID air purifier control system is that its parameters are fixed or the adjustment mechanism is imperfect, unable to simultaneously achieve a rapid response to sudden pollution and an effective compensation for filter clogging, resulting in the air purifier being difficult to achieve the best purification effect in actual use. Summary of the Invention

[0006] In view of this, the present invention aims to propose an intelligent control method for purifier filters to solve the above problems.

[0007] To achieve the above object, the technical solution of the present invention is realized as follows:

[0008] An intelligent control method for purifier filters includes the following steps:

[0009] Step S1: Data collection and preprocessing;

[0010] Step S2: Establish a rapid response mechanism for sudden pollution;

[0011] Step S3: Establish a feedforward gain coefficient optimization mechanism for filter clogging;

[0012] Step S4: Perform intelligent control of the purifier filter through the optimized control model.

[0013] Furthermore, in the said step S2, to establish a rapid response mechanism for sudden pollution, the specific steps include:

[0014] In the stage where the pollutant concentration starts to rise rapidly, send a signal to the PID controller and add a feedforward compensation term to the output of the PID controller;

[0015] Among them, use the first optimization factor as the gain of the feedforward compensation term, and the calculation formula of the first optimization factor is:

[0016] ;

[0017] Among them, represents Optimization factor at a moment; Represents the basic feedforward gain coefficient; Represents At the moment of Acceleration of the concentration change rate, and its calculation formula is: ; Represents At the moment of Concentration change rate, and its calculation formula is: ; Represents At the moment of Concentration measurement value; Represents Control error at the moment of The value of is the error between the set value and the actual measurement value; Represents At the moment of Standard deviation of the acceleration of the concentration change rate, which is evaluated through a sliding window; Represents Standard deviation of the control error at the moment of, which is evaluated through a sliding window; Represents At the moment of Standard deviation of, which is evaluated through a sliding window.

[0018] Furthermore, step S3 establishes a feedforward gain coefficient optimization mechanism for filter clogging, and the specific steps include:

[0019] Taking the pressure difference change rate of the monitored filter as an index of the filter clogging degree and its change trend; introducing a second optimization factor to calculate the feedforward gain coefficient, and the calculation formula of the second optimization factor is:

[0020] ;

[0021] Among them, Represents the filter clogging compensation gain coefficient, which is used to adjust Sensitivity to filter clogging; Represents Filter pressure difference measurement value at the moment of; Represents the reference pressure difference value; Represents the reference pressure difference value; Represents Maximum limit of;

[0022] Evaluating the feedforward gain coefficient through the second optimization factor, and the calculation formula of the feedforward gain coefficient is:

[0023] ;

[0024] Among them, Represents the feedforward gain coefficient introducing the second optimization factor; Represents the base value of the feedforward gain coefficient; Represents the second optimization factor;

[0025] After obtaining the feedforward gain coefficient introducing the second optimization factor, use the feedforward gain coefficient introducing the second optimization factor for the evaluation of the first optimization factor to obtain the gain of the final feedforward compensation term.

[0026] Furthermore, in step S4, the intelligent control of the purifier filter is performed through the optimized control model, and the specific steps are as follows:

[0027] Control the fan speed of the air purifier according to the optimized control quantity calculated in step S3;

[0028] Calculate the control output at the current moment according to the optimized PID control formula calculated in step S3 :

[0029] ;

[0030] Among them, Represents the control output; Represents The control error at time; Represents The feedforward compensation factor at time; Represents At time Concentration change rate; Represents the proportional coefficient; Represents the integral coefficient; Represents the differential coefficient;

[0031] Convert the calculated control output into a fan control signal and send it to the fan drive circuit to control the actual speed of the fan.

[0032] Furthermore, in step S1:

[0033] Data acquisition is to collect the following original data in real time during the operation of the PID air purifier: , at time Of Concentration measurement value, which is obtained by Sensor;

[0034] Represents time Filter differential pressure measurement value;

[0035] Represents time Wind speed;

[0036] Through the air purifier panel or Set target Concentration, i.e., the set value;

[0037] The preprocessing is as follows: during operation, the collected raw data is preprocessed, and for And Perform moving average filtering.

[0038] An intelligent control method for a purifier filter screen made by using the technical solution of the present invention can quickly respond to sudden pollution: by monitoring the Acceleration change of concentration ( ), actively inject a feedforward compensation term during the stage of accelerated pollutant diffusion, shorten the system response time, and reduce the Peak concentration.

[0039] Filter clogging adaptive compensation: Dynamically adjust the feedforward gain coefficient Based on the change rate of the filter differential pressure, offset the influence of the increased wind resistance on the purification efficiency, ensure the control accuracy, and extend the service life of the filter screen.

[0040] Anti-interference and stability enhancement: Normalize the control error and sensor noise by calculating the standard deviation of the data through a sliding window, and suppress the control oscillation caused by data fluctuations.

[0041] Energy efficiency optimization: Combine the intelligent adjustment of the filter screen state and pollution trend, avoid the ineffective increase of the fan speed, and reduce the overall energy consumption. Brief Description of the Drawings

[0042] The drawings forming a part of the present invention are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0043] Figure 1 Is the method flow chart of an intelligent control method for a purifier filter screen described in an embodiment of the present invention. Detailed Embodiments

[0044] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0045] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "upper", "lower", "inner", "back", etc. is based on the orientation or positional relationship shown in the drawings. It 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 of the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0046] The present invention will be described in detail below with reference to the drawings and in conjunction with embodiments.

[0047] See Figure 1 , which is a flowchart of a method for intelligent control of a purifier filter provided in Embodiment 1 of the present invention. As Figure 1 shown, a method for intelligent control of a purifier filter may include:

[0048] S1, data acquisition and preprocessing.

[0049] During the operation of the air purifier, the following raw data needs to be collected in real time: , the concentration measurement value at time , which is obtained by the sensor; , the filter differential pressure measurement value at time t, which is obtained by the differential pressure sensors installed on both sides of the filter; , the wind speed at time , which is directly measured by the wind speed sensor. In addition, the target concentration set by the user through the air purifier panel or App, that is, the set value, also needs to be obtained.

[0050] During the factory production of the air purifier, a calibration needs to be performed once to obtain the reference differential pressure curve. The specific steps are as follows: First, ensure that the air purifier is installed with a brand-new and unused filter; then, set the air purifier to different wind speed gears (for example, low gear, medium gear, high gear); at each wind speed gear, after the system is stable, measure and record the differential pressure values on both sides of the filter; finally, store the reference differential pressure values at different wind speed gears in the non-volatile memory of the air purifier to form the reference differential pressure curve. .

[0051] During operation, preprocess the collected raw data, including performing a moving average filter on and to remove noise interference. Calculate the control error according to the target concentration set by the user and the current concentration measurement value. The formula is .

[0052] S2. Establish a rapid response mechanism for sudden pollution.

[0053] Traditional Air purifier control systems often have a problem of lagged response when dealing with sudden increases in indoor pollutant concentrations (e.g., opening windows to introduce outdoor pollutants, indoor smoking, cooking fumes, etc.). The main reason is The inherent characteristics of the control algorithm. The controller adjusts the output according to the deviation between the set value and the actual measured value (i.e., the error signal ). When the pollutant concentration suddenly increases, the error signal will increase. The controller generates an adjustment signal through the proportional link ( ) to drive the fan to increase its speed. However, due to The controller lacks "foresight" for the changing trend of pollutant concentration. It can only passively adjust according to the current error magnitude and cannot predict and respond to the rapid rise of pollutants in advance.

[0054] More specifically, The proportional link of the controller ( ) only reflects the magnitude of the error at the current moment and does not consider the changing trend of the error. Even if the error is already large, but if the growth rate of the error is slowing down (i.e., the rising speed of the pollutant concentration is slowing down), The controller will still adjust according to the current error magnitude, which will lead to over-regulation of the wind speed and cause overshoot. On the contrary, if the error is not yet very large, but the growth rate of the error is very fast (i.e., the pollutant concentration is accelerating), The controller cannot increase the wind speed in time, resulting in a lagged response.

[0055] To solve this problem, a mechanism that can "foresee" the changing trend of pollutant concentration needs to be introduced. This mechanism should be able to send a signal to the controller at the early stage when the pollutant concentration begins to accelerate, enabling it to increase the control strength in advance, so as to achieve a rapid response to sudden pollution.

[0056] Optimization factor As the gain of the feedforward compensation term, its calculation formula is as follows:

[0057]

[0058] Where:

[0059] : The basic feedforward gain coefficient represents the feedforward compensation intensity in the steady state. This is a preset value, initially determined based on experience or experiments (for example, set to 0.1 or 0.2), and then fine-tuned according to the effect during actual operation.

[0060] : Time of The acceleration of the concentration change rate is calculated as follows:

[0061] ;

[0062] : Time of The concentration change rate is calculated as follows:

[0063] ;

[0064] : Time of The concentration measurement value.

[0065] : Time of The concentration measurement value.

[0066] : Time of The concentration change rate.

[0067] : Time The control error at time e(t) = set value - actual measurement value (target concentration - actual concentration). Divide it by its standard deviation , and is normalized.

[0068] It should be noted that: The algorithm of is similar, and the sliding window size is selected to be the same.

[0069] : Time of The standard deviation of

[0070] ;

[0071] : The size of the sliding window ( , using the past Standard deviation calculated from a number of data points).

[0072] : At time of Sliding average of:

[0073] ;

[0074] : At time of Standard deviation of, calculated using a sliding window:

[0075] ;

[0076] : Sliding average of at time t of:

[0077] ;

[0078] : At time of Standard deviation of, calculated using a sliding window:

[0079] ;

[0080] : At time of Sliding average of:

[0081] ;

[0082] Optimization factor Detailed explanation of the functions of each part:

[0083] Optimization factor is designed to actively adjust the control strength of the air purifier when the concentration of indoor pollutants changes, achieving fast response and precise control. To achieve this goal, 's calculation formula comprehensively considers the current state, change trend, and control error of the concentration change, and uses a non-linear function and normalization processing, enabling it to sensitively capture pollution changes and avoid over-adjustment.

[0084] 's calculation formula can be divided into two main parts:

[0085] The first part is This part of the design will Acceleration of the concentration change rate ( ), absolute value of the control error ( ), and the standard deviations of both ( and ), are combined to comprehensively judge the current pollution change trend and control requirements.

[0086] When a pollution event occurs indoors (such as smoking, cooking, etc.), the concentration will change. reflects the acceleration of the concentration change. If is positive, it means the rising speed of the concentration is accelerating; if is negative, it means the rising speed of the concentration is slowing down, or the concentration has reached its peak and started to decline, or the concentration is declining and the decline speed is accelerating. The control error represents the gap between the actual concentration and the set value. Since we are concerned about the magnitude of the error rather than its sign, the absolute value of is used here . Introducing the standard deviations and is to normalize and . Due to the difference in the numerical ranges of and in different environments, directly multiplying them will result in too large or too small values. By dividing by their respective standard deviations, their values can be mapped to a relatively stable range, making the calculation results comparable in different environments.

[0087] The hyperbolic tangent function is used to map the value of to between . The purpose of this is to limit the change range of , avoiding too strong or too weak feedforward compensation. When is positive and large, the output of is close to ; when it is negative and its absolute value is large, the output of is close to ; when it is close to ,

[0088] The second part is . The function of this part is to finely adjust according to the change trend of the acceleration of the concentration change rate. reflects The change amount of the acceleration of the concentration change. When the acceleration of the rising concentration increases, this term is positive; when the acceleration of the rising concentration decreases, this term is negative. When the concentration reaches the peak and starts to decline, it will become negative. If the acceleration of the decline increases (i.e., the concentration declines faster and faster), this term is negative. When the acceleration of the decline decreases (i.e., the concentration declines slower and slower), this term is positive. is the standard deviation of, which is used for normalization. Through the form of , it is ensured that this part is always positive. When is positive, this term is greater than , making slightly increase; when is negative, this term is less than , making decrease.

[0089] These two parts are combined in the form of a product. The first part determines the basic direction and approximate amplitude of , and the second part makes fine-tuning according to the trend of the PM2.5 concentration change. Finally, the entire expression of is multiplied by a coefficient . is the feedforward gain coefficient, which is used to adjust the amplitude of the entire , thereby controlling the overall strength of the feedforward compensation.

[0090] Finally, is multiplied by and added to the output of the controller as the feedforward compensation term:

[0091] .

[0092] S3. Establish a feedforward gain coefficient optimization mechanism for filter clogging.

[0093] In step S2, we proposed a fast response mechanism for sudden pollution. By introducing the feedforward compensation term , the response speed of the air purifier to the sudden increase in indoor pollutant concentration is improved. This feedforward compensation term can make the fan speed exceed the speed calculated only by the controller when the concentration suddenly increases, so as to reduce the pollutant concentration faster. However, the strength of the feedforward compensation term is determined by the feedforward gain coefficient ​Control The selection of the value directly affects the effect of the fast response mechanism.

[0094] It should be emphasized that the goal of the controller itself is to make the actual concentration as close as possible to the target value set by the user. To achieve this goal, the controller will calculate a target fan speed (or the corresponding control voltage) in real time based on factors such as the current concentration, error, and error change rate. This target fan speed is not a fixed value, but will change with the change of the system state (such as the degree of filter clogging). As the filter gradually clogs, the dynamic characteristics of the air purifier system will change, and the demand for feedforward compensation will also change accordingly. Our goal is to dynamically adjust the feedforward gain coefficient throughout the process from the filter being clean to gradually clogging, so that the control system of the air purifier can actively adapt to the change of the filter state, continuously optimize the performance of the fast response mechanism, and ensure the fastest response to the change of concentration in any filter state.

[0095] Specifically:

[0096] When the filter is clean, the system responds quickly, and the controller can relatively easily control the concentration near the set value. At this time, the feedforward compensation is mainly used to accelerate the response process.

[0097] When the filter gradually clogs, due to the increase in filter resistance, even if the controller still uses the same concentration set value as the target, in order to overcome the filter resistance and achieve the same purification effect, a larger control signal (higher voltage) needs to be output to drive the fan, which means the target fan speed calculated by the controller will be higher than that when the filter is clean. However, the adjustment ability of the controller is limited. The controller is adjusted based on the error, and it will only adjust when the actual value deviates from the set value. The integral term in the controller has the function of eliminating the steady-state error. In theory, as long as there is enough time, the integral term should be able to eliminate the error to 0. However, in actual applications, the adjustment effect of the integral term is limited by integral saturation, integral time constant, and system dynamic characteristics.

[0098] Filter clogging can be regarded as a continuous disturbance acting on the air purifier system. The controller can partially suppress such disturbances, but if the disturbance is too large or the change rate of the disturbance exceeds the adjustment ability of the controller, the controller cannot completely eliminate the influence of the disturbance. More specifically, the influence of the filter clogging can be equivalent to reducing the gain of the system. That is to say, for the same fan speed, the actual purification effect (the amount of air purified per unit time) after the filter is clogged will be lower than the level when the filter is clean.

[0099] Therefore, the core of the optimization scheme lies in introducing feedforward compensation and dynamically adjusting the feedforward gain coefficient according to the degree of filter clogging , to assist the controller. So that it can respond more quickly and accurately to the influence brought by the filter clogging. In the case of the filter gradually clogging, by increasing the value to enhance the role of feedforward compensation, the fan speed is further increased on the basis of the target speed calculated by the controller, so as to more fully compensate for the decrease in the purification effect caused by the filter clogging and make the actual PM2.5 concentration still as close as possible to the set value.

[0100] The specific solution is to monitor the change rate of the pressure difference of the filter and use it as an index of the degree of filter clogging and its change trend. In this way, the adaptive optimization of the fast response mechanism is realized in the case of the filter gradually clogging, ensuring that the air purifier can maintain the best purification performance under various working conditions.

[0101] Introduce an optimization factor to calculate the feedforward gain coefficient :

[0102] ;

[0103] where:

[0104] : The base value of the feedforward gain coefficient (preset value, corresponding to the value when the filter is clean). Suggested range: . The specific value is determined through experiments.

[0105] : The filter clogging compensation factor, and its calculation formula is as follows:

[0106] ;

[0107] : The filter clogging compensation gain coefficient, used to adjust the sensitivity to filter clogging. Suggested range: . The specific value is determined through experiments.

[0108] : Moment The measured value of the filter pressure difference (measured at the current wind speed ). It is measured in real time by the pressure difference sensors installed on both sides of the filter.

[0109] : Reference pressure difference value. When the air purifier leaves the factory, a new filter is used, and the filter pressure difference values are measured and recorded respectively at different wind speed gears to form a reference pressure difference curve. During operation, according to the current wind speed the corresponding reference pressure difference value is found from this curve.

[0110] : Reference pressure difference value. It represents the pressure difference value when the filter is blocked to a certain extent (when the filter needs to be replaced). Refer to the recommended replacement pressure difference value provided by the filter manufacturer.

[0111] : The maximum limit of

[0112] Optimization factor and Detailed explanations of the functions of each part:

[0113] The core of this optimization scheme lies in introducing the optimization factor to dynamically adjust the feedforward gain coefficient , so as to achieve adaptive compensation for filter blockage. : This item is the core of calculation. It represents the difference between the filter pressure difference at the current moment and the reference pressure difference. is the real-time measured filter pressure difference, which increases as the degree of filter blockage increases. is the reference pressure difference. Therefore, The value of directly reflects the degree of blockage of the filter relative to the brand-new state. This item normalizes the pressure difference increment. is a reference pressure difference value, representing the pressure difference value when the filter is blocked to a certain extent. By dividing by , the pressure difference increment is converted into a dimensionless ratio, so that The calculation of is not affected by the absolute value of the filter pressure difference. The function maps the normalized pressure difference increment to between. When the filter is close to the brand-new state ( is close to ), The output of is close to . When the filter is gradually blocked ( increases), The output gradually increases and approaches .

[0114] is an adjustment coefficient used to control the sensitivity to filter clogging. The larger is, the more sensitive the response to the differential pressure change is, and the larger the change amplitude of is. The smaller is, the more sluggish the response to the differential pressure change is, and the smaller the change amplitude of

[0115] The function of is to limit the maximum value of to avoid over-strong feedforward compensation. By limiting the maximum value of it ensures that does not exceed

[0116] The final :

[0117] .

[0118] S4, perform intelligent control of the purifier filter through the optimized control model.

[0119] This step aims to control the fan speed of the air purifier according to the optimized control quantity calculated in step to achieve intelligent control. First, according to the optimized calculated in step control formula, calculate the control output at the current moment:

[0120] ;

[0121] where the proportional, integral, and differential coefficients of the controller are existing preset values; is the control error at the current moment, calculated in step ; is the feedforward compensation factor at the current moment, calculated in step ; is the concentration change rate at the current moment, calculated in step . Convert the calculated control output into a fan control signal and send it to the fan drive circuit to control the actual speed of the fan. Use the above optimized The control algorithm realizes continuous, dynamic and intelligent control of the air purifier.

[0122] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent control method for a purifier filter, characterized in that: The method comprises the following steps: Step S1: data collection and preprocessing; Step S2: Establish a rapid response mechanism for sudden pollution; Step S3: Establishing a feedforward gain coefficient optimization mechanism for filter blockage; Step S4: Intelligently control the filter of the purifier through the optimized control model.

2. The intelligent control method for a purifier filter according to claim 1, characterized in that: In step S2, a rapid response mechanism for sudden pollution is established, and the specific steps include: When the pollutant concentration begins to rise rapidly, a signal is sent to the PID controller to add a feedforward compensation term to the output of the PID controller; The first optimization factor is used as the gain of the feedforward compensation term, and the calculation formula of the first optimization factor is: ； in, express The optimization factor of the moment; represents the basic feedforward gain coefficient; express Moment The acceleration of the concentration change rate is calculated as: ; express Moment The concentration change rate is calculated as: ; express Moment Concentration measurements; express The control error of the moment, The value is the error between the set value and the actual measured value; express Moment the standard deviation of the acceleration of the concentration change rate, evaluated over a sliding window; express The standard deviation of the control error at each moment is evaluated using a sliding window; express time The standard deviation of is evaluated over a sliding window.

3. The intelligent control method for a purifier filter according to claim 1, characterized in that: The step S3 establishes a feedforward gain coefficient optimization mechanism for filter blockage, and the specific steps include: The pressure difference change rate of the monitoring filter is used as an indicator of the filter blockage degree and its change trend; the second optimization factor is introduced to calculate the feedforward gain coefficient, and the calculation formula of the second optimization factor is: ； in, Indicates the filter blockage compensation gain coefficient, used to adjust sensitivity to filter clogging; express The measured value of the filter pressure difference at the moment; Indicates the reference pressure difference value; Indicates the reference pressure difference value; express The maximum value limit of The feedforward gain coefficient is evaluated by the second optimization factor, and the calculation formula of the feedforward gain coefficient is: ； in, represents the feedforward gain coefficient introduced into the second optimization factor; Indicates the base value of the feedforward gain coefficient; represents the second optimization factor; After the feedforward gain coefficient introduced into the second optimization factor is obtained, the feedforward gain coefficient introduced into the second optimization factor is used for evaluating the first optimization factor to obtain the gain of the final feedforward compensation term.

4. The intelligent control method for a purifier filter according to claim 1, characterized in that: The step S4 performs intelligent control of the purifier filter through the optimized control model, and the specific steps are: According to the optimized control amount calculated in step S3, the fan speed of the air purifier is controlled; According to the optimized PID control formula calculated in step S3, the control output at the current moment is calculated. : ； in, Indicates control output; express Control error at the moment; express Feedforward compensation factor at the moment; express Moment Concentration change rate; represents the proportionality coefficient; represents the integral coefficient; represents the differential coefficient; The calculated control output is converted into a fan control signal and sent to the fan drive circuit to control the actual speed of the fan.

5. The intelligent control method for a purifier filter according to claim 1, characterized in that: In step S1: Data collection: During the operation of the PID air purifier, the following raw data are collected in real time: ,time of Concentration measurement, which is obtained from Sensor acquisition; Indicates time The filter pressure difference measurement value; Indicates time wind speed; Through the air purifier panel or Set goals Concentration, i.e. set value; Preprocessing is to preprocess the collected raw data at runtime. and Perform sliding average filtering.

Images