A ventilation equipment air volume control method and device, ventilation equipment and storage medium

Abstract

The embodiment of the application discloses a ventilation equipment air volume control method and device, ventilation equipment and a storage medium. The method comprises the following steps: acquiring motor working condition parameters of the ventilation equipment in real time; acquiring the interval to which the static pressure in the air duct of the ventilation equipment belongs based on the motor working condition parameters through a pre-constructed static pressure interval classifier; and adjusting motor control parameters of the ventilation equipment based on the interval to which the static pressure in the air duct belongs and a control air volume target value, so that the real-time ventilation volume of the ventilation equipment follows the control air volume target value, wherein the motor control parameters comprise a motor rotating speed. The embodiment of the application can reduce equipment cost, improve operation reliability and environmental adaptability.

Description

Technical Field

[0001] This invention relates to the field of ventilation equipment control technology, and in particular to a ventilation equipment airflow control method, device, ventilation equipment, and storage medium. Background Technology

[0002] Constant airflow control of ventilation equipment is a key technology for ensuring stable operation, reducing energy consumption, and optimizing user experience. Traditional constant airflow control methods mostly rely on static pressure sensors, which collect static pressure data in the duct and adjust the fan speed accordingly to achieve constant airflow control. However, the high cost of static pressure sensors and related accessories, coupled with the need for ductwork openings, wiring, and sealing during installation, can easily lead to air leakage. Furthermore, the sensor's pressure measurement port is constantly exposed to airflow dust, moisture, and oil, making it prone to blockage. In addition, environmental temperature variations and airflow turbulence can cause static pressure sampling errors. Therefore, constant airflow control methods relying on static pressure sensors suffer from high equipment and maintenance costs, low operational reliability, and poor environmental adaptability. Summary of the Invention

[0003] This invention provides a method, device, ventilation equipment, and storage medium for controlling the air volume of a ventilation device, which can reduce equipment costs and improve operational reliability and environmental adaptability.

[0004] In a first aspect, embodiments of the present invention provide a method for controlling the air volume of a ventilation device, comprising: Real-time acquisition of motor operating parameters of ventilation equipment; Based on the motor operating parameters, the static pressure range within the ventilation equipment's duct is determined using a pre-built static pressure range classifier; and The motor control parameters of the ventilation equipment are adjusted based on the static pressure range within the duct and the target air volume value, so that the real-time ventilation volume of the ventilation equipment follows the target air volume value. The motor control parameters include the motor speed.

[0005] In a second aspect, embodiments of the present invention provide a ventilation equipment airflow control device, comprising: The motor parameter acquisition module is used to acquire the motor operating parameters of the ventilation equipment in real time. A static pressure range acquisition module is used to acquire the range of static pressure within the duct of the ventilation equipment based on the motor operating parameters using a pre-built static pressure range classifier; and The adjustment module is used to adjust the motor control parameters of the ventilation equipment based on the static pressure range in the air duct and the target value of the control air volume, so that the real-time ventilation volume of the ventilation equipment follows the target value of the control air volume. The motor control parameters include the motor speed.

[0006] Thirdly, embodiments of the present invention also provide a ventilation device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement airflow control of the ventilation device as described in any of the embodiments of the present invention.

[0007] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements airflow control of a ventilation device as described in any of the embodiments of the present invention.

[0008] This invention provides a ventilation equipment airflow control method, device, ventilation equipment, and storage medium. By acquiring the motor operating parameters of the ventilation equipment in real time, and using a pre-constructed static pressure range classifier based on the motor operating parameters to determine the static pressure range within the ventilation equipment's duct, the motor control parameters of the ventilation equipment are adjusted based on the static pressure range within the duct and the target airflow value. This allows the real-time ventilation volume of the ventilation equipment to follow the target airflow value, enabling constant airflow control of the ventilation equipment without relying on static pressure sensors, reducing equipment and maintenance costs, and improving operational reliability and environmental adaptability. Attached Figure Description

[0009] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a schematic flowchart of a ventilation equipment airflow control method provided in an embodiment of the present invention; Figure 2 This is a schematic flowchart of a ventilation equipment airflow control method provided in an embodiment of the present invention; Figure 3 This is a schematic flowchart of a ventilation equipment airflow control method provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of a ventilation equipment airflow control device provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of a ventilation device provided in an embodiment of the present invention. Detailed Implementation

[0011] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0012] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0013] Figure 1 This is a flowchart illustrating a ventilation equipment airflow control method provided in an embodiment of the present invention. This embodiment is applicable to scenarios involving constant airflow control of ventilation equipment. The method can be executed by the ventilation equipment airflow control device provided in this embodiment, which can be implemented using software and / or hardware. In a specific embodiment, the device can be integrated into the ventilation equipment, such as a computer or server. The following embodiments will illustrate this using the integration of the device into a ventilation equipment as an example. (Reference) Figure 1 The method may specifically include the following steps: Step 101: Obtain the motor operating parameters of the ventilation equipment in real time. This step enables the determination of the static pressure range within the ventilation equipment duct based on the motor operating parameters using a static pressure range classifier.

[0014] Specifically, the aforementioned ventilation equipment may include household ventilation equipment and / or commercial industrial ventilation equipment.

[0015] Specifically, the aforementioned household ventilation equipment may include, for example, air conditioners, air purifiers, and range hoods.

[0016] Specifically, the aforementioned motor operating parameters can be understood as a set of measured parameters that reflect the operating status of the ventilation motor during operation. There can be multiple parameters, which may include motor speed and motor power.

[0017] Specifically, the above-mentioned motor operating parameters may also include: motor input current and motor input voltage.

[0018] Specifically, the process of acquiring the motor operating parameters of the ventilation equipment in real time may include: acquiring the motor operating parameters collected by the corresponding sensors.

[0019] Step 102: Based on the motor operating parameters, the static pressure range within the ventilation equipment's duct is obtained using a pre-built static pressure range classifier. This step facilitates the adjustment of the ventilation equipment's motor control parameters based on the static pressure range within the duct.

[0020] Specifically, the structure of the static pressure interval classifier can be a decision tree, a random forest, or a support vector machine. In this embodiment of the invention, a decision tree is preferred to reduce the computational power requirement.

[0021] Specifically, the static pressure interval classifier described above can be constructed through the following steps: pre-setting multiple consecutive and non-overlapping static pressure intervals within the duct based on the historical operating conditions of the ventilation equipment, and generating corresponding classification labels; collecting historical values ​​of motor operating parameters and the corresponding static pressure intervals within the duct; using a decision tree as the basic classifier structure, taking the historical values ​​of motor operating parameters as input features, establishing branch judgment rules based on the classification labels matching the corresponding static pressure intervals within the duct, and constructing the static pressure interval classifier described above.

[0022] Specifically, the process of obtaining the static pressure range of the ventilation equipment's duct based on the motor operating parameters through a pre-built static pressure range classifier may include: inputting the motor operating parameters into the static pressure range classifier, obtaining the classification label of the static pressure range in the duct calculated and output by the static pressure range classifier based on the motor operating parameters, and determining the static pressure range of the ventilation equipment's duct based on the classification label of the static pressure range in the duct.

[0023] Step 103: Adjust the motor control parameters of the ventilation equipment based on the static pressure range within the duct and the target airflow value, so that the real-time ventilation volume of the ventilation equipment follows the target airflow value. The motor control parameters include the motor speed. Building upon steps 101 and 102, this step enables constant airflow control of the ventilation equipment without relying on a static pressure sensor, reducing equipment and maintenance costs, and improving operational reliability and environmental adaptability.

[0024] Specifically, the aforementioned motor control parameters may include one or more parameters, and may also include motor power.

[0025] Specifically, the process of determining the motor control parameters of the ventilation equipment based on the static pressure range in the duct and the target value of the control air volume can include: obtaining the motor control parameters by mapping the static pressure range in the duct and the target value of the control air volume together based on a pre-established mapping relationship.

[0026] Specifically, the above mapping relationship can be represented by a polynomial, a neural network, or a table.

[0027] The following further describes the ventilation equipment airflow control method provided by the embodiments of the present invention.

[0028] Optionally, before step 103, the ventilation equipment air volume control method provided in this embodiment of the invention further includes: obtaining a first air volume prediction value based on motor operating parameters through a pre-constructed polynomial air volume prediction model, and determining a future air volume prediction value based on the first air volume prediction value.

[0029] Optionally, the polynomial air volume prediction model includes: a second-order polynomial air volume fitting model and a fourth-order Taylor expansion model corresponding to the second-order polynomial air volume fitting model.

[0030] In a specific example, when the motor operating parameters include motor power and motor speed, the second-order polynomial function of the above second-order polynomial airflow fitting model can be expressed as: Where Q represents the first predicted air volume. The parameters represent the second-order polynomial air volume fitting model, where P represents the motor power and N represents the motor speed.

[0031] Specifically, the construction process of the aforementioned second-order polynomial air volume fitting model may include: constructing an objective function with the goal of minimizing the sum of squared errors between the model's predicted and measured air volume values; substituting the polynomial expression into the objective function, and adjusting each coefficient... Taking the partial derivatives and setting them to zero, we obtain the system of linear equations: The linear equations are solved by matrix inversion and Gaussian elimination to obtain the theoretical optimal values ​​of each model parameter. The theoretical optimal values ​​of each model parameter are then substituted into the above second-order polynomial function to obtain the above second-order polynomial air volume fitting model.

[0032] In a specific example, the theoretical optimal values ​​of each model parameter are converted to integers and then substituted into the above second-order polynomial function to obtain the above second-order polynomial air volume fitting model. This avoids floating-point operations, adapts to the characteristics of low-cost chips without hardware floating-point units, and ensures that the fitting error is controlled within the allowable range of engineering.

[0033] Specifically, the process of converting the theoretical optimal values ​​of each model parameter to integers may include approximating the theoretical optimal values ​​of each model parameter by powers of 2.

[0034] In a specific example, when the motor operating parameters include motor power and motor speed, the fourth-order Taylor expansion polynomial function of the above fourth-order Taylor expansion model can be expressed as: in, This indicates the Taylor expansion reference operating point. , The partial derivatives of each order are calculated using the numerical difference method based on measured data.

[0035] Specifically, the construction process of the above-mentioned fourth-order Taylor expansion model may include: based on the measured air volume, using the multivariate nonlinear least squares method to fit the coefficients of the fourth-order terms, first using the gradient descent algorithm for iterative optimization to reduce the fitting error of the model under boundary conditions, and focusing on correcting the coefficients of the third-order and fourth-order terms to improve the curve fit.

[0036] Specifically, the model parameters of the fourth-order Taylor expansion model can also be integerized.

[0037] Optionally, the process of obtaining the first predicted air volume value based on the motor operating parameters through a pre-built polynomial air volume prediction model includes: if the motor operating parameters belong to the range of rated operating parameters, then the first predicted air volume value is obtained based on the motor operating parameters through a fourth-order Taylor expansion model.

[0038] Specifically, the above-mentioned rated operating condition parameter range can be understood as the upper and lower limits of the allowable fluctuation of the motor's operating condition parameters under the standard operating conditions of rated voltage, rated frequency, rated load, and rated temperature.

[0039] Specifically, if the motor operating parameters fall within the range of rated operating parameters, the process of obtaining the first predicted air volume value based on the motor operating parameters through a fourth-order Taylor expansion model may include: if multiple motor operating parameters fall within the corresponding range of rated operating parameters, the first predicted air volume value is obtained based on each motor operating parameter through a fourth-order Taylor expansion model.

[0040] Specifically, when any motor operating parameter falls within the corresponding rated operating parameter range, the first predicted air volume value can be obtained based on each motor operating parameter using a fourth-order Taylor expansion model.

[0041] Optionally, the process of obtaining the first predicted air volume value based on the motor operating parameters through a pre-built polynomial air volume prediction model includes: if the motor operating parameters do not belong to the range of rated operating parameters, then the first predicted air volume value is obtained based on the motor operating parameters through a second-order polynomial air volume fitting model.

[0042] Specifically, the process of obtaining the first predicted air volume value based on the motor operating parameters through a second-order polynomial air volume fitting model if the motor operating parameters do not belong to the rated operating parameter value range may include: if any motor operating parameter among multiple motor operating parameters does not belong to the corresponding rated operating parameter value range, then the first predicted air volume value is obtained based on each motor operating parameter through a second-order polynomial air volume fitting model.

[0043] Specifically, when none of the motor operating parameters belong to the corresponding rated operating parameter range, the first predicted air volume value can be obtained based on the second-order polynomial air volume fitting sub-model using each motor operating parameter.

[0044] Understandably, second-order polynomial fitting can provide global robustness and extrapolation capability, while fourth-order Taylor expansion can achieve high-precision local approximation under normal operating conditions. The combination of the two makes the system power-saving and stable under normal operating conditions, and prevents it from going out of control or being damaged under different environmental conditions, thus balancing accuracy and safety.

[0045] Specifically, the process of determining the future air volume forecast value based on the first air volume forecast value may include: determining the first air volume forecast value as the future air volume forecast value.

[0046] Specifically, the process of determining the future air volume prediction value based on the first air volume prediction value may also include: obtaining the third air volume prediction value based on the motor operating parameters through a lightweight fitting model, and determining the future air volume prediction value based on the first air volume prediction value and the third air volume prediction value.

[0047] Specifically, the aforementioned lightweight fitting model can be obtained by removing high-order small coefficients that have minimal impact on the fitting results from the polynomial model, retaining the core contribution terms, and quantizing the remaining coefficients into integer or shiftable values.

[0048] Specifically, the aforementioned lightweight fitting model can also be a lookup table model.

[0049] Specifically, the process of determining the future air volume prediction value based on the first air volume prediction value and the third air volume prediction value may include weighting and summing the first air volume prediction value and the third air volume prediction value based on the predetermined prediction weight calibration value of the first air volume prediction value and the third air volume prediction value to obtain the future air volume prediction value.

[0050] Specifically, the prediction weights of the first and third air volume prediction values ​​can be determined based on the historical first air volume prediction value and the historical third air volume prediction value corresponding to the most recent first time period. The first and third air volume prediction values ​​can then be weighted and summed based on the corresponding prediction weights to obtain the aforementioned future air volume prediction value.

[0051] Understandably, combining multiple models can prevent constant air volume control from failing when a single model fails, thereby improving the reliability and stability of the constant air volume control system and enhancing the user experience.

[0052] Optional, such as Figure 2 As shown, that is Figure 1 Step 103 may include the following steps: Step 103A1: Determine the master control value for adjusting the motor speed based on the predicted future air volume and the target control air volume value.

[0053] Specifically, the process of determining the motor speed adjustment command value based on the future air volume prediction value and the control air volume target value may include: determining a first air volume deviation value based on the future air volume prediction value and the control air volume target value, and determining the motor speed adjustment command value based on the first air volume deviation value.

[0054] Specifically, the process of determining the adjustment command value of the motor speed based on the first air volume deviation value may include: obtaining the adjustment command value of the motor speed based on the first air volume deviation value through a proportional-integral-derivative control algorithm, a variable gain algorithm, or a lookup table method.

[0055] Step 103A2: Determine the adjustment compensation value of the motor speed based on the range of static pressure in the air duct.

[0056] Optionally, the process of determining the motor speed adjustment compensation value based on the static pressure range within the duct can include: determining the motor speed adjustment compensation value based on the static pressure range within the duct and a pre-determined mapping relationship between the static pressure range within the duct and the corresponding adjustment compensation value.

[0057] Specifically, the mapping relationship between the static pressure range in the aforementioned air duct and the corresponding adjustment compensation value can be pre-built into the static pressure compensation information table, which can include the mapping relationship between the static pressure range in different air ducts and the corresponding adjustment compensation value.

[0058] Specifically, before determining the motor speed adjustment compensation value based on the static pressure range within the duct and the pre-determined mapping relationship between the static pressure range within the duct and the corresponding adjustment compensation value, the mapping relationship between the static pressure range within the duct and the corresponding adjustment compensation value can be obtained by querying the static pressure compensation information table based on the static pressure range within the duct.

[0059] Step 103A3: Determine the target value for motor speed adjustment based on the master control value and the compensation value for motor speed adjustment.

[0060] Specifically, the process of determining the target value of motor speed adjustment based on the master control value and the compensation value of motor speed adjustment includes: summing the master control value and the compensation value of motor speed adjustment to obtain the target value of motor speed adjustment.

[0061] Specifically, the target value for motor speed adjustment can be obtained by weighted summation of the master control value and the compensation value for motor speed adjustment.

[0062] Step 103A4: Adjust the motor speed based on the target value of the motor speed adjustment.

[0063] It is understandable that when adjusting the motor speed, the motor power is used as a follow-up variable and is automatically matched to the target value of the motor speed adjustment.

[0064] Specifically, the process of adjusting the motor speed based on the adjustment target value of the motor speed may include: real-time detection of the actual motor speed, calculation of the speed deviation between the actual motor speed and the adjustment target value of the motor speed, and obtaining torque or current commands through the speed regulator based on the speed deviation, driving the motor to output corresponding torque through the current loop, so that the actual speed tends to and follows the adjustment target value of the motor speed.

[0065] Optionally, step 103 includes: determining the air volume prediction calibration value based on the range of static pressure in the duct; determining the motor speed adjustment target value based on the future air volume prediction value, the air volume prediction calibration value, and the control air volume target value; and adjusting the motor speed based on the motor speed adjustment target value.

[0066] Specifically, the process of determining the air volume prediction calibration value based on the static pressure range within the duct can include: determining the air volume prediction calibration value based on the static pressure range within the duct and the pre-determined mapping relationship between the static pressure range within the duct and the corresponding air volume prediction calibration value.

[0067] Specifically, the process of determining the adjustment target value of the motor speed based on the future air volume prediction value, the air volume prediction calibration value, and the control air volume target value may include: calculating the difference between the control air volume target value and the future air volume prediction value and the air volume prediction calibration value to obtain a second air volume deviation value, and calculating the adjustment target value of the motor speed based on the second air volume deviation value.

[0068] It should be noted that the embodiments of the present invention are applicable to ventilation equipment equipped with low-cost control chips.

[0069] Understandably, to control equipment costs, many ventilation devices employ low-cost control chips. However, these low-cost control chips have limited memory and computing resources. Using traditional neural networks to predict future airflow would result in insufficient memory and computing power, leading to low operating efficiency. Therefore, this invention, when equipping ventilation devices with low-cost control chips, uses a polynomial airflow prediction model to predict future airflow, reducing computing power requirements. Simultaneously, fixed segmental compensation is performed based on the static pressure range within the duct, effectively ensuring the stability of constant airflow control under different environmental conditions and improving user experience.

[0070] The following further describes the ventilation equipment airflow control method provided by the embodiments of the present invention. For example... Figure 3 As shown, that is Figure 1 Step 103 may include the following steps: Step 103B1: Based on the static pressure range in the duct and the motor operating parameters, obtain the second air volume prediction value through a pre-trained neural network air volume prediction model, and determine the future air volume prediction value based on the second air volume prediction value.

[0071] Specifically, the aforementioned neural network wind volume prediction model can be a backpropagation neural network model, a feedback neural network, or a long short-term memory network, etc.

[0072] Specifically, the above-mentioned neural network airflow prediction model can be trained through the following steps: obtain sample motor operating parameters, sample static pressure range, and corresponding measured airflow; randomly initialize the weights and biases of each layer of the neural network airflow prediction model to be trained, and set the activation function of the hidden layer and the linear activation of the output layer; after standardizing the sample motor operating parameters and sample static pressure range, input them into the neural network airflow prediction model to be trained, and obtain the training predicted airflow output by the neural network airflow prediction model; calculate the function value of the training loss function based on the training predicted airflow and the corresponding measured airflow; based on the function value of the training loss function, use the Adam optimizer or stochastic gradient descent optimizer to update the model parameters of the neural network airflow prediction model according to the gradient direction.

[0073] Specifically, the process of standardizing the sample motor operating parameters and sample static pressure range can include: performing power-of-2 quantization standardization on the sample motor operating parameters and sample static pressure range to replace division operations with shift operations, using integer operations throughout the process to reduce reliance on chip computing power.

[0074] Specifically, the process of obtaining the second predicted air volume value based on the static pressure range within the duct and the motor operating parameters through a pre-trained neural network air volume prediction model may include: performing power-of-2 quantization and standardization on the static pressure range within the duct and the motor operating parameters to obtain standardized static pressure range and standardized motor operating parameters; inputting the standardized static pressure range and standardized motor operating parameters into the neural network air volume prediction model; and obtaining the second predicted air volume value output by the neural network air volume prediction model.

[0075] Specifically, the process of determining the future air volume forecast value based on the second air volume forecast value may include: determining the second air volume forecast value as the future air volume forecast value.

[0076] Optionally, before determining the future air volume prediction value based on the second air volume prediction value, the ventilation equipment air volume control method provided in this embodiment of the invention further includes: obtaining a first air volume prediction value based on motor operating parameters through a pre-constructed polynomial air volume prediction model; determining the prediction weights of the first air volume prediction value and the second air volume prediction value based on the historical first air volume prediction value and the historical second air volume prediction value corresponding to the most recent first time period; the process of determining the future air volume prediction value based on the second air volume prediction value may include: weighting and summing the first air volume prediction value and the second air volume prediction value based on the prediction weights of the first air volume prediction value and the second air volume prediction value to obtain the future air volume prediction value.

[0077] Specifically, the prediction weight calibration values ​​of the first and second air volume prediction values ​​can be determined in advance, and the first and second air volume prediction values ​​can be weighted and summed based on the corresponding prediction weight calibration values ​​to obtain the future air volume prediction value.

[0078] Specifically, the process of determining the prediction weights of the first and second air volume prediction values ​​based on the historical first and second air volume prediction values ​​corresponding to the most recent first time period may include: determining the performance anomaly level of the neural network air volume prediction model based on the historical first and second air volume prediction values ​​corresponding to the most recent first time period, and determining the prediction weights of the first and second air volume prediction values ​​based on the performance anomaly level of the neural network air volume prediction model.

[0079] Specifically, the process of determining the performance anomaly level of the multinomial air volume prediction model and the neural network air volume prediction model based on the historical first air volume prediction value and the historical second air volume prediction value corresponding to the most recent first time period may include: weighting and summing the first air volume prediction value and the second air volume prediction value based on the corresponding prediction weight calibration value to obtain an air volume reference value; and determining the performance anomaly level of the neural network air volume prediction model based on the deviation value between the second air volume prediction value and the air volume reference value.

[0080] Specifically, the performance anomaly level of the neural network air volume prediction model can be determined based on whether the number of times the deviation between the second predicted air volume value and the air volume reference value within the most recent first historical period falls outside the allowable deviation range and whether it falls within the range of times corresponding to different performance anomaly levels.

[0081] Specifically, the allowable deviation range and frequency range mentioned above can be set based on empirical data.

[0082] Specifically, the performance anomaly level of the neural network air volume prediction model can be determined by whether the deviation between the second predicted air volume value and the reference air volume value within the most recent first historical period falls within the range of abnormal deviation values ​​corresponding to different performance anomaly levels.

[0083] Specifically, the above-mentioned performance abnormality levels include: no abnormality, slight abnormality, moderate abnormality, and severe abnormality.

[0084] Specifically, when the performance anomaly levels of both the polynomial air volume prediction model and the neural network air volume prediction model are normal, the prediction weight of the second air volume prediction value can be set to a larger value, while the prediction weight of the first air volume prediction value can be set to a smaller value.

[0085] Specifically, when the performance anomaly level of the neural network airflow prediction model is relatively severe, the prediction weight of the second airflow prediction value can be set to a smaller value, and the prediction weight of the first airflow prediction value can be set to a larger value; when the performance anomaly level of the neural network airflow prediction model is relatively mild, the prediction weight of the second airflow prediction value can be set to a larger value, and the prediction weight of the first airflow prediction value can be set to a smaller value.

[0086] Specifically, before determining the future air volume prediction value based on the second air volume prediction value, a third air volume prediction value can be obtained through a lightweight fitting model based on motor operating parameters; the prediction weights of the first air volume prediction value, the second air volume prediction value, and the historical third air volume prediction value corresponding to the most recent first time period can be determined; the process of determining the future air volume prediction value based on the second air volume prediction value can include: weighting and summing the first air volume prediction value, the second air volume prediction value, and the historical third air volume prediction value based on the corresponding prediction weights to obtain the future air volume prediction value.

[0087] Step 103B2: Determine the target value for adjusting the motor speed based on the predicted future air volume and the target value for controlling the air volume.

[0088] Step 103B3: Adjust the motor speed based on the target value of the motor speed adjustment.

[0089] This invention is applicable to ventilation equipment equipped with mid-to-high-performance computing chips that support neural network models. Based on the static pressure range within the duct and motor operating parameters, this invention can accurately predict the airflow of the ventilation equipment, thereby improving the accuracy of constant airflow control. Furthermore, this invention can use a method of multi-model prediction and weighted averaging to determine future airflow predictions, which avoids the failure of constant airflow control when a single model fails, thus improving the reliability and stability of the constant airflow control system and enhancing the user experience.

[0090] Figure 4 This is a structural diagram of a ventilation equipment airflow control device provided in an embodiment of the present invention. This device is suitable for executing the ventilation equipment airflow control method provided in an embodiment of the present invention. Figure 4 As shown, the device may specifically include: The motor parameter acquisition module 401 is used to acquire the motor operating parameters of the ventilation equipment in real time.

[0091] The static pressure range acquisition module 402 is used to acquire the range of static pressure in the duct of the ventilation equipment based on the motor operating parameters and a pre-built static pressure range classifier.

[0092] The adjustment module 403 is used to adjust the motor control parameters of the ventilation equipment based on the range of static pressure in the air duct and the target value of the control air volume, so that the real-time ventilation volume of the ventilation equipment follows the target value of the control air volume.

[0093] This invention provides a ventilation equipment airflow control method, device, ventilation equipment, and storage medium. By acquiring the motor operating parameters of the ventilation equipment in real time, and using a pre-built static pressure range classifier based on the motor operating parameters to obtain the static pressure range within the ventilation equipment's duct, the motor control parameters of the ventilation equipment are adjusted based on the static pressure range within the duct and the target airflow value. This allows the real-time ventilation volume of the ventilation equipment to follow the target airflow value, enabling constant airflow control of the ventilation equipment without relying on static pressure sensors, reducing equipment and maintenance costs, and improving operational reliability and environmental adaptability.

[0094] Optionally, the ventilation equipment air volume control device provided in this embodiment of the invention further includes: a future air volume prediction value acquisition module, used to obtain a first air volume prediction value based on the motor operating parameters through a pre-built polynomial air volume prediction model before determining the motor control parameters of the ventilation equipment based on the static pressure range in the air duct and the target value of the control air volume, and to determine the future air volume prediction value based on the first air volume prediction value.

[0095] Optionally, the aforementioned adjustment module 403 can be specifically used to: determine the adjustment command value of the motor speed based on the future air volume prediction value and the control air volume target value; determine the adjustment compensation value of the motor speed based on the static pressure range in the air duct; determine the adjustment target value of the motor speed based on the adjustment command value and the adjustment compensation value of the motor speed; and adjust the motor speed based on the adjustment target value of the motor speed.

[0096] Optionally, the aforementioned adjustment module 403 can be specifically used to determine the adjustment compensation value of the motor speed based on the range of static pressure in the air duct and the pre-determined mapping relationship between the range of static pressure in the air duct and the corresponding adjustment compensation value.

[0097] Optionally, the aforementioned adjustment module 403 can be specifically used to: determine the air volume prediction calibration value based on the range of static pressure in the duct; determine the adjustment target value of the motor speed based on the future air volume prediction value, the air volume prediction calibration value, and the control air volume target value; and adjust the motor speed based on the adjustment target value of the motor speed.

[0098] Optionally, the polynomial air volume prediction model includes: a second-order polynomial air volume fitting model and a fourth-order Taylor expansion model corresponding to the second-order polynomial air volume fitting model.

[0099] Optionally, the aforementioned future air volume prediction module can be specifically used to obtain the first air volume prediction value based on the motor operating parameters through a fourth-order Taylor expansion model if the motor operating parameters fall within the range of rated operating parameters.

[0100] Optionally, the aforementioned future air volume prediction module can be specifically used to obtain the first air volume prediction value based on the motor operating parameters through a second-order polynomial air volume fitting model if the motor operating parameters do not fall within the range of rated operating parameters.

[0101] Optionally, the aforementioned adjustment module 403 can be specifically used to: obtain a second air volume prediction value based on the static pressure range in the duct and the motor operating parameters through a pre-trained neural network air volume prediction model; determine a future air volume prediction value based on the second air volume prediction value; determine an adjustment target value for the motor speed based on the future air volume prediction value and the control air volume target value; and adjust the motor speed based on the adjustment target value for the motor speed.

[0102] Optionally, the ventilation equipment air volume control device provided in this embodiment of the invention further includes: a prediction weight acquisition module, which is used to determine the prediction weight of the first air volume prediction value and the second air volume prediction value based on the historical first air volume prediction value and the historical second air volume prediction value corresponding to the most recent first duration historical period before determining the future air volume prediction value based on the second air volume prediction value.

[0103] Optionally, the adjustment module 403 can be specifically used to obtain a future air volume prediction value by weighted summation of the first air volume prediction value and the second air volume prediction value based on the prediction weights of the first air volume prediction value and the second air volume prediction value.

[0104] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is merely an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the functional modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0105] This invention also provides a ventilation device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the ventilation device airflow control method provided in any of the above embodiments.

[0106] This invention also provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the ventilation equipment airflow control method provided in any of the above embodiments.

[0107] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the ventilation equipment airflow control method as described in any of the embodiments of this invention.

[0108] The following is for reference. Figure 5 It shows a schematic diagram of the structure of a computer system 500 suitable for implementing the ventilation equipment of the present invention. Figure 5 The ventilation device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0109] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 502 or programs loaded from storage section 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the system 500. The CPU 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0110] The following components are connected to I / O interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to I / O interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 510 as needed so that computer programs read from it can be installed into storage section 508 as needed.

[0111] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by central processing unit (CPU) 501, it performs the functions defined above in the system of this invention.

[0112] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0113] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0114] The modules and / or units described in the embodiments of the present invention can be implemented in software or hardware. The described modules and / or units can also be housed in a processor; for example, a processor can be described as including a motor parameter acquisition module, a static pressure range acquisition module, and an adjustment module. The names of these modules do not necessarily limit the functionality of the module itself.

[0115] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs that, when executed by the device, cause the device to implement a ventilation equipment airflow control method including the following steps: real-time acquisition of motor operating parameters of the ventilation equipment; acquisition of the static pressure range within the ventilation equipment's duct based on the motor operating parameters using a pre-constructed static pressure range classifier; and adjustment of the ventilation equipment's motor control parameters based on the static pressure range within the duct and the target airflow value, so that the real-time ventilation volume of the ventilation equipment follows the target airflow value, wherein the motor control parameters include motor speed.

[0116] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method of controlling the air volume of a ventilation device, characterized by, include: Real-time acquisition of motor operating parameters of ventilation equipment; Based on the motor operating parameters, the static pressure range within the ventilation equipment's duct is obtained using a pre-built static pressure range classifier. as well as The motor control parameters of the ventilation equipment are adjusted based on the static pressure range within the duct and the target air volume value, so that the real-time ventilation volume of the ventilation equipment follows the target air volume value. The motor control parameters include the motor speed.

2. The ventilation equipment airflow control method according to claim 1, characterized in that, Before determining the motor control parameters of the ventilation equipment based on the static pressure range within the duct and the target control air volume, the method further includes: Based on the motor operating parameters, a first air volume prediction value is obtained through a pre-constructed polynomial air volume prediction model, and a future air volume prediction value is determined based on the first air volume prediction value. The process of determining the motor control parameters of the ventilation equipment based on the static pressure range within the duct and the target control air volume includes: The control command value for adjusting the motor speed is determined based on the predicted future air volume and the target control air volume value. The adjustment compensation value of the motor speed is determined based on the range of static pressure in the air duct; The target value for motor speed adjustment is determined based on the master control value and the compensation value for motor speed adjustment; and The motor speed is adjusted based on the target adjustment value of the motor speed.

3. The ventilation equipment air volume control method according to claim 2, characterized by, The adjustment compensation value for determining the motor speed based on the static pressure range within the air duct includes: Based on the range of static pressure within the air duct and the pre-determined mapping relationship between the range of static pressure within the air duct and the corresponding adjustment compensation value, the adjustment compensation value of the motor speed is determined.

4. The ventilation equipment airflow control method according to claim 2, characterized in that, The process of determining the motor control parameters of the ventilation equipment based on the static pressure range within the duct and the target air volume value includes: The predicted air volume calibration value is determined based on the range of static pressure within the air duct. The target adjustment value of the motor speed is determined based on the predicted future air volume, the predicted air volume calibration value, and the target control air volume value; and The motor speed is adjusted based on the target adjustment value of the motor speed.

5. The ventilation equipment airflow control method according to claim 2, characterized in that, The polynomial air volume prediction model includes: a second-order polynomial air volume fitting model and a fourth-order Taylor expansion model corresponding to the second-order polynomial air volume fitting model. The step of obtaining the first predicted air volume value based on the motor operating parameters using a pre-built polynomial air volume prediction model includes: If the motor operating parameters fall within the range of rated operating parameters, the first predicted air volume value is obtained based on the motor operating parameters through the fourth-order Taylor expansion model. If the motor operating parameters do not fall within the range of rated operating parameters, then the first predicted air volume value is obtained based on the motor operating parameters through the second-order polynomial air volume fitting model.

6. The ventilation equipment airflow control method according to claim 1, characterized in that, The process of determining the motor control parameters of the ventilation equipment based on the static pressure range within the duct and the target air volume value includes: Based on the static pressure range within the duct and the motor operating parameters, a second predicted air volume value is obtained through a pre-trained neural network air volume prediction model, and a future predicted air volume value is determined based on the second predicted air volume value. The target value for adjusting the motor speed is determined based on the predicted future air volume and the target control air volume; and The motor speed is adjusted based on the target adjustment value of the motor speed.

7. The ventilation equipment airflow control method according to claim 6, characterized in that, Before determining the future air volume forecast based on the second air volume forecast, the method further includes: The first predicted air volume value is obtained based on the motor operating parameters through a pre-constructed polynomial air volume prediction model. The prediction weights of the first and second air volume prediction values ​​are determined based on the historical first and second air volume prediction values ​​corresponding to the most recent first time period. Determining the future air volume forecast value based on the second air volume forecast value includes: The future air volume prediction value is obtained by weighting and summing the first and second air volume prediction values ​​based on their prediction weights.

8. A ventilation equipment airflow control device, characterized in that, include: The motor parameter acquisition module is used to acquire the motor operating parameters of the ventilation equipment in real time. The static pressure range acquisition module is used to acquire the range of static pressure in the duct of the ventilation equipment based on the motor operating parameters and a pre-built static pressure range classifier. as well as The adjustment module is used to adjust the motor control parameters of the ventilation equipment based on the static pressure range in the air duct and the target value of the control air volume, so that the real-time ventilation volume of the ventilation equipment follows the target value of the control air volume. The motor control parameters include the motor speed.

9. A ventilation device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the ventilation equipment airflow control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the ventilation equipment airflow control method as described in any one of claims 1 to 7.

Images