Public chimney exhaust control method, control device and electronic equipment

Abstract

The application discloses a public flue exhaust control method, a control device and electronic equipment, and relates to the field of public flue exhaust control. The method comprises the following steps: acquiring the actual measured values of the exhaust fan power and the exhaust capacity of each floor in the public flue; establishing a causal effect model between the exhaust fan power and the exhaust capacity according to the actual measured values of the exhaust fan power and the exhaust capacity; determining the to-be-optimized exhaust fan associated with the target floor according to the causal effect model; establishing an exhaust capacity optimization model based on the number of the to-be-optimized exhaust fan, and determining the target power of the to-be-optimized exhaust fan according to the exhaust capacity optimization model. The application analyzes the causal relationship between the exhaust fan power of each floor and the exhaust capacity of a specific floor through modeling, controls the exhaust fan power in a targeted manner, optimizes the exhaust efficiency, reduces energy waste, and improves the comfort of high-rise residential buildings.

Description

Technical Field

[0001] This invention relates to the field of range hood control technology, and in particular to a method, control device and electronic equipment for controlling exhaust ventilation in a public flue. Background Technology

[0002] In modern high-rise buildings, the shared flue system is a crucial facility connecting the kitchens of residents on each floor to the outdoor environment, responsible for discharging cooking fumes and harmful gases. The effective operation of the shared flue system directly impacts residents' quality of life and indoor air quality.

[0003] In existing public flue systems, range hoods are typically controlled using fixed power control, timed control, or pressure-sensing control strategies. Fixed power control operates the range hood at a preset power, ignoring differences in usage between floors and dynamic changes in actual ventilation demand, resulting in low ventilation efficiency and significant energy waste. Timed control turns the range hood on and off according to a fixed schedule, failing to dynamically adjust the exhaust volume based on actual ventilation needs, leading to low ventilation efficiency. Pressure-sensing control adjusts the range hood power based on pressure changes within the flue, but this method is typically slow and struggles to precisely control the exhaust volume, impacting both ventilation efficiency and effectiveness. Summary of the Invention

[0004] This invention provides a public flue exhaust control method, control device, and electronic device to solve the problem that existing public flue range hood control strategies cannot dynamically adjust the exhaust volume according to the differences in usage between floors and actual exhaust demand, resulting in low exhaust efficiency, and can optimize exhaust efficiency.

[0005] According to one aspect of the present invention, a method for controlling exhaust ventilation in a public flue is provided, comprising: acquiring measured values ​​of range hood power and exhaust volume for each floor within the public flue; establishing a causal effect model between range hood power and exhaust volume based on the measured values ​​of range hood power and exhaust volume; determining the range hoods to be optimized associated with the target floor based on the causal effect model; establishing an exhaust volume optimization model based on the number of range hoods to be optimized; and determining the target power of the range hoods to be optimized based on the exhaust volume optimization model.

[0006] Optionally, a causal effect model between range hood power and exhaust volume is established based on the measured values ​​of range hood power and exhaust volume. This includes: using the measured values ​​of range hood power on all floors except the characteristic floor as input parameters and the predicted values ​​of range hood power on the characteristic floor as output parameters to establish a treatment variable prediction model; using the measured values ​​of range hood power on all floors as input parameters and the predicted values ​​of exhaust volume on the target floor as output parameters to establish an outcome variable prediction model; and establishing a causal effect model based on the treatment variable prediction model and the outcome variable prediction model.

[0007] Optionally, a causal effect model is established based on the treatment variable prediction model and the outcome variable prediction model, including: calculating the treatment variable residual based on the measured value of the range hood power of the characteristic floor and the predicted value of the treatment variable prediction model; calculating the outcome variable residual based on the measured value of the exhaust volume of the target floor and the predicted value of the outcome variable prediction model; and establishing a causal effect model based on the treatment variable residual and the outcome variable residual.

[0008] Optionally, a causal effect model between the range hood power and exhaust volume is established based on the measured values ​​of the range hood power and exhaust volume, including: establishing a training set and a test set based on the measured values ​​of the range hood power and exhaust volume; and performing cross-validation on the causal effect model based on the training set and the test set until the causal effect model meets the prediction performance conditions.

[0009] Optionally, an exhaust volume optimization model is established based on the number of range hoods to be optimized, and the target power of the range hoods to be optimized is determined according to the exhaust volume optimization model, including: using the power of the range hoods to be optimized as optimization parameters, using the predicted exhaust volume of the target floor as optimization results, and establishing an exhaust volume optimization model; and / or, using the measured power of the range hoods on each floor other than the range hoods to be optimized as fixed parameters, using the power of the range hoods to be optimized as optimization parameters, using the predicted exhaust volume of the target floor as optimization results, and establishing an exhaust volume optimization model.

[0010] Optionally, the measured power and exhaust volume of the range hoods on each floor within the public flue can be obtained, including performing at least one of the following data processing strategies on the measured power and exhaust volume of the range hoods: data cleaning, data denoising, and data standardization.

[0011] Optionally, the public flue exhaust control method also includes: acquiring environmental parameters of each floor within the public flue; and optimizing the causal effect model based on the environmental parameters.

[0012] Optionally, the causal effect model is optimized based on environmental parameters, including: using the measured power values ​​of the range hoods on all floors except the characteristic floor and environmental parameters as input parameters, and the predicted power values ​​of the range hoods on the characteristic floor as output parameters, to establish an optimized treatment variable prediction model; using the measured power values ​​of the range hoods on all floors and environmental parameters as input parameters, and the predicted exhaust volume of the target floor as output parameters, to establish an optimized outcome variable prediction model; and establishing a causal effect model based on the optimized treatment variable prediction model and outcome variable prediction model.

[0013] According to another aspect of the present invention, a public flue exhaust control device is provided, comprising: a data acquisition module for acquiring measured values ​​of range hood power and exhaust volume of each floor in the public flue; a causal analysis module for establishing a causal effect model between range hood power and exhaust volume based on the measured values ​​of range hood power and exhaust volume; a calculation module for determining the range hoods to be optimized associated with the target floor based on the causal effect model; and an optimization module for establishing an exhaust volume optimization model based on the number of range hoods to be optimized, and determining the target power of the range hoods to be optimized based on the exhaust volume optimization model.

[0014] According to another aspect of the present invention, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the above-described public flue exhaust control method.

[0015] The technical solution of this invention establishes a causal effect model between range hood power and exhaust volume by acquiring measured values ​​of range hood power and exhaust volume for each floor in a public flue. Based on the causal effect model, it determines the range hoods to be optimized associated with the target floor. After determining the range hoods to be optimized, it establishes an exhaust volume optimization model for the target floor based on the number of range hoods to be optimized, and determines the target power of the range hoods to be optimized based on the exhaust volume optimization model. This solves the problem that existing public flue range hood control strategies cannot dynamically adjust the exhaust volume according to differences in usage between floors and actual exhaust demand, resulting in low exhaust efficiency. It can respond promptly to the actual exhaust demand of each floor, optimize the exhaust efficiency of the public flue, and reduce energy waste from range hoods.

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

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

[0018] Figure 1 A flowchart of a public flue exhaust control method provided in an embodiment of the present invention;

[0019] Figure 2 This is a schematic diagram of a public flue provided in an embodiment of the present invention;

[0020] Figure 3 A flowchart illustrating a modeling method for a causal effect model provided in an embodiment of the present invention;

[0021] Figure 4 A flowchart illustrating another modeling method for a causal effect model provided in an embodiment of the present invention;

[0022] Figure 5 A flowchart of another public flue exhaust control method provided in an embodiment of the present invention;

[0023] Figure 6 A flowchart illustrating another public flue exhaust control method provided in this embodiment of the invention;

[0024] Figure 7 This is a schematic diagram of the structure of a public flue exhaust control device provided in an embodiment of the present invention;

[0025] Figure 8 This is a schematic diagram of the structure of an electronic device that implements the public flue exhaust control method of the present invention.

[0026] Figure label:

[0027] 101. Data acquisition module; 102. Causal analysis module; 103. Calculation module; 104. Optimization module; 10. Electronic device; 11. Processor; 12. ROM (Read-Only Memory); 13. RAM (Random Access Memory); 14. Bus; 15. I / O interface; 16. Input unit; 17. Output unit; 18. Storage unit; 19. Communication unit. Detailed Implementation

[0028] 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.

[0029] It should be noted that the terms "target floor," "characteristic floor," etc., used 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.

[0030] Figure 1 This is a flowchart of a public flue exhaust control method provided in an embodiment of the present invention. This embodiment is applicable to the application scenario of power regulation of range hoods in public flue systems of high-rise buildings.

[0031] Figure 2 This is a schematic diagram of a public flue provided in an embodiment of the present invention. Taking an L-story building (such as the 1st floor, ..., the i-th floor, the i+1th floor, ..., the L-th floor from bottom to top) as an example, it exemplarily illustrates the structure of a public flue in a high-rise building.

[0032] See Figure 1 and Figure 2 As shown, the public flue exhaust control method of this application specifically includes:

[0033] S1: Obtain the measured power and exhaust volume of the range hoods on each floor within the common flue.

[0034] Here, the range hood power refers to the output power of the motor when the range hood is performing its fume extraction operation. In this embodiment, the measured power values ​​of the range hoods on each floor can be obtained through real-time communication with the range hood controller. See [link / reference] Figure 2 As shown, the measured power of the range hood on the first floor is denoted as P1, the measured power of the range hood on the second floor is denoted as P2, ..., and the measured power of the range hood on the i-th floor is denoted as P... i ..., the measured power of the range hood on the Lth floor is denoted as P. L.

[0035] Exhaust volume refers to the exhaust volume of each floor within the common flue. In this embodiment, detection elements (such as flow sensors or wind speed sensors) can be installed at the connection points between the common flue and each floor to collect the measured exhaust volume values ​​for each floor. See also Figure 2 As shown, the measured exhaust volume of the first floor is denoted as Q1, the measured exhaust volume of the second floor is denoted as Q2, ..., and the measured exhaust volume of the i-th floor is denoted as Q. i ..., the measured exhaust volume of the Lth floor is denoted as Q. L .

[0036] Optionally, the measured power and exhaust volume of the range hoods on each floor within the public flue are obtained, including performing at least one of the following data processing strategies on the measured power and exhaust volume: data cleaning, data denoising, and data standardization. Data cleaning refers to processing and filtering the measured values ​​to ensure the accuracy, completeness, and consistency of the data. Typically, data cleaning methods include, but are not limited to, handling missing values, outliers, and deleting duplicate values. Data denoising refers to removing interfering data from the measured values, which may be caused by measurement errors, equipment malfunctions, or other external factors. Typically, data denoising methods include, but are not limited to, mean filtering, median filtering, wavelet transform, connected graph methods, and support vector machines. Data standardization refers to transforming the measured values ​​from their original range to a specific range. Typically, data standardization includes, but is not limited to, normalization.

[0037] Specifically, after the exhaust operation is started in the public flue, the power data of all range hoods in the high-rise building is collected. The power data of each floor is cleaned, denoised, or standardized. The final power data is recorded as the measured power value of the range hood on the corresponding floor. At the same time, the exhaust volume data of all floors is collected. The exhaust volume data of each floor is cleaned, denoised, or standardized. The final exhaust volume data is recorded as the measured exhaust volume value on the corresponding floor.

[0038] S2: Establish a causal effect model between range hood power and exhaust volume based on the measured values ​​of range hood power and exhaust volume.

[0039] The causal effect model is a model established based on the causal relationship between the power of the range hoods on each floor and the exhaust volume of the target floor. In this embodiment, the causal effect model can be established based on Double Machine Learning (DML) technology. This DML technology is an algorithm that combines machine learning models to infer causal relationships.

[0040] Specifically, in the causal effect model of this application, the power of the range hood on each floor is used as the processing variable (i.e., the independent variable of the model), and the exhaust volume of the target floor is used as the outcome variable (i.e., the dependent variable of the model). A regression prediction model is established based on the residuals between the predicted and measured values ​​of the processing variable and the residuals between the predicted and measured values ​​of the outcome variable. The model is optimized through machine learning to calculate the causal relationship between the power of the range hood on each floor and the exhaust volume of the target floor. The target floor is the floor that needs to be configured based on the actual range hood control requirements. In this embodiment, the target floor can be configured based on a specific control sequence or by user customization.

[0041] S3: Determine the range hoods to be optimized that are associated with the target floor based on the causal effect model.

[0042] In this context, the range hood to be optimized refers to one that has a relatively significant impact on the exhaust volume of the target floor. Correspondingly, range hoods with a relatively small impact on the exhaust volume of the target floor are defined as those not to be optimized. In this embodiment, only the power of the range hood to be optimized needs to be adjusted, while the power of the range hoods not to be optimized remains unchanged.

[0043] Specifically, the measured exhaust volume of the target floor can be substituted into the causal effect model. The range hoods whose influence on the change in the outcome variable is significantly affected by the processing variable can be selected. For example, the power of the range hood on any floor can be substituted into the causal effect model trained in the above steps. If the model calculation result is greater than or equal to the influence threshold, the range hood on that floor is identified as a range hood to be optimized; if the model calculation result is less than the influence threshold, the range hood on that floor is identified as a non-optimizable range hood. In this embodiment, the rate of change threshold can be established based on the degree of change in the exhaust volume of the target floor caused by an increase of one unit in the range hood power, and its value is not limited.

[0044] For example, if a building with a shared exhaust duct has a total of L floors, and the causal effect model calculates n range hoods to be optimized, then the number of non-optimized range hoods is Ln.

[0045] S4: Establish an exhaust volume optimization model based on the number of range hoods to be optimized, and determine the target power of the range hoods to be optimized based on the exhaust volume optimization model.

[0046] Among them, the exhaust volume optimization model is a regression prediction model established by taking the power of the range hood to be optimized as the optimization parameter and the exhaust volume of the target floor as the optimization target.

[0047] In some embodiments, an exhaust volume optimization model is established based on the number of range hoods to be optimized, and the target power of the range hoods to be optimized is determined according to the exhaust volume optimization model. This includes: using the power of the range hoods to be optimized as optimization parameters, using the predicted exhaust volume of the target floor as the optimization result, and establishing an exhaust volume optimization model. Specifically, if L floors are defined in the building where the common exhaust duct is located, and n range hoods to be optimized are identified through a causal effect model, the power of the n range hoods to be optimized is used as optimization parameters, denoted as p1', p2', ..., p n The predicted exhaust volume of the target floor is taken as the optimization result and denoted as Q. j Then, establish the exhaust volume optimization model as shown in Formula 1:

[0048]

[0049] Among them, y j (p'1, p'2, ..., p') n Q represents the regression prediction function for the exhaust volume of the j-th floor based on n unknown oil fume probabilities; min P represents the lower limit threshold of the range hood's exhaust volume. max This indicates the upper limit threshold of the range hood's power.

[0050] In other embodiments, an exhaust volume optimization model is established based on the number of range hoods to be optimized, and the target power of the range hoods to be optimized is determined according to the exhaust volume optimization model. This includes: using the measured power values ​​of the range hoods on each floor other than the range hoods to be optimized as fixed parameters, using the power of the range hoods to be optimized as optimization parameters, and using the predicted exhaust volume value of the target floor as the optimization result to establish an exhaust volume optimization model. Specifically, if L floors are defined in the building where the common exhaust duct is located, and n range hoods to be optimized are identified through the causal effect model, the power of the n range hoods to be optimized is used as optimization parameters, denoted as p1', p2', ..., p n Let m (L=m+n) measured power values ​​of the range hoods to be optimized be used as fixed parameters, denoted as g1, g2, ..., g m The predicted exhaust volume of the target floor is used as the optimization result, denoted as Q. j Then, establish the air volume optimization model for the target floor as shown in Formula 2:

[0051]

[0052] Among them, y j (g1,g1,…,g m ,p'1,p'2,…,p' n Q represents the regression prediction function for the exhaust volume of the j-th floor, established based on the power of the range hoods on all floors; minP represents the lower limit threshold of the range hood's exhaust volume. max Indicates the upper limit threshold of the range hood's power.

[0053] Specifically, after the exhaust operation is initiated in the public flue, power data of all range hoods and exhaust volume data of all floors in the high-rise building are collected, and the measured power and exhaust volume values ​​of the range hoods are recorded. A causal effect model is established based on the causal relationship between the power of the range hoods on each floor and the exhaust volume of the target floor. The aforementioned measured power and exhaust volume values ​​of the range hoods are substituted into the causal effect model for training and testing. After the causal effect model is trained, the measured exhaust volume value of the target floor is substituted into the causal effect model, and n range hoods to be optimized are selected whose influence on the change of the result variable is significant. Referring to Formula 1 or Formula 2 above, an exhaust volume optimization model for the target floor is established, and combined with a genetic algorithm optimization method, the target power of the n range hoods to be optimized is found, thereby controlling the power of the range hoods to be optimized to reach the corresponding target power.

[0054] Therefore, by modeling and analyzing the causal relationship between the power of range hoods on each floor and the exhaust volume of a specific floor, the power of range hoods that have a significant impact on the exhaust volume of the target floor can be controlled in a targeted manner. This solves the problem that existing range hood control strategies for public exhaust ducts cannot dynamically adjust the exhaust volume according to the differences in usage between floors and the actual exhaust demand, resulting in low exhaust efficiency. This approach can respond promptly to the actual exhaust demand of each floor, optimize the exhaust efficiency of public exhaust ducts, reduce energy waste, and improve the comfort of living in high-rise buildings.

[0055] Figure 3 A flowchart illustrating a modeling method for a causal effect model provided in an embodiment of the present invention is shown below. Figure 1 Based on the illustrated embodiment, a specific implementation method for establishing a causal effect model is shown as an example. See also Figure 3 As shown, in step S2 above, a causal model between the range hood power and exhaust volume is established based on the measured values ​​of the range hood power and exhaust volume. This specifically includes the following steps:

[0056] S201: Use the measured power values ​​of the range hoods on all floors except the characteristic floor as input parameters, and the predicted power values ​​of the range hoods on the characteristic floor as output parameters to establish a processing variable prediction model.

[0057] The characteristic floor refers to any floor within the building where the common smoke duct is located. See also Figure 2 As shown, if the building containing the common exhaust duct has a total of L floors, and the i-th floor is defined as the characteristic floor, then the processing variable prediction model is based on the measured power values ​​of the range hoods on all floors other than the characteristic floor (e.g., the i-th floor) (e.g., P1, P2, ..., P...). i-1 P i+1..., P L Calculate the predicted power P of the range hood for a characteristic floor (e.g., the i-th floor). i For example, taking an L-story building as an example, a predictive model for the processing variables can be established as shown in Formula 3:

[0058] P i '=z i (W i )=z i (P1,P2,……,P i-1 ,P i+1 ,……,P L ), 1≤i≤L (Formula 3)

[0059] Among them, z i (W i ) indicates based on W i A regression prediction model for the power of range hoods on a specific floor (e.g., the i-th floor) was established; W i This represents the measured power values ​​of the range hoods on all floors except the characteristic floor (e.g., the i-th floor) (P1, P2, ..., P...). i-1 P i+1 ..., P L ); P i ' represents the predicted power of the range hood on the characteristic floor (e.g., the i-th floor).

[0060] S202: Use the measured power of the range hoods on all floors as input parameters and the predicted exhaust volume of the target floor as output parameters to establish a predictive model for the result variables.

[0061] The target floor is either based on a specific control timing sequence or a user-defined configuration. See also Figure 2 As shown, if the building containing the common exhaust duct has a total of L floors, and the j-th floor is defined as the target floor, then the outcome variable prediction model is based on the measured power values ​​of the range hoods on all floors (e.g., P1, P2, ..., P...). j-1 P j P j+1 ..., P L Calculate the predicted exhaust volume Q for the target floor (e.g., floor j). j For example, taking an L-story building as an example, a predictive model for the outcome variables can be established as shown in Formula 4:

[0062] Q' j =y j (W)=y j (P1,P2,……,P L (Formula 4)

[0063] Among them, y j(W) represents the regression prediction model of the range hood power for the target floor (e.g., the j-th floor) based on W; W represents the measured power values ​​of the range hoods on all floors (P1, P2, ..., Pj). L );Q' j This represents the predicted exhaust volume for the target floor (e.g., floor j).

[0064] S203: Establish a causal effect model based on the treatment variable prediction model and the outcome variable prediction model.

[0065] In this embodiment, the processing variable prediction model and the outcome variable prediction model are based on a self-learning model built using dual machine learning techniques.

[0066] In some embodiments, a causal effect model is established based on a treatment variable prediction model and an outcome variable prediction model, including: calculating the treatment variable residual based on the measured value of the range hood power of the characteristic floor and the predicted value of the treatment variable prediction model; calculating the outcome variable residual based on the measured value of the exhaust volume of the target floor and the predicted value of the outcome variable prediction model; and establishing a causal effect model based on the treatment variable residual and the outcome variable residual.

[0067] Specifically, combining Formulas 3 and 4 above, the residual of the processing variable is equal to Zz. i (W i The residual of the resulting variable is equal to Yy. j (W), the causal effect model θ(W) is solved by optimizing the following formula five. i ):

[0068] Yy j (W)=θ(W i )*[Zz i (W i (Formula 5)

[0069] Where ∈ represents random error; θ(W i ) indicates based on variable W i The established causal effect function between the treatment variable and the structural variable has the physical meaning of W. i Under the given environment, the degree of change in the predicted value of the result variable Y (exhaust volume of the target floor) caused by increasing the processing variable Z (measured power of the range hood on the i-th characteristic floor) by one unit.

[0070] Therefore, the technical solution of the present invention constructs a processing variable prediction model and an outcome variable prediction model based on machine learning algorithms, and establishes a causal effect model between the range hood power of each floor and the exhaust volume of a specific floor based on the residual between the model prediction value and the measured value. This can accurately identify the floors that have a greater impact on the target floor, realize directional control of the range hood, and avoid low power adjustment accuracy caused by power regulation of all floors.

[0071] Figure 4 A flowchart of another causal effect modeling method provided in an embodiment of the present invention is shown. Figure 1 Based on the illustrated embodiment, a specific implementation method for training a causal effect model is exemplarily shown. See also Figure 4 As shown, in step S2 above, establishing a causal effect model between the range hood power and exhaust volume based on the measured values ​​of the range hood power and exhaust volume also includes:

[0072] S204: Establish training and testing sets based on the measured power and exhaust volume of the range hood.

[0073] The data in the training set is used to train the causal effect model; the data in the test set is used to validate the causal effect model. In this embodiment, the measured values ​​of range hood power and exhaust volume of all floors at the same sampling time form an association array, and each training set includes at least multiple association arrays obtained by continuous sampling within a specific time period.

[0074] Specifically, any machine learning algorithm can be used to process the input features (such as measured range hood power) and output features (such as predicted exhaust volume or predicted range hood power). For example, any standardization algorithm can be used to normalize the input and output features to make them suitable for the input / output requirements of a neural network model. Clustering or equal partitioning methods can be used to divide the processed data into k subsets. After determining the input and output features, a regression model with one or more LSTM layers followed by densely connected layers is constructed as the causal effect model. The input layer data dimension of this regression model is equal to the number of input features (such as measured range hood power for all floors or measured range hood power for all floors except the feature floor), and the output layer data dimension is equal to the number of output features (such as predicted exhaust volume or predicted range hood power). Preferably, one or two LSTM layers are used in the causal effect model. Preferably, the number of neurons in any LSTM layer in the causal effect model is greater than or equal to 10 and less than or equal to 1024.

[0075] S205: Cross-validate the causal effect model based on the training and test sets until the causal effect model meets the prediction performance conditions.

[0076] The prediction performance condition is a judgment condition established based on the stability and accuracy of the prediction model. For example, when the output parameters of the prediction model converge and the residual between the model's predicted value and the actual value is less than a preset residual threshold, the causal effect model is judged to meet the prediction performance condition.

[0077] Specifically, cross-validation was performed on the treatment variable prediction model and the outcome variable prediction model, respectively. During cross-validation, a subset of arrays from k subsets of the dataset was used alternately as the test set, and the remaining arrays were used as the training set. Specifically, in the treatment variable prediction model z... i (W i The training and testing sets are used as input features, which are the measured power values ​​of the range hoods on each floor except the feature floor (e.g., the i-th floor) (e.g., P1, P2, ..., P...). i-1 P i+1 ..., P L The output feature is the predicted power of the range hood for a specific floor (e.g., the i-th floor). In the processing variable prediction model z... i (W i After training, evaluate the model's predictive performance, such as stability and accuracy. If the processing variable is the predictive model z... i (W i If the prediction results of the processing variable z are unstable or inaccurate, adjust the parameters of the machine learning algorithm and retrain until the prediction model z is fully processed. i (W i The model that ultimately achieves the predictive performance condition is used as the optimal predictive model for the treatment variable, and this model is then used to calculate the predicted values ​​for the treatment variable.

[0078] Accordingly, in the outcome variable prediction model y j The training and testing sets of (W) contain the input features as the measured power values ​​of the range hoods on all floors (e.g., P1, P2, ..., P...). j-1 P j P j+1 ..., P L The output feature is the predicted exhaust volume for the target floor (e.g., floor j). In the outcome variable prediction model y... j (W) After training, evaluate the model's predictive performance, such as stability and accuracy. If the outcome variable predicts the model y... j If the prediction results of (W) are unstable or the accuracy is insufficient, adjust the parameters of the machine learning algorithm and retrain until the prediction model of the outcome variable y is established. j(W) Once the predictive performance condition is met, the model that finally meets the predictive performance condition is used as the best predictive model for the outcome variable and is used to calculate the predicted value of the outcome variable.

[0079] Therefore, the technical solution of the present invention, by constructing a test set and a training set to cross-validate the causal effect model, is conducive to improving the stability and accuracy of the model and improving the control precision of exhaust gas regulation based on the causal effect model.

[0080] Figure 5 A flowchart illustrating another public flue exhaust control method provided in an embodiment of the present invention. See also... Figure 5 As shown, in conjunction with the above embodiments, the public flue exhaust control method of this application specifically includes the following steps:

[0081] S501: Start.

[0082] S502: Collects air volume and range hood power data for each floor.

[0083] S503: Perform data preprocessing.

[0084] In this embodiment, data preprocessing includes, but is not limited to, data cleaning, data denoising, and data standardization.

[0085] S504: Divide the preprocessed data into k subsets.

[0086] S505: Initialize the regression prediction model.

[0087] In this embodiment, a regression model is established based on a machine learning model.

[0088] S506: Iterate through k subsets of data.

[0089] S507: Use a portion of the array as the test set and the rest as the training set.

[0090] S508: Regression prediction model on the training set, and evaluate regression prediction model on the test set.

[0091] S509: Record the model evaluation results.

[0092] S510: Determine whether k iterations have been completed.

[0093] If k iterations are completed, proceed to step S511; if k iterations are not completed, proceed to step S506.

[0094] S511: Determine whether the model is stable and accurate.

[0095] If the model is stable and accurate, proceed to step S513; if the model is unstable or inaccurate, proceed to step S512.

[0096] S512: Adjust the parameters of the regression prediction model.

[0097] After adjusting the model parameters, return to step S506.

[0098] S513: Determine the optimal regression prediction model.

[0099] S514: Retrain the regression prediction model.

[0100] S515: Obtain the regression prediction model of the exhaust volume of the target floor and the power of the range hoods on each floor, as well as the regression prediction model of the power of the range hoods on each floor and the power of the range hoods on other floors.

[0101] S516: Calculate the residuals between the predicted and measured values ​​of the regression prediction model, and derive the causal effect model between the exhaust volume of the target floor and the power of the range hoods on each floor based on the residuals.

[0102] S517: Identify the range hoods to be optimized that are associated with the target floor.

[0103] S518: Determine the optimization parameters and target parameters.

[0104] In this embodiment, the optimization parameter can be the power of the range hood to be optimized. The target parameter is the exhaust volume of the target floor.

[0105] S519: Establish an exhaust volume optimization model.

[0106] S520: Execute the optimization algorithm.

[0107] S521: Obtain the target power of the range hood to be optimized.

[0108] S522: End.

[0109] Figure 6 A flowchart of another public flue exhaust control method provided in this embodiment of the invention is shown. Figure 1 Based on the illustrated embodiment, the modeling accuracy of the causal effect model is optimized by introducing environmental parameters. See also Figure 6 As shown, the public flue exhaust control method of this application includes the following steps:

[0110] S601: Obtain the measured power and exhaust volume of the range hoods on each floor within the common flue.

[0111] S602: Establish a causal effect model between range hood power and exhaust volume based on the measured values ​​of range hood power and exhaust volume.

[0112] S603: Obtain environmental parameters for each floor within the public flue.

[0113] In this embodiment, environmental parameters refer to parameters that affect the exhaust airflow and exhaust resistance. Typically, environmental parameters include, but are not limited to, at least one of the following: atmospheric pressure, temperature, and humidity.

[0114] S604: Optimize the causal effect model based on environmental parameters.

[0115] In this embodiment, optimizing the causal effect model based on environmental parameters includes: using environmental parameters as input parameters to train at least one prediction model in the causal effect model, such as a treatment variable prediction model or an outcome variable prediction model.

[0116] Optionally, the causal effect model is optimized based on environmental parameters, including: using the measured power values ​​of the range hoods on all floors except the characteristic floor and environmental parameters as input parameters, and the predicted power values ​​of the range hoods on the characteristic floor as output parameters, to establish an optimized treatment variable prediction model; using the measured power values ​​of the range hoods on all floors and environmental parameters as input parameters, and the predicted exhaust volume of the target floor as output parameters, to establish an optimized outcome variable prediction model; and establishing a causal effect model based on the optimized treatment variable prediction model and outcome variable prediction model.

[0117] Specifically, see Figure 2 As shown, if the building containing the public flue has a total of L floors, the i-th floor is defined as the characteristic floor, and the environmental parameter is defined as η, then the prediction model of the processing variables optimized based on the environmental parameter is as shown in Formula 6:

[0118] P i '=z i (W i )

[0119] =z i (P1,P2,……,P i-1 ,P i+1 ,……,P L ,η1,η2,……,η i-1 ,η i+1 ,……,η L ), 1≤i≤L

[0120] (Formula Six)

[0121] Among them, z i (W i ) indicates based on W i A regression prediction model for the power of range hoods on a specific floor (e.g., the i-th floor) was established; W i This represents the measured power values ​​of the range hoods on all floors except the characteristic floor (e.g., the i-th floor) (P1, P2, ..., P...). i-1 Pi+1 ..., P L ) and environmental parameters (η1, η2, ..., η i-1 ,η i+1 ,……,η L ); P i ' represents the predicted power of the range hood on the characteristic floor (e.g., the i-th floor).

[0122] The prediction model for the outcome variables based on environmental parameter optimization is shown in Formula 7:

[0123] Q' j =y j (W)=y j (P1,P2,……,P L ,η1,η2,……,η L (Formula 7)

[0124] Among them, y j (W) represents the regression prediction model of the range hood power for the target floor (e.g., the j-th floor) based on W; W represents the measured power values ​​of the range hoods on all floors (P1, P2, ..., Pj). L ) and environmental parameters (η1, η2, ..., η L );Q' j This represents the predicted exhaust volume for the target floor (e.g., floor j).

[0125] Therefore, the technical solution of the present invention, by introducing environmental parameters, expands the dimension of the model input parameters, reduces the impact of environmental parameter changes on the causal effect between the range hood power of each floor and the exhaust volume of a specific floor, optimizes the modeling accuracy of the causal effect model, and improves the control accuracy of exhaust regulation based on the causal effect model.

[0126] Based on the above-mentioned inventive concept, the present invention also provides a public flue exhaust control device, which can execute the public flue exhaust control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0127] Figure 7 This is a schematic diagram of a public flue exhaust control device provided in an embodiment of the present invention. Figure 7 As shown, the public flue exhaust control device of this application includes: a data acquisition module 101, a causal analysis module 102, a calculation module 103, and an optimization module 104.

[0128] The system includes a data acquisition module 101, which acquires the measured power and exhaust volume of range hoods on each floor within the public flue; a causal analysis module 102, which establishes a causal effect model between range hood power and exhaust volume based on the measured power and exhaust volume; a calculation module 103, which determines the range hoods to be optimized on the target floor based on the causal effect model; and an optimization module 104, which establishes an exhaust volume optimization model based on the number of range hoods to be optimized and determines the target power of the range hoods to be optimized based on the exhaust volume optimization model.

[0129] Optionally, the causal analysis module 102 is configured to: use the measured power values ​​of the range hoods on all floors except the characteristic floor as input parameters and the predicted power values ​​of the range hoods on the characteristic floor as output parameters to establish a processing variable prediction model; use the measured power values ​​of the range hoods on all floors as input parameters and the predicted exhaust volume of the target floor as output parameters to establish an outcome variable prediction model; and establish a causal effect model based on the processing variable prediction model and the outcome variable prediction model.

[0130] Optionally, the causal analysis module 102 is further configured to: calculate the residual of the treatment variable based on the measured value of the range hood power of the characteristic floor and the predicted value of the treatment variable prediction model; calculate the residual of the result variable based on the measured value of the exhaust volume of the target floor and the predicted value of the result variable prediction model; and establish a causal effect model based on the residual of the treatment variable and the residual of the result variable.

[0131] Optionally, the causal analysis module 102 is also configured to: establish a training set and a test set based on the measured values ​​of the range hood power and exhaust volume; and perform cross-validation on the causal effect model based on the training set and the test set until the causal effect model meets the prediction performance conditions.

[0132] Optionally, the optimization module 104 is configured to: use the range hood power of the range hood to be optimized as the optimization parameter, use the predicted exhaust volume of the target floor as the optimization result, and establish an exhaust volume optimization model; and / or, use the measured power values ​​of the range hoods on each floor other than the range hood to be optimized as fixed parameters, use the range hood power of the range hood to be optimized as the optimization parameter, use the predicted exhaust volume of the target floor as the optimization result, and establish an exhaust volume optimization model.

[0133] Optionally, the data acquisition module 101 is configured to perform at least one of the following data processing strategies on the measured power and exhaust volume of the range hood: data cleaning, data denoising, and data standardization.

[0134] Optionally, the causal analysis module 102 is also configured to: acquire environmental parameters of each floor in the public flue, and optimize the causal effect model based on the environmental parameters.

[0135] Optionally, the causal analysis module 102 is further configured to: use the measured power values ​​of the range hoods on all floors except the characteristic floor and environmental parameters as input parameters, and the predicted power values ​​of the range hoods on the characteristic floor as output parameters, to establish an optimized processing variable prediction model; use the measured power values ​​of the range hoods on all floors and environmental parameters as input parameters, and the predicted exhaust volume of the target floor as output parameters, to establish an optimized outcome variable prediction model; and establish a causal effect model based on the optimized processing variable prediction model and the outcome variable prediction model.

[0136] According to another aspect of the present invention, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the above-described public flue exhaust control method.

[0137] Figure 8 This is a schematic diagram of the structure of an electronic device for implementing the public flue exhaust ventilation control method of this invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0138] like Figure 8 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0139] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0140] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the public flue exhaust control method described above.

[0141] In some embodiments, the above-described public flue exhaust control method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the public flue exhaust control method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the above-described public flue exhaust control method by any other suitable means (e.g., by means of firmware).

[0142] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0143] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0144] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0145] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0146] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0147] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0148] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0149] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for controlling exhaust ventilation in a public flue, characterized in that, include: Obtain the measured power and exhaust volume of the range hoods on each floor within the public flue. A causal effect model between range hood power and exhaust volume is established based on the measured values ​​of range hood power and exhaust volume. The step of establishing a causal effect model between range hood power and exhaust volume based on the measured power and exhaust volume of the range hood includes: using the measured power of the range hoods on all floors except the characteristic floor as input parameters and the predicted power of the range hoods on the characteristic floor as output parameters to establish a processing variable prediction model; using the measured power of the range hoods on all floors as input parameters and the predicted exhaust volume of the target floor as output parameters to establish an outcome variable prediction model; and establishing the causal effect model based on the processing variable prediction model and the outcome variable prediction model. The range hoods to be optimized are determined based on the causal effect model and their association with the target floor. An exhaust volume optimization model is established based on the number of range hoods to be optimized, and the target power of the range hoods to be optimized is determined according to the exhaust volume optimization model.

2. The public flue exhaust control method according to claim 1, characterized in that, The establishment of the causal effect model based on the treatment variable prediction model and the outcome variable prediction model includes: The residual of the processing variable is calculated based on the measured power of the range hood on the characteristic floor and the predicted value of the processing variable prediction model. The residual of the result variable is calculated based on the measured value of the exhaust volume of the target floor and the predicted value of the result variable prediction model; The causal effect model is established based on the residuals of the processing variables and the residuals of the outcome variables.

3. The public flue exhaust ventilation control method according to claim 1, characterized in that, The step of establishing a causal effect model between the range hood power and exhaust volume based on the measured power value and the measured exhaust volume value includes: A training set and a test set were established based on the measured power and exhaust volume of the range hood. The causal effect model is cross-validated based on the training set and the test set until the causal effect model meets the prediction performance conditions.

4. The public flue exhaust ventilation control method according to claim 1, characterized in that, The step of establishing an exhaust volume optimization model based on the number of range hoods to be optimized, and determining the target power of the range hoods to be optimized based on the exhaust volume optimization model, includes: Using the range hood power to be optimized as the optimization parameter, and the predicted exhaust volume of the target floor as the optimization result, an exhaust volume optimization model is established; and / or, The measured power values ​​of the range hoods on each floor, excluding the range hood to be optimized, are used as fixed parameters. The power of the range hood to be optimized is used as the optimization parameter. The predicted exhaust volume of the target floor is used as the optimization result to establish the exhaust volume optimization model.

5. The public flue exhaust control method according to claim 1, characterized in that, The acquisition of the measured power and exhaust volume of the range hoods on each floor within the public flue includes: The measured power and exhaust volume of the range hood shall be processed using at least one of the following data processing strategies: data cleaning, data denoising, and data standardization.

6. The public flue exhaust control method according to any one of claims 1-5, characterized in that, Also includes: Obtain environmental parameters for each floor within the public flue; The causal effect model is optimized based on the environmental parameters.

7. The public flue exhaust control method according to claim 6, characterized in that, The optimization of the causal effect model based on the environmental parameters includes: The measured power of the range hoods on all floors except the characteristic floor and environmental parameters are used as input parameters, and the predicted power of the range hoods on the characteristic floor is used as output parameters to establish an optimized processing variable prediction model. Using the measured power values ​​of range hoods on all floors and environmental parameters as input parameters, and the predicted exhaust volume of the target floor as output parameters, an optimized result variable prediction model is established. The causal effect model is established based on the optimized treatment variable prediction model and the outcome variable prediction model.

8. A public flue exhaust control device, characterized in that, The public flue exhaust control method according to any one of claims 1-7 includes: The data acquisition module is used to acquire the measured power and exhaust volume of the range hoods on each floor within the public flue. The causal analysis module is used to establish a causal effect model between the range hood power and the exhaust volume based on the measured values ​​of the range hood power and the exhaust volume. Specifically, the causal analysis module is configured to: use the measured power values ​​of the range hoods on all floors except the characteristic floor as input parameters and the predicted power values ​​of the range hoods on the characteristic floor as output parameters to establish a processing variable prediction model; use the measured power values ​​of the range hoods on all floors as input parameters and the predicted exhaust volume values ​​of the target floor as output parameters to establish an outcome variable prediction model; and establish a causal effect model based on the processing variable prediction model and the outcome variable prediction model. The calculation module is used to determine the range hood to be optimized that is associated with the target floor based on the causal effect model. An optimization module is used to establish an exhaust volume optimization model based on the number of range hoods to be optimized, and to determine the target power of the range hoods to be optimized based on the exhaust volume optimization model.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the public flue exhaust control method according to any one of claims 1-7.

Images