CN113803825B - Method and system for reducing noise of fan of fresh air system and electronic equipment - Google Patents

Method and system for reducing noise of fan of fresh air system and electronic equipment Download PDF

Info

Publication number
CN113803825B
CN113803825B CN202111198012.6A CN202111198012A CN113803825B CN 113803825 B CN113803825 B CN 113803825B CN 202111198012 A CN202111198012 A CN 202111198012A CN 113803825 B CN113803825 B CN 113803825B
Authority
CN
China
Prior art keywords
distance
output
data
wind
classification
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202111198012.6A
Other languages
Chinese (zh)
Other versions
CN113803825A (en
Inventor
江正红
陈思悦
罗修樟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Meien Microelectronics Co ltd
Original Assignee
Shenzhen Meien Microelectronics Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Meien Microelectronics Co ltd filed Critical Shenzhen Meien Microelectronics Co ltd
Priority to CN202111198012.6A priority Critical patent/CN113803825B/en
Publication of CN113803825A publication Critical patent/CN113803825A/en
Application granted granted Critical
Publication of CN113803825B publication Critical patent/CN113803825B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F7/00—Ventilation
    • F24F7/007—Ventilation with forced flow
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
    • F24F11/63—Electronic processing
    • F24F11/64—Electronic processing using pre-stored data
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/70—Control systems characterised by their outputs; Constructional details thereof
    • F24F11/72—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/88—Electrical aspects, e.g. circuits
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F13/00—Details common to, or for air-conditioning, air-humidification, ventilation or use of air currents for screening
    • F24F13/24—Means for preventing or suppressing noise
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F13/00—Details common to, or for air-conditioning, air-humidification, ventilation or use of air currents for screening
    • F24F13/24—Means for preventing or suppressing noise
    • F24F2013/247—Active noise-suppression
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
    • Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E10/00—Energy generation through renewable energy sources
    • Y02E10/70—Wind energy
    • Y02E10/72—Wind turbines with rotation axis in wind direction

Landscapes

  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Structures Of Non-Positive Displacement Pumps (AREA)

Abstract

The application discloses a fan noise reduction method, a fan noise reduction system and electronic equipment for a fresh air system, wherein output air is modeled on a complex plane, and the change of the output air is expressed by using a distance formula between two points of the complex plane, so that the noise generated by the work of a fan due to the change of the output air is accurately expressed, and therefore, when a distance matrix is used for extracting high-dimensional features, the method is equivalent to the high-dimensional feature extraction of the noise generated by the work of the fan, and the working power of the fan can be effectively controlled based on the extracted features.

Description

Method and system for reducing noise of fan of fresh air system and electronic equipment
Technical Field
The invention relates to the field of intelligent noise reduction of fans, in particular to a noise reduction method and system for fan noise of a fresh air system and electronic equipment.
Background
The fresh air conditioner is a healthy and comfortable air conditioner with fresh air function, and realizes the circulation and ventilation between room air and outdoor air by using a centrifugal fan, and has the function of purifying air. Compared with a common air conditioner, the fresh air conditioner has the following advantages that firstly, the fresh air conditioner can introduce outdoor oxygen-enriched air into a room through purification, so that the oxygen content and freshness of indoor air are increased; secondly, the fresh air conditioner can monitor the indoor air environment at all times, judge the comfort level of each person through season recognition, indoor environment recognition and the like and push different comfort modes to different people through a partition air supply mode; thirdly, the fresh air conditioner has a comfortable use function, and the comfort level of the fresh air conditioner is obviously superior to that of a common air conditioner during use.
However, the fresh air conditioning system comprises a fan, an air outlet and an air duct extending between the fan and the air outlet, and on the premise that the air duct is determined, the noise of the fresh air conditioning system is closely related to the working power of the fan. It can be understood that the power that reduces the fan can the noise reduction, and the power that improves the fan can the noise increase, nevertheless meanwhile, the air-out condition has been decided to the power size of fan and the position of air outlet, under actual conditions, often can take place although the noise is little enough but the air-out condition can't meet the demands, perhaps, the air-out condition meets the demands but the too big condition of noise.
Therefore, in order to better reduce the noise of the fan of the fresh air system and meet the air outlet requirements of users, a noise reduction scheme for the fan of the fresh air system is expected.
Disclosure of Invention
The present application is proposed to solve the above-mentioned technical problems. The embodiment of the application provides a fan noise reduction method, a fan noise reduction system and electronic equipment for a fresh air system, wherein output air is modeled on a complex plane, and a distance formula between two points of the complex plane is used for representing the change of the output air, so that the noise generated by the operation of a fan due to the change of the output air is accurately expressed, and therefore when a distance matrix is used for extracting high-dimensional features, the method is equivalent to the method for extracting the high-dimensional features of the noise generated by the operation of the fan, and the working power of the fan can be effectively controlled based on the extracted features.
According to one aspect of the present application, there is provided a method for reducing fan noise of a fresh air system, comprising:
acquiring data of a plurality of output air of a fresh air system along a time sequence through a sensor, wherein the data of the output air comprises a pitch angle and an azimuth angle of the output air;
modeling data of the output air on a complex plane;
calculating the distance between the data of the output wind at two adjacent time points on the complex plane as the distance between the data of the output wind at the two adjacent time points on the complex plane, and constructing a plurality of distances into a distance matrix, wherein the distance between the data of the output wind at two adjacent time points on the complex plane is used for representing the change of the data of the output wind at two adjacent time points on a time dimension;
obtaining a distance feature map from the distance matrix using a convolutional neural network, the distance feature map being used to represent high-dimensional implicit correlation features between transformed data of the output wind;
performing QR decomposition on each feature matrix of the distance feature map to decompose each feature matrix of the distance feature map into an orthogonal matrix Q and an upper triangular matrix R;
arranging a plurality of upper triangular matrixes R into a classification characteristic diagram; and
and obtaining a classification result by passing the classification characteristic diagram through a classifier, wherein the classification result is used for representing an adjustment result of the fan power of the fresh air system.
In the above noise reduction method for fan noise of a fresh air system, modeling data of the plurality of output airs on a complex plane includes: setting the pitch angle of the output air to be
Figure BDA0003303917480000021
The azimuth angle is theta, the output air data can be expressed as ^ and/or ^ on the complex plane>
Figure BDA0003303917480000022
Wherein, | P 0 And | is a module of the complex vector of the output air, wherein the module corresponds to the wind speed of the output air.
In the above noise reduction method for fan noise of a fresh air system, calculating a distance between the output wind data of two adjacent time points on the complex plane as a distance therebetween, and constructing a plurality of the distances as a distance matrix includes: calculating the distance between the output wind data of two adjacent time points on the complex plane as the distance between the output wind data and the complex plane according to the following formula; the formula is:
Figure BDA0003303917480000023
wherein, P 0 And P 1 The modeling representation of the data of the output wind of two adjacent time points on the complex plane;
Figure BDA0003303917480000024
representing the difference of the pitch angles of the output air at two adjacent time points; Δ θ represents a difference between the azimuth angles of the output wind at two adjacent time points.
In the above noise reduction method for fan noise of a fresh air system, obtaining a distance characteristic diagram from the distance matrix using a convolutional neural network includes: the convolutional neural network obtains the distance characteristic diagram from the distance matrix according to the following formula; the formula is:
f i ＝tanh(N i ×f i-1 +B i )
wherein f is i-1 Is the input of the i-th convolutional neural network, f i Is the output of the ith convolutional neural network, N i Is a filter of the i-th convolutional neural network, and B i For the bias vector of the ith convolutional neural network, tanh represents the nonlinear activation function.
In the above noise reduction method for fan noise of a fresh air system, passing the classification feature map through a classifier to obtain a classification result includes: fully concatenating the classification feature map using one or more fully concatenated layers of the classifier to obtain a classification feature vector; inputting the classification feature vector into a Softmax classification function of the classifier to obtain a first probability that power of the classification feature vector attributed to the wind turbine should be increased and a second probability that the probability of the classification feature vector attributed to the wind turbine should be decreased; and determining the classification result based on the comparison between the first probability and the second probability, wherein the classification result is used for indicating that the power of the fan should be increased or decreased.
According to another aspect of the present application, there is provided a noise reduction system for fan noise of a fresh air system, comprising:
the data acquisition unit is used for acquiring data of a plurality of output air of the fresh air system along a time sequence through a sensor, wherein the data of the output air comprises a pitch angle and an azimuth angle of the output air;
the modeling unit is used for modeling the data of the output air obtained by the data obtaining unit on a complex plane;
a distance matrix construction unit, configured to calculate a distance between the data of the output air obtained by the modeling unit at two adjacent time points on the complex plane as a distance therebetween, and construct a plurality of distances as a distance matrix, where the distance between the data of the output air at two adjacent time points on the complex plane is used to represent a change of the data of the output air at two adjacent time points in a time dimension;
a convolutional neural network processing unit, configured to obtain a distance feature map from the distance matrix obtained by the distance matrix constructing unit by using a convolutional neural network, where the distance feature map is used to represent a high-dimensional implicit correlation feature between the transformed data of the output wind;
the decomposition unit is used for carrying out QR decomposition on each feature matrix of the distance feature map obtained by the convolutional neural network processing unit so as to decompose each feature matrix of the distance feature map into an orthogonal matrix Q and an upper triangular matrix R;
the arrangement unit is used for arranging the upper triangular matrixes R obtained by the decomposition units into a classification characteristic diagram; and
and the classifier processing unit is used for enabling the classification characteristic diagram obtained by the arranging unit to pass through a classifier so as to obtain a classification result, wherein the classification result is used for representing an adjustment result of the fan power of the fresh air system.
In the above noise reduction system for fan noise of a fresh air system, the modeling unit is further configured to: setting the pitch angle of the output air to
Figure BDA0003303917480000041
The azimuth angle is theta, the output wind data can be expressed as
Figure BDA0003303917480000042
Wherein, | P 0 And | is a module of the complex vector of the output air, and the module corresponds to the wind speed of the output air.
In the above noise reduction system for fan noise of a fresh air system, the distance matrix constructing unit is further configured to: calculating the distance between the output wind data of two adjacent time points on the complex plane as the distance between the output wind data and the complex plane according to the following formula; the formula is:
Figure BDA0003303917480000043
wherein, P 0 And P 1 A modeling representation of data representing the output wind at two adjacent time points on the complex plane;
Figure BDA0003303917480000044
representing the difference of the pitch angles of the output air at two adjacent time points; Δ θ represents a difference in azimuth angle of the output air at two adjacent time points.
In the above noise reduction system for fan noise of a fresh air system, the convolutional neural network processing unit is further configured to: the convolutional neural network obtains the distance characteristic diagram from the distance matrix according to the following formula; the formula is:
f i ＝tanh(N i ×f i-1 +B i )
wherein, f i-1 As input to the ith convolutional neural network, f i Is the output of the ith convolutional neural network, N i Is a filter of the i-th convolutional neural network, and B i For the bias vector of the ith convolutional neural network, tanh represents the nonlinear activation function.
In the above noise reduction system for fan noise of a fresh air system, the classifier processing unit includes: a full-concatenation coding subunit, configured to perform full-concatenation coding on the classification feature map using one or more full-concatenation layers of the classifier to obtain a classification feature vector; a probability generating subunit, configured to input the classification feature vector obtained by the fully-connected coding subunit into a Softmax classification function of the classifier to obtain a first probability that power of the wind turbine to which the classification feature vector belongs should be increased and a second probability that the probability of the wind turbine to which the classification feature vector belongs should be decreased; and a comparison subunit, configured to determine the classification result based on a comparison between the first probability obtained by the probability generation subunit and the second probability obtained by the probability generation subunit, where the classification result is used to indicate that the power of the wind turbine should be increased or decreased.
According to still another aspect of the present application, there is provided an electronic apparatus including: a processor; and a memory in which computer program instructions are stored, which, when executed by the processor, cause the processor to perform the method of noise reduction for fan noise of a fresh air system as described above.
According to yet another aspect of the present application, a computer readable medium is provided, having stored thereon computer program instructions, which, when executed by a processor, cause the processor to perform the method for noise reduction of fan noise for a fresh air system as described above.
Compared with the prior art, the noise reduction method, the noise reduction system and the electronic equipment for the fan noise of the fresh air system have the advantages that the output air is modeled on the complex plane, the distance formula between two points of the complex plane is used for representing the change of the output air, so that the noise generated by the work of the fan due to the change of the output air is accurately expressed, and therefore when the distance matrix is used for extracting the high-dimensional features, the method is equivalent to the high-dimensional feature extraction of the noise generated by the work of the fan, and the working power of the fan can be effectively controlled based on the extracted features.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing in more detail embodiments of the present application with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings, like reference numbers generally represent like parts or steps.
Fig. 1 is an application scenario diagram of a noise reduction method for fan noise of a fresh air system according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for reducing fan noise of a fresh air system according to an embodiment of the present application;
fig. 3 is a schematic diagram of a system architecture of a noise reduction method for fan noise of a fresh air system according to an embodiment of the present application;
fig. 4 is a flowchart of passing the classification feature map through a classifier to obtain a classification result in the noise reduction method for the fan noise of the fresh air system according to the embodiment of the application;
FIG. 5 is a block diagram of a noise reduction system for fan noise of a fresh air system according to an embodiment of the present application;
FIG. 6 is a block diagram of a classifier processing unit in a noise reduction system for fan noise of a fresh air system according to an embodiment of the present application;
fig. 7 is a block diagram of an electronic device according to an embodiment of the application.
Detailed Description
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only a few embodiments of the present application, and not all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.
Overview of a scene
As described above, the existing fresh air conditioning system can not ensure the working effect of the output air while satisfying the preset noise reduction function of people, so that the noise reduction effect and the working effect of the output air can not be well considered. And because fresh air conditioner needs to judge everyone's comfort level and through the mode of subregion air supply to different people through season discernment, indoor environment discernment etc. regularly, consequently the operating condition of fan needs to adjust regularly, this is the leading factor who produces the noise. Therefore, in order to reduce the noise of the fan of the fresh air system better, a noise reduction scheme for the fan of the fresh air system is expected.
That is, in order to reduce the noise of the fan of the fresh air system, the characteristics of the output air need to be accurately expressed according to the relationship between the fan noise and the fan power and the relationship between the fan power and the output air, so that the characteristics of the output air contain the information of the wind direction and the wind speed that can fully realize the fresh air effect, and the characteristics are effectively regressed to obtain the control result of the fan power.
Based on this, firstly, because the fan noise of the fresh air system is directly related to the fan power, and the fan power is directly related to the output wind of the fan, the applicant of the present application considers that when the output wind changes, the fan noise is the most main factor for generating noise because the working state of the fan needs to be adjusted. Therefore, it is assumed that the two directions of the air ports of the fan are respectively
Figure BDA0003303917480000061
And θ, wherein>
Figure BDA0003303917480000062
For pitch angle, theta for azimuth angle, the modeling of the output wind can be done in the complex plane, i.e.
Figure BDA0003303917480000063
And P is 0 L is the modulus of the complex vector of the output wind, which corresponds to the wind speed, i.e. the furthest distance the wind travels. Thus, the change in wind can be represented by another point on the complex plane, i.e.
Figure BDA0003303917480000064
Figure BDA0003303917480000065
And, the distance d between two points can be expressed as
Figure BDA0003303917480000071
Therefore, when the fan is required to be denoised, the distance between every two output air can be obtained based on the formula when the data of the output air along the time sequence are sampled, so that the distance matrix of the output air is obtained. Then, inputting the distance matrix into a convolutional neural network to obtain a distance characteristic diagram, so that high-dimensional hidden correlation characteristics among output wind change data can be obtained, and each characteristic value comprises related change information of wind speed and wind direction.
In addition, considering that the distance matrix is a matrix which is substantially symmetrical along a diagonal line, in order to avoid overfitting in the regression process, QR decomposition is carried out on each feature matrix in the distance feature map, namely, each feature matrix is decomposed into an orthogonal matrix Q and an upper triangular matrix R, and since the operation process is substantially equivalent to solving a linear least square problem, the convergence of parameters of the neural network can be accelerated remarkably.
And finally, inputting the classification characteristic diagram formed by the upper triangular matrix R into a classifier to obtain the adjustment result of the fan power.
Based on this, the application provides a noise reduction method for fan noise of a fresh air system, which includes: acquiring data of a plurality of output air of a fresh air system along a time sequence through a sensor, wherein the data of the output air comprises a pitch angle and an azimuth angle of the output air; modeling data of the output air on a complex plane; calculating the distance between the data of the output wind at two adjacent time points on the complex plane as the distance between the data of the output wind at the two adjacent time points on the complex plane, and constructing a plurality of distances into a distance matrix, wherein the distance between the data of the output wind at two adjacent time points on the complex plane is used for representing the change of the data of the output wind at two adjacent time points on a time dimension; obtaining a distance feature map from the distance matrix using a convolutional neural network, the distance feature map being used to represent high-dimensional implicit correlation features between transformed data of the output wind; performing QR decomposition on each feature matrix of the distance feature map to decompose each feature matrix of the distance feature map into an orthogonal matrix Q and an upper triangular matrix R; arranging a plurality of upper triangular matrixes R into a classification characteristic diagram; and enabling the classification characteristic diagram to pass through a classifier to obtain a classification result, wherein the classification result is used for representing an adjustment result of the fan power of the fresh air system.
Fig. 1 illustrates an application scenario diagram of a noise reduction method for fan noise of a fresh air system according to an embodiment of the present application. As shown in fig. 1, in this application scenario, first, data of a plurality of output wind (e.g., W as illustrated in fig. 1) of the fresh air system along a time series is obtained through a wind direction and wind speed sensor (e.g., P as illustrated in fig. 1) disposed at an air outlet (e.g., O as illustrated in fig. 1) of the fresh air system, wherein the data of the output wind includes a pitch angle and an azimuth angle of the output wind. In other application scenarios, data of a plurality of output air of the fresh air system along the time sequence may also be obtained by other sensors, which is not limited by the present application. Accordingly, as shown in fig. 1, the fresh air system further includes a fan (e.g., M as illustrated in fig. 1), and an air duct (e.g., T as illustrated in fig. 1) extending between the fan and the outlet.
Then, the acquired data of the output wind is input into a server (for example, S as illustrated in fig. 1) deployed with a noise reduction algorithm for fan noise of the fresh air system, wherein the server can process the acquired data of the output wind by the noise reduction algorithm for fan noise of the fresh air system to generate a classification result representing an adjustment result of fan power of the fresh air system.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described with reference to the accompanying drawings.
Exemplary method
Fig. 2 illustrates a flow chart of a method of noise reduction for fan noise of a fresh air system. As shown in fig. 2, a noise reduction method for fan noise of a fresh air system according to an embodiment of the present application includes: s110, acquiring data of a plurality of output air of the fresh air system along a time sequence through a sensor, wherein the data of the output air comprises a pitch angle and an azimuth angle of the output air; s120, modeling the data of the output air on a complex plane; s130, calculating the distance between the data of the output wind at two adjacent time points on the complex plane as the distance between the data of the output wind at the two adjacent time points on the complex plane, and constructing a plurality of distances as a distance matrix, wherein the distance between the data of the output wind at two adjacent time points on the complex plane is used for representing the change of the data of the output wind at two adjacent time points on a time dimension; s140, obtaining a distance characteristic map from the distance matrix by using a convolutional neural network, wherein the distance characteristic map is used for representing high-dimensional implicit correlation characteristics between the transformed data of the output wind; s150, performing QR decomposition on each feature matrix of the distance feature map so as to decompose each feature matrix of the distance feature map into an orthogonal matrix Q and an upper triangular matrix R; s160, arranging a plurality of upper triangular matrixes R into a classification characteristic diagram; and S170, enabling the classification characteristic diagram to pass through a classifier to obtain a classification result, wherein the classification result is used for representing an adjustment result of the fan power of the fresh air system.
Fig. 3 illustrates an architecture diagram of a noise reduction method for fan noise of a fresh air system according to an embodiment of the present application. As shown in fig. 3, in the network architecture of the noise reduction method for fan noise of a fresh air system, firstly, modeling is performed on a complex plane on the obtained data (for example, P1 as illustrated in fig. 3) of the output wind; then, calculating a distance between the data (e.g., P2 as illustrated in fig. 3) of the output wind at two adjacent time points on the complex plane as a distance (e.g., D as illustrated in fig. 3) therebetween and constructing a plurality of the distances into a distance matrix (e.g., M as illustrated in fig. 3); then, a distance feature map (e.g., F1 as illustrated in fig. 3) is obtained from the distance matrix using a convolutional neural network (e.g., CNN as illustrated in fig. 3); next, performing QR decomposition on each feature matrix of the distance feature map to decompose each feature matrix of the distance feature map into an orthogonal matrix Q (e.g., M1 as illustrated in fig. 3) and an upper triangular matrix R (e.g., M2 as illustrated in fig. 3); then, a plurality of the upper triangular matrices R are arranged as a classification feature map (for example, FC as illustrated in fig. 3); and finally, passing the classification feature map through a classifier (e.g., a classifier as illustrated in fig. 3) to obtain a classification result, wherein the classification result is used for representing an adjustment result of the fan power of the fresh air system.
In step S110 and step S120, data of a plurality of output airs of the fresh air system along the time series are obtained through a sensor, where the data of the output airs include a pitch angle and an azimuth angle of the output airs, and the data of the plurality of output airs are modeled on a complex plane. As mentioned above, the fan noise of the fresh air system is directly related to the fan power, which is directly related to the output wind of the fan, and it is considered that when the output wind changes, the operating state of the fan needs to be adjusted, which is the most important factor for generating noise. Therefore, in the technical scheme of the application, in order to reduce the noise of the fan of the fresh air system, the characteristics of the output air need to be accurately expressed according to the relationship between the fan noise and the fan power and the relationship between the fan power and the output air, so that the characteristics of the output air contain the wind direction and the wind speed information which can fully realize the fresh air effect.
Accordingly, heretofore, that is, it was first necessary to acquire the plurality of output wind data; and then modeling the acquired output wind data on a complex plane for subsequent calculation. It should be understood that, in a specific example, data of a plurality of output airs of the fresh air system along a time series may be obtained by a wind direction and wind speed sensor disposed at a fresh air outlet of the fresh air conditioner body, wherein the data of the output airs includes a pitch angle and an azimuth angle of the output airs. It should be noted that, in another specific example, the data of the output air of the fresh air system along the time series may also be obtained by other sensors, which is not limited by the present application.
Specifically, in this embodiment of the present application, a process of modeling on a complex plane for data of the output wind includes: setting the pitch angle of the output air to
Figure BDA0003303917480000091
The azimuth angle is theta, the output air data can be expressed as ^ and/or ^ on the complex plane>
Figure BDA0003303917480000092
Wherein, | P 0 I is the module of the complex vector of the output wind, which corresponds to the wind speed of the output wind, i.e. the furthest distance of the wind propagation.
In step S130, a distance between the two adjacent time points of the output wind data on the complex plane is calculated as a distance therebetween, and a plurality of the distances are configured as a distance matrix, where the distance between the two adjacent time points of the output wind data on the complex plane is used to represent a change of the output wind data on the two adjacent time points in a time dimension. It will be appreciated that the modeling of the output air is due to its representation in the complex plane as
Figure BDA0003303917480000101
In the solution of the present application, therefore, the variation of the output wind can be represented by another point on the complex plane, that is,
Figure BDA0003303917480000102
thus, the distance d between two points can be expressed. When the fan needs to be denoised, data of a plurality of output wind along a time sequence can be sampled, and the distance between every two output wind is obtained based on the method, so that a distance matrix of the output wind is obtained.
Specifically, in the embodiment of the present application, the process of calculating a distance between the data of the output wind at two adjacent time points on the complex plane as a distance therebetween and constructing a plurality of the distances as a distance matrix includes: calculating the distance between the output wind data of two adjacent time points on the complex plane as the distance between the output wind data and the complex plane according to the following formula;
the formula is:
Figure BDA0003303917480000103
wherein, P 0 And P 1 The modeling representation of the data of the output wind of two adjacent time points on the complex plane;
Figure BDA0003303917480000104
representing the difference of the pitch angles of the output wind at two adjacent time points; Δ θ represents a difference between the azimuth angles of the output wind at two adjacent time points. It is worth mentioning that the distance between the output wind data at two adjacent time points on the complex plane is used to represent the change of the output wind data at two adjacent time points in the time dimension.
In step S140, a distance feature map representing high-dimensional implicit correlation features between the transformed data of the output wind is obtained from the distance matrix using a convolutional neural network. That is, the distance matrix is input into a convolutional neural network to be processed to obtain a distance feature map, it is worth mentioning that the distance feature map is used for representing high-dimensional implicit correlation features between the output wind change data, and each feature value includes related change information of wind speed and wind direction.
Specifically, in the embodiment of the present application, obtaining a distance feature map from the distance matrix using a convolutional neural network includes: the convolutional neural network obtains the distance feature map from the distance matrix according to the following formula;
the formula is:
f i ＝tanh(N i ×f i-1 +B i )
wherein f is i-1 Is the input of the i-th convolutional neural network, f i For the ith layer of convolutional neural networkOutput of (2), N i Is a filter of the i-th convolutional neural network, and B i For the bias vector of the ith convolutional neural network, tanh represents the nonlinear activation function.
In step S150, QR decomposition is performed on each feature matrix of the distance feature map to decompose each feature matrix of the distance feature map into an orthogonal matrix Q and an upper triangular matrix R. It should be understood that, considering that the distance matrix is a matrix that is substantially symmetrical along a diagonal line, in the technical solution of the present application, to avoid overfitting in the regression process, a QR decomposition is selected for each feature matrix in the distance feature map, that is, each feature matrix in the distance feature map is decomposed into an orthogonal matrix Q and an upper triangular matrix R, and since the operation process is substantially equivalent to solving the problem of linear least squares, convergence of parameters of the neural network can be significantly accelerated, so as to more effectively control the operating power of the wind turbine based on the extracted features.
Accordingly, in one specific example, each feature matrix of the distance feature map may be set to a i Then A is i ＝Q i R i Wherein Q is i For an orthogonal matrix, R, to which said characteristic matrix corresponds i And the feature matrix is an upper triangular matrix corresponding to the feature matrix.
In step S160 and step S170, a plurality of upper triangular matrices R are arranged into a classification feature map, and the classification feature map is passed through a classifier to obtain a classification result, where the classification result is used to indicate an adjustment result of the fan power of the fresh air system. It should be understood that, considering that the distance matrix is a matrix which is substantially symmetrical along the diagonal, and in order to avoid the problem of over-fitting in the regression process, in the technical solution of the present application, first, a plurality of the upper triangular matrices R will be obtained i Arranging into a classification characteristic graph; and then, the classification characteristic diagram is processed by a classifier to obtain a classification result for representing the adjustment result of the fan power of the fresh air system.
Specifically, in this embodiment of the present application, the process of passing the classification feature map through a classifier to obtain a classification result includes: first, the classification feature map is full-join encoded using one or more full-join layers of the classifier to obtain a classification feature vector. Inputting the classification feature vector into a Softmax classification function of the classifier to obtain a first probability that power of the classification feature vector attributed to the wind turbine should be increased and a second probability that the probability of the classification feature vector attributed to the wind turbine should be decreased. And determining the classification result based on the comparison between the first probability and the second probability, wherein the classification result is used for indicating that the power of the fan should be increased or decreased. Specifically, when the first probability is greater than the second probability, the classification result is that the power of a fan of the fresh air system should be increased; when the first probability is smaller than the second probability, the classification result is that the power of a fan of the fresh air system should be reduced.
Fig. 4 illustrates a flowchart of passing the classification feature map through a classifier to obtain a classification result according to an embodiment of the application. As shown in fig. 4, passing the classification feature map through a classifier to obtain a classification result includes: s210, performing full-joint coding on the classification feature map by using one or more full-joint layers of the classifier to obtain a classification feature vector; s220, inputting the classification feature vector into a Softmax classification function of the classifier to obtain a first probability that the power of the classification feature vector belonging to the fan should be increased and a second probability that the probability of the classification feature vector belonging to the fan should be decreased; and S230, determining the classification result based on the comparison between the first probability and the second probability, wherein the classification result is used for indicating that the power of the fan should be increased or decreased.
In summary, the noise reduction method for the fan noise of the fresh air system according to the embodiment of the present application is elucidated, and the output wind is modeled on the complex plane to express the change of the output wind by using the distance formula between two points of the complex plane, so as to accurately express the noise generated by the fan operation due to the change of the output wind, and therefore, when the distance matrix is used for performing the high-dimensional feature extraction, the method is equivalent to performing the high-dimensional feature extraction on the noise generated by the fan operation, and thus the operating power of the fan can be effectively controlled based on the extracted features.
Exemplary System
FIG. 5 illustrates a block diagram of a noise reduction system for fan noise of a fresh air system according to an embodiment of the application. As shown in fig. 5, a noise reduction system 500 for fan noise of a fresh air system according to an embodiment of the present application includes: a data obtaining unit 510, configured to obtain, through a sensor, data of a plurality of output airs of the fresh air system along a time sequence, where the data of the output airs includes a pitch angle and an azimuth angle of the output airs; a modeling unit 520, configured to perform modeling on a complex plane on the data of the output wind obtained by the data obtaining unit 510; a distance matrix constructing unit 530, configured to calculate a distance between the data of the output wind obtained by the modeling unit 520 at two adjacent time points on the complex plane as a distance therebetween, and construct a plurality of the distances as a distance matrix, where the distance between the data of the output wind at two adjacent time points on the complex plane is used to represent a change of the data of the output wind at two adjacent time points in a time dimension; a convolutional neural network processing unit 540, configured to obtain a distance feature map from the distance matrix obtained by the distance matrix constructing unit 530 by using a convolutional neural network, where the distance feature map is used to represent high-dimensional implicit correlation features between the transformed data of the output wind; a decomposition unit 550, configured to perform QR decomposition on each feature matrix of the distance feature map obtained by the convolutional neural network processing unit 540 to decompose each feature matrix of the distance feature map into an orthogonal matrix Q and an upper triangular matrix R; an arranging unit 560 configured to arrange the upper triangular matrices R obtained by the plurality of decomposition units 550 into a classification feature map; and a classifier processing unit 570, configured to pass the classification feature map obtained by the arranging unit 560 through a classifier to obtain a classification result, where the classification result is used to indicate an adjustment result of fan power of a fresh air system.
In one example, inIn the above noise reduction system 500 for fan noise of a fresh air system, the modeling unit 520 is further configured to: setting the pitch angle of the output air to
Figure BDA0003303917480000131
The azimuth angle is theta, the output air data can be expressed as ^ and/or ^ on the complex plane>
Figure BDA0003303917480000132
Wherein, | P 0 And | is a module of the complex vector of the output air, and the module corresponds to the wind speed of the output air.
In an example, in the above noise reduction system 500 for fan noise of a fresh air system, the distance matrix constructing unit 530 is further configured to: calculating the distance between the output wind data of two adjacent time points on the complex plane as the distance between the output wind data and the complex plane according to the following formula; the formula is:
Figure BDA0003303917480000133
wherein, P 0 And P 1 The modeling representation of the data of the output wind of two adjacent time points on the complex plane;
Figure BDA0003303917480000134
representing the difference of the pitch angles of the output air at two adjacent time points; Δ θ represents a difference between the azimuth angles of the output wind at two adjacent time points.
In an example, in the above noise reduction system 500 for fan noise of a fresh air system, the convolutional neural network processing unit 540 is further configured to: the convolutional neural network obtains the distance feature map from the distance matrix according to the following formula; the formula is:
f i ＝tanh(N i ×f i-1 +B i )
wherein, f i-1 As input to the ith convolutional neural network, f i Is the output of the ith convolutional neural network, N i Is a filter of the i-th convolutional neural network, and B i For the bias vector of the ith convolutional neural network, tanh represents the nonlinear activation function.
In an example, in the above noise reduction system 500 for fan noise of a fresh air system, as shown in fig. 6, the classifier processing unit 570 includes: a full-connection coding subunit 571, configured to perform full-connection coding on the classification feature map using one or more full-connection layers of the classifier to obtain a classification feature vector; a probability generating subunit 572, configured to input the classification feature vector obtained by the fully-connected encoding subunit 571 into a Softmax classification function of the classifier to obtain a first probability that the power of the wind turbine to which the classification feature vector belongs should be increased and a second probability that the probability of the wind turbine to which the classification feature vector belongs should be decreased; and a comparison subunit 573 configured to determine the classification result based on a comparison between the first probability obtained by the probability generation subunit 572 and the second probability obtained by the probability generation subunit 572, wherein the classification result indicates that the power of the fan should be increased or decreased.
Here, it can be understood by those skilled in the art that the specific functions and operations of the respective units and modules in the noise reduction system 500 for fan noise of a fresh air system described above have been described in detail in the description of the noise reduction method for fan noise of a fresh air system with reference to fig. 1 to 4, and thus, a repetitive description thereof will be omitted.
As described above, the noise reduction system 500 for fan noise of a fresh air system according to the embodiment of the present application may be implemented in various terminal devices, such as a server for a noise reduction algorithm for fan noise of a fresh air system. In one example, the noise reduction system 500 for fan noise of a fresh air system according to the embodiment of the present application may be integrated into a terminal device as a software module and/or a hardware module. For example, the noise reduction system 500 for fan noise of the fresh air system may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the noise reduction system 500 for fan noise of the fresh air system may also be one of many hardware modules of the terminal device.
Alternatively, in another example, the noise reduction system 500 for fan noise of the fresh air system and the terminal device may also be separate devices, and the noise reduction system 500 for fan noise of the fresh air system may be connected to the terminal device through a wired and/or wireless network and transmit the interaction information according to the agreed data format.
Exemplary electronic device
Next, an electronic apparatus according to an embodiment of the present application is described with reference to fig. 7. As shown in fig. 7, the electronic device 10 includes one or more processors 11 and a memory 12. The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.
Memory 12 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer readable storage medium and executed by the processor 11 to implement the functions of the noise reduction method for fan noise of a fresh air system of the various embodiments of the present application described above and/or other desired functions. Various contents such as a distance feature map, a classification feature map, etc. may also be stored in the computer-readable storage medium.
In one example, the electronic device 10 may further include: an input system 13 and an output system 14, which are interconnected by a bus system and/or other form of connection mechanism (not shown).
The input system 13 may comprise, for example, a keyboard, a mouse, etc.
The output system 14 may output various information including the classification result and the like to the outside. The output system 14 may include, for example, a display, speakers, a printer, and a communication network and its connected remote output devices, among others.
Of course, for simplicity, only some of the components of the electronic device 10 relevant to the present application are shown in fig. 7, and components such as buses, input/output interfaces, and the like are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer-readable storage Medium
In addition to the above-described methods and apparatus, embodiments of the present application may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform the steps in the functions in the noise reduction method for fan noise of a fresh air system according to various embodiments of the present application described in the "exemplary methods" section above of this specification.
The computer program product may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages, for carrying out operations according to embodiments of the present application. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present application may also be a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform the steps in the noise reduction method for fan noise of a fresh air system described in the "exemplary method" section above of this specification.
The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The basic principles of the present application have been described above with reference to specific embodiments, but it should be noted that advantages, effects, etc. mentioned in the present application are only examples and are not limiting, and the advantages, effects, etc. must not be considered to be possessed by various embodiments of the present application. Furthermore, the foregoing disclosure of specific details is provided for purposes of illustration and understanding only, and is not intended to limit the application to the details which are set forth in order to provide a thorough understanding of the present application.
The block diagrams of devices, apparatuses, systems referred to in this application are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," "comprising," "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
It should also be noted that in the devices, apparatuses, and methods of the present application, the components or steps may be decomposed and/or recombined. These decompositions and/or recombinations should be considered as equivalents of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, the description is not intended to limit embodiments of the application to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.

Claims (10)

1. A noise reduction method for fan noise of a fresh air system is characterized by comprising the following steps:
acquiring data of a plurality of output air of a fresh air system along a time sequence through a sensor, wherein the data of the output air comprises a pitch angle and an azimuth angle of the output air;
modeling data of the output air on a complex plane;
calculating the distance between the data of the output wind at two adjacent time points on the complex plane as the distance between the data of the output wind at the two adjacent time points on the complex plane, and constructing a plurality of distances into a distance matrix, wherein the distance between the data of the output wind at two adjacent time points on the complex plane is used for representing the change of the data of the output wind at two adjacent time points on a time dimension;
obtaining a distance feature map from the distance matrix using a convolutional neural network, the distance feature map being used to represent high-dimensional implicit correlation features between transformed data of the output wind;
performing QR decomposition on each feature matrix of the distance feature map to decompose each feature matrix of the distance feature map into an orthogonal matrix Q and an upper triangular matrix R;
arranging a plurality of upper triangular matrixes R into a classification characteristic diagram; and
and obtaining a classification result by passing the classification characteristic diagram through a classifier, wherein the classification result is used for representing an adjustment result of the fan power of the fresh air system.
2. The method of reducing fan noise for a fresh air system of claim 1, wherein modeling the data of the plurality of output airs on a complex plane comprises:
setting the pitch angle of the output air to
Figure FDA0003303917470000011
The azimuth angle is theta, the output air data can be expressed as ^ and/or ^ on the complex plane>
Figure FDA0003303917470000012
Wherein, | P 0 And | is a module of the complex vector of the output air, and the module corresponds to the wind speed of the output air.
3. The fan noise reduction method for the fresh air system according to claim 2, wherein calculating a distance between the output wind data of two adjacent time points on the complex plane as a distance therebetween and constructing a plurality of the distances as a distance matrix comprises:
calculating the distance between the output wind data of two adjacent time points on the complex plane as the distance between the output wind data and the complex plane according to the following formula;
the formula is:
Figure FDA0003303917470000013
Figure FDA0003303917470000021
wherein, P 0 And P 1 The modeling representation of the data of the output wind of two adjacent time points on the complex plane;
Figure FDA0003303917470000022
representing the difference of the pitch angles of the output air at two adjacent time points; Δ θ represents a difference between the azimuth angles of the output wind at two adjacent time points.
4. The fan noise reduction method for a fresh air system according to claim 1, wherein obtaining a distance feature map from the distance matrix using a convolutional neural network comprises:
the convolutional neural network obtains the distance characteristic diagram from the distance matrix according to the following formula;
the formula is:
f i ＝tanh(N i ×f i-1 +B i )
wherein f is i-1 As input to the ith convolutional neural network, f i Is the output of the ith convolutional neural network, N i Is a filter of the i-th convolutional neural network, and B i For the bias vector of the ith convolutional neural network, tanh represents the nonlinear activation function.
5. The method of claim 1, wherein the step of passing the classification feature map through a classifier to obtain a classification result comprises:
fully-concatenate encoding the classified feature map using one or more fully-concatenated layers of the classifier to obtain a classified feature vector;
inputting the classification feature vector into a Softmax classification function of the classifier to obtain a first probability that power of the classification feature vector attributed to the wind turbine should be increased and a second probability that the probability of the classification feature vector attributed to the wind turbine should be decreased; and
determining the classification result based on the comparison between the first probability and the second probability, the classification result being used for indicating that the power of the fan should be increased or decreased.
6. The utility model provides a noise reduction system for fan noise of new trend system which characterized in that includes:
the fresh air system comprises a data acquisition unit, a data acquisition unit and a control unit, wherein the data acquisition unit is used for acquiring data of a plurality of output air of the fresh air system along a time sequence through a sensor, and the data of the output air comprises a pitch angle and an azimuth angle of the output air;
the modeling unit is used for modeling the data of the output air obtained by the data obtaining unit on a complex plane;
a distance matrix construction unit, configured to calculate a distance between the data of the output wind obtained by the modeling unit at two adjacent time points on the complex plane as a distance therebetween, and construct a plurality of the distances as a distance matrix, where the distance between the data of the output wind at two adjacent time points on the complex plane is used to represent a change in the data of the output wind at two adjacent time points in a time dimension;
a convolutional neural network processing unit, configured to obtain a distance feature map from the distance matrix obtained by the distance matrix constructing unit by using a convolutional neural network, where the distance feature map is used to represent a high-dimensional implicit correlation feature between the transformed data of the output wind;
the decomposition unit is used for carrying out QR decomposition on each feature matrix of the distance feature map obtained by the convolutional neural network processing unit so as to decompose each feature matrix of the distance feature map into an orthogonal matrix Q and an upper triangular matrix R;
the arrangement unit is used for arranging the upper triangular matrixes R obtained by the decomposition units into a classification characteristic diagram; and
and the classifier processing unit is used for enabling the classification characteristic diagram obtained by the arranging unit to pass through a classifier so as to obtain a classification result, wherein the classification result is used for representing an adjustment result of the fan power of the fresh air system.
7. The fan noise reduction system for a fresh air system of claim 6, wherein the modeling unit is further configured to:
setting the pitch angle of the output air to
Figure FDA0003303917470000031
The azimuth angle is theta, the output air data can be expressed as ^ on the complex plane>
Figure FDA0003303917470000032
Wherein, | P 0 And | is a module of the complex vector of the output air, wherein the module corresponds to the wind speed of the output air.
8. The fan noise reduction system for a fresh air system of claim 6, wherein the distance matrix constructing unit is further configured to:
calculating the distance between the output wind data of two adjacent time points on the complex plane as the distance between the output wind data and the complex plane according to the following formula;
the formula is:
Figure FDA0003303917470000033
wherein, P 0 And P 1 The modeling representation of the data of the output wind of two adjacent time points on the complex plane;
Figure FDA0003303917470000041
representing the difference of the pitch angles of the output wind at two adjacent time points; Δ θ represents a difference between the azimuth angles of the output wind at two adjacent time points.
9. The fan noise reduction system for a fresh air system of claim 6, wherein the classifier processing unit comprises:
a full-concatenation coding subunit, configured to perform full-concatenation coding on the classification feature map using one or more full-concatenation layers of the classifier to obtain a classification feature vector;
a probability generating subunit, configured to input the classification feature vector obtained by the fully-connected coding subunit into a Softmax classification function of the classifier to obtain a first probability that power of the wind turbine to which the classification feature vector belongs should be increased and a second probability that the probability of the wind turbine to which the classification feature vector belongs should be decreased; and
a comparison subunit, configured to determine the classification result based on a comparison between the first probability obtained by the probability generation subunit and the second probability obtained by the probability generation subunit, where the classification result is used to indicate that the power of the wind turbine should be increased or decreased.
10. An electronic device, comprising:
a processor; and
a memory having stored therein computer program instructions which, when executed by the processor, cause the processor to carry out the method of noise reduction for fan noise of a fresh air system of any of claims 1 to 5.
CN202111198012.6A 2021-10-14 2021-10-14 Method and system for reducing noise of fan of fresh air system and electronic equipment Active CN113803825B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111198012.6A CN113803825B (en) 2021-10-14 2021-10-14 Method and system for reducing noise of fan of fresh air system and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111198012.6A CN113803825B (en) 2021-10-14 2021-10-14 Method and system for reducing noise of fan of fresh air system and electronic equipment

Publications (2)

Publication Number Publication Date
CN113803825A CN113803825A (en) 2021-12-17
CN113803825B true CN113803825B (en) 2023-03-31

Family

ID=78937582

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111198012.6A Active CN113803825B (en) 2021-10-14 2021-10-14 Method and system for reducing noise of fan of fresh air system and electronic equipment

Country Status (1)

Country Link
CN (1) CN113803825B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1748184A2 (en) * 2005-07-29 2007-01-31 General Electric Company Method and apparatus for reducing wind turbine noise
CN109188019A (en) * 2018-11-05 2019-01-11 华北电力大学 Tri-dimensional wind speed wind direction measurement method based on multiple signal classification algorithm

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DK2515122T3 (en) * 2011-04-18 2019-02-11 Siemens Ag Method for measuring wind direction just after a wind turbine rotor
CN112259069B (en) * 2020-10-21 2023-03-14 上海协格空调工程有限公司 Dynamic active noise reduction method and air conditioning equipment
CN112923523B (en) * 2021-02-03 2022-05-17 深圳市美兆环境股份有限公司 Intelligent fresh air system regulation and control method based on data link of Internet of things

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1748184A2 (en) * 2005-07-29 2007-01-31 General Electric Company Method and apparatus for reducing wind turbine noise
CN109188019A (en) * 2018-11-05 2019-01-11 华北电力大学 Tri-dimensional wind speed wind direction measurement method based on multiple signal classification algorithm

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
风电机组风速-功率特性曲线建模研究综述;杨茂等;《电力自动化设备》;20180209(第02期);全文 *

Also Published As

Publication number Publication date
CN113803825A (en) 2021-12-17

Similar Documents

Publication Publication Date Title
US20220083868A1 (en) Neural network training method and apparatus, and electronic device
US20200124307A1 (en) Control apparatus and computer readable medium
CN112488183B (en) Model optimization method, device, computer equipment and storage medium
CN107246714A (en) Air conditioning control method and its equipment
CN112923523B (en) Intelligent fresh air system regulation and control method based on data link of Internet of things
US10970128B2 (en) Server, air conditioner and method for controlling thereof
CN111738456A (en) Grading card model training method and device
CN114548246A (en) Control method and system of intelligent device and electronic device
CN111486571B (en) Wind direction adjusting method and device, storage medium and air outlet equipment
CN115755954A (en) Routing inspection path planning method and system, computer equipment and storage medium
CN113803825B (en) Method and system for reducing noise of fan of fresh air system and electronic equipment
CN112668482A (en) Face recognition training method and device, computer equipment and storage medium
CN116307624A (en) Resource scheduling method and system of ERP system
WO2019095587A1 (en) Face recognition method, application server, and computer-readable storage medium
CN115376075A (en) Fresh air energy-saving system of intelligent building and control method thereof
CN116151545A (en) Multi-wind motor group power control optimization system
CN114615641A (en) High-altitude platform equipment cooperative management method and system and electronic equipment
CN116624977B (en) Building automatic control system and method based on artificial intelligence
CN114187588A (en) Data processing method, data processing device, storage medium and computer program product
JP2020144555A (en) Control system of equipment
CN116483132A (en) Coal flow control system and method based on drive motor current control coordination
CN116844088A (en) Online dust remover control system and method thereof
CN112149052A (en) Daily load curve clustering method based on PLR-DTW
CN115756493A (en) Neural network model compiling method and device, storage medium and electronic equipment
CN115099875A (en) Data classification method based on decision tree model and related equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant