WO2023103468A1

WO2023103468A1 - Method for determining transformer multi-sound-source noise equivalent model, terminal, and storage medium

Info

Publication number: WO2023103468A1
Application number: PCT/CN2022/115386
Authority: WO
Inventors: 吴鹏; 胡源; 刘长江; 邢琳; 王宁; 张帅; 何晓阳; 段剑; 邵华; 李燕; 赵彭辉
Original assignee: 国网河北省电力有限公司经济技术研究院; 河北汇智电力工程设计有限公司; 国网河北省电力有限公司; 国家电网有限公司
Priority date: 2021-12-10
Filing date: 2022-08-29
Publication date: 2023-06-15
Also published as: CN114201875A

Abstract

The present invention provides a method for determining a transformer multi-sound-source noise equivalent model, a terminal, and a storage medium. The method comprises: acquiring spatial coordinates of multiple preset detection points around a transformer and actual sound pressure levels in a preset octave band; acquiring the number of equivalent sound sources of the transformer and spatial coordinates of each equivalent sound source; according to the spatial coordinates of the multiple preset detection points and the actual sound pressure levels in the preset octave band, the number of the equivalent sound sources, and the spatial coordinates of each equivalent sound source, constructing a univariate linear regression model corresponding to the preset octave band, and solving the univariate linear regression model corresponding to the preset octave band to obtain sound pressure levels of multiple equivalent sound sources in the preset octave band; and according to the number of the equivalent sound sources, the sound pressure level of each equivalent sound source, and the spatial coordinates of each equivalent sound source, obtaining a transformer multi-sound-source noise equivalent model corresponding to the preset octave band. The process of determining a transformer multi-sound-source noise equivalent model of the present invention is convenient and simple, and the amount of calculation is small.

Description

Determination method, terminal and storage medium of transformer multi-source noise equivalent model

technical field

The invention relates to the technical field of noise equivalent models, in particular to a method for determining an equivalent model of noise from multiple sound sources of a transformer, a terminal and a storage medium.

Background technique

As the location of substations is getting closer to residential areas, the problem of noise pollution caused by substations has attracted more and more attention. The transformer is the largest single device in the substation, and it is also the main source of noise in the substation. Constructing an accurate multi-source noise equivalent model of a transformer based on the acoustic equivalent source theory is of great significance for predicting the noise model of a substation.

At present, near-field acoustic holography is usually used to construct the equivalent model of transformer multi-source noise. However, this method is complex and computationally intensive.

Contents of the invention

Embodiments of the present invention provide a method for determining an equivalent model of transformer multi-sound source noise, a terminal and a storage medium, so as to solve the problems of complex calculation and large amount of calculation in the prior art.

In the first aspect, an embodiment of the present invention provides a method for determining an equivalent model of transformer multi-source noise, including:

Obtain the spatial coordinates of multiple preset detection points around the transformer and the actual sound pressure level in the preset octave band;

Obtain the number of equivalent sound sources of the transformer and the spatial coordinates of each equivalent sound source;

According to the spatial coordinates of multiple preset detection points and the actual sound pressure level in the preset octave band, the number of equivalent sound sources and the spatial coordinates of each equivalent sound source, a univariate linear regression model corresponding to the preset octave band is constructed , and solve the univariate linear regression model corresponding to the preset octave band to obtain the sound pressure levels of multiple equivalent sound sources in the preset octave band;

According to the number of equivalent sound sources, the sound pressure level of each equivalent sound source in the preset octave band and the spatial coordinates of each equivalent sound source, the transformer multi-source noise equivalent model corresponding to the preset octave band is obtained.

In a possible implementation manner, the preset The univariate linear regression model corresponding to the octave band, and solve the univariate linear regression model corresponding to the preset octave band, to obtain the sound pressure level of multiple equivalent sound sources in the preset octave band, including:

According to the spatial coordinates of multiple preset detection points and the actual sound pressure level in the preset octave band, the number of equivalent sound sources and the spatial coordinates of each equivalent sound source, a univariate linear regression model corresponding to the preset octave band is constructed ;

According to the predicted sound pressure level of each preset detection point in the preset octave band and the actual sound pressure level of each preset detection point in the preset octave band, the univariate linear regression model corresponding to the preset octave band is solved. Layer optimization obtains the sound pressure levels of multiple equivalent sound sources in preset octave bands.

In a possible implementation, according to the predicted sound pressure level of each preset detection point in the preset octave band and the actual sound pressure level of each preset detection point in the preset octave band, the unit corresponding to the preset octave band The variable linear regression model is solved, and the sound pressure levels of multiple equivalent sound sources in the preset octave bands are obtained through double-layer optimization, including:

Using the method of average distribution, the first batch of random variables are generated as the input variables for the first optimization of the univariate linear regression model corresponding to the preset octave band;

Calculate the error value of each random variable in the first batch of random variables according to the MSE loss function, and select a preset number of random variables in order from the first batch of random variables sorted according to the error value from small to large;

Calculate the mathematical expectation and variance of each selected random variable using the normal distribution method to generate the second batch of random variables as the input for the second optimization of the univariate linear regression model corresponding to the preset octave band variable;

According to the cross-entropy loss function, the second batch of random variables is solved to obtain the sound pressure level of each equivalent sound source in the preset octave band.

In one possible implementation, the MSE loss function is:

Among them, MSE is the error value calculated by the MSE loss function; m is the number of predicted detection points; Lm _j is the actual sound pressure level of the jth preset detection point in the preset octave band; Lw _j is the jth preset The predicted sound pressure level of the detection point in the preset octave band,

Lw _ij ＝Lp _i -20lg(d _ij )-0.001*α*d _ij -11; n is the number of equivalent sound sources; Lw _ij is the i-th equivalent sound source generated at the j-th preset detection point The sound pressure level in the preset octave band; Lp _i is the sound pressure level of the i-th equivalent sound source in the preset octave band, which is an unknown quantity; d _ij is the i-th equivalent sound source and the j-th The distance between preset detection points; α is the atmospheric absorption attenuation coefficient of noise during propagation.

In one possible implementation, the cross-entropy loss function is:

Among them, L is the value calculated by the cross-entropy loss function; P(Lp _i ) is the value probability of Lp _i in the normal distribution function.

In a possible implementation manner, the number of equivalent sound sources is 24;

The distribution of equivalent sound sources is as follows: the walls of the long box are arranged at equal intervals according to the 4*2 specification, and the walls of the short box are arranged at equal intervals according to the 2*2 specification.

In the second aspect, an embodiment of the present invention provides a device for determining an equivalent model of transformer multi-source noise, including:

The first acquisition module is used to acquire the spatial coordinates of multiple preset detection points around the transformer and the actual sound pressure level in the preset octave band;

The second acquisition module is used to acquire the number of equivalent sound sources of the transformer and the spatial coordinates of each equivalent sound source;

The solving module is used to construct the corresponding sound pressure level of the preset octave band according to the spatial coordinates of multiple preset detection points, the actual sound pressure level in the preset octave band, the number of equivalent sound sources, and the spatial coordinates of each equivalent sound source. A univariate linear regression model, and solve the univariate linear regression model corresponding to the preset octave band to obtain the sound pressure levels of multiple equivalent sound sources in the preset octave band;

The model determination module is used to obtain the transformer multi-source noise corresponding to the preset octave band according to the number of equivalent sound sources, the sound pressure level of each equivalent sound source in the preset octave band, and the spatial coordinates of each equivalent sound source effective model.

In a possible implementation, the solving module is specifically used for:

In a third aspect, an embodiment of the present invention provides a terminal, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, the The steps of the method for determining the equivalent model of transformer multi-source noise as described in the first aspect or any possible implementation manner of the first aspect.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements any of the above first aspect or the first aspect. Steps in the method for determining an equivalent model of transformer multi-source noise described in a possible implementation manner.

An embodiment of the present invention provides a method for determining an equivalent model of a transformer multi-sound source noise, a terminal, and a storage medium, by obtaining the spatial coordinates of multiple preset detection points around the transformer and the actual sound pressure level in a preset octave band; Obtain the number of equivalent sound sources of the transformer and the spatial coordinates of each equivalent sound source; according to the spatial coordinates of multiple preset detection points and the actual sound pressure level in the preset octave band, the number of equivalent sound sources and each The spatial coordinates of the effective sound source, construct the univariate linear regression model corresponding to the preset octave band, and solve the univariate linear regression model corresponding to the preset octave band, and obtain the sound of multiple equivalent sound sources in the preset octave band pressure level; according to the number of equivalent sound sources, the sound pressure level of each equivalent sound source and the spatial coordinates of each equivalent sound source, the transformer multi-source noise equivalent model corresponding to the preset octave band can be obtained, which can overcome the near-field sound For the problems of complex calculation and large amount of calculation in holographic technology, it is only necessary to measure the sound pressure level of a small number of detection points near the transformer, and obtain the equivalent model of transformer multi-sound source noise based on the method of univariate linear regression. The equivalent process is convenient and simple. The amount of calculation is small.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings that need to be used in the descriptions of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only of the present invention. For some embodiments, those of ordinary skill in the art can also obtain other drawings based on these drawings without paying creative efforts.

Fig. 1 is the implementation flowchart of the method for determining the transformer multi-source noise equivalent model provided by the embodiment of the present invention;

Fig. 2 is a schematic diagram of a transformer multi-source noise equivalent model provided by an embodiment of the present invention;

Fig. 3 is a plan view of equivalent source location distribution provided by an embodiment of the present invention;

4 is a schematic structural diagram of a device for determining an equivalent model of transformer multi-source noise provided by an embodiment of the present invention;

Fig. 5 is a schematic diagram of a terminal provided by an embodiment of the present invention.

Detailed ways

In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the invention may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

In order to make the purpose, technical solution and advantages of the present invention clearer, specific embodiments will be described below in conjunction with the accompanying drawings.

Referring to FIG. 1 , it shows a flow chart of a method for determining an equivalent model of transformer multi-source noise provided by an embodiment of the present invention. Wherein, the subject of execution of the method for determining the equivalent model of transformer multi-sound source noise may be the terminal.

Referring to Figure 1, the methods for determining the equivalent model of the above-mentioned transformer multi-source noise include:

In S101, the spatial coordinates of multiple preset detection points around the transformer and the actual sound pressure level in the preset octave band are obtained.

In this embodiment, the actual typical substation can be selected, the planar distribution map and three-dimensional space model of the substation can be obtained, and a certain point on the ground of the substation is used as the coordinate origin to establish a spatial rectangular coordinate system; several preset detection points in the free space around the substation (marked as m) to measure the sound pressure level, and record the spatial coordinates (x _Rj , y _Rj , z _Rj ) of the preset detection point and the actual sound pressure level Lm _j corresponding to the preset octave band. Wherein, the detection point may also be referred to as a field point.

In a possible implementation manner, the coordinate origin is used as a reference point, the east direction is used as the positive direction of the X-axis, the north direction is used as the positive direction of the Y-axis, and the upward direction is used as the positive direction of the Z-axis. According to the spatial position relationship between the detection point and the coordinate origin, the spatial position coordinates of the detection point are established, which are recorded as (x _Rj , y _Rj , z _Rj ), and the unit is "meter".

In this embodiment, a real-time noise signal analyzer can be used to measure the actual sound pressure level at each preset detection point. Noise real-time signal analyzer is a pocket real-time analyzer with digital signal processing technology, which can analyze the frequency spectrum and amplitude of noise, vibration or other electrical signals.

When measuring the sound pressure level of the detection point, choose a sunny and windless weather, and record the temperature, air humidity and atmospheric pressure of the day. When using a noise real-time signal analyzer to measure the sound pressure level at the detection point, each sampling point should be continuously sampled for 30 to 60 seconds, 5 times in a row, and the average value should be taken. Spectrum analysis is performed on the sampling results of the sampling points, and the sound pressure levels of the eight octave bands of 63HZ, 125HZ, 250HZ, 500HZ, 1000HZ, 2000HZ, 4000HZ and 8000HZ are respectively extracted.

The positions of each preset detection point can be selected according to actual needs, and the preset octave band can be any one of the above eight octave bands.

In S102, the number of equivalent sound sources of the transformer and the spatial coordinates of each equivalent sound source are acquired.

Wherein, the equivalent sound source may also be called an equivalent point sound source.

This embodiment can be based on the theory of multi-point equivalent sources, and according to the obtained spatial position parameters and geometric parameters of the transformer, use a correlation algorithm to obtain the geometric space information of the transformer equivalent point sound source, including the number of equivalent point sound sources and etc. Based on the spatial distribution of sound sources at effective points, etc., a transformer multi-point equivalent source noise radiation model (i.e. transformer multi-source noise equivalent model) is established, and the spatial position coordinates of n equivalent sources are marked as (x _NSi , y _NSi , _zNSi ).

Wherein, the transformer may be a 500KV three-phase main transformer, and the geometric parameters of the transformer are 16.0m in length, 5.0m in width, and 5.0m in height.

In some embodiments, the number of the above-mentioned equivalent sound sources is 24;

Based on the above-mentioned geometric parameter information of the transformer, when constructing the equivalent model of transformer multi-sound source noise, the number of equivalent sound sources is set to 24, and the arrangement method is 4x2 equivalent sound sources arranged at equal intervals on the wall of the long box, etc. effect, the equivalent sound sources arranged at 2x2 equal intervals on the wall of the short box are equivalent, as shown in Figure 2, the cuboid in Figure 2 is the virtual model of the transformer, the black dots are the equivalent sound sources, and the equivalent sound sources are distributed in the There are no equivalent sound sources for the four sides, the upper and lower sides. It should be noted that, in order to clearly show the equivalent sound source in Fig. 2, Fig. 2 only draws the equivalent sound source of a long box wall and a short box wall, but in the actual model, the two opposite long box walls are There are equivalent sound sources, and the two opposite short box walls have equivalent sound sources.

According to the spatial position of the equivalent sound source, the spatial position coordinates of the equivalent sound source are denoted as (x _NSi , y _NSi , z _NSi ).

In S103, according to the spatial coordinates of a plurality of preset detection points and the actual sound pressure level in the preset octave band, the number of equivalent sound sources and the spatial coordinates of each equivalent sound source, a single corresponding to the preset octave band is constructed. Variable linear regression model, and solve the univariate linear regression model corresponding to the preset octave band to obtain the sound pressure levels of multiple equivalent sound sources in the preset octave band.

In this embodiment, by constructing the univariate linear regression model corresponding to the preset octave band and solving the univariate linear regression model corresponding to the preset octave band, the sound pressure levels of multiple equivalent sound sources in the preset octave band can be obtained .

In this embodiment, if you want to obtain the sound pressure levels of the eight octave bands of the equivalent sound source, you can use the eight octave bands as the preset octave bands, perform the above S101-S103, and finally obtain the transformer multi-acoustic sound through S104. The sound pressure levels of the equivalent sound source of the source noise equivalent model may include sound pressure levels of eight octave bands. That is to say, different univariate linear regression models need to be constructed for different octave bands and solved to obtain the sound pressure level of the equivalent sound source in the octave band.

In some embodiments, the above S103 may include:

In this embodiment, the univariate linear regression model corresponding to the preset octave band is solved through double-layer optimization, which can improve the accuracy.

In some embodiments, according to the predicted sound pressure level of each preset detection point in the preset octave band and the actual sound pressure level of each preset detection point in the preset octave band, the univariate linearity corresponding to the preset octave band The regression model is solved, and the sound pressure levels of multiple equivalent sound sources in the preset octave bands are obtained through double-layer optimization, including:

Calculate the error value of each random variable in the first batch of random variables according to the MSE loss function, perform the first optimization, select in order from the first batch of random variables sorted according to the error value from small to large, and rank the first preset number the random variable;

The formula for the normal distribution is as follows:

Among them, μ is the mathematical expectation value of the random variable with the preset number in front, and σ ² is the variance value of the random variable with the preset number in the front.

According to the cross-entropy loss function, the second batch of random variables is solved, and the second optimization is carried out, and finally the sound pressure level of each equivalent sound source in the preset octave band is obtained through the solution.

Among them, the Uniform function can be used to generate the first batch of random variables with uniform distribution. Each random variable contains the sound pressure levels of 24 equivalent sound sources in preset octave bands, and each random variable can be different.

In the first optimization of this embodiment, the global error between the predicted value and the actual measured value is calculated according to the MSE loss function, and a preset number of random variables with smaller errors are selected, and according to the value of the preset number of random variables with smaller errors The mathematical expectation value and variance value are used to generate the second batch of random variables with a normal distribution. In the second optimization, the cross-entropy loss function is used to finally solve each equivalent sound source from the second batch of random variables in the preset Sound pressure level in octave bands. The sound pressure level of each equivalent sound source in the preset octave band is obtained through the second optimization solution.

In some embodiments, the above MSE loss function is:

in,

As shown in Figure 3, Figure 3 shows 4 field points (field point 1, field point 2, field point 3 and field point 4) and an equivalent source plane in which there are 4 equivalent acoustic source, d in Figure 3 represents the distance between one of the field points (detection points) and one of the equivalent sound sources.

The MSE loss function is a globally sensitive loss function, which is used to locate the candidate interval of Lp _i in the second optimization.

In this embodiment, the sound pressure level of the equivalent sound source in the space is the quantity to be sought, which is set as Lp _i first. According to the attenuation formula of noise in free field propagation, during the propagation of each equivalent sound source from the transformer to the detection point, the noise propagation only undergoes geometric divergence attenuation and atmospheric absorption attenuation, and the sound pressure level generated at the detection point is : Lw _ij ＝Lp _i -20lg(d _ij )-0.001*α*d _ij -11, wherein, α can be obtained by looking up Table 1, when measuring the sound pressure level of the preset detection point, the temperature and relative humidity will be recorded . The propagation distance d _ii determines the geometric divergence attenuation and atmospheric absorption attenuation in the propagation process.

Superimpose the sound pressure levels generated by all equivalent sound sources at the detection point, which is the predicted sound pressure level at the detection point. The superposition formula is as follows:

Table 1 Atmospheric absorption attenuation coefficient table

In some embodiments, the above-mentioned cross-entropy loss function is:

As a loss function, cross entropy provides data for the gradient descent in the iterative convergence process. Through small-batch stochastic gradient descent, the value interval of Lp _i is converged, and finally the value of Lp _i is solved, which is the required transformer polyphony The sound pressure level of the equivalent sound source of the source noise equivalent model in the preset octave band.

The above requirements are only the sound pressure level of the single octave band of the equivalent sound source. If you want to obtain the sound pressure level of the eight octave bands of 63HZ, 125HZ, 250HZ, 500HZ, 1000HZ, 2000HZ, 4000HZ and 8000HZ, you need to build an 8-time model. The sound pressure level of the 8 octave bands of the equivalent sound source can be obtained by using the double-layer optimization method to perform 8 optimal solutions.

In S104, according to the number of equivalent sound sources, the sound pressure level of each equivalent sound source in the preset octave band and the spatial coordinates of each equivalent sound source, the transformer multi-source noise equivalent model corresponding to the preset octave band is obtained .

After solving the sound pressure level of each equivalent sound source in the preset octave band, according to the number of equivalent sound sources, the sound pressure level of each equivalent sound source in the preset octave band and the spatial coordinates of each equivalent sound source, The equivalent model of transformer multi-source noise corresponding to the preset octave band can be obtained.

After solving the sound pressure levels of each equivalent sound source in eight octave bands, the final multi-source noise equivalent model of the transformer can be obtained.

This embodiment obtains the spatial coordinates of multiple preset detection points around the transformer and the actual sound pressure level in the preset octave band; obtains the number of equivalent sound sources of the transformer and the spatial coordinates of each equivalent sound source; according to multiple The spatial coordinates of a preset detection point and the actual sound pressure level in the preset octave band, the number of equivalent sound sources and the spatial coordinates of each equivalent sound source, construct a univariate linear regression model corresponding to the preset octave band, and Solve the univariate linear regression model corresponding to the preset octave band to obtain the sound pressure levels of multiple equivalent sound sources in the preset octave band; according to the number of equivalent sound sources, the sound pressure levels of each equivalent sound source and The spatial coordinates of each equivalent sound source obtain the equivalent model of transformer multi-source noise corresponding to the preset octave band, which can overcome the problems of complex calculation and large amount of calculation in near-field acoustic holography technology, and only need to measure a small number of detection points near the transformer The sound pressure level of the transformer is obtained based on the method of univariate linear regression to obtain the equivalent model of transformer multi-sound source noise. The equivalent process is convenient and simple, and the amount of calculation is small.

In this embodiment, a univariate linear regression model is constructed based on the noise radiation attenuation characteristics, using MSE and cross-entropy as loss functions, and the sound pressure level of the multi-sound source equivalent model of the transformer is obtained through double-layer optimization. The equivalent process is convenient and simple, and the calculation amount is small, and the equivalent result is more accurate through double-layer optimization.

It should be understood that the sequence numbers of the steps in the above embodiments do not mean the order of execution, and the execution order of each process should be determined by its functions and internal logic, and should not constitute any limitation to the implementation process of the embodiment of the present invention.

The following are device embodiments of the present invention. For details that are not exhaustively described therein, reference may be made to the corresponding method embodiments above.

Fig. 4 shows a schematic structural diagram of a device for determining the equivalent model of transformer multi-source noise provided by an embodiment of the present invention. For the convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:

As shown in FIG. 4 , the device 30 for determining the equivalent model of transformer multi-source noise includes: a first acquisition module 31 , a second acquisition module 32 , a solution module 33 and a model determination module 34 .

The first acquisition module 31 is used to acquire the spatial coordinates of a plurality of preset detection points around the transformer and the actual sound pressure level in the preset octave band;

The second acquisition module 32 is used to acquire the quantity of equivalent sound sources of the transformer and the spatial coordinates of each equivalent sound source;

The solution module 33 is used to construct a preset octave band corresponding and solve the univariate linear regression model corresponding to the preset octave band to obtain the sound pressure levels of multiple equivalent sound sources in the preset octave band;

The model determination module 34 is used to obtain the transformer multi-source noise corresponding to the preset octave band according to the number of equivalent sound sources, the sound pressure level of each equivalent sound source in the preset octave band and the spatial coordinates of each equivalent sound source equivalent model.

In a possible implementation, the solving module 33 is specifically used for:

According to the MSE loss function, the first optimization is carried out, and the error value calculated by the MSE loss function is selected from the first batch of random variables in order from small to large, and the first preset number of random variables are ranked;

According to the mathematical expectation and variance of the preset number of random variables, the second batch of random variables is generated by using the normal distribution method, as the second optimization of the univariate linear regression model corresponding to the preset octave band input variable;

According to the cross-entropy loss function, the second optimization is carried out, and the sound pressure level of each equivalent sound source in the preset octave band is finally obtained from the second batch of random variables.

In one possible implementation, the MSE loss function is:

In one possible implementation, the cross-entropy loss function is:

In another implementation example, the above-mentioned device for determining the multi-source noise equivalent model of a transformer includes: a processor, wherein the processor is used to execute the above-mentioned program modules stored in the memory, including: a first acquisition module 31, a second acquisition module 32. A solution module 33 and a model determination module 34.

Fig. 5 is a schematic diagram of a terminal provided by an embodiment of the present invention. As shown in FIG. 5 , the terminal 4 of this embodiment includes: a processor 40 , a memory 41 and a computer program 42 stored in the memory 41 and operable on the processor 40 . When the processor 40 executes the computer program 42, it implements the steps in the embodiment of the method for determining the equivalent model of each transformer multi-source noise, such as S101 to S104 shown in FIG. 1 . Or, when the processor 40 executes the computer program 42, it realizes the functions of the modules/units in the above-mentioned device embodiments, such as the functions of the modules/units 31 to 34 shown in FIG. 4 .

Exemplarily, the computer program 42 can be divided into one or more modules/units, and the one or more modules/units are stored in the memory 41 and executed by the processor 40 to complete this invention. The one or more modules/units may be a series of computer program instruction segments capable of accomplishing specific functions, and the instruction segments are used to describe the execution process of the computer program 42 in the terminal 4 . For example, the computer program 42 may be divided into the modules/units 31 to 34 shown in FIG. 4 .

The terminal 4 can be a computing device such as a desktop computer, a notebook, a palmtop computer, or a cloud server. The terminal 4 may include, but not limited to, a processor 40 and a memory 41 . Those skilled in the art can understand that FIG. 5 is only an example of the terminal 4 and does not constitute a limitation to the terminal 4. It may include more or less components than those shown in the figure, or combine certain components, or different components, such as The terminal may also include an input and output device, a network access device, a bus, and the like.

The so-called processor 40 can be a central processing unit (Central Processing Unit, CPU), and can also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.

The memory 41 may be an internal storage unit of the terminal 4 , such as a hard disk or memory of the terminal 4 . The memory 41 can also be an external storage device of the terminal 4, such as a plug-in hard disk equipped on the terminal 4, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, Flash card (Flash Card), etc. Further, the memory 41 may also include both an internal storage unit of the terminal 4 and an external storage device. The memory 41 is used to store the computer program and other programs and data required by the terminal. The memory 41 can also be used to temporarily store data that has been output or will be output.

Those skilled in the art can clearly understand that for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used for illustration. In practical applications, the above-mentioned functions can be assigned to different functional units, Completion of modules means that the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment may be integrated into one processing unit, or each unit may exist separately physically, or two or more units may be integrated into one unit, and the above-mentioned integrated units may adopt hardware It can also be implemented in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the present application. For the specific working processes of the units and modules in the above system, reference may be made to the corresponding processes in the aforementioned method embodiments, and details will not be repeated here.

In the above-mentioned embodiments, the descriptions of each embodiment have their own emphases, and for parts that are not detailed or recorded in a certain embodiment, refer to the relevant descriptions of other embodiments.

Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the present invention.

In the embodiments provided in the present invention, it should be understood that the disclosed device/terminal and method may be implemented in other ways. For example, the device/terminal embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or Components may be combined or integrated into another system, or some features may be omitted, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

If the integrated module/unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention realizes all or part of the processes in the methods of the above embodiments, and can also be completed by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer When the program is executed by the processor, the steps in the above embodiments of the method for determining the equivalent model of the transformer multi-source noise can be realized. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a removable hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (Read-Only Memory, ROM) , random access memory (Random Access Memory, RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, computer-readable media Excluding electrical carrier signals and telecommunication signals.

The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still carry out the foregoing embodiments Modifications to the technical solutions recorded in the examples, or equivalent replacement of some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should be included in within the protection scope of the present invention.

Claims

A method for determining an equivalent model of transformer multi-source noise, characterized in that it includes:

Obtain the spatial coordinates of multiple preset detection points around the transformer and the actual sound pressure level in the preset octave band;

Obtain the number of equivalent sound sources of the transformer and the spatial coordinates of each equivalent sound source;

According to the spatial coordinates of a plurality of preset detection points and the actual sound pressure level in the preset octave band, the number of the equivalent sound sources and the spatial coordinates of each equivalent sound source, construct the unit corresponding to the preset octave band A variable linear regression model, and solving the univariate linear regression model corresponding to the preset octave band to obtain the sound pressure levels of multiple equivalent sound sources in the preset octave band;

According to the number of equivalent sound sources, the sound pressure level of each equivalent sound source in the preset octave band and the spatial coordinates of each equivalent sound source, the transformer multi-source noise equivalent model corresponding to the preset octave band is obtained .
The method for determining the equivalent model of transformer multi-sound source noise according to claim 1, wherein the spatial coordinates of multiple preset detection points and the actual sound pressure level in the preset octave band, the etc. The number of effective sound sources and the spatial coordinates of each equivalent sound source, construct the univariate linear regression model corresponding to the preset octave band, and solve the univariate linear regression model corresponding to the preset octave band, and obtain multiple The sound pressure level of an equivalent sound source in the preset octave band, including:

According to the spatial coordinates of a plurality of preset detection points and the actual sound pressure level in the preset octave band, the number of the equivalent sound sources and the spatial coordinates of each equivalent sound source, construct the unit corresponding to the preset octave band variable linear regression model;

According to the predicted sound pressure level of each preset detection point in the preset octave band and the actual sound pressure level of each preset detection point in the preset octave band, the univariate linear regression model corresponding to the preset octave band is solved, The sound pressure levels of multiple equivalent sound sources in the preset octave bands are obtained through double-layer optimization.
The method for determining the equivalent model of transformer multi-sound source noise according to claim 2, wherein the predicted sound pressure level of each preset detection point in the preset octave band and each preset detection point in the preset For the actual sound pressure level of the octave band, the univariate linear regression model corresponding to the preset octave band is solved, and the sound pressure levels of multiple equivalent sound sources in the preset octave band are obtained through double-layer optimization, including:

Using the method of average distribution, generate the first batch of random variables, as the input variable when the univariate linear regression model corresponding to the preset octave band is optimized for the first time;

Calculate the error value of each random variable in the first batch of random variables according to the MSE loss function, and select a preset number of random variables in order from the first batch of random variables sorted from small to large according to the error value;

The mathematical expectation value and variance value of each selected random variable are calculated using the method of normal distribution, and the second batch of random variables are generated as the second optimization of the univariate linear regression model corresponding to the preset octave band the input variable;

The second batch of random variables are solved according to the cross-entropy loss function to obtain the sound pressure level of each equivalent sound source in the preset octave band.
The method for determining the equivalent model of transformer multi-sound source noise according to claim 3, wherein the MSE loss function is:

Among them, MSE is the error value calculated by the MSE loss function; m is the number of predicted detection points; Lm j is the actual sound pressure level of the jth preset detection point in the preset octave band; Lw j is the jth preset The predicted sound pressure level of the detection point in the preset octave band,
Lw ij ＝Lp i -20lg(d ij )-0.001*α*d ij -11; n is the number of equivalent sound sources; Lw ij is the i-th equivalent sound source generated at the j-th preset detection point The sound pressure level in the preset octave band; Lp i is the sound pressure level of the i-th equivalent sound source in the preset octave band, which is an unknown quantity; d ij is the i-th equivalent sound source and the j-th The distance between preset detection points; α is the atmospheric absorption attenuation coefficient of noise during propagation.
The method for determining the equivalent model of transformer multi-source noise according to claim 4, wherein the cross-entropy loss function is:

Among them, L is the value calculated by the cross-entropy loss function; P(Lp i ) is the value probability of Lp i in the normal distribution function.
The method for determining the equivalent model of transformer multi-sound source noise according to any one of claims 1 to 5, wherein the number of said equivalent sound sources is 24;

The distribution of the equivalent sound sources is as follows: the wall surface of the long box is arranged at equal intervals according to the 4*2 specification, and the wall surface of the short box is arranged at equal intervals according to the 2*2 specification.
A device for determining an equivalent model of transformer multi-source noise, characterized in that it includes:

The first acquisition module is used to acquire the spatial coordinates of multiple preset detection points around the transformer and the actual sound pressure level in the preset octave band;

The second acquisition module is used to acquire the number of equivalent sound sources of the transformer and the spatial coordinates of each equivalent sound source;

A solution module, configured to construct the preset according to the spatial coordinates of multiple preset detection points, the actual sound pressure level in the preset octave band, the number of the equivalent sound sources, and the spatial coordinates of each equivalent sound source A univariate linear regression model corresponding to the octave band, and solving the univariate linear regression model corresponding to the preset octave band to obtain the sound pressure levels of multiple equivalent sound sources in the preset octave band;

The model determination module is used to obtain the number of transformers corresponding to the preset octave band according to the number of equivalent sound sources, the sound pressure level of each equivalent sound source in the preset octave band and the spatial coordinates of each equivalent sound source Equivalent model of sound source noise.
The device for determining the equivalent model of transformer multi-sound source noise according to claim 7, wherein the solving module is specifically used for:

According to the spatial coordinates of a plurality of preset detection points and the actual sound pressure level in the preset octave band, the number of the equivalent sound sources and the spatial coordinates of each equivalent sound source, construct the unit corresponding to the preset octave band variable linear regression model;

According to the predicted sound pressure level of each preset detection point in the preset octave band and the actual sound pressure level of each preset detection point in the preset octave band, the univariate linear regression model corresponding to the preset octave band is solved, The sound pressure levels of multiple equivalent sound sources in the preset octave bands are obtained through double-layer optimization.
A terminal, comprising a memory, a processor, and a computer program stored in the memory and operable on the processor, characterized in that, when the processor executes the computer program, the above claims 1 to 1 are implemented. Steps in the determination method of the multi-source noise equivalent model of the transformer described in any one of 6.
A computer-readable storage medium, the computer-readable storage medium stores a computer program, characterized in that, when the computer program is executed by a processor, it realizes the multi-sound transformer described in any one of claims 1 to 6 above. The steps of the determination method of the source noise equivalent model.