Substation composite sound barrier sound reduction index prediction method and system based on linear regression

Abstract

The invention discloses a transformer substation composite sound barrier sound reduction index prediction method and system based on linear regression, and the method comprises the steps: determining key influence factors of different material layers in a multi-layer composite sound barrier on the overall sound reduction index based on an acoustic theory, collecting data related to the key influence factors, and constructing a data set; and analyzing the data set based on a linear regression method, establishing a mathematical relationship between the key influence factors and the sound reduction index, and forming a sound reduction index prediction model, thereby predicting the sound reduction index of the multilayer composite sound barrier. According to the method, multiple factors such as the density, the thickness and the elastic modulus of the material are comprehensively considered, and different influence factors are respectively considered particularly for different structural parts of the composite material. And accurately predicting the sound insulation performance of the composite material on the basis of the multiple linear regression model. Experimental results show that the prediction precision of the sound insulation index can be remarkably improved, and a scientific basis is provided for sound insulation design of the multi-layer composite material.

Description

Technical Field

[0001] The present invention relates to the technical field of sound insulation prediction, and in particular to a method and system for predicting the sound insulation of a composite sound barrier of a substation based on linear regression. Background Art

[0002] In recent years, with the continuous acceleration of urbanization, the power supply load is getting higher and higher. In order to ease the pressure of urban power supply, more substations have to be built in the city. Due to the high noise of substation transformers and the close distance to residential areas, if the substation noise cannot be effectively controlled, it will inevitably affect the normal life of surrounding residents, cause environmental complaints and disputes, and endanger the harmony and stability of society. Sound barriers are currently the most important noise reduction facilities for substation noise control. It is an effective way to control substation noise and can cut off the propagation path of noise. In order to achieve the sound insulation effect of sound barriers, it is very important to accurately predict their sound insulation.

[0003] There are three main existing technologies for estimating the sound insulation of sound insulation materials: laboratory measurement method, theoretical calculation method and empirical formula method.

[0004] The experimental measurement method is currently the main means of evaluating the sound insulation of materials. The sound insulation effect is measured by constructing material samples and conducting acoustic performance tests in a laboratory environment. The advantage of this method is that the sound insulation performance of the actual material can be directly obtained with high accuracy. However, the disadvantages are also obvious, which is costly and time-consuming. The laboratory measurement method requires the construction of actual samples, which involves material and labor costs. The testing process is also relatively complicated, and each test takes a certain amount of time. In particular, when multiple materials need to be tested, the cost is higher, and it is difficult to quickly evaluate and optimize different materials and structural solutions during the design stage.

[0005] The theoretical calculation method uses the physical properties of materials and acoustic theory to establish a mathematical model to predict the sound insulation performance of materials. Common methods include Finite Element Analysis (FEA) and Boundary Element Method (BEM). The advantage of this method is that it does not require actual samples and can be predicted through computer simulation, saving the cost and time of building samples. It can also simulate the combination of different materials and structures, and compare and optimize multiple design schemes. However, the results are very dependent on the accuracy of the model, and there may be deviations in practical applications.

[0006] The empirical formula method is based on a large amount of experimental data. By summarizing the rules, a simple empirical formula is established to predict the sound insulation of the material. The prediction using the empirical formula is simple and fast, and the use of the empirical formula does not require complex computer simulations and advanced theoretical knowledge, making it easy to apply in actual engineering. However, the existing empirical formulas are usually targeted at specific types of materials and application scenarios, and have poor versatility. For example, the empirical formula for the sound insulation of a double-layer sound insulation structure with an air layer in the middle at medium frequencies can be calculated as follows.

[0007] R=18lg(ρ A1 +ρ A2 )+8+ΔTL(when ρ A1 +ρ A2 >100Kg / m 2 hour)

[0008] R=13.5lg(ρ A1 +ρ A2 )+13+ΔTL(when ρ A1 +ρ A2 <100Kg / m 2 hour)

[0009] Where R is the sound insulation, ρ A1 and ρ A2 They are the surface density of the double-layer structure (Kg / m 2 ), ΔTL is the additional sound insulation of air. Although the above formula is simple and convenient, it is only applicable to calculate the sound insulation of specific structures and materials under specific conditions.

[0010] The sound insulation performance of materials is affected by many factors, such as the density, thickness, elastic modulus, etc. However, the existing empirical formulas usually only consider one of these factors, which results in only a rough estimate and is difficult to accurately reflect the complexity of the actual situation. In addition, these empirical formulas are usually applicable to simpler situations such as single-layer homogeneous components or double-layer structures, while in actual engineering, the materials used are usually composed of multi-layer composite structures, including sound insulation layers, damping layers, sound absorption layers and other materials. Therefore, there is an urgent need for a method that can accurately estimate the sound insulation performance of composite materials in actual engineering. Summary of the invention

[0011] Existing experimental measurement methods, theoretical calculation methods and empirical formulas are the main means of evaluating the sound insulation performance of materials, but these methods have their own limitations, which makes it difficult to achieve efficient and accurate predictions in practical applications. Therefore, the present invention proposes a method and system for predicting the sound insulation of a composite sound barrier in a substation based on linear regression, which comprehensively considers multiple influencing factors such as material density, thickness, elastic modulus, and especially considers different influencing factors for different structural parts of the composite material. For example, the sound absorption layer will specifically consider the sound absorption coefficient and thickness, while the sound insulation layer mainly considers the surface density and thickness. The prediction model established using the linear regression model can not only accurately estimate the sound insulation performance of multi-layer composite materials, overcome the limitations of empirical formulas, but also quickly evaluate and optimize different materials and structural schemes in the design stage, reduce costs, and improve engineering design efficiency.

[0012] The technical solution adopted by the present invention is as follows:

[0013] A method for predicting the sound insulation of a substation composite sound barrier based on linear regression, comprising:

[0014] Based on acoustic theory, determine the key influencing factors of different material layers in multi-layer composite sound barriers on the overall sound insulation, collect data related to the key influencing factors and construct a data set;

[0015] The data set is analyzed based on the linear regression method, a mathematical relationship between key influencing factors and sound insulation is established, and a sound insulation prediction model is formed to predict the sound insulation of the multi-layer composite sound barrier.

[0016] Furthermore, the key influencing factors of different material layers in the multi-layer composite sound barrier on the overall sound insulation are determined based on acoustic theory, including:

[0017] Based on acoustic theory, the influencing factors of the multi-layer composite sound barrier on the overall sound insulation are divided into material structure attributes and external influencing factors. The material structure attributes include thickness, surface density, elastic modulus, loss factor and average sound absorption coefficient. The external influencing factors include the frequency of the incident sound wave.

[0018] Determine the key influencing factors of different material layers in the multi-layer composite sound barrier on the overall sound insulation. The types of material layers in the multi-layer composite sound barrier include sound insulation layer, sound absorption layer, damping layer and air layer. The key influencing factors of the sound insulation layer on the overall sound insulation include thickness, surface density, elastic modulus and loss factor; the key influencing factors of the sound absorption layer on the overall sound insulation include average sound absorption coefficient and thickness; the key influencing factors of the damping layer on the overall sound insulation include elastic modulus, loss factor and thickness; the key influencing factors of the air layer on the overall sound insulation include thickness.

[0019] Furthermore, the collecting of data related to key influencing factors and constructing a data set includes:

[0020] After determining the key influencing factors, obtain data related to the key influencing factors through experimental measurement or citing existing literature data, and screen and process them to remove abnormal data that does not meet the preset standards;

[0021] A corresponding data set is constructed based on the screened and processed data, and the data set includes material structure properties of different material layers and corresponding sound insulation values; the data set is divided into a training set and a validation set, and it is ensured that the data types of the two are evenly distributed. The training set will be used for model construction and training, and the validation set will be used for model evaluation and optimization.

[0022] Furthermore, the data set is analyzed based on a linear regression method to establish a mathematical relationship between key influencing factors and sound insulation and form a sound insulation prediction model, including:

[0023] After the dataset is constructed, the material structural properties that have a significant impact on the sound insulation are identified and selected from the training set of the dataset as input features of the sound insulation prediction model;

[0024] The training set is used to fit the sound insulation prediction model, and the mathematical relationship between the material structure properties and the sound insulation is established to predict the sound insulation performance of the material.

[0025] Furthermore, the data set is analyzed based on a linear regression method to establish a mathematical relationship between key influencing factors and sound insulation and form a sound insulation prediction model, and further includes:

[0026] After the sound insulation prediction model is constructed, the material structure properties in the validation set of the data set are input into the sound insulation prediction model, and the corresponding sound insulation is predicted by the sound insulation prediction model; the prediction results are compared and analyzed with the actual measurement data to evaluate the prediction error and applicability of the sound insulation prediction model, and the comparison between the actual value and the predicted value in the validation set is displayed.

[0027] A substation composite sound barrier sound insulation prediction system based on linear regression, comprising:

[0028] A data set construction module, configured to determine the key influencing factors of different material layers in the multi-layer composite sound barrier on the overall sound insulation based on acoustic theory, collect data related to the key influencing factors and construct a data set;

[0029] The sound insulation prediction module is configured to analyze the data set based on a linear regression method, establish a mathematical relationship between key influencing factors and sound insulation and form a sound insulation prediction model, thereby predicting the sound insulation of the multi-layer composite sound barrier.

[0030] Furthermore, in the dataset construction module, the key influencing factors of different material layers in the multi-layer composite sound barrier on the overall sound insulation are determined based on acoustic theory, including:

[0031] Based on acoustic theory, the influencing factors of the multi-layer composite sound barrier on the overall sound insulation are divided into material structure attributes and external influencing factors. The material structure attributes include thickness, surface density, elastic modulus, loss factor and average sound absorption coefficient. The external influencing factors include the frequency of the incident sound wave.

[0032] Determine the key influencing factors of different material layers in the multi-layer composite sound barrier on the overall sound insulation. The types of material layers in the multi-layer composite sound barrier include sound insulation layer, sound absorption layer, damping layer and air layer. The key influencing factors of the sound insulation layer on the overall sound insulation include thickness, surface density, elastic modulus and loss factor; the key influencing factors of the sound absorption layer on the overall sound insulation include average sound absorption coefficient and thickness; the key influencing factors of the damping layer on the overall sound insulation include elastic modulus, loss factor and thickness; the key influencing factors of the air layer on the overall sound insulation include thickness.

[0033] Furthermore, in the data set construction module, data related to key influencing factors are collected and a data set is constructed, including:

[0034] After determining the key influencing factors, obtain data related to the key influencing factors through experimental measurement or citing existing literature data, and screen and process them to remove abnormal data that does not meet the preset standards;

[0035] A corresponding data set is constructed based on the screened and processed data, and the data set includes material structure properties of different material layers and corresponding sound insulation values; the data set is divided into a training set and a validation set, and it is ensured that the data types of the two are evenly distributed. The training set will be used for model construction and training, and the validation set will be used for model evaluation and optimization.

[0036] Furthermore, in the sound insulation prediction module, the data set is analyzed based on a linear regression method, a mathematical relationship between key influencing factors and sound insulation is established, and a sound insulation prediction model is formed, including:

[0037] After the dataset is constructed, the material structural properties that have a significant impact on the sound insulation are identified and selected from the training set of the dataset as input features of the sound insulation prediction model;

[0038] The training set is used to fit the sound insulation prediction model, and the mathematical relationship between the material structure properties and the sound insulation is established to predict the sound insulation performance of the material.

[0039] Furthermore, in the sound insulation prediction module, the data set is analyzed based on a linear regression method, a mathematical relationship between key influencing factors and sound insulation is established, and a sound insulation prediction model is formed, which also includes:

[0040] After the sound insulation prediction model is constructed, the material structure properties in the validation set of the data set are input into the sound insulation prediction model, and the corresponding sound insulation is predicted by the sound insulation prediction model; the prediction results are compared and analyzed with the actual measurement data to evaluate the prediction error and applicability of the sound insulation prediction model, and the comparison between the actual value and the predicted value in the validation set is displayed.

[0041] The beneficial effects of the present invention are:

[0042] In view of the limitations of traditional methods in estimating the sound insulation of multi-layer materials, the present invention proposes a method and system for predicting the sound insulation of substation composite sound barriers based on linear regression, which comprehensively considers multiple factors such as material density, thickness, elastic modulus, and especially considers different influencing factors for different structural parts of the composite material. Based on the multivariate linear regression model, the sound insulation performance of the composite material is accurately predicted. Experimental results show that the present invention can significantly improve the prediction accuracy of the sound insulation and provide a scientific basis for the sound insulation design of multi-layer composite materials. Compared with traditional methods, the present invention has the following advantages:

[0043] (1) Accurately predict the sound insulation of multi-layer materials: The present invention can effectively solve the shortcomings of traditional methods in dealing with complex multi-layer composite materials and provide more accurate sound insulation estimation results.

[0044] (2) Improve design efficiency: The prediction method based on the multivariate linear regression model can quickly complete the evaluation of sound insulation performance during the design stage, avoiding the high cost and time consumption of traditional experimental measurement methods, and greatly improving the efficiency of engineering design. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a flow chart of a method for predicting the sound insulation of a composite sound barrier in a substation based on linear regression in Example 1 of the present invention.

[0046] Figure 2 It is a comparison chart of the true value and the predicted value of the verification set in Example 1 of the present invention. DETAILED DESCRIPTION

[0047] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific implementation methods of the present invention are now described. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention, that is, the embodiments described are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0048] Example 1

[0049] Existing experimental measurement methods, theoretical calculation methods and empirical formulas are the main means to evaluate the sound insulation performance of materials, but these methods have their own limitations, which makes it difficult to achieve efficient and accurate predictions in practical applications. The details are as follows.

[0050] 1. Experimental measurement method: Although the experimental measurement method can directly obtain the sound insulation performance of the material with high accuracy, its disadvantages are that it is costly and time-consuming. Especially when multiple materials need to be tested, it is difficult to quickly evaluate and optimize different materials and structural solutions in the design stage.

[0051] 2. Theoretical calculation method: Theoretical calculation method predicts the sound insulation performance of materials by establishing mathematical models. Common methods include finite element analysis and boundary element method. Although this method does not require actual samples, can save costs and time, and can simulate multiple material combinations for design optimization, its results depend on the accuracy of the model, and there may be deviations in actual applications, which cannot fully reflect the actual sound insulation performance of composite materials.

[0052] 3. Empirical formula: Existing empirical formulas are usually based on a single factor, such as the density or thickness of the material, and only provide a rough estimate that is difficult to accurately reflect the complex situations in actual applications. Especially for complex multi-layer composite structures, the applicability and accuracy of empirical formulas are limited.

[0053] Based on this, this embodiment provides a method for predicting the sound insulation of a substation composite sound barrier based on linear regression. Figure 1 As shown, it includes: determining the key influencing factors of different material layers in the multi-layer composite sound barrier on the overall sound insulation based on acoustic theory, collecting data related to the key influencing factors and constructing a data set; analyzing the data set based on the linear regression method, establishing a mathematical relationship between the key influencing factors and the sound insulation and forming a sound insulation prediction model, so as to predict the sound insulation of the multi-layer composite sound barrier.

[0054] To illustrate the specific application of the sound insulation prediction method, this embodiment will take a three-layer composite structure commonly used in engineering (i.e., sound insulation layer-sound absorption layer-sound insulation layer) as an example for detailed description. Specifically, the sound insulation prediction method can adopt the following key steps to achieve accurate prediction of the sound insulation of multi-layer materials:

[0055] Step 1: Determine the factors that affect the sound insulation of different materials in the composite structure.

[0056] First, based on acoustic theory, identify the key factors that affect the sound insulation of multilayer materials. These factors include both the inherent properties of the material (such as surface density, thickness and elastic modulus) and external factors (such as the frequency of the incident sound wave). Through theoretical analysis and literature research, clarify how these factors affect the sound insulation performance of the material.

[0057] In this embodiment, the materials in the composite structure are mainly divided into four types: sound insulation layer, sound absorption layer, damping layer and air layer. For the sound insulation layer, the general single-layer board sound insulation curve can be divided into four main frequency regions: stiffness control region, damping control region, quality control region and matching effect region.

[0058] In the stiffness control area, when the sound wave frequency is lower than the resonant frequency of the board, the sound insulation is mainly determined by the stiffness of the material. The elastic modulus of the material is a key indicator for measuring stiffness. The greater the stiffness, the better the sound insulation effect.

[0059] In the damping control area, the sound insulation is mainly affected by the damping properties of the material, which is usually characterized by the loss factor.

[0060] In the quality control area, the sound insulation increases linearly with the increase of frequency. At this time, the sound insulation is mainly determined by the surface density of the board.

[0061] In the matching effect area, when the wavelength of the sound wave is the same as the wavelength of the bending wave of the plate structure, the plate is easily excited to vibrate, resulting in a significant decrease in sound insulation. The key parameter in this area is the critical frequency, which is closely related to the surface quality, elastic modulus, thickness and surface density.

[0062] For the sound absorbing layer and the damping layer, the factors affecting the overall sound insulation performance are similar to those of the sound insulation layer. However, the elastic modulus and loss factors are usually not considered for the sound absorbing layer, and the key parameter is mainly the average sound absorption coefficient. In addition, since the sound absorbing layer and the damping layer are usually thinner and have lower density than the sound insulation layer, they contribute less to the overall surface density, so the surface density factor can be ignored. For the air layer, the only important factor is the thickness. The following table lists the main factors affecting the total sound insulation of these four materials.

[0063] Table 1 - Factors affecting the sound insulation of different materials in composite structures

[0064] Material Influencing factors Sound insulation layer Thickness, area density, elastic modulus, loss factor Air layer thickness Sound absorbing layer Average sound absorption coefficient, thickness Damping layer Elastic modulus, loss factor, thickness

[0065] For this embodiment, i.e., a three-layer composite structure of sound insulation layer-sound absorption layer-sound insulation layer, factors affecting the total sound insulation include: the thickness, surface density, elastic modulus and loss factor of the two sound insulation layers, the thickness, surface density and average sound absorption coefficient of the sound absorption layer and the frequency of the external incident sound wave.

[0066] Step 2: Build the dataset.

[0067] After determining the key influencing factors, a detailed data set needs to be constructed through experimental measurements or reference to existing literature data. This data set should cover parameters such as the density, thickness, elastic modulus, thickness of the sound-absorbing layer, average sound absorption coefficient, and the corresponding sound insulation of various materials. The types of materials involved include common metal plates (such as steel plates, aluminum plates), gypsum boards, brick walls commonly used in construction, etc., while sound-absorbing materials include ultra-fine wool, glass wool, mineral wool, and other types. The collection and systematic analysis of these data will lay a solid foundation for the construction of subsequent sound insulation prediction models.

[0068] Subsequently, the collected data needs to be strictly screened and processed to remove abnormal data that does not meet the standards to ensure the reliability and consistency of the data. To ensure the effectiveness and accuracy of the model, the data set is divided into a training set and a validation set at a ratio of 80% and 20%, and the data types of the two are ensured to be evenly distributed. The training set will be used for model construction and training, while the validation set will be used for model evaluation and optimization to further improve the accuracy of the prediction.

[0069] Step 3: Linear regression model construction.

[0070] After completing the construction of the data set, the linear regression method was used to develop a sound insulation prediction model. First, key structural properties that have a significant impact on sound insulation, such as surface density, thickness, average sound absorption coefficient, etc., were identified and selected from the data set as input features of the model. Then, the model was fitted using the training data set to establish a linear relationship model between these structural properties and the sound insulation of the material. The model generates a mathematical formula through regression coefficients to predict the sound insulation performance of the material. Through model fitting, the mathematical formula for predicting sound insulation was obtained:

[0071] R=19.5886+0.0468h1+0.0474h2+0.0623M1+0.0611M2-0.0257E1

[0072] -0.0252E2+0.0558η1+0.0560η2+0.0036f+0.0742h a +4.5062α

[0073] Where R is the sound insulation value (dB), h1 and h2 are the thickness of the two sound insulation layers (mm), M1 and M2 are the surface density of the two sound insulation layers (kg / m 2 ), E1 and E2 are the elastic moduli of the two sound insulation layers (1×10 9 ×N / m 2 ), η1 and η2 are the loss factors of the two sound insulation layers (1×10 -4 ), f is the incident sound wave frequency (Hz), h a is the thickness of the sound absorbing layer, and α is the average sound absorption coefficient of the sound absorbing layer.

[0074] Step 4: Linear regression model validation.

[0075] After the model is built, it needs to be verified to evaluate the prediction accuracy and reliability of the model. Specifically, using the validation data set, the structural properties of the multilayer material (such as surface density, thickness, etc.) are input into the model, and the corresponding sound insulation is calculated using the aforementioned regression formula. Then, the prediction results are compared and analyzed with the actual measured data to evaluate the prediction error and applicability of the model. The comparison between the true value and the predicted value in the validation set is shown.

[0076] like Figure 2 The following is the comparison between the actual value and the predicted value of the validation set. Figure 2 It can be seen that the error between the model prediction value and the actual sound insulation value is within an acceptable range, indicating that the model has good prediction performance.

[0077] In summary, the method for predicting the sound insulation of composite sound barriers for substations based on linear regression in this embodiment comprehensively considers multiple influencing factors such as material density, thickness, elastic modulus, etc., and especially considers different influencing factors for different structural parts of the composite material. The sound insulation prediction model established using the linear regression model can not only accurately estimate the sound insulation performance of multi-layer composite materials, overcome the limitations of empirical formulas, but also quickly evaluate and optimize different materials and structural solutions in the design stage, reduce costs, and improve engineering design efficiency.

[0078] Example 2

[0079] This embodiment provides a substation composite sound barrier sound insulation prediction system based on linear regression, including:

[0080] A data set construction module, configured to determine the key influencing factors of different material layers in the multi-layer composite sound barrier on the overall sound insulation based on acoustic theory, collect data related to the key influencing factors and construct a data set;

[0081] The sound insulation prediction module is configured to analyze the data set based on the linear regression method, establish the mathematical relationship between the key influencing factors and the sound insulation and form a sound insulation prediction model, so as to predict the sound insulation of the multi-layer composite sound barrier.

[0082] Preferably, in the data set construction module, the key influencing factors of different material layers in the multi-layer composite sound barrier on the overall sound insulation are determined based on acoustic theory, including:

[0083] Based on acoustic theory, the influencing factors of multi-layer composite sound barriers on the overall sound insulation are divided into material structural properties and external influencing factors. The material structural properties include thickness, surface density, elastic modulus, loss factor and average sound absorption coefficient, and the external influencing factors include the frequency of the incident sound wave.

[0084] Determine the key influencing factors of different material layers in the multi-layer composite sound barrier on the overall sound insulation. The types of material layers in the multi-layer composite sound barrier include sound insulation layer, sound absorption layer, damping layer and air layer. The key influencing factors of the sound insulation layer on the overall sound insulation include thickness, surface density, elastic modulus and loss factor; the key influencing factors of the sound absorption layer on the overall sound insulation include average sound absorption coefficient and thickness; the key influencing factors of the damping layer on the overall sound insulation include elastic modulus, loss factor and thickness; the key influencing factors of the air layer on the overall sound insulation include thickness.

[0085] Preferably, in the data set construction module, collecting data related to key influencing factors and constructing a data set includes:

[0086] After determining the key influencing factors, obtain data related to the key influencing factors through experimental measurement or citing existing literature data, and screen and process them to remove abnormal data that does not meet the preset standards;

[0087] Based on the screened and processed data, the corresponding data set is constructed. The data set includes the material structure properties of different material layers and the corresponding sound insulation. The data set is divided into a training set and a validation set, and it is ensured that the data types of the two are evenly distributed. The training set will be used for model construction and training, and the validation set will be used for model evaluation and optimization.

[0088] Preferably, in the sound insulation prediction module, the data set is analyzed based on a linear regression method, a mathematical relationship between key influencing factors and sound insulation is established, and a sound insulation prediction model is formed, including:

[0089] After the dataset is constructed, the material structural properties that have a significant impact on the sound insulation are identified and selected from the training set of the dataset as input features of the sound insulation prediction model;

[0090] The training set is used to fit the sound insulation prediction model, and the mathematical relationship between the material structure properties and the sound insulation is established to predict the sound insulation performance of the material.

[0091] Preferably, in the sound insulation prediction module, the data set is analyzed based on a linear regression method, a mathematical relationship between key influencing factors and sound insulation is established, and a sound insulation prediction model is formed, which also includes:

[0092] After the sound insulation prediction model is constructed, the material structure properties in the validation set of the data set are input into the sound insulation prediction model, and the corresponding sound insulation is predicted by the sound insulation prediction model; the prediction results are compared and analyzed with the actual measurement data to evaluate the prediction error and applicability of the sound insulation prediction model, and the comparison between the actual value and the predicted value in the validation set is displayed.

[0093] Example 3

[0094] This embodiment is based on embodiment 1:

[0095] This embodiment provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method for predicting the sound insulation of a substation composite sound barrier based on linear regression of Embodiment 1 is implemented. The computer program may be in source code form, object code form, executable file, or some intermediate form.

[0096] Example 4

[0097] This embodiment is based on embodiment 1:

[0098] This embodiment provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for predicting the sound insulation of a composite sound barrier in a substation based on linear regression of Embodiment 1. The computer program may be in source code form, object code form, executable file, or some intermediate form, etc. The storage medium includes: any entity or device capable of carrying computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content contained in the storage medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the storage medium does not include electric carrier signals and telecommunication signals.

[0099] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity of description, they are expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

Claims

1. A method for predicting the sound insulation of a composite sound barrier in a substation based on linear regression, characterized in that: include: Based on acoustic theory, determine the key influencing factors of different material layers in multi-layer composite sound barriers on the overall sound insulation, collect data related to the key influencing factors and construct a data set; The data set is analyzed based on the linear regression method, a mathematical relationship between key influencing factors and sound insulation is established, and a sound insulation prediction model is formed to predict the sound insulation of the multi-layer composite sound barrier.

2. According to a linear regression-based method for predicting the sound insulation of a substation composite sound barrier, the method is characterized in that: The key factors affecting the overall sound insulation of different material layers in the multi-layer composite sound barrier based on acoustic theory include: Based on acoustic theory, the influencing factors of the multi-layer composite sound barrier on the overall sound insulation are divided into material structure attributes and external influencing factors. The material structure attributes include thickness, surface density, elastic modulus, loss factor and average sound absorption coefficient. The external influencing factors include the frequency of the incident sound wave. Determine the key influencing factors of different material layers in the multi-layer composite sound barrier on the overall sound insulation. The types of material layers in the multi-layer composite sound barrier include sound insulation layer, sound absorption layer, damping layer and air layer. The key influencing factors of the sound insulation layer on the overall sound insulation include thickness, surface density, elastic modulus and loss factor; the key influencing factors of the sound absorption layer on the overall sound insulation include average sound absorption coefficient and thickness; the key influencing factors of the damping layer on the overall sound insulation include elastic modulus, loss factor and thickness; the key influencing factors of the air layer on the overall sound insulation include thickness.

3. According to a linear regression-based method for predicting the sound insulation of a substation composite sound barrier, the method is characterized in that: The collecting of data related to key influencing factors and constructing of data sets include: After determining the key influencing factors, obtain data related to the key influencing factors through experimental measurement or citing existing literature data, and screen and process them to remove abnormal data that does not meet the preset standards; A corresponding data set is constructed based on the screened and processed data, and the data set includes material structure properties of different material layers and corresponding sound insulation values; the data set is divided into a training set and a validation set, and it is ensured that the data types of the two are evenly distributed. The training set will be used for model construction and training, and the validation set will be used for model evaluation and optimization.

4. According to a linear regression-based method for predicting the sound insulation of a substation composite sound barrier, the method is characterized in that: The method of analyzing the data set based on the linear regression method, establishing a mathematical relationship between key influencing factors and sound insulation and forming a sound insulation prediction model includes: After the dataset is constructed, the material structural properties that have a significant impact on the sound insulation are identified and selected from the training set of the dataset as input features of the sound insulation prediction model; The training set is used to fit the sound insulation prediction model, and the mathematical relationship between the material structure properties and the sound insulation is established to predict the sound insulation performance of the material.

5. A method for predicting the sound insulation of a substation composite sound barrier based on linear regression according to claim 4, characterized in that: The method of analyzing the data set based on the linear regression method, establishing a mathematical relationship between key influencing factors and sound insulation and forming a sound insulation prediction model also includes: After the sound insulation prediction model is constructed, the material structure properties in the validation set of the data set are input into the sound insulation prediction model, and the corresponding sound insulation is predicted by the sound insulation prediction model; the prediction results are compared and analyzed with the actual measurement data to evaluate the prediction error and applicability of the sound insulation prediction model, and the comparison between the actual value and the predicted value in the validation set is displayed.

6. A substation composite sound barrier sound insulation prediction system based on linear regression, characterized in that: include: A data set construction module, configured to determine the key influencing factors of different material layers in the multi-layer composite sound barrier on the overall sound insulation based on acoustic theory, collect data related to the key influencing factors and construct a data set; The sound insulation prediction module is configured to analyze the data set based on a linear regression method, establish a mathematical relationship between key influencing factors and sound insulation and form a sound insulation prediction model, thereby predicting the sound insulation of the multi-layer composite sound barrier.

7. A linear regression-based substation composite sound barrier sound insulation prediction system according to claim 6, characterized in that: In the dataset construction module, the key influencing factors of different material layers in the multi-layer composite sound barrier on the overall sound insulation are determined based on acoustic theory, including: Based on acoustic theory, the influencing factors of the multi-layer composite sound barrier on the overall sound insulation are divided into material structure attributes and external influencing factors. The material structure attributes include thickness, surface density, elastic modulus, loss factor and average sound absorption coefficient. The external influencing factors include the frequency of the incident sound wave. Determine the key influencing factors of different material layers in the multi-layer composite sound barrier on the overall sound insulation. The types of material layers in the multi-layer composite sound barrier include sound insulation layer, sound absorption layer, damping layer and air layer. The key influencing factors of the sound insulation layer on the overall sound insulation include thickness, surface density, elastic modulus and loss factor; the key influencing factors of the sound absorption layer on the overall sound insulation include average sound absorption coefficient and thickness; the key influencing factors of the damping layer on the overall sound insulation include elastic modulus, loss factor and thickness; the key influencing factors of the air layer on the overall sound insulation include thickness.

8. A linear regression-based substation composite sound barrier sound insulation prediction system according to claim 6, characterized in that: In the data set construction module, data related to key influencing factors are collected and a data set is constructed, including: After determining the key influencing factors, obtain data related to the key influencing factors through experimental measurement or citing existing literature data, and screen and process them to remove abnormal data that does not meet the preset standards; A corresponding data set is constructed based on the screened and processed data, and the data set includes material structure properties of different material layers and corresponding sound insulation values; the data set is divided into a training set and a validation set, and it is ensured that the data types of the two are evenly distributed. The training set will be used for model construction and training, and the validation set will be used for model evaluation and optimization.

9. A linear regression-based substation composite sound barrier sound insulation prediction system according to claim 6, characterized in that: In the sound insulation prediction module, the data set is analyzed based on a linear regression method, a mathematical relationship between key influencing factors and sound insulation is established, and a sound insulation prediction model is formed, including: After the dataset is constructed, the material structural properties that have a significant impact on the sound insulation are identified and selected from the training set of the dataset as input features of the sound insulation prediction model; The training set is used to fit the sound insulation prediction model, and the mathematical relationship between the material structure properties and the sound insulation is established to predict the sound insulation performance of the material.

10. A linear regression-based substation composite sound barrier sound insulation prediction system according to claim 9, characterized in that: In the sound insulation prediction module, the data set is analyzed based on a linear regression method, a mathematical relationship between key influencing factors and sound insulation is established, and a sound insulation prediction model is formed, which also includes: After the sound insulation prediction model is constructed, the material structure properties in the validation set of the data set are input into the sound insulation prediction model, and the corresponding sound insulation is predicted by the sound insulation prediction model; the prediction results are compared and analyzed with the actual measurement data to evaluate the prediction error and applicability of the sound insulation prediction model, and the comparison between the actual value and the predicted value in the validation set is displayed.

Images