A sound barrier screen sound insulation amount prediction method, device, medium and product

Abstract

The application discloses a sound barrier screen sound insulation amount prediction method and device, medium and product, relates to the sound barrier design field, and the method comprises the following steps: according to the material composition parameters, matching prediction is carried out in the pre-established sound barrier screen actual measurement database; if there is an accurate matching record, the actual measurement sound insulation amount of the accurate matching record is taken as the predicted sound insulation amount; if there is no accurate matching record, similar screen body records meeting a preset similarity condition are searched in the actual measurement database; according to the actual measurement sound insulation amount and the parameter difference degree of the similar screen body records, the predicted sound insulation amount is determined through weighted regression interpolation; if no similar screen body record is searched, the area density reduction coefficient is determined according to the type of each layer of material; the equivalent area density is determined; and the predicted sound insulation amount is determined based on the equivalent area density. The application can improve the sound insulation amount prediction accuracy and realize the balance between the prediction accuracy and the data coverage rate.

Description

Technical Field

[0001] This application relates to the field of sound barrier design, and in particular to a method, device, medium and product for predicting the sound insulation of a sound barrier. Background Technology

[0002] Sound barriers are the most commonly used noise reduction measure in transportation infrastructure such as highways and railways. Their core acoustic indicators are weighted sound insulation (Rw) and noise reduction coefficient (NRC). Weighted sound insulation (Rw) is a single numerical evaluation index obtained by weighting the sound insulation of the sound barrier panel at different frequencies according to the GB / T 19889.3 standard. The unit is dB, and a higher value indicates better sound insulation performance. The noise reduction coefficient is the arithmetic mean of the sound absorption coefficients at four frequencies: 250Hz, 500Hz, 1000Hz, and 2000Hz. It is used to evaluate the sound absorption performance of sound-absorbing materials or structures, with a value ranging from 0 to 1. During the research and development and engineering selection of sound barriers, engineers need to predict their sound insulation performance based on the material composition of the panel (panel, back panel, sound-absorbing materials, accessories, etc.) in order to optimize costs while meeting acoustic requirements.

[0003] Currently, the main method used in the industry to predict the sound insulation of sound barriers is the Mass Law, which estimates the sound insulation based on the sum of the surface densities of each layer of material in the barrier using the empirical formula Rw = 20lg(m·f) - 47.2, where m is the surface density (kg / m³). 2 (where f is the frequency (Hz)). However, the traditional mass law has the following significant drawbacks when applied to composite sound barrier panels: (1) Traditional methods simply add up the surface densities of all materials without distinguishing the differences in the contribution of different materials to sound insulation: Sound barrier composite panels are usually composed of rigid metal plates (aluminum plates, galvanized steel plates, stainless steel plates, etc.), flexible porous sound-absorbing materials (rock wool, glass wool, etc.), and semi-rigid accessories (cement boards, etc.). Rigid plates achieve sound insulation by reflecting sound waves, and their surface density contributes nearly 100% to sound insulation; while the main function of flexible sound-absorbing materials is sound absorption rather than sound insulation, and their surface density contributes far less to sound insulation than that of rigid plates; although cement boards have a certain degree of rigidity, their porous structure and installation method result in a lower contribution to sound insulation than metal plates with the same surface density. Traditional methods treat the surface densities of the three materials equally, leading to a systematic overestimation of sound insulation.

[0004] (2) Traditional methods do not take into account the finite size effect and installation process loss in actual engineering: the mass law assumes that the sound insulation component is an infinitely large plane, but the actual sound barrier screen size is limited (usually 500mm wide and 500mm high). Edge diffraction and installation gaps will cause the actual sound insulation to be lower than the theoretical value.

[0005] Furthermore, the average absolute deviation of the traditional mass law in estimating the sound insulation of sound barriers is high and shows a systematic upward trend; the excessive deviation cannot meet the accuracy requirements of engineering selection, which may lead to over-selection (increasing unnecessary costs) or under-selection (acoustic performance not meeting standards).

[0006] Therefore, there is an urgent need for a method to predict the sound insulation of a sound barrier that can distinguish the differences in the contribution of different materials to sound insulation and take into account the actual losses in engineering. Summary of the Invention

[0007] The purpose of this application is to provide a method, device, medium, and product for predicting the sound insulation of a sound barrier, which can improve the accuracy of sound insulation prediction and achieve a balance between prediction accuracy and data coverage.

[0008] To achieve the above objectives, this application provides the following solution: In a first aspect, this application provides a method for predicting the sound insulation of a sound barrier, including: Obtain the material composition parameters of the target sound barrier screen; the material composition parameters include the type and physical size parameters of each layer of material in the target sound barrier screen. Based on the material composition parameters, matching and prediction are performed in a pre-established measured database of sound barrier panels; If a precise matching record exists, the measured sound insulation of the precise matching record shall be used as the predicted sound insulation; the precise matching record is a screen record that is completely matched with the material composition parameters retrieved from the sound barrier screen measurement database. If no exact matching record exists, a similar screen record that meets the preset similarity condition is retrieved from the sound barrier screen measurement database; and the predicted sound insulation is determined by weighted regression interpolation based on the measured sound insulation and parameter difference of the similar screen record. If no similar screen records that meet the preset similarity conditions are found, the corresponding areal density reduction factor is determined according to the type of material in each layer; different types of materials correspond to different areal density reduction factors. The equivalent surface density of the target sound barrier is determined based on the surface density of each layer of material and the corresponding surface density reduction factor. Based on the equivalent surface density, the predicted sound insulation of the target sound barrier is determined.

[0009] Secondly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the sound barrier screen sound insulation prediction method.

[0010] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the sound insulation prediction method for the sound barrier screen.

[0011] Fourthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the sound insulation prediction method for the sound barrier screen.

[0012] According to the specific embodiments provided in this application, this application has the following technical effects: This application provides a method, device, medium, and product for predicting the sound insulation of a sound barrier. It employs a three-level matching prediction architecture: "measurement first → regression correction → theoretical fallback." Through these three levels of matching, sound insulation is predicted separately, avoiding the limitations of purely theoretical or purely data-driven methods and achieving a balance between prediction accuracy and data coverage. Specifically, it organically combines precise matching of material composition parameters with a sound barrier's measured database (first level), regression correction with similar barriers (second level), and differential areal density reduction theoretical estimation (third level) to form a layered and progressive prediction architecture, achieving an optimal balance between accuracy and coverage. In the differential areal density reduction theoretical estimation, different areal density reduction coefficients are determined for different types of materials in the composite sound barrier, replacing the traditional method of simply adding the areal densities of all materials using the mass law. This establishes a differential areal density reduction coefficient system, significantly improving the accuracy of sound insulation prediction. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a schematic diagram of a method for predicting the sound insulation of a sound barrier in one embodiment of this application. Detailed Implementation

[0015] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0016] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0017] In one exemplary embodiment, such as Figure 1 As shown, a method for predicting the sound insulation of a sound barrier is provided. This method is executed by a computer device, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is described using a server as an example, and includes the following steps S101 to S107. Wherein: S101, Obtain the material composition parameters of the target sound barrier screen; the material composition parameters include the type and physical size parameters of each layer of material in the target sound barrier screen. S102, according to the material composition parameters, perform matching prediction in the pre-established sound barrier screen measurement database; wherein, the sound barrier screen measurement database includes multiple sound barrier screen measurement records; each sound barrier screen measurement record includes fields as shown in Table 1; Table 1

[0018] S103, if a precise matching record exists, the measured sound insulation of the precise matching record is used as the predicted sound insulation; the precise matching record is a screen record that is completely matched with the material composition parameters retrieved from the sound barrier screen measurement database. Specifically, the panel material, panel thickness, back panel material, back panel thickness, sound-absorbing material type, sound-absorbing material density, sound-absorbing material thickness, and accessory configuration are all the same. If one or more records are matched, the measured Rw value (average of multiple records) is directly returned as the prediction result, and the prediction deviation is close to 0dB.

[0019] S104, if no exact matching record exists, then search the sound barrier screen measurement database for similar screen records that meet the preset similarity conditions; and determine the predicted sound insulation amount by weighted regression interpolation based on the measured sound insulation amount and parameter difference of the similar screen records. As a specific embodiment, the preset similarity conditions include: the panel material is the same or belongs to the same category of metal sheet, the back panel material is the same or belongs to the same category of metal sheet, the sound-absorbing material type is the same, the density deviation of the sound-absorbing material is within a preset density threshold, and the thickness deviation of the sound-absorbing material is within a preset thickness threshold.

[0020] Specifically, the density deviation of the sound-absorbing material is within ±30%, and the thickness deviation of the sound-absorbing material is within ±20mm; S104 specifically includes: S41, calculate the parameter difference degree based on the difference in sound-absorbing material density and the difference in sound-absorbing material thickness between the similar screen and the target sound barrier screen; S42, using the reciprocal of the parameter difference as a weight, a weighted average is calculated on the measured sound insulation recorded for the similar screens to obtain the predicted sound insulation. The predicted sound insulation in this step has a prediction deviation of approximately 1dB to 2dB. The following is an illustration through a specific embodiment. Suppose that n similar screen records are retrieved from the measured database, and the measured weighted sound insulation of the i-th record is Rw. i The parameter difference between it and the target screen is d. i The predicted sound insulation of the target screen is calculated using a weighted average: Rw _预测 =Σ(w i ×Rw i ) / Σ(w i ), where i = 1, 2, ..., n; Among them, using formula w i =1 / (1+d i Determine the weight w i ; d i =|Δρ 吸声 / ρ 目标 |×k1+|Δt 吸声 / t 目标 |×k2; Where, Δρ 吸声 Δt represents the density difference of the sound-absorbing materials. 吸声 K1 and K2 are the difference in sound-absorbing material thickness, and normalized weighting coefficients (it is recommended to take K1=0.6 and K2=0.4, which reflects that density has a greater impact on sound insulation than thickness).

[0021] S105, if no similar screen records that meet the preset similarity conditions are found, the corresponding areal density reduction factor is determined according to the type of each layer of material; wherein, different types of materials correspond to different areal density reduction factors; S105 specifically includes: S51, acquire multiple sets of sound barrier panel sample data with known material composition and measured sound insulation; S52, using the surface density of each layer of material as the independent variable and the measured sound insulation as the dependent variable, establish a sound insulation prediction regression model that includes the surface density reduction coefficient; wherein, the sound insulation prediction regression model is: w 实测 =20×lg(α1·m1+α2·m2+α3·m3+α4·m4)×f _ref -47.2-C; Where m1 is the surface density of the panel, m2 is the surface density of the back panel, m3 is the surface density of the sound-absorbing material, m4 is the surface density of the cement board, and C is the engineering penalty term constant; S53, the sound insulation prediction regression model is solved by fitting the least squares method to obtain the surface density reduction coefficient corresponding to each material type.

[0022] The optimal values ​​of α1, α2, α3, and α4 were obtained by fitting the least squares method, and the results were: α1 = α2 ≈ 1.0, α3 ≈ 0.15~0.25 (depending on the type of sound-absorbing material), α4 ≈ 0.35; The surface density reduction factor, after cross-validation (leave-one method), has an average absolute deviation of 2dB~3dB, which is significantly better than the 5.3dB of the traditional mass law.

[0023] Among them, rigid boards achieve sound insulation through reflection, with surface density contributing nearly 100%; the main function of flexible sound-absorbing materials is sound absorption rather than sound insulation, and their effective contribution to sound insulation is only 15% to 25% of surface density; cement boards, due to their porous structure and installation method, contribute approximately 35% effectively.

[0024] α1=α2=1.0 (rigid metal sheets, including aluminum sheets, galvanized steel sheets, stainless steel sheets, and galvanized aluminum-magnesium sheets) α3 = 0.15; α4 = 0.30~0.40 (for semi-rigid attachments, 0.35 is used for cement boards); The surface density of each material is given by: m = ρ × t, where ρ is the material density (kg / m³). 3 ), t is the thickness (m), as shown in Table 2.

[0025] Table 2

[0026] S106, determine the equivalent surface density of the target sound barrier screen body based on the surface density of each layer of material and the corresponding surface density reduction factor; Using formula m eff = m1×α1+m2×α2+m3×α3+m4×α4 determines the equivalent surface density m eff ; Where m1 is the surface density of the panel, m2 is the surface density of the back panel, m3 is the surface density of the sound-absorbing material, m4 is the surface density of the semi-rigid accessory, α1=α2 are the reduction coefficients of the rigid board, α3 is the reduction coefficient of the sound-absorbing material, and α4 is the reduction coefficient of the semi-rigid accessory.

[0027] S107, Based on the equivalent surface density, determine the predicted sound insulation of the target sound barrier screen.

[0028] Using the formula Rw _预测=Rw _理论 -ΔR _尺寸 -ΔR _安装 Determine the predicted sound insulation value Rw _预测 ; Among them, Rw _理论 For theoretical sound insulation, Rw _理论 = 20×lg(m eff ×f _ref )-47,m eff For the equivalent surface density, f _ref For the reference frequency, ΔR _尺寸 The finite-size penalty term characterizes the edge diffraction loss due to the finite screen size, ΔR. _安装 This is an installation process loss item, used to characterize the sound insulation loss caused by installation gaps, poor sealing, etc.

[0029] This application introduces an engineering penalty term correction mechanism based on theoretical estimation, namely, introducing a finite size penalty term and an installation process loss term, so that the prediction results are closer to the actual engineering situation.

[0030] The technical effects of this application are as follows: First, it significantly improves the accuracy of sound insulation prediction. Verified by 18 sets of measured data, the average absolute deviation of the traditional mass law is 5.3 dB, with a deviation as high as 810 dB for cement board screens. After adopting the differentiated surface density reduction method of this application, the average absolute deviation is reduced to 3 dB, improving accuracy by approximately 50% to 60%. This technical effect stems from the differentiated surface density reduction coefficient system, which eliminates the systematic overestimation of sound insulation by distinguishing the actual contribution of different materials.

[0031] Second, it achieves a balance between prediction accuracy and data coverage. The three-level matching architecture enables a prediction bias close to 0dB when measured data is available, and still provides a reasonable estimate of 2-3dB when measured data is unavailable, avoiding the limitations of purely theoretical or purely data-driven methods.

[0032] Third, the prediction results are closer to engineering reality. The engineering penalty term correction mechanism bridges the gap between the theoretical formula's assumption of an "infinitely large plane" and the engineering reality of a "finite-size screen," allowing the predicted values ​​to be directly used for engineering selection decisions.

[0033] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The I / O interfaces of the computer device are used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for predicting the sound insulation of a sound barrier.

[0034] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0035] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0036] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0037] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0038] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0039] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0040] In this application, all actions to acquire signals, information, or data are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with the authorization granted by the owner of the relevant device.

[0041] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0042] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for predicting the sound insulation of a sound barrier, characterized in that, include: Obtain the material composition parameters of the target sound barrier screen; the material composition parameters include the type and physical size parameters of each layer of material in the target sound barrier screen. Based on the material composition parameters, matching and prediction are performed in a pre-established measured database of sound barrier panels; If a precise matching record exists, the measured sound insulation of the precise matching record shall be used as the predicted sound insulation; the precise matching record is a screen record that is completely matched with the material composition parameters retrieved from the sound barrier screen measurement database. If no exact matching record exists, a similar screen record that meets the preset similarity condition is retrieved from the sound barrier screen measurement database; and the predicted sound insulation is determined by weighted regression interpolation based on the measured sound insulation and parameter difference of the similar screen record. If no similar screen records that meet the preset similarity conditions are found, the corresponding areal density reduction factor is determined according to the type of material in each layer; different types of materials correspond to different areal density reduction factors. The equivalent surface density of the target sound barrier is determined based on the surface density of each layer of material and the corresponding surface density reduction factor. Based on the equivalent surface density, the predicted sound insulation of the target sound barrier is determined.

2. The method for predicting the sound insulation of a sound barrier according to claim 1, characterized in that, The preset similarity conditions include: the panel material is the same or belongs to the same metal plate category, the back panel material is the same or belongs to the same metal plate category, the sound-absorbing material type is the same, the density deviation of the sound-absorbing material is within a preset density threshold, and the thickness deviation of the sound-absorbing material is within a preset thickness threshold.

3. The method for predicting the sound insulation of a sound barrier according to claim 2, characterized in that, Based on the measured sound insulation and parameter differences recorded by the similar screens, the predicted sound insulation is calculated using weighted regression interpolation, specifically including: The parameter difference is calculated based on the difference in sound-absorbing material density and the difference in sound-absorbing material thickness between the similar screen and the target sound barrier screen. Using the reciprocal of the parameter difference as the weight, the measured sound insulation recorded by the similar screens is weighted and averaged to obtain the predicted sound insulation.

4. The method for predicting the sound insulation of a sound barrier according to claim 1, characterized in that, The determination of the corresponding areal density reduction factor based on the type of each layer of material specifically includes: Acquire multiple sets of sound barrier sample data with known material composition and measured sound insulation; Using the surface density of each layer of material as the independent variable and the measured sound insulation as the dependent variable, a sound insulation prediction regression model including the surface density reduction coefficient is established. The sound insulation prediction regression model was solved by fitting the least squares method to obtain the areal density reduction coefficient corresponding to each material type.

5. The method for predicting the sound insulation of a sound barrier according to claim 1, characterized in that, The determination of the equivalent surface density of the target sound barrier screen body based on the surface density of each layer of material and the corresponding surface density reduction factor specifically includes: Using formula m eff = m1×α1+m2×α2+m3×α3+m4×α4 determines the equivalent surface density m eff ; Where m1 is the surface density of the panel, m2 is the surface density of the back panel, m3 is the surface density of the sound-absorbing material, m4 is the surface density of the semi-rigid accessory, α1=α2 are the reduction coefficients of the rigid board, α3 is the reduction coefficient of the sound-absorbing material, and α4 is the reduction coefficient of the semi-rigid accessory.

6. The method for predicting the sound insulation of a sound barrier according to claim 1, characterized in that, The step of determining the predicted sound insulation of the target sound barrier based on the equivalent surface density specifically includes: Using the formula Rw _预测 =Rw _理论 -ΔR _尺寸 -ΔR _安装 Determine the predicted sound insulation value Rw _预测 ; Among them, Rw _理论 For theoretical sound insulation, Rw _理论 = 20×lg(m eff ×f _ref -47, m eff For the equivalent surface density, f _ref For the reference frequency, ΔR _尺寸 The finite-size penalty term characterizes the edge diffraction loss due to the finite screen size, ΔR. _安装 This is an installation process loss item, used to characterize the sound insulation loss caused by installation gaps, poor sealing, etc.

7. The method for predicting the sound insulation of a sound barrier according to claim 1, characterized in that, Each record in the measured database of the sound barrier panel includes the following fields: Panel parameters, including panel material and panel thickness; Back panel parameters, including back panel material and back panel thickness; Sound-absorbing material parameters, including material type, density, and thickness; Attachment parameters, including whether it includes cement board and the thickness of the cement board; Measured acoustic properties, including weighted sound insulation.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the sound barrier panel sound insulation prediction method according to any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for predicting the sound insulation of a sound barrier as described in any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for predicting the sound insulation of a sound barrier as described in any one of claims 1-7.

Images