A method and device for evaluating noise reduction effect of a generator set

Abstract

The present invention discloses a method and device for evaluating the noise reduction effect of a generator set. The method comprises: after applying a noise reduction method to the generator set, testing and obtaining a noise reduction value set of the generator set; obtaining a noise reduction method technical indicator set; the noise reduction method technical indicator set includes a structural noise reduction method technical indicator subset, a material noise reduction method technical indicator subset, a simulation noise reduction method technical indicator subset and an overall design noise reduction method technical indicator subset; constructing a noise reduction quantitative evaluation model; based on the noise reduction value set and the noise reduction method technical indicator set, solving the noise reduction quantitative evaluation model to obtain a solved noise reduction quantitative evaluation model; based on the solved noise reduction quantitative evaluation model, obtaining noise reduction effect evaluation values ​​of various noise reduction methods.

Description

Technical Field

[0001] The present invention relates to the fields of technology evaluation and data modeling, and in particular to a method and device for evaluating the noise reduction effect of a generator set. Background Art

[0002] With the widespread application of generator sets in industrial, civil, and emergency power supply fields, the noise pollution generated during their operation has received increasing attention. Noise not only interferes with the surrounding environment, but may also have a negative impact on the health of operators. Therefore, it is of great significance to accurately evaluate the noise reduction effect of generator sets. However, there are currently some technical problems in the evaluation of the noise reduction effect of generator sets. First, traditional evaluation methods usually only focus on the effect of a single noise reduction technology, such as structural noise reduction or material noise reduction, and lack an evaluation of the comprehensive effect of multiple noise reduction technologies. Second, existing methods fail to fully consider the temporal and spatial characteristics of noise reduction technical indicators during the evaluation process, resulting in incomplete and inaccurate evaluation results.

[0003] Furthermore, existing technologies lack a systematic quantitative noise reduction evaluation model, making it difficult to effectively integrate the relationship between the technical indicators of different noise reduction methods and their actual noise reduction effects, making it difficult to scientifically determine the optimal noise reduction method. These issues limit the optimization and application of generator set noise reduction technologies and fail to provide strong technical support for the design and improvement of generator set noise reduction. Summary of the Invention

[0004] The present invention mainly solves the problem of how to accurately and quickly evaluate the noise reduction effect of a generator set and determine the optimal noise reduction strategy. The present invention discloses a method and device for evaluating the noise reduction effect of a generator set.

[0005] In a first aspect of an embodiment of the present invention, a method for evaluating the noise reduction effect of a generator set is disclosed, comprising:

[0006] S1, after applying a noise reduction method to a generator set, testing and obtaining a set of noise reduction values ​​for the generator set; the set of noise reduction values ​​includes noise reduction values ​​obtained from tests at each test time and test location;

[0007] S2, obtaining a set of technical indicators for noise reduction methods; the set of technical indicators for noise reduction methods includes a subset of technical indicators for structural noise reduction methods, a subset of technical indicators for material noise reduction methods, a subset of technical indicators for simulation noise reduction methods, and a subset of technical indicators for overall design noise reduction methods; each subset of technical indicators includes a time series of several technical indicators; the time series is a sequence of values ​​obtained from testing a technical indicator at each test time and test location;

[0008] S3, construct a noise reduction quantitative evaluation model;

[0009] S4, solving the noise reduction quantitative evaluation model based on the noise reduction value set and the noise reduction method technical indicator set to obtain a solved noise reduction quantitative evaluation model;

[0010] S5, based on the solved noise reduction quantitative evaluation model, obtain the noise reduction effect evaluation value of various noise reduction methods.

[0011] The expression of the noise reduction quantitative evaluation model is:

[0012]

[0013] Where p is the location coordinate of the test site, t is the test time, E(p,t), T(p,t), G(p,t), and M(p,t) represent the technical index values ​​of the structural noise reduction method, the material noise reduction method, the simulation noise reduction method, and the overall design noise reduction method at the location coordinate p of the test site at the test time t, respectively; f1(), f2(), f3(), and f4() are the mechanical noise reduction function, thermal noise reduction function, dynamic noise reduction function, and structural noise reduction function, respectively; k e 、k t 、k g 、k m are the first, second, third and fourth weighting coefficients, respectively; J(E(p,t), T(p,t), G(p,t), M(p,t)) represents the noise reduction value obtained by testing the generator set at the test location coordinate p at the test time t according to the technical index values ​​of E(p,t), T(p,t), G(p,t) and M(p,t), respectively, after noise reduction using the structural noise reduction method, material noise reduction method, simulation noise reduction method and overall design noise reduction method; f1( ), f2( ), f3( ) and f4( ) are all linear high-order polynomial functions.

[0014] The step of solving the noise reduction quantitative evaluation model based on the noise reduction value set and the noise reduction method technical indicator set to obtain the solved noise reduction quantitative evaluation model includes:

[0015] S41, for each type of denoising function, determining a corresponding technical indicator subset in the denoising method technical indicator set according to its input quantity, performing order calculation on the determined technical indicator subset to obtain a polynomial order value of the corresponding denoising function;

[0016] S42, taking the noise reduction value set as the dependent variable and the noise reduction method technical indicator set as the independent variable, performing function fitting and solving the function parameter values ​​of all weighting coefficients and f1( ), f2( ), f3( ), and f4( ) in the noise reduction quantitative evaluation model to obtain the solved noise reduction quantitative evaluation model.

[0017] The order calculation includes:

[0018] The technical indicator subset is represented as a technical indicator matrix; the row vector of the technical indicator matrix is ​​a time series of a type of technical indicator in the technical indicator subset;

[0019] Performing QR decomposition on the technical indicator matrix to obtain corresponding Q matrix and R matrix;

[0020] Performing eigenvalue calculation processing on the technical indicator matrix to obtain an eigenvalue vector; the eigenvalue vector is a vector constructed by all eigenvalues;

[0021] Calculate the mean and variance of all elements of the eigenvalue vector;

[0022] Decomposing and calculating the technical indicator matrix to obtain a decomposition vector;

[0023] Based on the decomposition vector, the polynomial order value of the noise reduction function is calculated; the calculation expression of the polynomial order value of the noise reduction function is:

[0024]

[0025] in, Indicates rounding up, N indicates the row dimension of the technical indicator matrix, M indicates the length of the decomposition vector, L indicates the polynomial order value of the noise reduction function, t i represents the element of the i-th item of the decomposition vector, and t0 represents the mean of the decomposition vector.

[0026] The expression of the decomposition calculation process is:

[0027] t=(δP T V+μI) -1 P T y,

[0028] V=QR -1 ,

[0029] Where t is the decomposition vector, Q and R are the Q matrix and R matrix obtained by QR decomposition of the technical indicator matrix P, V is the intermediate matrix, μ and δ are the mean and variance of all elements of the eigenvalue vector, y is the eigenvalue vector, and I is the identity matrix.

[0030] The noise reduction quantitative evaluation model after solution is used to obtain the noise reduction effect evaluation values ​​of various noise reduction methods, including:

[0031] S51, for each type of noise reduction method, calculating derivative values ​​of the solved noise reduction quantitative evaluation model with respect to all types of technical indicators of the noise reduction method;

[0032] S52, performing a fusion calculation on the derivative values ​​of all categories of technical indicators calculated by each type of noise reduction method to obtain a noise reduction effect evaluation value of the noise reduction method.

[0033] The derivative values ​​of all categories of technical indicators calculated by each type of noise reduction method are fused and calculated to obtain the noise reduction effect evaluation value of the noise reduction method, including:

[0034] For each type of noise reduction method, a derivative value matrix is ​​constructed using the corresponding derivative values ​​of all types of technical indicators; the row vectors of the derivative value matrix are the derivative values ​​of a type of technical indicator at all test times and test locations;

[0035] An evaluation calculation process is performed on the derivative value matrix to obtain an evaluation value of the noise reduction effect of the noise reduction method.

[0036] According to a second aspect of the present invention, a device for evaluating the noise reduction effect of a generator set is disclosed, the device comprising:

[0037] a memory storing executable program code;

[0038] a processor coupled to the memory;

[0039] The processor calls the executable program code stored in the memory to execute the method for evaluating the noise reduction effect of the generator set.

[0040] According to a third aspect of the present invention, a computer-storable medium is disclosed, wherein the computer-storable medium stores computer instructions. When the computer instructions are called by a computer, the computer instructions are used to execute the method for evaluating the noise reduction effect of a generator set.

[0041] According to a fourth aspect of the present invention, an information data processing terminal is disclosed. The information data processing terminal is used to implement the method for evaluating the noise reduction effect of a generator set.

[0042] The beneficial effects of the present invention are:

[0043] The present invention provides a method for evaluating the noise reduction effect of a generator set. By comprehensively considering the technical indicators of multiple noise reduction methods and their noise reduction values ​​at different times and locations, and constructing a noise reduction quantitative evaluation model, a comprehensive and accurate evaluation of the noise reduction effect of the generator set is achieved. Specifically, the present invention has the following beneficial effects:

[0044] 1. Comprehensive evaluation of multiple technologies: This invention covers the technical indicators of multiple noise reduction methods, including structural noise reduction, material noise reduction, simulation noise reduction, and overall design noise reduction. It can comprehensively evaluate the combined effects of different noise reduction technologies, overcoming the limitation of traditional methods that only focus on a single technology, and providing a comprehensive evaluation perspective for the noise reduction design of generator sets.

[0045] 2. Spatiotemporal Analysis: This method integrates the technical indicators of noise reduction methods with time and location, fully accounting for variations in noise reduction effectiveness at different test times and locations. This makes the evaluation results more scientific and practical. This spatiotemporal analysis helps users understand the adaptability and stability of different noise reduction methods in practical applications.

[0046] 3. Quantitative Noise Reduction Evaluation Model: This paper constructs a quantitative noise reduction evaluation model and, through function fitting, scientifically quantifies the relationship between the technical indicators of noise reduction methods and their actual noise reduction effects. This approach not only improves the accuracy of the evaluation but also provides a scientific basis for optimizing noise reduction technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 4 is an implementation flow chart of the method of the present invention. DETAILED DESCRIPTION

[0048] In order to better understand the content of the present invention, an embodiment is given here.

[0049] Figure 1 4 is an implementation flow chart of the method of the present invention.

[0050] In a first aspect of an embodiment of the present invention, a method for evaluating the noise reduction effect of a generator set is disclosed, comprising:

[0051] S1, after applying a noise reduction method to a generator set, testing and obtaining a set of noise reduction values ​​for the generator set; the set of noise reduction values ​​includes noise reduction values ​​obtained from tests at each test time and test location;

[0052] S2, obtaining a set of technical indicators of noise reduction methods; the set of technical indicators of noise reduction methods includes a subset of technical indicators of structural noise reduction methods, a subset of technical indicators of material noise reduction methods, a subset of technical indicators of simulation noise reduction methods, and a subset of technical indicators of overall design noise reduction methods; each subset of technical indicators includes a time series of several technical indicators; the time series is a data sequence obtained from the test of the technical indicators at each test time and test location;

[0053] S3, construct a noise reduction quantitative evaluation model;

[0054] S4, solving the noise reduction quantitative evaluation model based on the noise reduction value set and the noise reduction method technical indicator set to obtain a solved noise reduction quantitative evaluation model;

[0055] S5, based on the solved noise reduction quantitative evaluation model, obtain noise reduction effect evaluation values ​​of various noise reduction methods; and determine the noise reduction method with the largest noise reduction effect evaluation value as the optimal noise reduction method.

[0056] The expression of the noise reduction quantitative evaluation model is:

[0057]

[0058] Where p is the location coordinate of the test site, t is the test time, E(p,t), T(p,t), G(p,t), and M(p,t) represent the technical index values ​​of the structural noise reduction method, the material noise reduction method, the simulation noise reduction method, and the overall design noise reduction method at the location coordinate p of the test site at the test time t, respectively; f1( ), f2( ), f3( ), and f4( ) are the mechanical noise reduction function, the thermal noise reduction function, the dynamic noise reduction function, and the structural noise reduction function, respectively; k e 、k t 、k g 、k m are the first weighting coefficient, the second weighting coefficient, the third weighting coefficient and the fourth weighting coefficient respectively; J(E(p,t), T(p,t), G(p,t), M(p,t)) represents the technical index values ​​of E(p,t), T(p,t), G(p,t) and M(p,t) for the generator set at the test location coordinate p at the test time t, and corresponds to the noise reduction value obtained after noise reduction using the structural noise reduction method, the material noise reduction method, the simulation noise reduction method and the overall design noise reduction method; f1(), f2(), f3() and f4() are all linear high-order polynomial functions;

[0059] The noise reduction quantitative evaluation model incorporates the indicators of multiple noise reduction technologies such as structural noise reduction, material noise reduction, simulation noise reduction and overall design noise reduction into the same expression, breaking the limitation of traditional evaluation that only focuses on a single noise reduction technology. In practical applications, noise reduction of generator sets often requires the synergy of multiple technologies, such as reducing vibration noise by optimizing the structure and using sound-absorbing materials to reduce sound propagation. The model can quantify the contribution of each technology to the noise reduction effect by combining different technical indicators (such as technical indicator values ​​of structural noise reduction methods, technical indicator values ​​of material noise reduction methods, etc.) with corresponding noise reduction functions. For example, during the evaluation, it is possible to clearly judge the extent to which structural optimization reduces noise under specific working conditions, as well as the impact of material performance improvement on overall noise reduction, thereby comprehensively reflecting the combined effect of multiple noise reduction technologies and providing a more accurate basis for technical optimization.

[0060] Using linear high-order polynomial functions to describe the relationship between technical indicators and noise reduction effects allows for more flexible fitting of complex nonlinear changes compared to traditional simple linear relationships or empirical formulas. During generator set noise reduction, technical indicators and noise reduction effects are not simply linearly related. For example, a small adjustment to a structural parameter can cause a significant change in noise. High-order polynomial functions accurately capture this nonlinear characteristic through multiple coefficients and higher-order terms, improving the model's accuracy in fitting actual data. Furthermore, the weighting coefficients can be dynamically adjusted based on the importance of different noise reduction technologies. Under different operating conditions, if structural noise reduction plays a dominant role in noise reduction, the weight can be increased to make the model more prominent in highlighting the contribution of this technology, thereby achieving dynamic optimization of the evaluation and providing scientific support for determining the optimal noise reduction solution.

[0061] The step of solving the noise reduction quantitative evaluation model based on the noise reduction value set and the noise reduction method technical indicator set to obtain the solved noise reduction quantitative evaluation model includes:

[0062] For each type of denoising function, a corresponding subset of technical indicators in the denoising method technical indicator set is determined based on its input quantity, and the order of the determined subset of technical indicators is calculated to obtain the polynomial order value of the corresponding denoising function;

[0063] For example, for a structural noise reduction function, its input is the technical index value of the structural noise reduction method and the technical index value of the overall design noise reduction method, a subset of the technical index of the structural noise reduction method and a subset of the technical index of the overall design noise reduction method are determined, and the order of these two types of technical index subsets is calculated to obtain the polynomial order value of the structural noise reduction function;

[0064] Taking the noise reduction value set as the dependent variable and the noise reduction method technical indicator set as the independent variable, performing function fitting and solving for all weighting coefficients and function parameter values ​​of f1(), f2(), f3(), and f4() in the noise reduction quantitative evaluation model to obtain a solved noise reduction quantitative evaluation model;

[0065] The said denoising method technical indicator set is used as an independent variable, and the time series of each type of technical indicator is used as an independent variable respectively;

[0066] The function fitting solution may adopt a polynomial function fitting method or a least squares fitting method;

[0067] The order calculation includes:

[0068] The technical indicator subset is represented as a technical indicator matrix; the row vector of the technical indicator matrix is ​​a time series of a type of technical indicator in the technical indicator subset;

[0069] Performing QR decomposition on the technical indicator matrix to obtain corresponding Q matrix and R matrix;

[0070] Performing eigenvalue calculation processing on the technical indicator matrix to obtain an eigenvalue vector; the eigenvalue vector is a vector constructed by all eigenvalues;

[0071] Calculate the mean and variance of all elements of the eigenvalue vector;

[0072] Decomposing and calculating the technical indicator matrix to obtain a decomposition vector;

[0073] Based on the decomposition vector, the polynomial order value of the noise reduction function is calculated; the calculation expression of the polynomial order value of the noise reduction function is:

[0074]

[0075] in, Indicates rounding up, N indicates the row dimension of the technical indicator matrix, M indicates the length of the decomposition vector, L indicates the polynomial order value of the noise reduction function, t i represents the element of the i-th item of the decomposition vector, and t0 represents the mean of the decomposition vector;

[0076] By calculating the order of a subset of noise reduction method technical indicators, this method effectively extracts key features, reduces data dimensionality, and improves evaluation efficiency. Furthermore, a function fitting solution using the noise reduction value set as the dependent variable ensures the accuracy and reliability of the evaluation model.

[0077] The expression of the decomposition calculation process is:

[0078] t=(δP T V+μI) -1 P T y,

[0079] V=QR -1 ,

[0080] Where t is the decomposition vector, Q and R are the Q matrix and R matrix obtained by QR decomposition of the technical indicator matrix P, V is the intermediate matrix, μ and δ are the mean and variance of all elements of the eigenvalue vector, y is the eigenvalue vector, and I is the identity matrix.

[0081] The eigenvalue calculation process can be implemented by using an eigenvalue decomposition algorithm of a matrix;

[0082] The eigenvalue calculation process for the technical indicator matrix is ​​to first crop the technical indicator matrix to obtain a corresponding square matrix, and then perform eigenvalue calculation process on the square matrix; the cropping is to crop the matrix into an n×n dimensional square matrix corresponding to the maximum value n in the row dimension and the column dimension.

[0083] The noise reduction quantitative evaluation model after solution is used to obtain the noise reduction effect evaluation values ​​of various noise reduction methods, including:

[0084] For each type of noise reduction method, calculating the derivative value of the solved noise reduction quantitative evaluation model with respect to all types of technical indicators of the noise reduction method;

[0085] Performing a fusion calculation on the derivative values ​​of all categories of technical indicators obtained by each type of noise reduction method to obtain a noise reduction effect evaluation value of the noise reduction method;

[0086] The derivative values ​​of all categories of technical indicators obtained by each type of noise reduction method are fused and calculated to obtain the noise reduction effect evaluation value of the noise reduction method, including:

[0087] For each type of noise reduction method, a derivative value matrix is ​​constructed using the corresponding derivative values ​​of all types of technical indicators; the row vectors of the derivative value matrix are the derivative values ​​of a type of technical indicator at all test times and test locations;

[0088] The column vectors of the derivative value matrix are the derivative values ​​of all types of technical indicators obtained at the same test time and test location;

[0089] Performing evaluation calculation on the derivative value matrix to obtain a noise reduction effect evaluation value of the noise reduction method;

[0090] The evaluation calculation process includes:

[0091] Performing principal component analysis on the derivative value matrix to obtain a coefficient matrix and a principal component matrix; each row vector of the principal component matrix is ​​a sampling value of the extracted principal component index at each moment;

[0092] Performing cross-correlation calculation on the principal component matrix to obtain a cross-correlation coefficient matrix;

[0093] Performing scoring calculation on the mutual correlation coefficient matrix to obtain a noise reduction effect evaluation value;

[0094] The score calculation process is as follows:

[0095]

[0096] Where, ω j is the preset j-th importance weight, zij is the element of the i-th row and j-th column of the mutual correlation coefficient matrix, s is the noise reduction effect evaluation value, m and n are the row dimension and column dimension of the mutual correlation coefficient matrix respectively, z j is the mean of the jth column;

[0097] ω j , obtained by presetting or by calculating the variance of each column of the derivative value matrix;

[0098] The cross-correlation calculation process is to perform cross-correlation calculation on every two row vectors of the principal component matrix;

[0099] The expression of the principal component analysis process is:

[0100] Y=CX,

[0101] Wherein, Y is the principal component matrix, C is the coefficient matrix, and X is the derivative value matrix. The principal component analysis process can be implemented by the PCA algorithm, and the principal component matrix and the coefficient matrix are both determined by the principal component analysis process;

[0102] By calculating the derivatives of the noise reduction quantitative evaluation model and performing a fusion calculation, this method can scientifically determine the noise reduction effect evaluation values ​​of various noise reduction methods and screen the optimal noise reduction method. This optimization method can provide a clear direction for the noise reduction design and improvement of generator sets, thereby improving the noise reduction effect.

[0103] The structural noise reduction method includes: laying high-efficiency sound-absorbing materials on the inner wall of the cabin to absorb the reverberation in the cabin and reduce the noise intensity in the cabin;

[0104] The material noise reduction method includes: laying high-efficiency sound-absorbing materials on the inner wall of the cabin to absorb reverberation in the cabin and reduce the noise intensity in the cabin;

[0105] The simulation noise reduction method includes: using simulation analysis to optimize the air intake system, setting sound absorption components, and using a high-efficiency tube-type silencer box in the exhaust system to improve the noise reduction effect of the air intake and exhaust systems;

[0106] The overall design noise reduction method includes: using a frame-type large-plate cabin structure and a profile structure to improve cabin sealing and reduce noise transmission; using a combined composite smoke exhaust silencer and a first-stage + second-stage silencer structure to reduce exhaust noise;

[0107] According to a second aspect of the present invention, a device for evaluating the noise reduction effect of a generator set is disclosed, the device comprising:

[0108] a memory storing executable program code;

[0109] a processor coupled to the memory;

[0110] The processor calls the executable program code stored in the memory to execute the method for evaluating the noise reduction effect of the generator set.

[0111] According to a third aspect of the present invention, a computer-storable medium is disclosed, wherein the computer-storable medium stores computer instructions. When the computer instructions are called by a computer, the computer instructions are used to execute the method for evaluating the noise reduction effect of a generator set.

[0112] According to a fourth aspect of the present invention, an information data processing terminal is disclosed. The information data processing terminal is used to implement the method for evaluating the noise reduction effect of a generator set.

[0113] The foregoing is merely an embodiment of the present invention and is not intended to limit the present invention. It will be apparent to those skilled in the art that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are intended to be included within the scope of the claims of the present invention.

Claims

1. A method for evaluating the noise reduction effect of a generator set, characterized in that: include: S1, after applying the noise reduction method to the generator set, a noise reduction value set of the generator set is obtained through testing; The noise reduction value set includes the noise reduction value obtained from the test at each test time and test location; S2, obtaining a set of technical indicators for noise reduction methods; the set of technical indicators for noise reduction methods includes a subset of technical indicators for structural noise reduction methods, a subset of technical indicators for material noise reduction methods, a subset of technical indicators for simulation noise reduction methods, and a subset of technical indicators for overall design noise reduction methods; each subset of technical indicators includes a time series of several technical indicators; the time series is a sequence of values ​​obtained from testing a technical indicator at each test time and test location; S3, construct a noise reduction quantitative evaluation model; S4, solving the noise reduction quantitative evaluation model based on the noise reduction value set and the noise reduction method technical indicator set to obtain a solved noise reduction quantitative evaluation model; S5, based on the solved noise reduction quantitative evaluation model, obtain the noise reduction effect evaluation value of various noise reduction methods; The expression of the noise reduction quantitative evaluation model is: Where p is the location coordinate of the test site, t is the test time, E(p,t), T(p,t), G(p,t), and M(p,t) represent the technical index values ​​of the structural noise reduction method, the material noise reduction method, the simulation noise reduction method, and the overall design noise reduction method at the location coordinate p of the test site at the test time t, respectively; f1, f2, f3, and f4 are the mechanical noise reduction function, the thermal noise reduction function, the dynamic noise reduction function, and the structural noise reduction function, respectively; k e 、k t 、k g 、k m are the first weighting coefficient, the second weighting coefficient, the third weighting coefficient, and the fourth weighting coefficient, respectively; J(E(p,t), T(p,t), G(p,t), M(p,t)) represents the noise reduction value obtained by testing the generator set at the position coordinate p of the test site at the test time t according to the technical indicator values ​​of E(p,t), T(p,t), G(p,t), and M(p,t), respectively, after noise reduction is performed using the structural noise reduction method, the material noise reduction method, the simulation noise reduction method, and the overall design noise reduction method; f1, f2, f3, and f4 are all linear high-order polynomial functions.

2. The method for evaluating the noise reduction effect of a generator set according to claim 1, wherein: The step of solving the noise reduction quantitative evaluation model based on the noise reduction value set and the noise reduction method technical indicator set to obtain the solved noise reduction quantitative evaluation model includes: S41, for each type of denoising function, determining a corresponding technical indicator subset in the denoising method technical indicator set according to its input quantity, performing order calculation on the determined technical indicator subset to obtain a polynomial order value of the corresponding denoising function; S42, taking the noise reduction value set as the dependent variable and the noise reduction method technical indicator set as the independent variable, performing function fitting and solving all weighting coefficients and function parameter values ​​of f1, f2, f3, and f4 in the noise reduction quantitative evaluation model to obtain the solved noise reduction quantitative evaluation model.

3. The method for evaluating the noise reduction effect of a generator set according to claim 2, wherein: The order calculation includes: The technical indicator subset is represented as a technical indicator matrix; the row vector of the technical indicator matrix is ​​a time series of a type of technical indicator in the technical indicator subset; Performing QR decomposition on the technical indicator matrix to obtain corresponding Q matrix and R matrix; Performing eigenvalue calculation processing on the technical indicator matrix to obtain an eigenvalue vector; the eigenvalue vector is a vector constructed by all eigenvalues; Calculate the mean and variance of all elements of the eigenvalue vector; Decomposing and calculating the technical indicator matrix to obtain a decomposition vector; Based on the decomposition vector, the polynomial order value of the noise reduction function is calculated; the calculation expression of the polynomial order value of the noise reduction function is: in, Indicates rounding up, N indicates the row dimension of the technical indicator matrix, M indicates the length of the decomposition vector, L indicates the polynomial order value of the noise reduction function, t i represents the element of the i-th item of the decomposition vector, and t0 represents the mean of the decomposition vector.

4. The method for evaluating the noise reduction effect of a generator set according to claim 3, wherein: The expression of the decomposition calculation process is: t=(δP T V+μI) -1 P T y, V=QR -1 , Where t is the decomposition vector, Q and R are the Q matrix and R matrix obtained by QR decomposition of the technical indicator matrix P, V is the intermediate matrix, μ and δ are the mean and variance of all elements of the eigenvalue vector, y is the eigenvalue vector, and I is the identity matrix.

5. The method for evaluating the noise reduction effect of a generator set according to claim 1, wherein: The noise reduction quantitative evaluation model after solution is used to obtain the noise reduction effect evaluation values ​​of various noise reduction methods, including: S51, for each type of noise reduction method, calculating derivative values ​​of the solved noise reduction quantitative evaluation model with respect to all types of technical indicators of the noise reduction method; S52, performing a fusion calculation on the derivative values ​​of all categories of technical indicators calculated by each type of noise reduction method to obtain a noise reduction effect evaluation value of the noise reduction method.

6. The method for evaluating the noise reduction effect of a generator set according to claim 5, wherein: The derivative values ​​of all categories of technical indicators calculated by each type of noise reduction method are fused and calculated to obtain the noise reduction effect evaluation value of the noise reduction method, including: For each type of noise reduction method, a derivative value matrix is ​​constructed using the corresponding derivative values ​​of all types of technical indicators; the row vectors of the derivative value matrix are the derivative values ​​of a type of technical indicator at all test times and test locations; An evaluation calculation process is performed on the derivative value matrix to obtain an evaluation value of the noise reduction effect of the noise reduction method.

7. A device for evaluating the noise reduction effect of a generator set, characterized in that: The device comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the method for evaluating the noise reduction effect of a generator set according to any one of claims 1 to 6.

8. A computer storable medium, characterized in that The computer storable medium stores computer instructions, and when the computer instructions are called by a computer, they are used to execute the method for evaluating the noise reduction effect of a generator set according to any one of claims 1 to 6.

9. An information data processing terminal, characterized in that: The information data processing terminal is used to implement the method for evaluating the noise reduction effect of a generator set according to any one of claims 1 to 6.

Images