Method, device, equipment and medium for accurately detecting and imaging porosity of closing resistor disc based on ultrasonic back scattering signal

Abstract

The invention discloses a closing resistor disc porosity accurate detection and imaging method, device, equipment and medium based on an ultrasonic back scattering signal, and relates to the technical field of ultrasonic nondestructive evaluation.The method comprises the steps that a low-frequency ultrasonic probe is adopted to conduct water immersion type ultrasonic scanning on a target closing resistor disc, and data to be processed are obtained; preprocessing the to-be-processed data, and extracting characteristic parameters of a back scattering signal, including back scattering average power, back scattering spectrum energy and the like; determining the reference porosity of a specific area of the target resistor disc through a standard water immersion method, and establishing a calibration data set; constructing a porosity prediction model based on particle swarm optimization support vector regression (PSO-SVR), and realizing accurate mapping of back scattering characteristic parameters and porosity through nonlinear regression analysis; and based on the established prediction model, carrying out porosity calculation on the whole area of the resistor disc, and generating a two-dimensional pore distribution image. By means of the method, accurate detection and imaging of the porosity of the closing resistor disc can be achieved.

Description

Technical Field

[0001] This invention relates to the field of ultrasonic nondestructive testing technology, and in particular to a method, apparatus, equipment and medium for accurate detection and imaging of porosity of a closing resistor based on ultrasonic backscatter signals. Background Technology

[0002] With the rapid development of ultra-high voltage and extra-high voltage power transmission, gas-insulated switchgear (GIS), hybrid gas-insulated switchgear (HGIS), and tank-type circuit breakers equipped with closing resistors are widely used. However, because variations in the porosity of the closing resistor significantly affect its electrical and mechanical properties, operational reliability is not ideal. Therefore, a complete and effective method for inspecting and testing the porosity of the closing resistor element is urgently needed. Summary of the Invention

[0003] To address the issue of unsatisfactory equipment reliability caused by variations in porosity, this invention provides a method, apparatus, equipment, and medium for accurate detection and imaging of porosity in closing resistor sheets based on ultrasonic backscattering signals, thereby achieving accurate detection and imaging of porosity in closing resistor sheets.

[0004] To achieve the above object, the present invention provides the following solutions:

[0005] In a first aspect, the present invention provides a method for accurate detection and imaging of porosity of a closing resistor based on ultrasonic backscattering signals, comprising:

[0006] The target closing resistor was subjected to water immersion ultrasonic scanning to obtain the data to be processed.

[0007] After preprocessing the data to be processed, the characteristic parameters of the backscattered signal are extracted;

[0008] A calibration dataset was established by determining the reference porosity of a specific region of the target resistor using the standard water immersion method.

[0009] A porosity prediction model based on particle swarm optimization support vector regression (PSO-SVR) was constructed, and the backscattering characteristic parameters and porosity were accurately mapped through nonlinear regression analysis.

[0010] Based on the established prediction model, the porosity of the entire resistive sheet is calculated, and a two-dimensional pore distribution image is generated.

[0011] Optionally, after preprocessing the data to be processed, the characteristic parameters of the backscatter signal are extracted. The backscatter signal is extracted from the 70% range from the front surface echo to the bottom surface echo. The characteristic parameters include: average backscatter power and backscatter spectral energy.

[0012] Optionally, the average power of the backscattered signal can be calculated:

[0013] Perform an FFT transform on the backscattered signal and calculate the backscattered spectral energy: E bs =ΣF(ω) 2 ;

[0014] Empirical Mode Decomposition (EMD) is performed on the backscattered signal to extract the average power of each intrinsic mode function (IMF).

[0015] Where bs is the average backscattered power, n is the backscattered signal length, u(s) is the amplitude of the backscattered signal, s is time; F is the spectral amplitude of the backscattered signal, k is the frequency of the backscattered signal; i is the IMF order, i = 1, 2, 3; u i (s) represents the magnitude of the i-th order IMF.

[0016] Optionally, the reference porosity of a specific region of the target resistor is determined by the standard water immersion method, and the measurement is performed according to GB / T25995-2010.

[0017] Optionally, the construction of a porosity prediction model based on particle swarm optimization support vector regression (PSO-SVR), which achieves accurate mapping between backscattering characteristic parameters and porosity through nonlinear regression analysis, specifically includes:

[0018] (1) Correlation analysis: Pearson correlation coefficient analysis was performed on the ultrasonic backscattering characteristic parameters and the measured porosity data to calculate the correlation coefficient matrix between each characteristic parameter and porosity;

[0019] (2) Model Construction: A Support Vector Regression (SVR) model framework is established, and the Radial Basis Function (RBF) is used to map the low-dimensional nonlinear problem to a high-dimensional feature space.

[0020] K(x,x')=exp(-γ||x-x'|| 2 )

[0021] Where K(x,x') is the similarity measure between two samples x and x', γ is a positive number that determines the width of the kernel function, ||x-x'|| 2 Represents the Euclidean distance between samples;

[0022] The mathematical expression for the SVR model is shown below:

[0023]

[0024] stf(x i )-y i ≤ε+ξ i

[0025]

[0026] Where w and b are parameters determined by the model, x i Represents the sample feature value, y i ξ represents the sample label value, C is the penalty coefficient, and ξ is the penalty coefficient. i Let ε represent the error term, and let f(x) represent the error term. i ) and y i Deviation between;

[0027] An adaptive expression for the inertia coefficient is used:

[0028] w = w max -(w max -w min )×t / epochs

[0029] Where t represents the current iteration number, and epochs represents the number of iterations of the PSO algorithm, and the SVR parameter combination is dynamically adjusted by the particle position;

[0030] Using backscattering characteristics as input and measured pore parameters as output, regression fitting is performed on backscattering signal characteristics and pore parameters based on PSO-SVR.

[0031] (3) Model evaluation: The coefficient of determination (R-squared, R) was used. 2 The sum of squared residuals (RSS) is used to evaluate the performance of the model.

[0032] Optionally, the coefficient of determination R in the model evaluation 2 The value ranges from 0 to 1, with values ​​closer to 1 indicating a higher degree of fit. The calculation formula is as follows:

[0033]

[0034] In the formula, y i These are the actual values ​​in the fitted model, i.e., the response variable values ​​given the pore parameters. These are predicted values, calculated by the fitted model based on the input features. It is the sample mean.

[0035] Optionally, the porosity calculation for the entire resistive sheet based on the established prediction model, and the generation of a two-dimensional pore distribution image, includes:

[0036] Based on the established PSO-SVR prediction model, the ultrasonic backscattering characteristic parameters of each scanning point in the entire area of ​​the resistor are processed, and the predicted porosity value is calculated point by point. According to the XY coordinate information in the three-dimensional matrix of the A-scan signal obtained by ultrasonic C-scan, the spatial position mapping relationship of the resistor surface is established. The porosity-color mapping relationship is established, and a gradient color system is used to represent different porosity ranges. A two-dimensional pseudo-color image is generated, where: the horizontal and vertical axes represent the actual size ratio of the resistor; and the pixel color depth corresponds to the porosity.

[0037] Secondly, the present invention provides a device for precise detection and imaging of porosity of a closing resistor based on ultrasonic backscattered signals. The device utilizes any one of the methods described above for precise detection and imaging of porosity of a closing resistor based on ultrasonic backscattered signals. The device comprises:

[0038] The ultrasonic data acquisition module is used to perform water immersion ultrasonic scanning on the target closing resistor using a low-frequency ultrasonic probe to acquire data to be processed.

[0039] The feature parameter extraction module is used to extract the feature parameters of the backscattered signal after preprocessing the data to be processed, including the average backscattered power and the backscattered spectral energy.

[0040] The porosity calibration module is used to determine the reference porosity of a specific region of the target resistive element by standard water immersion method and to establish a calibration dataset.

[0041] The intelligent modeling module is used to construct a porosity prediction model based on particle swarm optimization support vector regression (PSO-SVR), and achieves accurate mapping between backscattering characteristic parameters and porosity through nonlinear regression analysis.

[0042] The visualization imaging module is used to calculate the porosity of the entire resistive sheet based on the established prediction model and generate a two-dimensional pore distribution image.

[0043] Thirdly, the present invention provides a computer device, comprising: 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 steps of the method for accurate detection and imaging of porosity of a closing resistor sheet based on ultrasonic backscattering signals as described above.

[0044] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for accurate detection and imaging of porosity of a closing resistor sheet based on ultrasonic backscattering signals as described above. According to specific embodiments provided by the present invention, the following technical effects are disclosed:

[0045] This invention provides a method, apparatus, device, and medium for accurate detection and imaging of porosity in a closing resistor based on ultrasonic backscattered signals. The method calculates the porosity of the entire resistor area based on ultrasonic backscattered signals and generates a two-dimensional porosity distribution image. This invention enables accurate detection and imaging of the porosity of a closing resistor. Attached Figure Description

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 This is a flowchart illustrating a method for accurate detection and imaging of porosity of a closing resistor based on ultrasonic backscattering signals, provided in an embodiment of the present invention.

[0048] Figure 2 This is a schematic diagram of the A-scan signal at a certain point of the closing resistor obtained by an ultrasonic probe according to an embodiment of the present invention;

[0049] Figure 3 This is a backscattering feature imaging result provided in an embodiment of the present invention;

[0050] Figure 4 The PSO-SVR regression result is provided in one embodiment of the present invention;

[0051] Figure 5 This is a two-dimensional pore distribution image provided in an embodiment of the present invention;

[0052] Figure 6 This is a schematic diagram of a device for precise detection and imaging of porosity of a closing resistor based on ultrasonic backscattering signals, provided in an embodiment of the present invention.

[0053] Figure 7 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0054] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0055] The purpose of this invention is to provide a method, device, equipment, and medium for accurate detection and imaging of porosity of a closing resistor based on ultrasonic backscattering signals. The invention involves ultrasonic scanning of a target closing resistor, calculating the porosity of the entire resistor area based on the ultrasonic backscattering signals, and generating a two-dimensional porosity distribution image, thereby achieving accurate detection and imaging of the porosity of the closing resistor.

[0056] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0057] This invention provides a method for accurate detection and imaging of porosity of a closing resistor based on ultrasonic backscattering signals, such as... Figure 1 As shown, the ultrasonic imaging method for the closing resistor element includes:

[0058] Step 101: Use a low-frequency ultrasonic probe to perform a water immersion ultrasonic scan on the target closing resistor to obtain the data to be processed.

[0059] Step 102: After preprocessing the data to be processed, extract the characteristic parameters of the backscattered signal, including the average backscattered power and the backscattered spectral energy.

[0060] Step 103: Determine the reference porosity of a specific region of the target resistor using the standard water immersion method to establish a calibration dataset.

[0061] Step 104: Construct a porosity prediction model based on particle swarm optimization support vector regression (PSO-SVR), and achieve accurate mapping between backscattering characteristic parameters and porosity through nonlinear regression analysis.

[0062] Step 105: Based on the established prediction model, calculate the porosity of the entire resistive sheet and generate a two-dimensional pore distribution image.

[0063] In an exemplary embodiment, step 101 specifically includes: using a low-frequency ultrasonic probe to perform a water immersion ultrasonic scan on the target closing resistor to obtain data to be processed.

[0064] Specifically, the closing resistor was scanned using an ultrasonic C-scan method. An OLYMPUS 1.0MHz / 0.5-inch, 0.8-inch focal length water immersion point focusing low-frequency probe was used to scan the closing resistor using the water immersion ultrasonic longitudinal wave vertical incidence method to obtain three-dimensional matrix data containing A-scan signal coordinate information.

[0065] In an exemplary embodiment, step 102 specifically includes: after preprocessing the data to be processed, extracting characteristic parameters of the backscattered signal, including the average backscattered power, backscattered spectral energy, etc.

[0066] It should be noted that the backscattered signal is extracted from the 70% range between the front surface echo and the bottom surface echo. For example... Figure 2 As shown in (a).

[0067] The average power of the backscattered signal is calculated based on the time-domain signal:

[0068] Perform an FFT transform on the backscattered signal to obtain the backscattered spectrum, as shown below. Figure 2 As shown in (b). Based on frequency domain analysis, the backscattered spectral energy is calculated: E bs =∑F(ω) 2 ;

[0069] Empirical Mode Decomposition (EMD) is performed on the backscattered signal to extract the average power of each intrinsic mode function (IMF).

[0070] Where bs is the average backscattered power, n is the backscattered signal length, u(s) is the amplitude of the backscattered signal, s is time; F is the backscattered signal spectrum, k is the backscattered signal frequency; i is the IMF order, i = 1, 2, 3; u i (s) represents the magnitude of the i-th order IMF.

[0071] By correlating the aforementioned characteristic parameters with the scanning position information, a backscattering feature matrix is ​​constructed, enabling a visual characterization of the material's internal structure. The feature imaging results clearly reflect the porosity distribution characteristics within the resistor sheet. For example... Figure 3 As shown.

[0072] In an exemplary embodiment, step 103 specifically includes: determining the reference porosity of a specific region of the target resistor using a standard water immersion method, and establishing a calibration dataset.

[0073] The resistance element was cut to obtain 18 resistance element test blocks. The reference porosity was measured using the water immersion method according to B / T 25995-2010. The specific measurement steps are as follows: First, the material to be tested was dried to ensure no residual moisture, and the mass m1 of the dried sample was weighed using an electronic scale. Then, a water tank was placed on the electronic scale, and the material to be tested was suspended by a thin rope and immersed in the water tank. The change in the mass of the electronic scale was recorded; this is the buoyancy m2. Finally, the material to be tested was placed in the water tank until it reached saturation. After wiping off the surface water, the mass m3 of the wet sample was recorded.

[0074] Based on the measurement data, calculate the apparent porosity of the material to be tested: The measured porosity results are shown in Table 1.

[0075] Table 1

[0076]

[0077] In an exemplary embodiment, step 104 specifically includes: constructing a porosity prediction model based on particle swarm optimization support vector regression (PSO-SVR), and achieving accurate mapping between backscattering characteristic parameters and porosity through nonlinear regression analysis.

[0078] (1) Correlation analysis: Pearson correlation coefficient analysis was performed on the ultrasonic backscattering characteristic parameters and the measured porosity data to calculate the correlation coefficient matrix between each characteristic parameter and porosity. See Table 2. ave and E bs ave With pore parameters and π a The correlations are strongly negative, with correlation coefficients of -0.76 and -0.72, respectively. This indicates that these parameters are highly sensitive to changes in porosity and can effectively reflect the distribution and characteristics of pores within the material.

[0079] Table 2

[0080]

[0081] (2) Model Construction: A Support Vector Regression (SVR) model framework is established, and the Radial Basis Function (RBF) is used to map the low-dimensional nonlinear problem to a high-dimensional feature space.

[0082] K(x,x')=exp(-γ||x-x'|| 2 )

[0083] Where K(x,x') is the similarity measure between two samples x and x', γ is a positive number that determines the width of the kernel function, ||x-x'|| 2 This represents the Euclidean distance between samples.

[0084] The mathematical expression for the SVR model is shown below:

[0085]

[0086] stf(x i )-y i ≤ε+ξ i

[0087]

[0088] Where w and b are parameters determined by the model, x i Represents the sample feature value, y i ξ represents the sample label value, C is the penalty coefficient, and ξ is the penalty coefficient. i Let ε represent the error term, and let f(x) represent the error term. i ) and y i The deviation between them.

[0089] An adaptive expression for the inertia coefficient is used:

[0090] w = w max -(w max -w min )×t / epochs

[0091] Where t represents the current iteration number, and epochs represents the number of iterations of the PSO algorithm, and the SVR parameter combination is dynamically adjusted by the particle position.

[0092] Using backscattering characteristics as input and measured pore parameters as output, regression fitting was performed on the backscattering signal characteristics and pore parameters based on PSO-SVR. The results are as follows: Figure 4 As shown.

[0093] (3) Model evaluation: The coefficient of determination (R-squared, R) was used. 2 The sum of squared residuals (RSS) is a performance metric for evaluating a model. The coefficient of determination (R²) is a statistical indicator used to measure the proportion of variation in the dependent variable that can be explained by the independent variables. 2 The value ranges from 0 to 1, with values ​​closer to 1 indicating a higher degree of fit. Squared residuals and RSS measure the bias of the fitted model. RSS can effectively amplify larger errors, thus helping to identify significant biases in the model. Calculation formula:

[0094]

[0095] In the formula, y i These are the actual values ​​in the fitted model, i.e., the response variable values ​​given the pore parameters. These are predicted values, calculated by the fitted model based on the input features. It is the sample mean.

[0096] Based on the above calculations, the determination coefficient R0 based on the PSO-SVR regression model is obtained. 2 The value is 0.918, and the SSR is 0.3109.

[0097] In an exemplary embodiment, step 105 specifically includes: calculating the porosity of the entire resistive sheet based on the established prediction model, and generating a two-dimensional pore distribution image.

[0098] Based on the XY coordinate information in the three-dimensional matrix of the A-scan signal obtained from ultrasonic C-scan, a spatial position mapping relationship of the resistor surface is established. A porosity-color mapping relationship is established, using a gradient color system to represent different porosity ranges; a two-dimensional pseudo-color image is generated, where: the horizontal and vertical axes represent the actual size ratio of the resistor; and the pixel color depth corresponds to the porosity. The two-dimensional distribution results are as follows: Figure 5 As shown.

[0099] Based on the same inventive concept, embodiments of the present invention also provide an ultrasonic imaging device for implementing the above-described method for accurate detection and imaging of the porosity of a closing resistor based on ultrasonic backscattered signals. The solution provided by this device is similar to the implementation described in the above method. Therefore, the specific limitations of one or more embodiments of the device for accurate detection and imaging of the porosity of a closing resistor based on ultrasonic backscattered signals provided below can be found in the limitations of the method for accurate detection and imaging of the porosity of a closing resistor based on ultrasonic backscattered signals described above, and will not be repeated here.

[0100] In one exemplary embodiment, such as Figure 6 As shown, a device for precise detection and imaging of porosity of a closing resistor based on ultrasonic backscattered signals is provided. This device applies any one of the methods described above for precise detection and imaging of porosity of a closing resistor based on ultrasonic backscattered signals. The device includes:

[0101] The ultrasonic data acquisition module is used to perform water immersion ultrasonic scanning on the target closing resistor using a low-frequency ultrasonic probe to acquire data to be processed.

[0102] The feature parameter extraction module is used to extract the feature parameters of the backscattered signal after preprocessing the data to be processed, including the average backscattered power and the backscattered spectral energy.

[0103] The porosity calibration module is used to determine the reference porosity of a specific region of the target resistive element by standard water immersion method and to establish a calibration dataset.

[0104] The intelligent modeling module is used to construct a porosity prediction model based on particle swarm optimization support vector regression (PSO-SVR), and achieves accurate mapping between backscattering characteristic parameters and porosity through nonlinear regression analysis.

[0105] The visualization imaging module is used to calculate the porosity of the entire resistive sheet based on the established prediction model and generate a two-dimensional pore distribution image.

[0106] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 7 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores ultrasonic imaging data of the closing resistor. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements an ultrasonic imaging method for a closing resistor.

[0107] Those skilled in the art will understand that Figure 7 The structures shown are merely block diagrams of some structures related to the present invention and do not constitute a limitation on the computer device to which the present invention is applied. Specific computer devices may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0108] 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.

[0109] 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.

[0110] 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 invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with relevant regulations.

[0111] 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 of the above methods. Any references to memory, databases, or other media used in the embodiments provided by this invention 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).

[0112] The databases involved in the various embodiments provided by this invention 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 various embodiments provided by this invention may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, data processing logic units, etc., and are not limited to these.

[0113] 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.

[0114] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, 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 the present invention.

Claims

1. A method for accurate detection and imaging of porosity of a closing resistor based on ultrasonic backscattered signals, characterized in that, include: The target closing resistor was subjected to water immersion ultrasonic scanning to obtain the data to be processed. After preprocessing the data to be processed, the characteristic parameters of the backscattered signal are extracted; Determine the reference porosity of a specific region of the target resistor sheet and establish a calibration dataset; A porosity prediction model based on particle swarm optimization support vector regression (PSO-SVR) was constructed, and the backscattering characteristic parameters and porosity were accurately mapped through nonlinear regression analysis. Based on the established prediction model, the porosity of the entire resistive sheet is calculated, and a two-dimensional pore distribution image is generated.

2. The method for accurate detection and imaging of porosity of closing resistor sheet based on ultrasonic backscattering signal as described in claim 1, characterized in that, After preprocessing the data to be processed, the characteristic parameters of the backscatter signal are extracted. The backscatter signal is extracted from the 70% range from the front surface echo to the bottom surface echo. The characteristic parameters include: average backscatter power and backscatter spectral energy.

3. The method for accurate detection and imaging of porosity of closing resistor sheet based on ultrasonic backscattering signal as described in claim 2, characterized in that, The average power of the backscattered signal is calculated based on the time-domain signal: Perform an FFT transform on the backscattered signal and calculate the backscattered spectral energy based on frequency domain analysis: E bs =ΣF(ω) 2 ; Empirical Mode Decomposition (EMD) is performed on the backscattered signal to extract the average power of each intrinsic mode function (IMF). Where bs is the average backscattered power, n is the backscattered signal length, u(s) is the amplitude of the backscattered signal, s is time; F is the spectral amplitude of the backscattered signal, k is the frequency of the backscattered signal; i is the IMF order, i = 1, 2, 3; u i (s) represents the magnitude of the i-th order IMF.

4. The method for accurate detection and imaging of porosity of closing resistor sheet based on ultrasonic backscattering signal as described in claim 1, characterized in that, The reference porosity of a specific region of the target resistive element is measured according to GB / T 25995-2010.

5. The method for accurate detection and imaging of porosity of closing resistor sheet based on ultrasonic backscattering signal as described in claim 1, characterized in that, The construction of a porosity prediction model based on particle swarm optimization support vector regression (PSO-SVR) achieves an accurate mapping between backscattering characteristic parameters and porosity through nonlinear regression analysis, specifically including: (1) Correlation analysis: Pearson correlation coefficient analysis was performed on the ultrasonic backscattering characteristic parameters and the measured porosity data to calculate the correlation coefficient matrix between each characteristic parameter and porosity; (2) Model Construction: A Support Vector Regression (SVR) model framework is established, and the Radial Basis Function (RBF) is used to map the low-dimensional nonlinear problem to a high-dimensional feature space. K(x,x')=exp(-γ||x-x'|| 2 ) Where K(x,x') is the similarity measure between two samples x and x', γ is a positive number that determines the width of the kernel function, ||x-x'|| 2 Represents the Euclidean distance between samples; The mathematical expression for the SVR model is shown below: s.t.f(x i )-y i ≤ε+ξ i Where w and b are parameters determined by the model, x i Represents the sample feature value, y i ξ represents the sample label value, C is the penalty coefficient, and ξ is the penalty coefficient. i Let ε represent the error term, and let f(x) represent the error term. i ) and y i Deviation between; An adaptive expression for the inertia coefficient is used: w=w max -(w max -w min )×t / epochs Where t represents the current iteration number, and epochs represents the number of iterations of the PSO algorithm, and the SVR parameter combination is dynamically adjusted by the particle position; Using backscattering characteristics as input and measured pore parameters as output, regression fitting is performed on backscattering signal characteristics and pore parameters based on PSO-SVR. (3) Model evaluation: The coefficient of determination (R-squared, R) was used. 2 The sum of squared residuals (RSS) is used to evaluate model performance.

6. The method for accurate detection and imaging of porosity of closing resistor sheet based on ultrasonic backscattering signal as described in claim 5, characterized in that, The coefficient of determination R in the model evaluation 2 The value ranges from 0 to 1, with values ​​closer to 1 indicating a higher degree of fit. The calculation formula is as follows: In the formula, y i These are the actual values ​​in the fitted model, i.e., the response variable values ​​given the pore parameters. These are predicted values, calculated by the fitted model based on the input features. It is the sample mean.

7. The method for accurate detection and imaging of porosity of closing resistor sheet based on ultrasonic backscattering signal as described in claim 1, characterized in that, Based on the established prediction model, the porosity of the entire resistive sheet is calculated, and a two-dimensional porosity distribution image is generated, including: Based on the established PSO-SVR prediction model, the ultrasonic backscattering characteristic parameters of each scanning point in the entire area of ​​the resistor are processed, and the predicted porosity value is calculated point by point. According to the XY coordinate information in the three-dimensional matrix of the A-scan signal obtained by ultrasonic C-scan, the spatial position mapping relationship of the resistor surface is established. The porosity-color mapping relationship is established, and a gradient color system is used to represent different porosity ranges. A two-dimensional pseudo-color image is generated, where: the horizontal and vertical axes represent the actual size ratio of the resistor; and the pixel color depth corresponds to the porosity.

8. A device for precise detection and imaging of porosity of a closing resistor based on ultrasonic backscattered signals, using the method described in any one of claims 1-7, characterized in that, The poisoning data is generated through preset triggers and category mapping transformations, including: The ultrasonic data acquisition module is used to perform water immersion ultrasonic scanning on the target closing resistor using a low-frequency ultrasonic probe to acquire data to be processed. The feature parameter extraction module is used to extract the feature parameters of the backscattered signal after preprocessing the data to be processed, including the average backscattered power and the backscattered spectral energy. The porosity calibration module is used to determine the reference porosity of a specific region of the target resistive element by standard water immersion method and to establish a calibration dataset. The intelligent modeling module is used to construct a porosity prediction model based on particle swarm optimization support vector regression (PSO-SVR), and achieves accurate mapping between backscattering characteristic parameters and porosity through nonlinear regression analysis. The visualization imaging module is used to calculate the porosity of the entire resistive sheet based on the established prediction model and generate a two-dimensional pore distribution image.

9. A computer-readable storage medium storing a computer program that, when executed by a processor, implements the method for accurate detection and imaging of porosity of a closing resistor based on ultrasonic backscattering signals as described in any one of claims 1-7.

10. An electronic device, comprising a memory and a processor, wherein the memory stores a computer program and the processor runs the computer program to cause the electronic device to perform the method for accurate detection and imaging of porosity of a closing resistor based on ultrasonic backscattering signals as described in any one of claims 1-7.

Images