Ultrasonic-based substation reinforced concrete corrosion thickness evaluation method and system

Abstract

The present application belongs to the technical field of rust thickness measurement, and provides a substation reinforced concrete rust thickness evaluation method and system based on ultrasonic waves, which determines the ultrasonic wave parameter combination according to the geometric shape information and spatial position information, realizes the real-time adjustment of the ultrasonic wave parameters, obtains the rust category according to the frequency spectrum characteristic parameters and the preset support vector machine classification model, obtains the rust thickness and rust degree grade according to the rust category and rust degree evaluation model, and solves the influence of different rust product categories and distribution characteristics on the propagation and reflection of ultrasonic waves on the surface of the component; the overall rust condition is fully reflected by adjusting the ultrasonic detection parameters, the geometric shape and spatial position of the rust part are considered, and the comprehensive improvement according to the rust category evaluation makes the evaluation method adapt to complex rust parts, improves the detection data quality, realizes the comprehensive and accurate evaluation of the rust degree of the metal component, and provides a reliable basis for component maintenance and safety evaluation.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of rust thickness measurement, and particularly relates to a transformer substation reinforced concrete corrosion thickness evaluation method and system based on ultrasonic waves. BACKGROUND

[0002] The transformer substation is an important hub of the power system, and undertakes the functions of power transmission and distribution. Once a failure occurs, it may cause a large-scale power outage, so it is crucial to ensure the safe and stable operation of the transformer substation. Early transformer substations mostly use reinforced concrete structures. However, due to the insufficient durability of concrete, as well as the influence of technical level and construction quality, there are problems of aging and deterioration in concrete structures to varying degrees.

[0003] Among the many factors that harm the durability of concrete structures, steel bar corrosion is one of the most serious factors. Steel bar corrosion generates rust, which leads to a decrease in cross-sectional area and causes cracks on the surface and inside the concrete. The appearance of cracks further accelerates the corrosion of steel bars, forming a vicious cycle. This condition significantly reduces the durability and reliability of the concrete structure of the transformer substation, shortens the service life, and poses a serious threat to the safe and stable operation of the transformer substation. Therefore, real-time detection of the degree of steel bar corrosion in the concrete structure has become an important aspect of evaluating the residual mechanical properties of the concrete structure.

[0004] Because the steel bars are located inside the concrete, and the substation has importance and particularity, the integrity and durability of the concrete structure need to be avoided during the detection process. Therefore, non-destructive testing technology becomes the first choice. At present, the methods of non-destructive testing include electromagnetic method, macro-current method and ultrasonic detection method, etc. Among them, ultrasonic detection has shown broad application prospects in the field of steel bar corrosion detection due to its high efficiency and accuracy. However, in practical application, ultrasonic detection technology still faces certain technical problems and needs to be further optimized and improved. First, in the parts with light corrosion thickness, the ultrasonic signal attenuation is small, and the reflected signal intensity is high; while in the parts with serious corrosion thickness, the ultrasonic signal attenuation is large, and the reflected signal intensity is low; the corrosion thickness and degree of different corrosion parts are quite different, and a single ultrasonic detection parameter is difficult to comprehensively evaluate the overall corrosion condition of the component. Second, the geometry and spatial position of the corrosion part are complex and changeable, which significantly affects the propagation and reflection characteristics of the ultrasonic wave; the irregular shape of the corrosion part will cause scattering and diffraction of the ultrasonic wave, affecting the accuracy of the detection signal; the spatial position change of the corrosion part will lead to the change of the ultrasonic incidence angle and propagation path, and then affect the reliability of the detection data. Finally, different types of corrosion products, such as iron oxide and iron hydroxide, have different acoustic characteristics; the distribution of corrosion products on the component surface is also uneven; the type and distribution characteristics of corrosion products will affect the propagation and reflection behavior of ultrasonic wave on the component surface, and then affect the accuracy of corrosion degree evaluation. In summary, in the current ultrasonic-based substation reinforced concrete corrosion thickness evaluation method, a single ultrasonic detection parameter is difficult to comprehensively evaluate the overall corrosion condition of the component, the geometry and spatial position of the corrosion part are complex and changeable, and the type and distribution characteristics of corrosion products will affect the propagation and reflection behavior of ultrasonic wave on the component surface, which leads to inaccurate evaluation results. SUMMARY

[0005] In order to solve the above problems, the application provides a substation reinforced concrete corrosion thickness evaluation method and system based on ultrasonic wave. According to the geometry and spatial position information of the corrosion area to be detected, the application determines the ultrasonic parameter combination through matching, realizes the real-time adjustment of the ultrasonic parameters for different corrosion parts, extracts the frequency spectrum characteristic parameters of the ultrasonic detection data, and obtains the corrosion type in the corrosion area to be detected according to the preset support vector machine classification model. According to the corrosion type and the preset corrosion degree evaluation model, the corrosion thickness and corrosion degree grade are obtained, and the influence of different corrosion product types and distribution characteristics on the propagation and reflection of ultrasonic wave on the component surface is solved.

[0006] In order to achieve the above purpose, the application is realized by the following technical scheme:

[0007] In a first aspect, the present application provides an ultrasonic-based substation reinforced concrete corrosion thickness evaluation method, comprising:

[0008] Obtain the geometric shape information and spatial position information of the corrosion area to be detected; determine the ultrasonic parameter combination by matching according to the geometric shape information and the spatial position information;

[0009] Based on the ultrasonic parameter combination, perform ultrasonic detection on the corrosion area to be detected to obtain ultrasonic detection data;

[0010] Extract the spectral feature parameters of the ultrasonic detection data; according to the spectral feature parameters and a preset support vector machine classification model, obtain the corrosion type in the corrosion area to be detected;

[0011] According to the corrosion type and a preset corrosion degree evaluation model, obtain the corrosion thickness and corrosion degree grade; wherein the corrosion degree evaluation model is a machine learning model.

[0012] Further, obtain the three-dimensional model data of the corrosion target to be detected, and obtain the geometric shape information of the corrosion area to be detected according to the three-dimensional model data; register the ultrasonic detection data with the three-dimensional model data to obtain the spatial position information of the corrosion target to be detected;

[0013] According to the geometric shape information and the spatial position information, combine the preset ultrasonic detection parameter library, and obtain the ultrasonic parameter combination by using a pattern matching algorithm; wherein the parameter combination includes ultrasonic frequency and probe type.

[0014] Further, register the ultrasonic detection data with the three-dimensional model data by point cloud registration, and solve the rigid body transformation matrix by least squares method to obtain the ultrasonic detection data in three-dimensional space; perform image segmentation processing on the ultrasonic detection data in three-dimensional space to obtain the spatial position information of the corrosion area to be detected in three-dimensional space;

[0015] Use the reflection feature of the ultrasonic detection data of the corrosion area as a seed point to extract the contour information of the corrosion area and obtain the geometric shape of the corrosion area; according to the geometric shape of the corrosion area and the three-dimensional model data, obtain the spatial position information of the corrosion area to be detected in three-dimensional space by triangulation principle.

[0016] Further, use wavelet transform to perform several levels of decomposition on the ultrasonic detection data, select and perform soft threshold denoising on the decomposed ultrasonic detection data; perform normalization processing on the denoised data, use Fourier transform to perform spectral analysis on the normalized data, and extract spectral feature parameters.

[0017] Further, the Euclidean distance measurement method is used to calculate the similarity of the spectrum characteristic parameters and the spectrum characteristics of each corrosion product in the preset spectrum characteristic database; a preset number of multiple corrosion products with high similarity are selected as candidates; the spectrum characteristic parameters of the candidates and the spectrum characteristic parameters of the ultrasonic detection data are input into the support vector machine classification model to obtain the corrosion type of the corrosion area to be detected.

[0018] Further, the corrosion degree evaluation model includes multiple types, and each type of corrosion degree evaluation model corresponds to a type of corrosion product; if there is no corresponding corrosion degree evaluation model for a type of corrosion product, the Euclidean distance measurement method is used to calculate the similarity of the spectrum characteristic parameters of the corrosion product and the spectrum characteristics of the corrosion product corresponding to the constructed corrosion degree evaluation model, and the corrosion degree evaluation model corresponding to the corrosion product with the highest similarity is selected for evaluation.

[0019] In a second aspect, the present application further provides an ultrasonic-based substation reinforced concrete corrosion thickness evaluation system, comprising:

[0020] The ultrasonic parameter combination determination module is configured to: obtain the geometric shape information and the spatial position information of the corrosion area to be detected; and determine the ultrasonic parameter combination by matching according to the geometric shape information and the spatial position information.

[0021] The ultrasonic detection module is configured to: perform ultrasonic detection on the corrosion area to be detected based on the ultrasonic parameter combination to obtain ultrasonic detection data.

[0022] The classification module is configured to: extract the spectrum characteristic parameters of the ultrasonic detection data; and obtain the corrosion type in the corrosion area to be detected according to the spectrum characteristic parameters and a preset support vector machine classification model.

[0023] The evaluation module is configured to: obtain the corrosion thickness and the corrosion degree grade according to the corrosion type and a preset corrosion degree evaluation model; and the corrosion degree evaluation model is a machine learning model.

[0024] In a third aspect, the present application further provides a computer readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement the steps of the ultrasonic-based substation reinforced concrete corrosion thickness evaluation method of the first aspect.

[0025] In a fourth aspect, the present application further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the program to implement the steps of the ultrasonic-based substation reinforced concrete corrosion thickness evaluation method of the first aspect.

[0026] In a fifth aspect, the present application also provides a computer program product, which comprises a computer program, and when the computer program is executed by a processor, the steps of the ultrasonic-based substation reinforced concrete corrosion thickness evaluation method of the first aspect are realized.

[0027] Compared with the prior art, the present application has the following beneficial effects:

[0028] In the present application, the ultrasonic parameter combination is determined by matching according to the geometric shape information and spatial position information of the corrosion area to be detected, realizing real-time adjustment of the ultrasonic parameters when different corrosion parts are adapted; the corrosion type in the corrosion area to be detected is obtained according to the extracted spectral feature parameters of the ultrasonic detection data and the preset support vector machine classification model; the corrosion thickness and corrosion degree grade are obtained according to the corrosion type and the preset corrosion degree evaluation model, solving the influence of different corrosion product types and distribution characteristics on the propagation and reflection of ultrasonic waves on the surface of the component; the overall corrosion condition is fully reflected by adjusting the ultrasonic detection parameters, the geometric shape and spatial position of the corrosion part are considered, and the comprehensive improvement according to the corrosion type for evaluation makes the evaluation method adapt to complex corrosion parts, improves the detection data quality, realizes comprehensive and accurate evaluation of the corrosion degree of the substation reinforced concrete structure, and provides a reliable basis for maintenance and safety evaluation of the substation reinforced concrete structure. BRIEF DESCRIPTION OF DRAWINGS

[0029] The accompanying drawings, which form a part of this implementation, are used to provide further understanding of this implementation, and the schematic embodiments of this implementation and the description thereof are used to explain this implementation, and do not constitute an improper limitation to this implementation.

[0030] Figure 1 The method flowchart of the present application embodiment 1. DETAILED DESCRIPTION

[0031] The present application will be further described below in combination with the accompanying drawings and embodiments.

[0032] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as generally understood by those skilled in the art to which the present application belongs.

[0033] Embodiment 1:

[0034] Ultrasonic testing is a non-destructive testing method that uses ultrasonic technology to detect defects. Non-destructive testing is a method of inspecting the surface and internal quality of a component without damaging the workpiece or raw material. Ultrasonic waves have low transmission loss in solids and can penetrate deep into the material. Due to the reflection and refraction of ultrasonic waves at heterogeneous interfaces, especially the inability to pass through gas-solid interfaces, ultrasonic waves are reflected or refracted when they encounter defects such as pores, cracks, or inclusions in the metal. When ultrasonic waves propagate to the interface between the metal and the defect, they are reflected or partially reflected. The reflected ultrasonic waves are received by the probe and processed by the internal circuit of the instrument, which displays different waveforms with certain intervals on the instrument's fluorescent screen.

[0035] As described in the background, in practical applications, ultrasonic testing technology faces some technical problems that need to be solved. First, the corrosion degree of different corrosion sites varies greatly, and a single ultrasonic testing parameter cannot fully evaluate the overall corrosion condition of the component. The ultrasonic signal attenuation is small and the reflected signal intensity is high in areas with light corrosion; while the ultrasonic signal attenuation is large and the reflected signal intensity is low in areas with severe corrosion; how to establish a reasonable corrosion degree evaluation model based on different ultrasonic testing data of different parts to accurately evaluate the overall corrosion condition of the component is a problem that needs to be solved. Second, the geometry and spatial position of the corrosion site are complex and variable, which significantly affects the propagation and reflection characteristics of ultrasonic waves. The irregular shape of the corrosion site causes scattering and diffraction of ultrasonic waves, affecting the accuracy of the detection signal; the spatial position change of the corrosion site changes the incident angle and propagation path of the ultrasonic wave, affecting the reliability of the detection data; how to optimize the ultrasonic testing parameters for different shapes and positions of the corrosion site to improve the accuracy and reliability of the detection data is another problem that needs to be solved. Finally, the influence of the type and distribution of corrosion products on the ultrasonic testing results cannot be ignored; different types of corrosion products, such as iron oxide and iron hydroxide, have different acoustic characteristics; the distribution of corrosion products on the component surface is also uneven; the type and distribution characteristics of corrosion products affect the propagation and reflection behavior of ultrasonic waves on the component surface, and thus affect the accuracy of corrosion degree evaluation; how to identify the type of corrosion product through ultrasonic testing data and consider the influence of its distribution characteristics on the detection results is the key to improving the accuracy of corrosion degree evaluation.

[0036] Based on the comprehensive influence of the single ultrasonic testing parameter that cannot fully evaluate the overall corrosion condition of the component, the complex and variable geometry and spatial position of the corrosion site, and the type and distribution characteristics of the corrosion product affecting the propagation and reflection behavior of ultrasonic waves on the component surface, the evaluation result accuracy is not accurate, such as Figure 1As shown, the embodiment provides an ultrasonic-based substation reinforced concrete corrosion thickness evaluation method, which is suitable for complex corrosion sites, improves the quality of detection data, realizes comprehensive and accurate evaluation of the corrosion degree of metal components, and provides reliable basis for component maintenance and safety evaluation; the method can be used to evaluate the corrosion thickness of the reinforced concrete structure of the substation, and the method comprises:

[0037] S1, obtain the geometric shape information and spatial position information of the corrosion area to be detected, and obtain the ultrasonic parameter combination according to the geometric shape information and spatial position information.

[0038] S2, ultrasonic detection is performed on the corrosion area to be detected based on the ultrasonic parameter combination, and ultrasonic detection data is obtained.

[0039] S3, input the frequency spectrum feature parameters of the ultrasonic detection data into a support vector machine classification model, and output the corrosion type judgment result in the corrosion area to be detected; wherein the support vector machine classification model is obtained by training based on a first training set, and the first training set includes known corrosion types and corresponding ultrasonic spectrum feature parameters.

[0040] S4, according to the corrosion type judgment result, input the ultrasonic detection data into the corresponding corrosion degree evaluation model to obtain the corrosion thickness and corrosion degree grade; wherein the corrosion degree evaluation model is constructed based on a machine learning model and obtained by training based on a second training set, and the second training set includes corrosion historical ultrasonic detection data corresponding to the corrosion type judgment result, historical degree evaluation results and historical corrosion thickness.

[0041] In step S1, the ultrasonic parameter combination is obtained according to the geometric shape information and spatial position information, which comprises:

[0042] S1.1, according to the three-dimensional model data of the corrosion target to be detected, the geometric shape information of the corrosion area to be detected is obtained; optionally, a laser scanner is used to capture the three-dimensional model data of the surface of the component in the corrosion area to be detected. Wherein, the corrosion target to be detected refers to a metal component, and the corrosion area to be detected can be a detection area on the metal component of the reinforced concrete structure of the substation.

[0043] S1.2, register the ultrasonic detection data with the three-dimensional model data of the corrosion area to be detected to obtain the spatial position information of the corrosion target to be detected.

[0044] S1.2.1, the ICP (Iterative Closest Point) algorithm is used to perform point cloud registration on the ultrasonic detection data and the three-dimensional model data, and a rigid transformation matrix is obtained by least square optimization solution, and the ultrasonic detection data in the three-dimensional space is obtained.

[0045] S1.2.2, image segmentation processing is performed on the ultrasonic detection data in three-dimensional space to obtain spatial position information of the corrosion area to be detected in three-dimensional space.

[0046] S1.2.2.1, a region growing algorithm is used, and the reflection characteristics of the ultrasonic detection data of the corrosion area are used as seed points to extract the contour information of the corrosion area to obtain the geometric shape of the corrosion area.

[0047] Optionally, the region growing algorithm is used, and the reflection characteristics of the ultrasonic detection data of the corrosion area are used as seed points to extract the contour information of the corrosion area, and the specific steps include:

[0048] 1) Determine the seed point: According to the reflection characteristics of the ultrasonic detection data, identify the feature points of the corrosion area as initial seed points. These seed points are usually regions with abnormal reflection intensity, indicating that corrosion may exist.

[0049] 2) Define the growth criterion: Set a growth criterion based on the similarity of the reflection characteristics of the pixel points in the ultrasonic data and the seed points. A threshold is preset, and only when the reflection characteristics of the adjacent pixels are within the threshold range of the characteristics of the seed points, the pixel will be added to the growing region.

[0050] 3) Initialize the growth region: Create a label image with the same size as the ultrasonic image to record which pixels have been added to the growing region. Initially, except for the seed point, the rest of the pixels are not marked.

[0051] 4) Growth process: Starting from the seed point, check the pixel points in its neighborhood, using 8-neighborhood or 4-neighborhood. For each neighborhood pixel, calculate the similarity of its reflection characteristics and the seed point.

[0052] If the reflection characteristics of the neighborhood pixels are within the predefined growth criterion threshold, add them to the growing region and mark the corresponding position in the label image.

[0053] 5) Iterative growth: Take the newly added pixel points in the growing region as new seed points, repeat step 4), continue the growth process until there are no more pixels that meet the growth criterion or reach the preset termination condition.

[0054] 6) Termination condition: A termination condition is preset, which can be based on the size, shape or density of the growing region. Once the termination condition is met, the growth process stops.

[0055] 7) Extract the contour information: After the growth is completed, post-process the label image to extract the contour information of the growing region.

[0056] S1.2.2.2. Obtain the spatial position information of the rust area to be detected in the three-dimensional space according to the rust area geometry and the three-dimensional model data by the triangulation principle.

[0057] Optionally, first, the ultrasonic detection data is registered with the pre-built three-dimensional model data of the target area, point cloud matching is performed by using the ICP algorithm, a rigid transformation matrix is solved by optimization by the least square method, accurate alignment of the ultrasonic detection data and the three-dimensional model is realized, and the ultrasonic detection data in the three-dimensional space is obtained. Then, the registered ultrasonic detection data is subjected to image segmentation processing, and the contour information of the rust area is extracted. According to the geometry of the rust area and the three-dimensional model data, the accurate position coordinates of the rust area in the three-dimensional space are calculated by the triangulation principle, and the positioning accuracy can reach 1 mm. Finally, the geometry and position coordinate information of the rust area are visualized and displayed, the Marching Cubes algorithm is used for three-dimensional reconstruction of the rust area, and the rust area is displayed in red highlight, and an intuitive rust distribution map is generated.

[0058] S1.3. Obtain the ultrasonic parameter combination according to the geometry information and the spatial position information and in combination with a pre-set ultrasonic detection parameter library by using a pattern matching algorithm; wherein the parameter combination includes an ultrasonic frequency and a probe type.

[0059] Optionally, the pattern matching algorithm is a kind of operation in string processing in a data structure, mainly including a naive pattern matching algorithm, a KMP (Knuth-Morris-Pratt) algorithm, a BM (Bad Match) algorithm and a Rabin-Karp algorithm.

[0060] In this embodiment, the naive pattern matching algorithm is used to select the most suitable ultrasonic frequency and probe type from the pre-set ultrasonic detection parameter library, and the specific steps are as follows:

[0061] 1) Construct the parameter library: a parameter library containing different ultrasonic frequencies and probe types is established. The library contains the use characteristic parameters and acoustic performance parameters of each probe, such as center frequency, pulse width, relative bandwidth, near-field length, beam diameter and diffusion angle.

[0062] 2) Define the matching rule: define the matching rule according to the geometry information and the spatial position information of the detected object. These rules are used as pattern strings for matching with the entries in the parameter library.

[0063] 3) Pattern string construction: construct a pattern string containing the characteristics of the required ultrasonic frequency and probe type.

[0064] 4) Traverse the parameter library: traverse each entry in the parameter library, treat each entry as a text string, and match the pattern string with each entry.

[0065] 4) Perform naive pattern matching: for each entry in the parameter library, use the naive pattern matching algorithm to match. Starting from the first entry of the parameter library, compare the pattern string with the entry character by character.

[0066] 5) Matching process: use two nested loops to traverse the pattern string and the parameter library entries. The outer loop traverses each entry in the parameter library, and the inner loop compares the features of the pattern string and the entry one by one. If a mismatched feature is found, the inner loop will immediately exit and continue to compare the next entry. If the entire pattern string matches a certain entry, record the entry as a potential matching result.

[0067] 6) Result screening: according to the degree of matching, screen out the entries that best match the matching rules.

[0068] In step S2, after obtaining the ultrasonic detection data, wavelet denoising and normalization processing are performed on the collected ultrasonic detection data to improve the signal-to-noise ratio. Based on wavelet packet decomposition, frequency domain characteristic parameters reflecting the corrosion degree are extracted, such as wavelet packet energy spectrum entropy and wavelet packet singular value.

[0069] S2.1, the wavelet transform is used to decompose the ultrasonic detection data for several levels, and the decomposed ultrasonic detection data is selected and subjected to soft threshold denoising.

[0070] S2.2, the normalized data is subjected to spectral analysis by Fourier transform, and the spectral feature parameters are extracted; wherein the spectral feature parameters include spectral centroid, spectral peak value and frequency corresponding to the spectral peak value.

[0071] Optionally, the signal is decomposed by 5 levels using the wavelet transform method, the high frequency coefficients of the 3rd to 5th levels are selected and subjected to soft threshold denoising, and the denoised signal is subjected to normalization processing, mapping the signal amplitude to the [0, 1] interval. Then, the preprocessed signal is subjected to spectral analysis by 512-point fast Fourier transform, and the frequency domain feature parameters of the signal are extracted, including spectral centroid, spectral peak value and frequency corresponding to the spectral peak value.

[0072] In step S3, the spectral feature parameters of the ultrasonic detection data are input into the support vector machine classification model, and the output of the corrosion type judgment result in the corrosion area to be detected includes:

[0073] S3.1, a spectral feature database of corrosion products is established in advance, the similarity between the spectral feature parameters and the spectral features of each corrosion product in the database is calculated by using the Euclidean distance measurement method, and the top several corrosion products with the highest similarity are selected as candidates.

[0074] Optionally, the Euclidean distance measurement method is used to calculate the similarity between the spectrum feature parameters and the spectrum features of each corrosion product in the database, which includes:

[0075] The feature parameters are extracted from the spectrum data of the corrosion product, the extracted feature parameters are constructed into a feature vector, and the Euclidean distance formula is used to calculate the distance between the feature vector of the spectrum feature parameters and the feature vector of each sample in the database. For two n-dimensional vectors a and b, the calculation formula of the Euclidean distance d is:

[0076]

[0077] where x 1k and x 2k are the values of vectors a and b in the kth dimension.

[0078] S3.2, input the candidate corrosion product spectrum feature parameters and the spectrum feature parameters of the ultrasonic detection data into the support vector machine classification model to obtain the corrosion type judgment result in the corrosion area to be detected.

[0079] Optionally, according to the pre-established spectrum feature database containing 100 common corrosion products, the Euclidean distance measurement method is used to calculate the similarity between the spectrum feature parameters of the current signal and the spectrum features of each corrosion product in the database, and the top 5 corrosion products with the highest similarity are selected as candidates. Finally, the candidate corrosion product spectrum feature parameters and the spectrum feature parameters of the ultrasonic detection data are input into a multi-classification model based on support vector machine (SVM) for discrimination. The model uses RBF (Radial Basis Function) kernel function, and the classification accuracy after cross-validation optimization can reach more than 95%.

[0080] In step S4, the machine learning model is a support vector machine and / or a random forest. The support vector machine algorithm is selected to construct the corrosion degree evaluation model, a radial basis kernel function is adopted, the penalty factor C=10, the kernel function parameter g=1, and the optimal parameters are determined through 5-fold cross-validation. The training set data is used to train the machine learning model, and the prediction accuracy on the test set can reach more than 90%. The corrosion degree evaluation model includes several types, and each corrosion degree evaluation model corresponds to a type of corrosion product. If there is no corresponding corrosion degree evaluation model for a certain type of corrosion product, the Euclidean distance measurement method is used to calculate the similarity of the spectral features of the corrosion product and the corrosion product corresponding to the constructed corrosion degree evaluation model, and the corrosion degree evaluation model corresponding to the corrosion product with the highest similarity is selected. This embodiment adopts an adaptive ultrasonic detection technology to adapt to different corrosion parts by adjusting the ultrasonic parameters in real time; the corrosion product type is identified through ultrasonic spectral analysis, and a multi-scale fusion strategy is adopted to comprehensively utilize the detection data obtained by different parameters. Finally, the machine learning algorithm is used to establish the corrosion degree evaluation model to accurately evaluate the overall corrosion condition of the component. This embodiment can adapt to complex corrosion parts, improve the quality of detection data, and realize comprehensive and accurate evaluation of the corrosion degree of the metal component, providing a reliable basis for component maintenance and safety evaluation.

[0081] Embodiment 2:

[0082] The embodiment provides an ultrasonic-based transformer substation reinforced concrete corrosion thickness evaluation system, which comprises:

[0083] The ultrasonic parameter combination determination module is configured to: acquire geometric shape information and spatial position information of a to-be-detected corrosion area; and determine an ultrasonic parameter combination through matching according to the geometric shape information and the spatial position information.

[0084] The ultrasonic detection module is configured to: perform ultrasonic detection on the to-be-detected corrosion area based on the ultrasonic parameter combination, and obtain ultrasonic detection data.

[0085] The classification module is configured to: extract spectral feature parameters of the ultrasonic detection data; and obtain a corrosion type in the to-be-detected corrosion area according to the spectral feature parameters and a preset support vector machine classification model.

[0086] The evaluation module is configured to: obtain a corrosion thickness and a corrosion degree grade according to the corrosion type and a preset corrosion degree evaluation model; and the corrosion degree evaluation model is a machine learning model.

[0087] The working method of the system is the same as the ultrasonic-based transformer substation reinforced concrete corrosion thickness evaluation method in Embodiment 1, and details are not repeated here.

[0088] Embodiment 3:

[0089] The embodiment provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement steps of the ultrasonic-based substation reinforced concrete corrosion thickness evaluation method in the embodiment 1.

[0090] Embodiment 4:

[0091] The embodiment provides an electronic device, which comprises a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor implements steps of the ultrasonic-based substation reinforced concrete corrosion thickness evaluation method in the embodiment 1 when executing the program.

[0092] Embodiment 5:

[0093] The embodiment provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement steps of the ultrasonic-based substation reinforced concrete corrosion thickness evaluation method in the embodiment 1.

[0094] The above merely describes the preferred embodiments of the present embodiment and is not intended to limit the present embodiment. The present embodiment can have various modifications and changes for those skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present embodiment shall be included in the protection scope of the present embodiment.

Claims

1. A method for ultrasonic-based substation reinforced concrete corrosion thickness evaluation, characterized in that, The method comprises the following steps: Obtaining the geometric shape information and the spatial position information of the rust area to be detected; determining the ultrasonic parameter combination by matching according to the geometric shape information and the spatial position information; Based on the ultrasonic parameter combination, the ultrasonic detection is carried out on the rust area to be detected, and the ultrasonic detection data is obtained; Extracting the frequency spectrum feature parameters of the ultrasonic detection data; obtaining the rust type in the rust area to be detected according to the frequency spectrum feature parameters and the preset support vector machine classification model; According to the rust type and the preset rust degree evaluation model, the rust thickness and the rust degree grade are obtained; wherein the rust degree evaluation model is a machine learning model.

2. A method of ultrasonic based substation reinforced concrete corrosion thickness evaluation as claimed in claim 1, wherein, Obtaining the three-dimensional model data of the rust target to be detected, and obtaining the geometric shape information of the rust area to be detected according to the three-dimensional model data; registering the ultrasonic detection data and the three-dimensional model data to obtain the spatial position information of the rust target to be detected; According to the geometric shape information and the spatial position information, the ultrasonic detection parameter library is combined, and the mode matching algorithm is used to obtain the ultrasonic parameter combination; wherein the parameter combination includes ultrasonic frequency and probe type.

3. A method of ultrasonic based substation reinforced concrete corrosion thickness evaluation as claimed in claim 2, wherein, The point cloud registration is carried out on the ultrasonic detection data and the three-dimensional model data, and the least square method is used to solve the rigid body transformation matrix to obtain the ultrasonic detection data in the three-dimensional space; the image segmentation processing is carried out on the ultrasonic detection data in the three-dimensional space to obtain the spatial position information of the rust area to be detected in the three-dimensional space; The region growing algorithm is used, the reflection feature of the ultrasonic detection data of the rust area is taken as the seed point, the contour information of the rust area is extracted, and the geometric shape of the rust area is obtained; according to the geometric shape of the rust area and the three-dimensional model data, the spatial position information of the rust area to be detected in the three-dimensional space is obtained through the triangulation principle.

4. The ultrasonic-based substation reinforced concrete corrosion thickness evaluation method of claim 1, wherein, The ultrasonic detection data is decomposed by several levels by using wavelet transform, the decomposed ultrasonic detection data is selected and denoised by soft threshold, the denoised data is normalized, the normalized data is analyzed by using Fourier transform, and the frequency spectrum feature parameters are extracted.

5. A method for ultrasonic based substation reinforced concrete corrosion thickness evaluation as claimed in claim 1, wherein, The Euclidean distance measurement method is used to calculate the similarity of the frequency spectrum feature parameters and the frequency spectrum feature parameters of the preset frequency spectrum feature database of each rust product; The preset number of multiple rust products arranged in the front are selected as candidates; the frequency spectrum feature parameters of the candidate rust products and the frequency spectrum feature parameters of the ultrasonic detection data are input into the support vector machine classification model to obtain the rust type of the rust area to be detected.

6. A method of ultrasonic based substation reinforced concrete corrosion thickness evaluation as claimed in claim 5, wherein, The rust degree evaluation model includes multiple kinds, and each rust degree evaluation model corresponds to a kind of rust product; if there is no corresponding rust degree evaluation model for a kind of rust product, the Euclidean distance measurement method is used to calculate the similarity of the rust product and the frequency spectrum feature of the rust product corresponding to the constructed rust degree evaluation model, and the rust degree evaluation model corresponding to the rust product with the highest similarity is selected for evaluation.

7. An ultrasonic based substation reinforced concrete corrosion thickness evaluation system, characterized by, The method comprises the following steps: The ultrasonic parameter combination determination module is configured to: acquire geometric shape information and spatial position information of the rusted area to be detected; and determine an ultrasonic parameter combination by matching according to the geometric shape information and the spatial position information; The ultrasonic detection module is configured to: perform ultrasonic detection on the rusted area to be detected based on the ultrasonic parameter combination, and obtain ultrasonic detection data; The classification module is configured to: extract a frequency spectrum characteristic parameter of the ultrasonic detection data; and obtain a rusted area type in the rusted area to be detected according to the frequency spectrum characteristic parameter and a preset support vector machine classification model; The evaluation module is configured to: obtain a rusted thickness and a rusted degree grade according to the rusted area type and a preset rusted degree evaluation model; and the rusted degree evaluation model is a machine learning model.

8. A computer readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the steps of the substation reinforced concrete rusted thickness evaluation method based on ultrasonic waves according to any one of claims 1-6.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and capable of running on the processor, characterized in that, The processor executes the program to implement the steps of the substation reinforced concrete rusted thickness evaluation method based on ultrasonic waves according to any one of claims 1-6.

10. A computer program product, characterised in that, The computer program product comprises a computer program, and the computer program is executed by the processor to implement the steps of the substation reinforced concrete rusted thickness evaluation method based on ultrasonic waves according to any one of claims 1-6.

Images