A copper ratio testing system and method for NbTi / Cu superconducting wire based on image recognition

Abstract

The present application discloses a copper ratio testing system and method for NbTi / Cu superconducting wire based on image recognition. The method includes the following steps: S1: Collect metallographic image data of the cross-section of the sample NbTi / Cu superconducting wire and obtain the true copper ratio by the density method; S2: Obtain the calculated copper ratio according to the number of pixel points of the binary image; S3: Use the metallographic image data, the true copper ratio, and the calculated copper ratio as a data set to train a support vector regression model; S4: Obtain the cross-sectional image of the NbTi / Cu superconducting wire to be tested, input the cross-sectional image and the calculated copper ratio obtained in S2 into the support vector regression model in S3 to obtain the actual copper ratio. The present application belongs to the field of superconducting composite wires. The present application solves the problems of low efficiency of the paper-cutting method, inaccurate copper ratio results, and cumbersome operation process of the density method in the current copper ratio testing methods. The present application ensures the accuracy of copper ratio testing and improves the efficiency.

Description

Technical Field

[0001] The present invention belongs to the technical field of superconducting composite wire processing, and particularly relates to a copper ratio testing system and method for NbTi / Cu superconducting wire based on image recognition. Background Art

[0002] NbTi / Cu superconducting wire is one of the most widely used superconducting materials in MRI at present. To ensure the stability of MRI operation, strict requirements for the copper ratio of the superconducting wire are imposed at the initial design stage. The copper ratio is one of the important performance indicators of NbTi / Cu superconducting wire. To meet the delivery requirements of the product, accurate copper ratio testing of the wire must be carried out.

[0003] The copper ratio of NbTi / Cu superconducting wire refers to the area ratio of the copper region to the superconducting region (i.e., the NbTi region) in the superconducting wire. The current copper ratio testing methods mainly include the paper-cutting method, the density method, etc. However, the paper-cutting method has low efficiency and can only measure a rough copper ratio range, and the copper ratio result is inaccurate; although the density method has accurate test results, it is necessary to soak the superconducting wire sample in concentrated nitric acid to corrode and dissolve the copper, and weigh and convert the weight of the sample before corrosion and the weight of the NbTi core wire after corrosion to obtain the copper ratio result. The operation process is cumbersome, and at the same time, the use of chemical pollutants is involved, posing a risk of environmental pollution. Summary of the Invention

[0004] The purpose of the present invention is to provide a copper ratio testing system and method for NbTi / Cu superconducting wire based on image recognition, which solves the problems of low efficiency of the paper-cutting method, inaccurate copper ratio results, cumbersome operation process and environmental pollution risk in the existing copper ratio testing methods.

[0005] The present invention adopts the following technical solutions: A copper ratio testing method for NbTi / Cu superconducting wire based on image recognition, comprising the following steps:

[0006] S1: Collect the metallographic image data of the cross-section of the sample NbTi / Cu superconducting wire and the true copper ratio obtained by the density method.

[0007] The metallographic image data is obtained by the following method:

[0008] S11: Take a sample from the sample NbTi / Cu superconducting wire and collect the color image of the metallographic cross-section of the NbTi / Cu superconducting wire.

[0009] S12: Preprocess the color image; then perform gray-scale transformation on the preprocessed color image, and convert the gray-scale image into a binary image again through threshold processing; the binary image is the metallographic image data.

[0010] S2: Obtain the calculated copper ratio using formula (1) based on the number of pixel points in the copper region, superconducting region, and background region in the binary image.

[0011] (1)

[0012] where, is the calculated copper ratio, is the number of pixel points in the copper region, is the number of pixel points in the background region, is the number of pixel points in the superconducting region, M is the number of pixel points in the horizontal direction of the binary image, and N is the number of pixel points in the vertical direction of the binary image.

[0013] S3: Use the metallographic image data, true copper ratio, and calculated copper ratio in S1 as a data set to train a support vector regression model using the data set.

[0014] S4: Obtain a cross-sectional image of the NbTi / Cu superconducting wire to be tested, and input the cross-sectional image and the calculated copper ratio obtained by processing the cross-sectional image in S2 into the support vector regression model trained in S3 to obtain the actual copper ratio.

[0015] Further, perform dimensionality reduction on the metallographic images in the data set in S3 and the metallographic images input into the trained model through the principal component analysis method, and select the results of the first ten principal components as the image data after dimensionality reduction.

[0016] Further, the data set is divided into a training set and a test set at a ratio of 3:1, and the support vector regression model is trained using the data in the training set. The kernel function used by the support vector regression model is the Gaussian kernel.

[0017] Further, the S12 preprocessing includes removing image noise and contrast enhancement.

[0018] Further, the methods for removing image noise include Gaussian filtering, bilateral filtering, and median filtering; the methods for contrast enhancement include contrast stretching and adaptive histogram equalization methods.

[0019] Further, S12 uses the linear weighted average method to convert the color image into a grayscale image. The grayscale image is a single-channel image, and the value of each pixel point is between 0 and 255.

[0020] Furthermore, the methods for threshold processing include the Otsu threshold segmentation method and the maximum entropy threshold segmentation method.

[0021] Further, in S2, the flood filling algorithm is used to convert the pixel values in the superconducting region to values consistent with the pixel values in the surrounding copper region, that is, the pixel values in the superconducting region are converted to 1.

[0022] The present invention also provides another technical solution: an NbTi / Cu superconducting wire copper ratio testing system based on image recognition, which system includes: a collection module, a copper ratio calculation module, a model training module, and a copper ratio calculation module.

[0023] Further, the collection module: is used to collect the metallographic image data of the cross-section of the sample NbTi / Cu superconducting wire and obtain the true copper ratio through the density method.

[0024] The copper ratio calculation module: obtains the calculated copper ratio according to the data of the collection module.

[0025] The model training module: uses the data of the collection module and the copper ratio calculation module as a data set to train a support vector regression model.

[0026] The copper ratio calculation module: obtains the data of the collection module and inputs it into the model training module by the copper ratio calculation module to obtain the actual copper ratio.

[0027] The beneficial effects of the present invention are: the NbTi / Cu superconducting wire copper ratio testing system and method based on image recognition provided by the present invention reduce the influence of factors such as equipment and personnel operation on the calculation result of the copper ratio. It ensures the accuracy of the test and improves the efficiency of the copper ratio test of the superconducting wire. At the same time, it avoids the risk of environmental pollution. Description of the Drawings

[0028] Figure 1 is the flowchart of the NbTi / Cu superconducting wire copper ratio testing method based on image recognition of this application;

[0029] Figure 2 is the schematic diagram of the cross-section of the NbTi / Cu superconducting wire after image processing of this application;

[0030] Figure 3 is the schematic diagram of the cross-section of the NbTi / Cu superconducting wire after the flood filling algorithm of this application;

[0031] Among them, 1. background area; 2. copper area; 3. superconducting area; 4. copper area and superconducting area. Detailed Embodiments

[0032] The technical solutions in the embodiments of the present application will be clearly and completely described below. Apparently, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0033] Such as Figure 1As shown in the figure, the present application provides a copper ratio test system and method for NbTi / Cu superconducting wire based on image recognition. This method uses image recognition to test the copper ratio of NbTi / Cu superconducting wire, which can not only ensure the accuracy of the test, but also has higher efficiency, and at the same time avoids the use of chemical pollutants.

[0034] A copper ratio test method for NbTi / Cu superconducting wire based on image recognition includes the following steps:

[0035] S1: Collect the metallographic image data of the cross-section of the sample NbTi / Cu superconducting wire and obtain the true copper ratio by the density method.

[0036] The metallographic image data is obtained by the following method:

[0037] S11: Take a sample from the sample NbTi / Cu superconducting wire and collect the color image of the metallographic cross-section of the NbTi / Cu superconducting wire.

[0038] S12: Preprocess the color image. The preprocessing includes removing image noise and contrast enhancement. The methods for removing image noise include Gaussian filtering, bilateral filtering and median filtering; the methods for contrast enhancement include contrast stretching and adaptive histogram equalization method.

[0039] Subsequently, perform gray-scale transformation on the preprocessed color image, and use the linear weighted average method to convert the color image into a gray-scale image. The gray-scale image is a single-channel image, and the value of each pixel point is between 0 and 255.

[0040] Convert the gray-scale image into a binary image again through threshold processing; the methods for threshold processing include Otsu threshold segmentation method and maximum entropy threshold segmentation method. The binary image is the metallographic image data. The binary image is a single-channel image, and the value of each pixel point is 0 or 1. In the image, white pixels represent "0" and black pixel points represent "1".

[0041] At this time, according to the color difference of each region of the image, the pixel value of the copper region 2 will be 1, and the pixel values of the NbTi region 3 and the background region 1 will be 0.

[0042] S2: According to the number of pixel points in the copper region 2, superconducting region 3 and background region 1 in the binary image, count the number of pixel points with a value of 1 in the binary image, and mark it as ; Use the flood fill algorithm to convert the pixel value of the superconducting region into a value consistent with the pixel value of the surrounding copper region, that is, the pixel value of the superconducting region is converted to 1, and count the number of pixel points that are 0 at this time, denoted as , and use formula (1) to obtain the calculated copper ratio.

[0043] (1)

[0044] Among them, To calculate the copper ratio, is the number of pixel points in copper region 2, is the number of pixel points in background region 1, is the number of pixel points in superconducting region 3, M is the number of pixel points in the horizontal direction of the binary image, and N is the number of pixel points in the vertical direction of the binary image.

[0045] S3: Use the metallographic image data, the true copper ratio, and the calculated copper ratio in S1 as a data set, and use the data set to train a support vector regression model.

[0046] When establishing the data set, the dimensionality of the metallographic image data is reduced by the principal component analysis method. After dimensionality reduction, the first ten principal component results are selected as image features and added to the data set; the data set is divided into a training set and a test set in a ratio of 3:1. Use the data in the training set to train the support vector regression model, and select the Gaussian kernel as the kernel function.

[0047] The data is stored in the form of M×N×3. M is the number of pixel points in the horizontal direction of the image, N is the number of pixel points in the vertical direction. To ensure the accuracy of calculating the copper ratio, the image needs to be as clear as possible. Therefore, M and N should be at least greater than 1000.

[0048] The image data includes copper region 2, NbTi region 3, and background region 1. The image data obtained by the image acquisition device is in RGB three channels, each pixel point contains 3 values, and each value is between 0 and 255.

[0049] S4: Obtain the cross-sectional image of the NbTi / Cu superconducting wire to be tested. The cross-sectional image and the calculated copper ratio obtained by processing the cross-sectional image in S2 are input into the support vector regression model trained in S3 to obtain the actual copper ratio.

[0050] A copper ratio test system for NbTi / Cu superconducting wires based on image recognition in this application includes: an acquisition module, a copper ratio calculation module, a model training module, and a copper ratio calculation module.

[0051] Acquisition module: This module is used to acquire the metallographic image data of the cross-section of the sample NbTi / Cu superconducting wire and obtain the true copper ratio by the density method.

[0052] Copper ratio calculation module: According to the number of pixel points in copper region 2, superconducting region 3, and background region 1 in the binary image in the acquisition module, use formula (1) to obtain the calculated copper ratio.

[0053] (1)

[0054] Among them, is the calculated copper ratio, is the number of pixel points in copper region 2, is the number of pixels in the background area 1, is the number of pixels in the superconducting area 3, M is the number of pixels in the horizontal direction of the binary image, and N is the number of pixels in the vertical direction of the binary image.

[0055] Model training module: Using the S1 metallographic image data, the true copper ratio, and the calculated copper ratio as a data set, a support vector regression model is trained using the data set.

[0056] When establishing the data set, the dimensionality of the metallographic image data is reduced by the principal component analysis method. After dimensionality reduction, the first ten principal component results are selected as image features and supplemented into the data set.

[0057] The principal component analysis method is an efficient data dimensionality reduction method. It can project large data into the feature space through orthogonal transformation, capture the key features of the data through a few principal components, reduce the data dimension, and improve the efficiency and accuracy of subsequent analysis and modeling.

[0058] The main reason for using the support vector regression model is that the model has good training effects on large data sets and high model training efficiency. Therefore, the data can be frequently supplemented to update the model to improve the accuracy of the copper ratio results.

[0059] Copper ratio calculation module: Obtain the cross-sectional image of the NbTi / Cu superconducting wire to be tested, input the cross-sectional image and the S2 calculated copper ratio into the support vector regression model trained in S3, and obtain the actual copper ratio. The purpose is to improve the accuracy and effectiveness of the copper ratio results and reduce the influence of factors such as equipment and personnel operations on the final calculated copper ratio results.

[0060] The trained model is trained using the test set. The coefficient of determination between the predicted value and the actual value is 0.955, and the absolute root mean square error is less than 0.002.

[0061] The process of setting the pixel value of the superconducting area to 1 uses the flood fill algorithm. This algorithm detects the information of the pixel point and the surrounding eight pixel points, and adjusts the point with a smaller pixel value to the larger pixel value of the surrounding pixels. Through this algorithm, the pixel value of the superconducting area 3 can be adjusted to be the same as the pixel value of the copper area 2.

[0062] Figure 2 is the schematic diagram of the cross-section of the superconducting wire after image processing. Figure 3 is the image after the flood fill algorithm. Among them, 1 is the background area, and its pixel value is 0; 2 is the copper area, and its pixel value is 1; 3 is the superconducting area, and its pixel value is 0. 4 is the copper area and the superconducting area. 4 is the sum of the copper area 2 and the superconducting area 3, and its pixel value is 1.

[0063] Example 1:

[0064] This embodiment provides a method for testing the copper ratio of NbTi / Cu superconducting single-core wire with a copper ratio of 0.410 ± 0.010, including the following steps:

[0065] S1: Collect the metallographic image data of the cross-section of the sample NbTi / Cu superconducting wire and obtain the true copper ratio by the density method. The metallographic image data is obtained by the following method:

[0066] S11: Take a sample from the sample NbTi / Cu superconducting wire and collect the color image of the metallographic cross-section of the NbTi / Cu superconducting wire.

[0067] Take a sample from the NbTi / Cu superconducting single-core wire to be tested for copper ratio. Grind and polish the cross-section of the wire, and use an image acquisition device to collect RGB color image data with a complete metallographic cross-section of the wire. The number of pixel points of the image is set to 2000×2000, and the image data is stored in the form of M×N×3, where M = 2000 and N = 2000.

[0068] S12: Preprocess the color image data, including removing noise and contrast enhancement. Subsequently, perform gray-scale transformation on the color image to convert it into a gray-scale image, and then convert the gray-scale image into a binary image through threshold processing. The binary image is the metallographic image data; at this time, according to the color difference of each region of the image, the pixel value of the copper region will be 1, and the pixel values of the superconducting region and the background region will be 0.

[0069] S2: According to the number of pixel points in the copper region 2, superconducting region 3, and background region 1 in the binary image, use formula (1) to obtain the calculated copper ratio.

[0070] The number of pixel points with a value of 1 in the binary image is counted as 985622, that is ; Use the flood fill algorithm to set the pixel value of the superconducting region to 1, and count the number of pixel points that are 0 at this time as 586737, that is , and calculate the copper ratio result as 0.398 according to the following formula (1).

[0071] Formula (1)

[0072] Among them, is the calculated copper ratio, is the number of pixel points in the copper region 2, is the number of pixel points in the background region 1, is the number of pixel points in the superconducting region 3, M is the number of pixel points in the horizontal direction of the binary image, and N is the number of pixel points in the vertical direction of the binary image.

[0073] S3: Use the metallographic image data, true copper ratio, and calculated copper ratio in S1 as a data set, and use the data set to train a support vector regression model.

[0074] S4: Obtain a cross-sectional image of the NbTi / Cu superconducting wire to be tested, input the cross-sectional image and the calculated copper ratio obtained by S2 into the support vector regression model trained in S3, and obtain an actual copper ratio result of 0.406.

[0075] The sample was tested for copper ratio by density method and the copper ratio was re-tested. The copper ratio by density method was 0.407. The experimental test result differed by 0.24% from the test result of this application. The experiment was repeated 10 times and it was found that the test result of this application was basically consistent with the test result by density method, and the error was controlled within 1%. The results are as follows:

[0076]

[0077] From the above test experiments, it can be seen that the copper ratio test method of NbTi / Cu superconducting wire based on image recognition in the present application, during the implementation of Example 1, the copper ratio test result of the superconducting wire is accurate and more efficient.

[0078] Embodiment 2:

[0079] This embodiment provides a method for testing the copper ratio of a NbTi / Cu superconducting composite wire having a copper ratio of 4.50±0.40, comprising the following steps:

[0080] S1: Collect metallographic image data of the cross section of the sample NbTi / Cu superconducting wire and obtain the true copper ratio through the density method.

[0081] Metallographic image data is obtained by the following method:

[0082] S11: Take a sample from the NbTi / Cu superconducting wire and collect a color image of the metallographic cross section of the NbTi / Cu superconducting wire.

[0083] A sample was taken from the NbTi / Cu superconducting single-core wire to be tested for copper ratio, the cross section of the wire was ground and polished, and an image acquisition device was used to collect RGB color image data with a complete metallographic cross section of the wire. The number of pixels in the image was set to 2000×2000, and the image data was stored in the form of M×N×3, where M=2000 and N=2000.

[0084] S12: Preprocess the color image data, including removing noise and contrast enhancement. Then, the color image is gray-scaled and converted into a gray-scale image, and the gray-scale image is converted into a binary image again through threshold processing, and the binary image is metallographic image data; at this time, according to the color difference of each area of ​​the image, the pixel value of the copper area will be 1, and the pixel value of the superconducting area and the background area will be 0.

[0085] S2: Based on the number of pixels in copper region 2, superconducting region 3 and background region 1 in the binary image, the copper ratio is calculated using formula (1).

[0086] The number of pixels with a value of 1 in the binary image is 2954121, that is, ; Use the flood filling algorithm to set the pixel value of the NbTi area to 1. The number of pixels that are 0 at this time is 398613, that is, =398613, and the copper ratio calculated according to formula (1) is 4.564.

[0087] Formula (1)

[0088] in, To calculate the copper ratio, is the number of pixels in copper area 2, is the number of pixels in background area 1, is the number of pixels in the superconducting region 3, M is the number of pixels in the horizontal direction of the binary image, and N is the number of pixels in the vertical direction of the binary image.

[0089] S3: The metallographic image data, the true copper ratio and the calculated copper ratio in S1 are used as data sets, and the support vector regression model is trained using the data sets.

[0090] S4: Obtain a cross-sectional image of the NbTi / Cu superconducting wire to be tested, input the cross-sectional image and the calculated copper ratio obtained by S2 into the support vector regression model trained in S3, and obtain an actual copper ratio result of 4.582.

[0091] The samples were subjected to a density method copper ratio test and the copper ratio results were re-tested. The density method copper ratio was 4.591. The experimental test results differed by 0.20% from the test results of this application.

[0092] The experiment was repeated 10 times and it was found that the test results of this application were basically consistent with the test results of the density method, and the error was controlled within 1%. The results are as follows:

[0093]

[0094] From the above examples, it can be seen that the copper ratio test method of superconducting wire based on image recognition in this application has accurate test results of the copper ratio of superconducting wire and higher efficiency in the specific implementation process.

[0095] Although the content of the present application has been described in detail through the above preferred embodiments, it should be appreciated that the above description should not be considered as a limitation of the present application. After reading the above content, it will be apparent to those skilled in the art that various modifications and substitutions of the present application can be made. Therefore, the protection scope of the present application should be limited by the appended claims.

Claims

1. A method for testing the copper ratio of NbTi / Cu superconducting wire based on image recognition, characterized in that: The steps include: S1: Collect metallographic image data of the cross section of the sample NbTi / Cu superconducting wire and obtain the real copper ratio by density method; Metallographic image data is obtained by the following method: S11: Take samples from the superconducting wire and collect color images of the metallographic cross-section of the superconducting wire; S12: preprocessing the color image; then performing grayscale conversion on the preprocessed color image, and converting the grayscale image into a binary image again through threshold processing; the binary image is metallographic image data; S2: Based on the number of pixels in the copper area, superconducting area and background area in the binary image, the copper ratio is calculated using formula (1); （1） in, To calculate the copper ratio, is the number of pixels in the copper area, is the number of pixels in the background area, is the number of pixels in the superconducting region, M is the number of pixels in the horizontal direction of the binary image, and N is the number of pixels in the vertical direction of the binary image; S3: The metallographic image data of S1, the real copper ratio and the calculated copper ratio are used as data sets, and the support vector regression model is trained using the data sets; after establishing the data set and inputting the metallographic images into the trained model, the metallographic images are reduced in dimension by the principal component analysis method, and the first ten principal component results are selected as image data after the dimension reduction; S4: obtaining a cross-sectional image of the NbTi / Cu superconducting wire to be tested, and inputting the cross-sectional image and the copper ratio of the image calculated by S2 into the support vector regression model trained by S3 to obtain the actual copper ratio; S12 uses a linear weighted average method to convert a color image into a grayscale image. A grayscale image is a single-channel image, and each pixel value is between 0 and 255. The pixel value of the copper area in the binary image is 1, and the pixel value of the superconducting area and the background area is 0. According to the number of pixels in the copper area, superconducting area and background area in the binary image, the number of pixels with a value of 1 in the binary image is counted and recorded as ; Use the flood filling algorithm to convert the pixel value of the superconducting area into a value consistent with the pixel value of the copper area surrounding the area, that is, the pixel value of the superconducting area is converted to 1, and the number of pixels with a value of 0 is counted and recorded as .

2. The copper ratio testing method of NbTi / Cu superconducting wire based on image recognition according to claim 1, characterized in that: The data set is divided into a training set and a test set in a ratio of 3:

1. The support vector regression model is trained using the data in the training set. The kernel function used by the support vector regression model is a Gaussian kernel.

3. The copper ratio testing method of NbTi / Cu superconducting wire based on image recognition according to claim 1, characterized in that: The S12 preprocessing includes removing image noise and enhancing contrast.

4. The copper ratio testing method of NbTi / Cu superconducting wire based on image recognition according to claim 3, characterized in that: The image noise removal method includes Gaussian filtering, bilateral filtering and median filtering; the contrast enhancement method includes contrast stretching and adaptive histogram equalization method.

5. The copper ratio testing method of NbTi / Cu superconducting wire based on image recognition according to claim 1, characterized in that: The threshold processing method includes Otsu threshold segmentation method and maximum entropy threshold segmentation method.

6. A copper ratio testing system for NbTi / Cu superconducting wire based on image recognition according to any one of claims 1 to 5, characterized in that: The system includes: an acquisition module, a copper ratio calculation module, a model training module and a copper ratio calculation module.

7. The copper ratio testing system of NbTi / Cu superconducting wire based on image recognition according to claim 6, characterized in that: The acquisition module is used to acquire metallographic image data of the cross section of the NbTi / Cu superconducting wire sample and obtain the real copper ratio by density method; The copper ratio calculation module is used to calculate the copper ratio according to the data of the acquisition module; The model training module is used to train a support vector regression model using the data from the acquisition module and the copper ratio calculation module as a data set; The copper ratio calculation module: obtains the data from the acquisition module and the copper ratio calculation module and inputs them into the model training module to obtain the actual copper ratio.

Images