Nuclear metal aging grade diagnosis system and method

Abstract

The invention discloses a nuclear metal aging grade diagnosis system and method. The system comprises a fiber laser, a collimation light receiving lens group, a spectrometer and a data analysis module. Wherein the optical fiber laser is used for gathering laser on the surface of a nuclear metal sample and generating plasma; the collimation light receiving lens group is used for gathering the plasmas and outputting the gathered plasmas to the optical fiber coupler; the optical fiber coupler transmits the collected plasma into the spectrograph through an optical fiber; and the data analysis module is used for reading the spectrum of the spectrograph and acquiring a spectrum capable of representing the element composition of the nuclear metal sample. Compared with a detection method of a traditional LIBS system, the method has the advantages of in-situ detection, high efficiency, good economical efficiency, high robustness and the like. Therefore, the system and the method can provide new technical support for rapid in-situ diagnosis of the aging state of the key metal component of the nuclear power station.

Description

Technical Field

[0001] The data detection and diagnosis technology of the present invention specifically relates to a nuclear metal aging level diagnosis system and method. Background Art

[0002] Whether the aging status of key metal components of the nuclear island can be quickly diagnosed during the service of the nuclear power plant will directly affect the safe operation of the nuclear power plant. The pressurized water reactor nuclear power plants put into operation in my country are mainly light water reactor type. The safety of the pressurized water reactor reactor unit mainly relies on three barriers, namely fuel and cladding, pressure vessel and primary loop pipeline and containment. Among them, the pressure vessel and primary loop pipeline are exposed to extreme conditions such as high temperature, high pressure and radiation for a long time, and there are huge safety hazards caused by material failure. Therefore, the diagnosis of the aging status of such key metal components of the nuclear island has always been the focus and difficulty of nuclear power unit operation and maintenance. In addition, the special service environment of the nuclear power plant makes the aging mechanism very complicated, which increases the difficulty of diagnosing the aging status.

[0003] At present, the diagnostic methods for the aging status of nuclear metal materials can be divided into two types: non-in-situ detection and in-situ detection. As a laboratory analysis method, non-in-situ detection requires cutting pipes for sampling. Although the results obtained are relatively accurate, the operation is cumbersome and time-consuming, and it will also cause irreversible damage to the original metal components. In-situ detection methods, including ultrasonic testing, X-ray testing, magnetic particle testing, and eddy current testing, do not require cutting pipes for sampling, but can only analyze existing macroscopic defects, which is difficult to meet the needs of early warning of failure of serving metal components. Therefore, in recent years, a diagnostic method for the aging status of nuclear metal components based on Laser-Induced Breakdown Spectroscopy (LIBS) has been developed.

[0004] Due to the complex equipment layout and harsh working environment of nuclear power plants, the existing LIBS diagnostic system for nuclear metal components mainly uses Nd:YAG lasers as plasma excitation light sources, combined with fiber-coupled transmission (Fiber Optic-LIBS, FO-LIBS). FO-LIBS transmits the laser beam to the metal surface to be tested over a long distance through optical fiber, effectively improving the flexibility of the LIBS diagnostic system. However, optical fiber transmission is extremely sensitive to laser energy and coupling mode, and the output laser pulse energy is low, resulting in poor sensitivity in trace metal detection. In addition, the laser focusing effect after optical fiber transmission is significantly deteriorated, further affecting the detection effect. At the same time, the traditional Nd:YAG laser is large in size and bulky in structure, making it difficult to integrate into a portable device. In addition, the low laser repetition frequency (Hz level) limits the detection speed, making it impossible to achieve short-term, efficient scanning measurement.

[0005] Therefore, the existing LIBS diagnostic system for nuclear metal components has the problems of low detection efficiency, poor sensitivity and inability to meet the on-site detection needs of nuclear power plants. Summary of the invention

[0006] The purpose of the present invention is to overcome the above-mentioned deficiencies of the prior art and to provide a nuclear metal aging level diagnosis system and method to improve the efficiency and accuracy of diagnosis.

[0007] To achieve the above object, the technical solution of the present invention is:

[0008] In a first aspect, the present invention provides a nuclear metal aging level diagnosis system, comprising a fiber laser, a focusing lens, a collimating light-collecting lens group, a spectrometer, and a data analysis module; wherein:

[0009] The fiber laser is used to generate laser light, and the generated laser light is focused on the surface of the nuclear metal sample after passing through the focusing lens to generate plasma;

[0010] The collimating light-collecting lens group is used to gather the plasma and output it to the optical fiber coupler;

[0011] The optical fiber coupler transmits the collected plasma to the spectrometer via an optical fiber;

[0012] The data analysis module is used to read the spectrum of the spectrometer and obtain a spectrum that can characterize the elemental composition of the nuclear metal sample.

[0013] Optionally, the nuclear metal aging level diagnostic system further includes:

[0014] The measuring platform is used for placing the nuclear metal sample and controlling the moving process of the nuclear metal sample.

[0015] Optionally, the fiber laser includes a fiber laser host, a laser transmission fiber and a laser probe; the fiber laser host is used to turn on the laser, the laser transmission fiber is used to transmit the laser over a long distance, and the laser probe is used to output the laser; the laser output by the laser probe is focused on the surface of the nuclear metal sample after passing through a focusing lens.

[0016] In a second aspect, the present invention provides a method for diagnosing nuclear metal aging levels, comprising:

[0017] Obtain nuclear metal samples of different aging levels;

[0018] Based on the nuclear metal aging level diagnosis system, nuclear metal samples with different aging levels are tested to obtain spectra of nuclear metal samples with different aging levels;

[0019] Preprocessing the spectrum to obtain an effective spectrum;

[0020] The scores between the characteristic variables of the effective spectrum and the aging grade labels are calculated using mutual information, and the features whose scores reach the threshold are extracted and stored as a new spectrum data matrix;

[0021] The spectral data matrix was input into the random forest model to establish an aging grade classification model;

[0022] Based on the above nuclear metal aging level diagnosis system, the nuclear metal to be tested is tested to obtain the spectrum of the nuclear metal to be tested;

[0023] The spectrum of the nuclear metal to be tested is input into the aging grade classification model to obtain the aging grade of the nuclear metal to be tested.

[0024] Optionally, obtaining nuclear metal samples of different aging levels includes:

[0025] Conduct artificial aging experiments on nuclear metals to obtain nuclear metal samples in different aging states;

[0026] The aging level of nuclear metal samples is comprehensively determined based on the aging time and mechanical performance indicators.

[0027] Optionally, the mutual information calculation process is:

[0028]

[0029] Among them, p(x,y) represents the joint probability distribution of feature variable X and classification label Y, and p(x) and p(y) represent the marginal probability distribution of feature variable X and classification label Y respectively.

[0030] Optionally, the optimization range of the variable trees of the random forest is 50-500, and the optimization range of the random variables is 1-7.

[0031] Optionally, the number of variable trees of the random forest is 150 and the number of random variables is 3.

[0032] Optionally, the aging grade classification model is:

[0033]

[0034] Where f(x) is the prediction result of random forest, B is the number of decision trees, and f b (x) is the prediction result of the bth decision tree, k is the category label, I(f b (x) = k) is the indicator function.

[0035] For label k, calculate the proportion of predictions for k in all decision trees, and then select the category with the highest proportion as the final prediction result;

[0036] The aging grade of the steel material of the main pipeline under test is calculated according to f(x) to achieve aging grade measurement.

[0037] Optionally, the preprocessing of the spectrum includes: preprocessing the spectrum by effectiveness screening, channel total intensity normalization, and spectrum averaging.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The system and method disclosed in the present invention do not require pipe cutting or mechanical processing of the sample surface before diagnosing the aging grade of nuclear main pipeline steel. The fiber laser can quickly remove oxides on the sample surface due to its high repetition rate ablation characteristics, and directly collect a plasma spectrum that can reflect the characteristics of the sample matrix. Based on a method combining mutual information feature extraction and random forest, an aging grade classification model is established to achieve in-situ rapid diagnosis of the aging status of nuclear metal components. Compared with the detection method of the traditional LIBS system, the system established by the present invention has the advantages of in-situ detection, high efficiency and good economy. Compared with the traditional aging grade detection method, the method proposed by the present invention has the advantages of accurate results, short calculation time and high robustness. Therefore, the system and method of the present invention can provide new technical support for the rapid in-situ diagnosis of the aging status of key metal components in nuclear power plants. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A schematic diagram of the composition of a nuclear metal aging level diagnostic system provided in an embodiment of the present application;

[0041] Figure 2 A flow chart of a method for diagnosing nuclear metal aging levels provided in an embodiment of the present application;

[0042] Figure 3 Spectra of samples with different aging levels;

[0043] Figure 4 This is a diagram showing the prediction results of the nuclear metal aging level diagnosis method provided in the embodiment of the present application;

[0044] In the figure: 1. Fiber laser; 2. Fiber laser host; 3. Laser transmission fiber; 4. Laser probe; 5. Focusing lens; 6. Measuring platform; 7. Collimating light receiving lens group; 8. Fiber coupler; 9. Multi-channel optical fiber; 10. Multi-channel spectrometer; 11. Computer. DETAILED DESCRIPTION

[0045] Example:

[0046] The technical solution of the present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0047] See also Figure 1 As shown, the nuclear metal aging level diagnosis system provided in this embodiment mainly includes a fiber laser 1, a focusing lens 5, a collimating light-collecting lens group 7, a multi-channel spectrometer 10 and a data analysis module 11.

[0048] Among them, the fiber laser 1 is used to generate laser light, and the generated laser light is gathered on the surface of the nuclear metal sample after passing through the focusing lens 5 and generates plasma; while the traditional LIBS system mainly uses Nd:YAG laser as a plasma excitation source, which has the disadvantages of bulky structure and slow output power. The present application adopts a fiber laser, which has outstanding advantages such as good beam quality, compact structure, long-term stable output power, high repetition frequency (kHz level) and adaptability to harsh environments such as high temperature and high dust, which greatly increases the detection efficiency, effectively improves the portability and flexibility of the measurement system, and can realize large-area in-situ rapid scanning of the surface of nuclear metal components, thereby obtaining more complete information characterizing the aging characteristics of the material, thereby solving the fundamental defects of the traditional LIBS system.

[0049] The collimating light-collecting lens group 7 is used to gather the plasma and output it to the fiber coupler 8, and the fiber coupler 8 transmits the collected plasma to the multi-channel spectrometer 10 through the multi-channel optical fiber 9; the data analysis module is used to read the spectrum of the spectrometer to obtain a spectrum that can characterize the elemental composition of the nuclear metal sample.

[0050] It can be seen that the fiber laser of the nuclear metal aging level diagnostic system provided in this embodiment can quickly remove oxides on the sample surface and form a high-temperature plasma by virtue of its high-repetition-rate ablation characteristics. By analyzing the wavelength and intensity of the plasma emission spectrum during the cooling process, the type and concentration information of the sample elements can be obtained, so that the plasma spectrum that can reflect the characteristics of the sample matrix can be directly collected, thereby greatly improving the detection efficiency.

[0051] In addition, in order to facilitate the laser emitted by the fiber laser to focus on different positions on the surface of the nuclear metal sample, the nuclear metal aging level diagnostic system provided in this embodiment also includes a measuring platform for placing the nuclear metal sample and controlling the movement process of the nuclear metal sample.

[0052] In a specific embodiment, the fiber laser 1 includes a fiber laser host 2, a laser transmission fiber 3 and a laser probe 4. The fiber laser host 2 is used to turn on the laser, the laser transmission fiber 3 is used to transmit the laser over a long distance, and the laser probe 4 is used to output the laser. The laser output by the laser probe 4 is focused on the sample surface after passing through a focusing lens 5. Since the fiber laser is mainly composed of the fiber laser host 2, the laser transmission fiber 3 and the laser probe 4, it has a compact structure, stable output power, fast detection frequency, and can also reduce costs, showing great potential in practical applications.

[0053] The data analysis module mainly includes a computer 11. The collimating light collecting lens group 7 mainly includes two focusing lenses 5.

[0054] Accordingly, if Figure 2 As shown, this embodiment also provides a nuclear metal aging level diagnosis method, which mainly includes the following steps:

[0055] Step 110, obtaining nuclear metal samples of different aging levels;

[0056] In the specific implementation, taking the main pipeline steel as an example, an artificial aging experiment was conducted on the Z3CN20-09M material according to the national standard "T / CNS80-2022 Nuclear Power Plant Stainless Steel Material Thermal Aging Test Method" to obtain nuclear metal material samples in different aging states. The aging level of the sample is comprehensively determined based on the aging time of the main pipeline steel sample and the Charpy V-type impact energy, and the aging level of the nuclear metal sample is comprehensively determined.

[0057] Step 120: Based on the above nuclear metal aging level diagnosis system, nuclear metal samples with different aging levels are tested to obtain spectra of nuclear metal samples with different aging levels. In the present application, the spectrum is also a plasma spectrum.

[0058] Step 130, preprocessing the spectrum to obtain an effective spectrum;

[0059] In this step, the spectrum is preprocessed to reduce interference such as invalid spectrum and background noise, and improve the spectrum quality, so that the effective spectrum of nuclear metal samples with different aging levels can be obtained.

[0060] In the specific implementation, the spectrum is preprocessed by using the methods of validity screening, channel total intensity normalization, and spectral averaging to reduce the interference of invalid spectra and noise on subsequent analysis. At the same time, considering that the spectral characteristics will be affected by the fluctuation of spectral intensity at different measurement points, the acquired spectra are averaged in 10 groups, that is, a total of 50 spectra are used to characterize the same material, among which the standard deviation (SD) of the characteristic spectral line Fe I 424.11nm is selected for validity screening, and the SD value is set to 4500.

[0061] Step 140, using mutual information to calculate the scores between the feature variables of the effective spectrum and the aging level labels, and extracting features with high scores and storing them as a new spectrum data matrix.

[0062] In this step, by using mutual information to extract characteristic variables from the plasma spectra of samples with different aging levels, data features with high correlation with aging characteristics in nuclear metal components with different aging levels can be effectively identified.

[0063] In the specific implementation, the scores between the characteristic variables of the effective spectrum and the aging level labels are calculated and arranged in descending order. Taking the classification accuracy of the prediction set as an indicator, the variables with the highest scores are added to the random forest classification model one by one until all variables are re-entered. The variable combination corresponding to the best classification accuracy is used as the final variable for modeling. The mutual information calculation process is:

[0064]

[0065] Among them, p(x,y) represents the joint probability distribution of feature variable X and classification label Y, p(x) and p(y) represent the marginal probability distribution of feature variable X and classification label Y respectively;

[0066] Step 150, input the spectral data matrix after mutual information feature extraction into the random forest model to establish an aging grade classification model.

[0067] In this step, random forest is used to establish an aging grade classification model for the spectral data matrix, which has good robustness to the alloy steel matrix characteristics (element concentration and uneven distribution of metallographic structure) and can quickly and accurately predict the aging grade of the sample.

[0068] In a preferred embodiment, in order to optimize the classification accuracy of the model, the key parameters of the random forest are optimized through grid search, and the optimization range of the variable tree is 50 to 500; the optimization range of the random variable is 1 to 7;

[0069] Step 160: Detect the nuclear metal to be tested based on the above-mentioned nuclear metal aging level diagnosis system to obtain the spectrum of the nuclear metal to be tested.

[0070] Step 170: input the spectrum of the nuclear metal to be tested into the aging grade classification model to obtain the aging grade of the nuclear metal to be tested.

[0071] In a specific embodiment, the aging grade classification model is:

[0072]

[0073] Where f(x) is the prediction result of random forest, B is the number of decision trees, and f b (x) is the prediction result of the bth decision tree, k is the category label, I(f b (x) = k) is the indicator function.

[0074] For label k, calculate the proportion of predictions for k in all decision trees, and then select the category with the highest proportion as the final prediction result. Calculate the aging grade of the tested main pipeline steel based on f(x) to achieve aging grade measurement.

[0075] It can be seen that the nuclear metal aging grade diagnosis method provided in this embodiment first performs artificial aging treatment on the nuclear metal, and comprehensively determines the aging grade of the sample based on the aging time and Charpy V-type impact energy; then, the FL-LIBS system is used to obtain the spectral data of samples with different aging grades, and the spectral data is pre-processed by effectiveness screening, channel total intensity normalization and averaging, and 50 representative spectra are obtained for each aging grade sample. Subsequently, the mutual information algorithm is used to extract features of the full spectrum variables, and a random forest aging grade classification model is established; finally, the FL-LIBS system is used to measure the spectrum of the nuclear metal to be tested, and it is input into the aging grade classification model to obtain the aging grade of the tested material. Compared with the traditional aging grade detection method, this method has the advantages of accurate prediction results, short calculation time and high robustness.

[0076] The following is a further description of the nuclear metal aging level diagnosis method of the present application in conjunction with an application scenario embodiment:

[0077] Step 1: Design and build a LIBS detection system (Fiber Laser Based-LIBS, FL-LIBS) with fiber laser as plasma excitation source, specifically including a 1064nm wavelength single pulse fiber laser, a three-dimensional electric translation stage, a multi-channel grating spectrometer, a computer and optical components. Among them, the fiber laser frequency, power, spectrometer integration time and electric translation stage moving speed are adjustable. In this embodiment, the fiber laser frequency is set to 25kHz, the power is 20W, the spectrometer integration time is 30ms, and the electric translation stage moving speed is 3mm / s.

[0078] Step 2: Obtain samples of nuclear island main pipeline steel Z3CN20-09M in different aging states. Based on the aging mechanism of the main pipeline service process, the thermal aging caused by the spinodal decomposition of the ferrite phase and the precipitation of the G phase is the main cause of its material failure. Therefore, according to the national standard "T / CNS80-2022 Nuclear Power Plant Stainless Steel Material Thermal Aging Test Method", an artificial aging experiment was carried out on the nuclear island main pipeline material Z3CN20-09M. At 400°C, thermal aging treatments were carried out for 0, 500h, 1000h, 3000h, 6000h and 12000h, respectively. The microstructure and mechanical properties of samples in different aging states were analyzed. The aging level of the sample is comprehensively determined based on the aging time and Charpy V-type impact energy, i.e., 1-6.

[0079] Step 3: Use the FL-LIBS system designed and built in step 1 to obtain the plasma spectra of nuclear main pipeline steel Z3CN20-09M with different aging levels, such as Figure 3 As shown, 500 spectra were obtained for each aging grade sample. The SD value of the characteristic spectral line Fe I 424.11nm was selected as the basis for judging the validity of the spectrum, and the SD value was set to 4500. Finally, all spectra of each aging grade sample were judged as valid spectra. Subsequently, the valid spectral data were normalized for the total channel intensity. Finally, 50 representative spectra were obtained for each aging grade sample.

[0080] Step 4: Use the mutual information algorithm to calculate the scores between the spectral feature variables and the aging level labels and arrange them in descending order. Extract the first 1476 feature variables, that is, the 1 to 6 aging level samples to obtain a spectral data matrix of 1476 × 300 dimensions.

[0081] Step 5: Input the spectral data matrix into the random forest algorithm to establish an aging grade classification model. The key parameters of the random forest were optimized through grid search, that is, the optimal parameter of the tree was 150 and the optimal parameter of the random variable was 3.

[0082] Step 6: Use the established FL-LIBS system to measure the plasma emission spectrum of the main pipeline steel sample to be tested, and input its spectrum matrix into the aging grade classification model:

[0083]

[0084] Where f(x) is the prediction result of random forest, B is the number of decision trees, and f b (x) is the prediction result of the bth decision tree, k is the category label, I(f b (x) = k) is the indicator function. For label k, the proportion of predictions for k in all decision trees is calculated, and then the category with the highest proportion is selected as the final prediction result.

[0085] The aging grade of the tested main pipeline steel is calculated based on f(x) to achieve aging grade prediction. Figure 4 As shown, the accuracy of the prediction results is as high as 99%.

[0086] In summary, the system and method disclosed in the present invention do not require pipe cutting or mechanical processing of the sample surface before diagnosing the aging grade of nuclear main pipeline steel. The fiber laser can quickly remove oxides on the sample surface due to its high repetition rate ablation characteristics, and directly collect a plasma spectrum that can reflect the characteristics of the sample matrix. Based on a method combining mutual information feature extraction and random forest, an aging grade classification model is established to achieve in-situ rapid diagnosis of the aging status of nuclear metal components. Compared with traditional LIBS systems, the system established by the present invention has the advantages of in-situ detection, high efficiency and good economy. Compared with traditional aging grade detection methods, the method proposed in the present invention has the advantages of accurate results, short calculation time and high robustness. Therefore, the system and method of the present invention can provide new technical support for the rapid in-situ diagnosis of the aging status of key metal components in nuclear power plants.

[0087] The above embodiments are only for illustrating the technical concept and features of the present invention, and their purpose is to enable ordinary technicians in the field to understand the content of the present invention and implement it accordingly, and they cannot be used to limit the protection scope of the present invention. Any equivalent changes or modifications made based on the essence of the content of the present invention should be included in the protection scope of the present invention.

Claims

1. A nuclear metal aging level diagnostic system, characterized in that: It includes a fiber laser, a focusing lens, a collimating light-collecting lens group, a spectrometer and a data analysis module; among which, The fiber laser is used to generate laser light, and the generated laser light is focused on the surface of the nuclear metal sample after passing through the focusing lens to generate plasma; The collimating light-collecting lens group is used to gather the plasma and output it to the optical fiber coupler; The optical fiber coupler transmits the collected plasma to the spectrometer via an optical fiber; The data analysis module is used to read the spectrum of the spectrometer to obtain a spectrum that can characterize the elemental composition of the nuclear metal sample.

2. The nuclear metal aging level diagnostic system according to claim 1, characterized in that: Also includes: The measuring platform is used for placing the nuclear metal sample and controlling the moving process of the nuclear metal sample.

3. The nuclear metal aging level diagnostic system according to claim 1, characterized in that: The fiber laser includes a fiber laser host, a laser transmission fiber and a laser probe; the fiber laser host is used to turn on the laser, the laser transmission fiber is used to transmit the laser over a long distance, and the laser probe is used to output the laser.

4. A method for diagnosing nuclear metal aging levels, characterized in that: include: Obtain nuclear metal samples of different aging levels; Based on the nuclear metal aging level diagnosis system of claim 1, nuclear metal samples with different aging levels are tested to obtain spectra of nuclear metal samples with different aging levels; Preprocessing the spectrum to obtain an effective spectrum; The scores between the characteristic variables of the effective spectrum, the aging level labels, are calculated using mutual information, and the features whose scores reach the threshold are extracted and stored as a new spectrum data matrix; The spectral data matrix was input into the random forest model to establish an aging grade classification model; Based on the nuclear metal aging level diagnosis system of claim 1, the nuclear metal to be tested is detected to obtain the spectrum of the nuclear metal to be tested; The spectrum of the nuclear metal to be tested is input into the aging grade classification model to obtain the aging grade of the nuclear metal to be tested.

5. The nuclear metal aging level diagnosis method according to claim 4, characterized in that: The method of obtaining nuclear metal samples of different aging levels includes: Conduct artificial aging experiments on nuclear metals to obtain nuclear metal samples in different aging states; The aging level of nuclear metal samples is comprehensively determined based on the aging time and mechanical performance indicators.

6. The nuclear metal aging level diagnosis method according to claim 4, characterized in that: The process of mutual information calculation is: Among them, p(x,y) represents the joint probability distribution of feature variable X and classification label Y, and p(x) and p(y) represent the marginal probability distribution of feature variable X and classification label Y respectively.

7. The nuclear metal aging level diagnosis method according to claim 4, characterized in that: The optimization range of the variable trees of the random forest is 50-500, and the optimization range of the random variables is 1-7.

8. The nuclear metal aging level diagnosis method according to claim 7, characterized in that: The random forest has 150 trees and 3 random variables.

9. The nuclear metal aging level diagnosis method according to claim 4, characterized in that: The aging grade classification model is: Where f(x) is the prediction result of random forest, B is the number of decision trees, and f b (x) is the prediction result of the bth decision tree, k is the category label, I(f b (x) = k) is the indicator function. For label k, calculate the proportion of predictions for k in all decision trees, and then select the category with the highest proportion as the final prediction result; The aging grade of the steel material of the main pipeline under test is calculated according to f(x) to achieve aging grade measurement.

10. The nuclear metal aging level diagnosis method according to claim 4, characterized in that: The preprocessing of the spectrum includes: preprocessing the spectrum by using methods of effectiveness screening, channel total intensity normalization, and spectrum averaging.

Images